Upload 9 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+combined_output.csv filter=lfs diff=lfs merge=lfs -text

MLM.ipynb

@@ -0,0 +1,539 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "OSError",
+     "evalue": "[WinError 126] Belirtilen modül bulunamadı. Error loading \"c:\\Users\\info\\anaconda3\\Lib\\site-packages\\torch\\lib\\fbgemm.dll\" or one of its dependencies.",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mOSError\u001b[0m                                   Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[1], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtransformers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m BertTokenizer, BertForMaskedLM, DPRContextEncoderTokenizer,DPRContextEncoder\n\u001b[0;32m      2\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtorch\u001b[39;00m\n",
+      "File \u001b[1;32mc:\\Users\\info\\anaconda3\\Lib\\site-packages\\transformers\\__init__.py:26\u001b[0m\n\u001b[0;32m     23\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtyping\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m TYPE_CHECKING\n\u001b[0;32m     25\u001b[0m \u001b[38;5;66;03m# Check the dependencies satisfy the minimal versions required.\u001b[39;00m\n\u001b[1;32m---> 26\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m dependency_versions_check\n\u001b[0;32m     27\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[0;32m     28\u001b[0m     OptionalDependencyNotAvailable,\n\u001b[0;32m     29\u001b[0m     _LazyModule,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m     48\u001b[0m     logging,\n\u001b[0;32m     49\u001b[0m )\n\u001b[0;32m     52\u001b[0m logger \u001b[38;5;241m=\u001b[39m logging\u001b[38;5;241m.\u001b[39mget_logger(\u001b[38;5;18m__name__\u001b[39m)  \u001b[38;5;66;03m# pylint: disable=invalid-name\u001b[39;00m\n",
+      "File \u001b[1;32mc:\\Users\\info\\anaconda3\\Lib\\site-packages\\transformers\\dependency_versions_check.py:16\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[38;5;66;03m# Copyright 2020 The HuggingFace Team. All rights reserved.\u001b[39;00m\n\u001b[0;32m      2\u001b[0m \u001b[38;5;66;03m#\u001b[39;00m\n\u001b[0;32m      3\u001b[0m \u001b[38;5;66;03m# Licensed under the Apache License, Version 2.0 (the \"License\");\u001b[39;00m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m     12\u001b[0m \u001b[38;5;66;03m# See the License for the specific language governing permissions and\u001b[39;00m\n\u001b[0;32m     13\u001b[0m \u001b[38;5;66;03m# limitations under the License.\u001b[39;00m\n\u001b[0;32m     15\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mdependency_versions_table\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m deps\n\u001b[1;32m---> 16\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutils\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mversions\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m require_version, require_version_core\n\u001b[0;32m     19\u001b[0m \u001b[38;5;66;03m# define which module versions we always want to check at run time\u001b[39;00m\n\u001b[0;32m     20\u001b[0m \u001b[38;5;66;03m# (usually the ones defined in `install_requires` in setup.py)\u001b[39;00m\n\u001b[0;32m     21\u001b[0m \u001b[38;5;66;03m#\u001b[39;00m\n\u001b[0;32m     22\u001b[0m \u001b[38;5;66;03m# order specific notes:\u001b[39;00m\n\u001b[0;32m     23\u001b[0m \u001b[38;5;66;03m# - tqdm must be checked before tokenizers\u001b[39;00m\n\u001b[0;32m     25\u001b[0m pkgs_to_check_at_runtime \u001b[38;5;241m=\u001b[39m [\n\u001b[0;32m     26\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpython\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m     27\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtqdm\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m     37\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpyyaml\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m     38\u001b[0m ]\n",
+      "File \u001b[1;32mc:\\Users\\info\\anaconda3\\Lib\\site-packages\\transformers\\utils\\__init__.py:34\u001b[0m\n\u001b[0;32m     25\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mconstants\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD, IMAGENET_STANDARD_MEAN, IMAGENET_STANDARD_STD\n\u001b[0;32m     26\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mdoc\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[0;32m     27\u001b[0m     add_code_sample_docstrings,\n\u001b[0;32m     28\u001b[0m     add_end_docstrings,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m     32\u001b[0m     replace_return_docstrings,\n\u001b[0;32m     33\u001b[0m )\n\u001b[1;32m---> 34\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mgeneric\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[0;32m     35\u001b[0m     ContextManagers,\n\u001b[0;32m     36\u001b[0m     ExplicitEnum,\n\u001b[0;32m     37\u001b[0m     ModelOutput,\n\u001b[0;32m     38\u001b[0m     PaddingStrategy,\n\u001b[0;32m     39\u001b[0m     TensorType,\n\u001b[0;32m     40\u001b[0m     add_model_info_to_auto_map,\n\u001b[0;32m     41\u001b[0m     add_model_info_to_custom_pipelines,\n\u001b[0;32m     42\u001b[0m     cached_property,\n\u001b[0;32m     43\u001b[0m     can_return_loss,\n\u001b[0;32m     44\u001b[0m     expand_dims,\n\u001b[0;32m     45\u001b[0m     filter_out_non_signature_kwargs,\n\u001b[0;32m     46\u001b[0m     find_labels,\n\u001b[0;32m     47\u001b[0m     flatten_dict,\n\u001b[0;32m     48\u001b[0m     infer_framework,\n\u001b[0;32m     49\u001b[0m     is_jax_tensor,\n\u001b[0;32m     50\u001b[0m     is_numpy_array,\n\u001b[0;32m     51\u001b[0m     is_tensor,\n\u001b[0;32m     52\u001b[0m     is_tf_symbolic_tensor,\n\u001b[0;32m     53\u001b[0m     is_tf_tensor,\n\u001b[0;32m     54\u001b[0m     is_torch_device,\n\u001b[0;32m     55\u001b[0m     is_torch_dtype,\n\u001b[0;32m     56\u001b[0m     is_torch_tensor,\n\u001b[0;32m     57\u001b[0m     reshape,\n\u001b[0;32m     58\u001b[0m     squeeze,\n\u001b[0;32m     59\u001b[0m     strtobool,\n\u001b[0;32m     60\u001b[0m     tensor_size,\n\u001b[0;32m     61\u001b[0m     to_numpy,\n\u001b[0;32m     62\u001b[0m     to_py_obj,\n\u001b[0;32m     63\u001b[0m     torch_float,\n\u001b[0;32m     64\u001b[0m     torch_int,\n\u001b[0;32m     65\u001b[0m     transpose,\n\u001b[0;32m     66\u001b[0m     working_or_temp_dir,\n\u001b[0;32m     67\u001b[0m )\n\u001b[0;32m     68\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mhub\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[0;32m     69\u001b[0m     CLOUDFRONT_DISTRIB_PREFIX,\n\u001b[0;32m     70\u001b[0m     HF_MODULES_CACHE,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m     96\u001b[0m     try_to_load_from_cache,\n\u001b[0;32m     97\u001b[0m )\n\u001b[0;32m     98\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mimport_utils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[0;32m     99\u001b[0m     ACCELERATE_MIN_VERSION,\n\u001b[0;32m    100\u001b[0m     ENV_VARS_TRUE_AND_AUTO_VALUES,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    219\u001b[0m     torch_only_method,\n\u001b[0;32m    220\u001b[0m )\n",
+      "File \u001b[1;32mc:\\Users\\info\\anaconda3\\Lib\\site-packages\\transformers\\utils\\generic.py:462\u001b[0m\n\u001b[0;32m    458\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mtuple\u001b[39m(\u001b[38;5;28mself\u001b[39m[k] \u001b[38;5;28;01mfor\u001b[39;00m k \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mkeys())\n\u001b[0;32m    461\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_torch_available():\n\u001b[1;32m--> 462\u001b[0m     \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtorch\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutils\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m_pytree\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01m_torch_pytree\u001b[39;00m\n\u001b[0;32m    464\u001b[0m     \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_model_output_flatten\u001b[39m(output: ModelOutput) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tuple[List[Any], \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_torch_pytree.Context\u001b[39m\u001b[38;5;124m\"\u001b[39m]:\n\u001b[0;32m    465\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mlist\u001b[39m(output\u001b[38;5;241m.\u001b[39mvalues()), \u001b[38;5;28mlist\u001b[39m(output\u001b[38;5;241m.\u001b[39mkeys())\n",
+      "File \u001b[1;32mc:\\Users\\info\\anaconda3\\Lib\\site-packages\\torch\\__init__.py:148\u001b[0m\n\u001b[0;32m    146\u001b[0m                 err \u001b[38;5;241m=\u001b[39m ctypes\u001b[38;5;241m.\u001b[39mWinError(ctypes\u001b[38;5;241m.\u001b[39mget_last_error())\n\u001b[0;32m    147\u001b[0m                 err\u001b[38;5;241m.\u001b[39mstrerror \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m Error loading \u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mdll\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m or one of its dependencies.\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m--> 148\u001b[0m                 \u001b[38;5;28;01mraise\u001b[39;00m err\n\u001b[0;32m    150\u001b[0m     kernel32\u001b[38;5;241m.\u001b[39mSetErrorMode(prev_error_mode)\n\u001b[0;32m    153\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_preload_cuda_deps\u001b[39m(lib_folder, lib_name):\n",
+      "\u001b[1;31mOSError\u001b[0m: [WinError 126] Belirtilen modül bulunamadı. Error loading \"c:\\Users\\info\\anaconda3\\Lib\\site-packages\\torch\\lib\\fbgemm.dll\" or one of its dependencies."
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import BertTokenizer, BertForMaskedLM, DPRContextEncoderTokenizer,DPRContextEncoder\n",
+    "import torch "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\gitProjects\\makaleChatUI\\myenv\\Lib\\site-packages\\huggingface_hub\\file_download.py:159: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\\Users\\info\\.cache\\huggingface\\hub\\models--bert-base-uncased. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.\n",
+      "To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to see activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development\n",
+      "  warnings.warn(message)\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `beta` will be renamed internally to `bias`. Please use a different name to suppress this warning.\n",
+      "A parameter name that contains `gamma` will be renamed internally to `weight`. Please use a different name to suppress this warning.\n",
+      "Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertForMaskedLM: ['bert.pooler.dense.bias', 'bert.pooler.dense.weight', 'cls.seq_relationship.bias', 'cls.seq_relationship.weight']\n",
+      "- This IS expected if you are initializing BertForMaskedLM from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
+      "- This IS NOT expected if you are initializing BertForMaskedLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
+     ]
+    }
+   ],
+   "source": [
+    "tokenizer= BertTokenizer.from_pretrained('bert-base-uncased')\n",
+    "model=BertForMaskedLM.from_pretrained('bert-base-uncased')\n",
+    "\n",
+    "text=(\"After reading these reports,\"\n",
+    "       \"we start an outline of the application of ML.\"\n",
+    "        \"It includes the [MASK] process \"\n",
+    "        \"and various applications (from various software development to hardware development), to [MASK] of IT systems, and various approaches on analytics.\"\n",
+    "        \"The approach incorporates [MASK] as well as computing and data mining.\"\n",
+    "        \"For example, software developers and manufacturing engineers used AI \"\n",
+    "        \"in manufacturing to develop their applications.\"\n",
+    "      )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "dict_keys(['input_ids', 'token_type_ids', 'attention_mask'])"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#maskeleme yaptıktan sonra tokenlere çeviriyoruz\n",
+    "inputs= tokenizer(text,return_tensors='pt')\n",
+    "inputs.keys()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tensor([[  101,  2044,  3752,  2122,  4311,  1010,  2057,  2707,  2019, 12685,\n",
+       "          1997,  1996,  4646,  1997, 19875,  1012,  2009,  2950,  1996,   103,\n",
+       "          2832,  1998,  2536,  5097,  1006,  2013,  2536,  4007,  2458,  2000,\n",
+       "          8051,  2458,  1007,  1010,  2000,   103,  1997,  2009,  3001,  1010,\n",
+       "          1998,  2536,  8107,  2006, 25095,  1012,  1996,  3921, 12374,   103,\n",
+       "          2004,  2092,  2004,  9798,  1998,  2951,  5471,  1012,  2005,  2742,\n",
+       "          1010,  4007,  9797,  1998,  5814,  6145,  2109,  9932,  1999,  5814,\n",
+       "          2000,  4503,  2037,  5097,  1012,   102]])"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "inputs.input_ids"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text_normal= (\"After reading these reports,\"\n",
+    "       \"we start an outline of the application of ML.\"\n",
+    "        \"It includes the learning process \"\n",
+    "        \"and various applications (from various software development to hardware development), to analysis of IT systems, and various approaches on analytics.\"\n",
+    "        \"The approach incorporates AI as well as computing and data mining.\"\n",
+    "        \"For example, software developers and manufacturing engineers used AI \"\n",
+    "        \"in manufacturing to develop their applications.\"\n",
+    "      )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "dict_keys(['input_ids', 'token_type_ids', 'attention_mask'])"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#texti tokenlere çeviriyoruz\n",
+    "inputs_2= tokenizer(text_normal,return_tensors='pt')\n",
+    "inputs_2.keys()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tensor([[  101,  2044,  3752,  2122,  4311,  1010,  2057,  2707,  2019, 12685,\n",
+       "          1997,  1996,  4646,  1997, 19875,  1012,  2009,  2950,  1996,  4083,\n",
+       "          2832,  1998,  2536,  5097,  1006,  2013,  2536,  4007,  2458,  2000,\n",
+       "          8051,  2458,  1007,  1010,  2000,  4106,  1997,  2009,  3001,  1010,\n",
+       "          1998,  2536,  8107,  2006, 25095,  1012,  1996,  3921, 12374,  9932,\n",
+       "          2004,  2092,  2004,  9798,  1998,  2951,  5471,  1012,  2005,  2742,\n",
+       "          1010,  4007,  9797,  1998,  5814,  6145,  2109,  9932,  1999,  5814,\n",
+       "          2000,  4503,  2037,  5097,  1012,   102]])"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "inputs_2.input_ids"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "inputs_2['labels']= inputs_2.input_ids.detach().clone()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'input_ids': tensor([[  101,  2044,  3752,  2122,  4311,  1010,  2057,  2707,  2019, 12685,\n",
+       "          1997,  1996,  4646,  1997, 19875,  1012,  2009,  2950,  1996,  4083,\n",
+       "          2832,  1998,  2536,  5097,  1006,  2013,  2536,  4007,  2458,  2000,\n",
+       "          8051,  2458,  1007,  1010,  2000,  4106,  1997,  2009,  3001,  1010,\n",
+       "          1998,  2536,  8107,  2006, 25095,  1012,  1996,  3921, 12374,  9932,\n",
+       "          2004,  2092,  2004,  9798,  1998,  2951,  5471,  1012,  2005,  2742,\n",
+       "          1010,  4007,  9797,  1998,  5814,  6145,  2109,  9932,  1999,  5814,\n",
+       "          2000,  4503,  2037,  5097,  1012,   102]]), 'token_type_ids': tensor([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
+       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
+       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
+       "         0, 0, 0, 0]]), 'attention_mask': tensor([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
+       "         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
+       "         1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
+       "         1, 1, 1, 1]]), 'labels': tensor([[  101,  2044,  3752,  2122,  4311,  1010,  2057,  2707,  2019, 12685,\n",
+       "          1997,  1996,  4646,  1997, 19875,  1012,  2009,  2950,  1996,  4083,\n",
+       "          2832,  1998,  2536,  5097,  1006,  2013,  2536,  4007,  2458,  2000,\n",
+       "          8051,  2458,  1007,  1010,  2000,  4106,  1997,  2009,  3001,  1010,\n",
+       "          1998,  2536,  8107,  2006, 25095,  1012,  1996,  3921, 12374,  9932,\n",
+       "          2004,  2092,  2004,  9798,  1998,  2951,  5471,  1012,  2005,  2742,\n",
+       "          1010,  4007,  9797,  1998,  5814,  6145,  2109,  9932,  1999,  5814,\n",
+       "          2000,  4503,  2037,  5097,  1012,   102]])}"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "inputs_2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "torch.Size([1, 76])"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#random tokenler oluşturacağız labelsiz\n",
+    "rand=torch.rand(inputs_2.input_ids.shape)\n",
+    "rand.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tensor([[0.9397, 0.1325, 0.1893, 0.8258, 0.7453, 0.1766, 0.9338, 0.0806, 0.0626,\n",
+       "         0.6665, 0.4240, 0.3946, 0.5413, 0.3799, 0.4023, 0.8699, 0.8159, 0.1511,\n",
+       "         0.6842, 0.0242, 0.7235, 0.0063, 0.1857, 0.9684, 0.8930, 0.8208, 0.5711,\n",
+       "         0.0345, 0.9919, 0.1140, 0.7597, 0.4546, 0.6478, 0.2295, 0.2846, 0.6314,\n",
+       "         0.3640, 0.9291, 0.3843, 0.3553, 0.1125, 0.0790, 0.4261, 0.4307, 0.6724,\n",
+       "         0.8569, 0.4476, 0.8032, 0.0241, 0.0152, 0.4196, 0.5609, 0.0010, 0.7240,\n",
+       "         0.4531, 0.5834, 0.5232, 0.3602, 0.6575, 0.9012, 0.1519, 0.2255, 0.0799,\n",
+       "         0.5673, 0.7244, 0.4387, 0.2713, 0.4243, 0.8435, 0.1670, 0.8664, 0.6261,\n",
+       "         0.4090, 0.2988, 0.3379, 0.7784]])"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "rand"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tensor([[False,  True, False, False, False, False, False,  True,  True, False,\n",
+       "         False, False, False, False, False, False, False, False, False,  True,\n",
+       "         False,  True, False, False, False, False, False,  True, False,  True,\n",
+       "         False, False, False, False, False, False, False, False, False, False,\n",
+       "          True,  True, False, False, False, False, False, False,  True,  True,\n",
+       "         False, False,  True, False, False, False, False, False, False, False,\n",
+       "         False, False,  True, False, False, False, False, False, False, False,\n",
+       "         False, False, False, False, False, False]])"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#cümledeki toknelerin yüzde 15 alınır \n",
+    "#mask_arr = rand < 0.15 ifadesi, rand fonksiyonunun her bir token için rastgele bir sayı üreteceğini ve bu sayının 0.15'ten küçük olup olmadığına bakarak token'ın maskelenip maskelenmeyeceğini belirler. Eğer sayı 0.15'ten küçükse, token maskelenir; değilse, maskelenmez. \n",
+    "mask_arr = rand < 0.15\n",
+    "mask_arr"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[1, 7, 8, 19, 21, 27, 29, 40, 41, 48, 49, 52, 62]"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#burada seçilen değer maskeleme yapılan tokenlarda 0 olmayan karakterlerin yazılmasıdır.\n",
+    "#torch flatten özelliği listeden çıkartarak yalnızca bir array olmasını sağladı\n",
+    "selection= torch.flatten(mask_arr[0].nonzero()).tolist()\n",
+    "selection"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tensor([[  101,   103,  3752,  2122,  4311,  1010,  2057,   103,   103, 12685,\n",
+       "          1997,  1996,  4646,  1997, 19875,  1012,  2009,  2950,  1996,   103,\n",
+       "          2832,   103,  2536,  5097,  1006,  2013,  2536,   103,  2458,   103,\n",
+       "          8051,  2458,  1007,  1010,  2000,  4106,  1997,  2009,  3001,  1010,\n",
+       "           103,   103,  8107,  2006, 25095,  1012,  1996,  3921,   103,   103,\n",
+       "          2004,  2092,   103,  9798,  1998,  2951,  5471,  1012,  2005,  2742,\n",
+       "          1010,  4007,   103,  1998,  5814,  6145,  2109,  9932,  1999,  5814,\n",
+       "          2000,  4503,  2037,  5097,  1012,   102]])"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#input_ids değerleri 0 olanlar için 103 değerinim atadık \n",
+    "inputs_2.input_ids[0,selection]=103\n",
+    "inputs_2.input_ids"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "outputs= model(**inputs_2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "odict_keys(['loss', 'logits'])"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "outputs.keys()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tensor(0.8399, grad_fn=<NllLossBackward0>)"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "outputs.loss"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\gitProjects\\makaleChatUI\\myenv\\Lib\\site-packages\\huggingface_hub\\file_download.py:159: UserWarning: `huggingface_hub` cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\\Users\\info\\.cache\\huggingface\\hub\\models--facebook--dpr-ctx_encoder-single-nq-base. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the `HF_HUB_DISABLE_SYMLINKS_WARNING` environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.\n",
+      "To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to see activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development\n",
+      "  warnings.warn(message)\n",
+      "Some weights of DPRQuestionEncoder were not initialized from the model checkpoint at facebook/dpr-ctx_encoder-single-nq-base and are newly initialized: ['bert_model.embeddings.LayerNorm.bias', 'bert_model.embeddings.LayerNorm.weight', 'bert_model.embeddings.position_embeddings.weight', 'bert_model.embeddings.token_type_embeddings.weight', 'bert_model.embeddings.word_embeddings.weight', 'bert_model.encoder.layer.0.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.0.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.0.attention.output.dense.bias', 'bert_model.encoder.layer.0.attention.output.dense.weight', 'bert_model.encoder.layer.0.attention.self.key.bias', 'bert_model.encoder.layer.0.attention.self.key.weight', 'bert_model.encoder.layer.0.attention.self.query.bias', 'bert_model.encoder.layer.0.attention.self.query.weight', 'bert_model.encoder.layer.0.attention.self.value.bias', 'bert_model.encoder.layer.0.attention.self.value.weight', 'bert_model.encoder.layer.0.intermediate.dense.bias', 'bert_model.encoder.layer.0.intermediate.dense.weight', 'bert_model.encoder.layer.0.output.LayerNorm.bias', 'bert_model.encoder.layer.0.output.LayerNorm.weight', 'bert_model.encoder.layer.0.output.dense.bias', 'bert_model.encoder.layer.0.output.dense.weight', 'bert_model.encoder.layer.1.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.1.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.1.attention.output.dense.bias', 'bert_model.encoder.layer.1.attention.output.dense.weight', 'bert_model.encoder.layer.1.attention.self.key.bias', 'bert_model.encoder.layer.1.attention.self.key.weight', 'bert_model.encoder.layer.1.attention.self.query.bias', 'bert_model.encoder.layer.1.attention.self.query.weight', 'bert_model.encoder.layer.1.attention.self.value.bias', 'bert_model.encoder.layer.1.attention.self.value.weight', 'bert_model.encoder.layer.1.intermediate.dense.bias', 'bert_model.encoder.layer.1.intermediate.dense.weight', 'bert_model.encoder.layer.1.output.LayerNorm.bias', 'bert_model.encoder.layer.1.output.LayerNorm.weight', 'bert_model.encoder.layer.1.output.dense.bias', 'bert_model.encoder.layer.1.output.dense.weight', 'bert_model.encoder.layer.10.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.10.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.10.attention.output.dense.bias', 'bert_model.encoder.layer.10.attention.output.dense.weight', 'bert_model.encoder.layer.10.attention.self.key.bias', 'bert_model.encoder.layer.10.attention.self.key.weight', 'bert_model.encoder.layer.10.attention.self.query.bias', 'bert_model.encoder.layer.10.attention.self.query.weight', 'bert_model.encoder.layer.10.attention.self.value.bias', 'bert_model.encoder.layer.10.attention.self.value.weight', 'bert_model.encoder.layer.10.intermediate.dense.bias', 'bert_model.encoder.layer.10.intermediate.dense.weight', 'bert_model.encoder.layer.10.output.LayerNorm.bias', 'bert_model.encoder.layer.10.output.LayerNorm.weight', 'bert_model.encoder.layer.10.output.dense.bias', 'bert_model.encoder.layer.10.output.dense.weight', 'bert_model.encoder.layer.11.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.11.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.11.attention.output.dense.bias', 'bert_model.encoder.layer.11.attention.output.dense.weight', 'bert_model.encoder.layer.11.attention.self.key.bias', 'bert_model.encoder.layer.11.attention.self.key.weight', 'bert_model.encoder.layer.11.attention.self.query.bias', 'bert_model.encoder.layer.11.attention.self.query.weight', 'bert_model.encoder.layer.11.attention.self.value.bias', 'bert_model.encoder.layer.11.attention.self.value.weight', 'bert_model.encoder.layer.11.intermediate.dense.bias', 'bert_model.encoder.layer.11.intermediate.dense.weight', 'bert_model.encoder.layer.11.output.LayerNorm.bias', 'bert_model.encoder.layer.11.output.LayerNorm.weight', 'bert_model.encoder.layer.11.output.dense.bias', 'bert_model.encoder.layer.11.output.dense.weight', 'bert_model.encoder.layer.2.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.2.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.2.attention.output.dense.bias', 'bert_model.encoder.layer.2.attention.output.dense.weight', 'bert_model.encoder.layer.2.attention.self.key.bias', 'bert_model.encoder.layer.2.attention.self.key.weight', 'bert_model.encoder.layer.2.attention.self.query.bias', 'bert_model.encoder.layer.2.attention.self.query.weight', 'bert_model.encoder.layer.2.attention.self.value.bias', 'bert_model.encoder.layer.2.attention.self.value.weight', 'bert_model.encoder.layer.2.intermediate.dense.bias', 'bert_model.encoder.layer.2.intermediate.dense.weight', 'bert_model.encoder.layer.2.output.LayerNorm.bias', 'bert_model.encoder.layer.2.output.LayerNorm.weight', 'bert_model.encoder.layer.2.output.dense.bias', 'bert_model.encoder.layer.2.output.dense.weight', 'bert_model.encoder.layer.3.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.3.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.3.attention.output.dense.bias', 'bert_model.encoder.layer.3.attention.output.dense.weight', 'bert_model.encoder.layer.3.attention.self.key.bias', 'bert_model.encoder.layer.3.attention.self.key.weight', 'bert_model.encoder.layer.3.attention.self.query.bias', 'bert_model.encoder.layer.3.attention.self.query.weight', 'bert_model.encoder.layer.3.attention.self.value.bias', 'bert_model.encoder.layer.3.attention.self.value.weight', 'bert_model.encoder.layer.3.intermediate.dense.bias', 'bert_model.encoder.layer.3.intermediate.dense.weight', 'bert_model.encoder.layer.3.output.LayerNorm.bias', 'bert_model.encoder.layer.3.output.LayerNorm.weight', 'bert_model.encoder.layer.3.output.dense.bias', 'bert_model.encoder.layer.3.output.dense.weight', 'bert_model.encoder.layer.4.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.4.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.4.attention.output.dense.bias', 'bert_model.encoder.layer.4.attention.output.dense.weight', 'bert_model.encoder.layer.4.attention.self.key.bias', 'bert_model.encoder.layer.4.attention.self.key.weight', 'bert_model.encoder.layer.4.attention.self.query.bias', 'bert_model.encoder.layer.4.attention.self.query.weight', 'bert_model.encoder.layer.4.attention.self.value.bias', 'bert_model.encoder.layer.4.attention.self.value.weight', 'bert_model.encoder.layer.4.intermediate.dense.bias', 'bert_model.encoder.layer.4.intermediate.dense.weight', 'bert_model.encoder.layer.4.output.LayerNorm.bias', 'bert_model.encoder.layer.4.output.LayerNorm.weight', 'bert_model.encoder.layer.4.output.dense.bias', 'bert_model.encoder.layer.4.output.dense.weight', 'bert_model.encoder.layer.5.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.5.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.5.attention.output.dense.bias', 'bert_model.encoder.layer.5.attention.output.dense.weight', 'bert_model.encoder.layer.5.attention.self.key.bias', 'bert_model.encoder.layer.5.attention.self.key.weight', 'bert_model.encoder.layer.5.attention.self.query.bias', 'bert_model.encoder.layer.5.attention.self.query.weight', 'bert_model.encoder.layer.5.attention.self.value.bias', 'bert_model.encoder.layer.5.attention.self.value.weight', 'bert_model.encoder.layer.5.intermediate.dense.bias', 'bert_model.encoder.layer.5.intermediate.dense.weight', 'bert_model.encoder.layer.5.output.LayerNorm.bias', 'bert_model.encoder.layer.5.output.LayerNorm.weight', 'bert_model.encoder.layer.5.output.dense.bias', 'bert_model.encoder.layer.5.output.dense.weight', 'bert_model.encoder.layer.6.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.6.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.6.attention.output.dense.bias', 'bert_model.encoder.layer.6.attention.output.dense.weight', 'bert_model.encoder.layer.6.attention.self.key.bias', 'bert_model.encoder.layer.6.attention.self.key.weight', 'bert_model.encoder.layer.6.attention.self.query.bias', 'bert_model.encoder.layer.6.attention.self.query.weight', 'bert_model.encoder.layer.6.attention.self.value.bias', 'bert_model.encoder.layer.6.attention.self.value.weight', 'bert_model.encoder.layer.6.intermediate.dense.bias', 'bert_model.encoder.layer.6.intermediate.dense.weight', 'bert_model.encoder.layer.6.output.LayerNorm.bias', 'bert_model.encoder.layer.6.output.LayerNorm.weight', 'bert_model.encoder.layer.6.output.dense.bias', 'bert_model.encoder.layer.6.output.dense.weight', 'bert_model.encoder.layer.7.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.7.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.7.attention.output.dense.bias', 'bert_model.encoder.layer.7.attention.output.dense.weight', 'bert_model.encoder.layer.7.attention.self.key.bias', 'bert_model.encoder.layer.7.attention.self.key.weight', 'bert_model.encoder.layer.7.attention.self.query.bias', 'bert_model.encoder.layer.7.attention.self.query.weight', 'bert_model.encoder.layer.7.attention.self.value.bias', 'bert_model.encoder.layer.7.attention.self.value.weight', 'bert_model.encoder.layer.7.intermediate.dense.bias', 'bert_model.encoder.layer.7.intermediate.dense.weight', 'bert_model.encoder.layer.7.output.LayerNorm.bias', 'bert_model.encoder.layer.7.output.LayerNorm.weight', 'bert_model.encoder.layer.7.output.dense.bias', 'bert_model.encoder.layer.7.output.dense.weight', 'bert_model.encoder.layer.8.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.8.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.8.attention.output.dense.bias', 'bert_model.encoder.layer.8.attention.output.dense.weight', 'bert_model.encoder.layer.8.attention.self.key.bias', 'bert_model.encoder.layer.8.attention.self.key.weight', 'bert_model.encoder.layer.8.attention.self.query.bias', 'bert_model.encoder.layer.8.attention.self.query.weight', 'bert_model.encoder.layer.8.attention.self.value.bias', 'bert_model.encoder.layer.8.attention.self.value.weight', 'bert_model.encoder.layer.8.intermediate.dense.bias', 'bert_model.encoder.layer.8.intermediate.dense.weight', 'bert_model.encoder.layer.8.output.LayerNorm.bias', 'bert_model.encoder.layer.8.output.LayerNorm.weight', 'bert_model.encoder.layer.8.output.dense.bias', 'bert_model.encoder.layer.8.output.dense.weight', 'bert_model.encoder.layer.9.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.9.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.9.attention.output.dense.bias', 'bert_model.encoder.layer.9.attention.output.dense.weight', 'bert_model.encoder.layer.9.attention.self.key.bias', 'bert_model.encoder.layer.9.attention.self.key.weight', 'bert_model.encoder.layer.9.attention.self.query.bias', 'bert_model.encoder.layer.9.attention.self.query.weight', 'bert_model.encoder.layer.9.attention.self.value.bias', 'bert_model.encoder.layer.9.attention.self.value.weight', 'bert_model.encoder.layer.9.intermediate.dense.bias', 'bert_model.encoder.layer.9.intermediate.dense.weight', 'bert_model.encoder.layer.9.output.LayerNorm.bias', 'bert_model.encoder.layer.9.output.LayerNorm.weight', 'bert_model.encoder.layer.9.output.dense.bias', 'bert_model.encoder.layer.9.output.dense.weight']\n",
+      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n",
+      "Some weights of DPRQuestionEncoder were not initialized from the model checkpoint at facebook/dpr-ctx_encoder-single-nq-base and are newly initialized: ['bert_model.embeddings.LayerNorm.bias', 'bert_model.embeddings.LayerNorm.weight', 'bert_model.embeddings.position_embeddings.weight', 'bert_model.embeddings.token_type_embeddings.weight', 'bert_model.embeddings.word_embeddings.weight', 'bert_model.encoder.layer.0.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.0.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.0.attention.output.dense.bias', 'bert_model.encoder.layer.0.attention.output.dense.weight', 'bert_model.encoder.layer.0.attention.self.key.bias', 'bert_model.encoder.layer.0.attention.self.key.weight', 'bert_model.encoder.layer.0.attention.self.query.bias', 'bert_model.encoder.layer.0.attention.self.query.weight', 'bert_model.encoder.layer.0.attention.self.value.bias', 'bert_model.encoder.layer.0.attention.self.value.weight', 'bert_model.encoder.layer.0.intermediate.dense.bias', 'bert_model.encoder.layer.0.intermediate.dense.weight', 'bert_model.encoder.layer.0.output.LayerNorm.bias', 'bert_model.encoder.layer.0.output.LayerNorm.weight', 'bert_model.encoder.layer.0.output.dense.bias', 'bert_model.encoder.layer.0.output.dense.weight', 'bert_model.encoder.layer.1.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.1.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.1.attention.output.dense.bias', 'bert_model.encoder.layer.1.attention.output.dense.weight', 'bert_model.encoder.layer.1.attention.self.key.bias', 'bert_model.encoder.layer.1.attention.self.key.weight', 'bert_model.encoder.layer.1.attention.self.query.bias', 'bert_model.encoder.layer.1.attention.self.query.weight', 'bert_model.encoder.layer.1.attention.self.value.bias', 'bert_model.encoder.layer.1.attention.self.value.weight', 'bert_model.encoder.layer.1.intermediate.dense.bias', 'bert_model.encoder.layer.1.intermediate.dense.weight', 'bert_model.encoder.layer.1.output.LayerNorm.bias', 'bert_model.encoder.layer.1.output.LayerNorm.weight', 'bert_model.encoder.layer.1.output.dense.bias', 'bert_model.encoder.layer.1.output.dense.weight', 'bert_model.encoder.layer.10.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.10.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.10.attention.output.dense.bias', 'bert_model.encoder.layer.10.attention.output.dense.weight', 'bert_model.encoder.layer.10.attention.self.key.bias', 'bert_model.encoder.layer.10.attention.self.key.weight', 'bert_model.encoder.layer.10.attention.self.query.bias', 'bert_model.encoder.layer.10.attention.self.query.weight', 'bert_model.encoder.layer.10.attention.self.value.bias', 'bert_model.encoder.layer.10.attention.self.value.weight', 'bert_model.encoder.layer.10.intermediate.dense.bias', 'bert_model.encoder.layer.10.intermediate.dense.weight', 'bert_model.encoder.layer.10.output.LayerNorm.bias', 'bert_model.encoder.layer.10.output.LayerNorm.weight', 'bert_model.encoder.layer.10.output.dense.bias', 'bert_model.encoder.layer.10.output.dense.weight', 'bert_model.encoder.layer.11.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.11.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.11.attention.output.dense.bias', 'bert_model.encoder.layer.11.attention.output.dense.weight', 'bert_model.encoder.layer.11.attention.self.key.bias', 'bert_model.encoder.layer.11.attention.self.key.weight', 'bert_model.encoder.layer.11.attention.self.query.bias', 'bert_model.encoder.layer.11.attention.self.query.weight', 'bert_model.encoder.layer.11.attention.self.value.bias', 'bert_model.encoder.layer.11.attention.self.value.weight', 'bert_model.encoder.layer.11.intermediate.dense.bias', 'bert_model.encoder.layer.11.intermediate.dense.weight', 'bert_model.encoder.layer.11.output.LayerNorm.bias', 'bert_model.encoder.layer.11.output.LayerNorm.weight', 'bert_model.encoder.layer.11.output.dense.bias', 'bert_model.encoder.layer.11.output.dense.weight', 'bert_model.encoder.layer.2.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.2.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.2.attention.output.dense.bias', 'bert_model.encoder.layer.2.attention.output.dense.weight', 'bert_model.encoder.layer.2.attention.self.key.bias', 'bert_model.encoder.layer.2.attention.self.key.weight', 'bert_model.encoder.layer.2.attention.self.query.bias', 'bert_model.encoder.layer.2.attention.self.query.weight', 'bert_model.encoder.layer.2.attention.self.value.bias', 'bert_model.encoder.layer.2.attention.self.value.weight', 'bert_model.encoder.layer.2.intermediate.dense.bias', 'bert_model.encoder.layer.2.intermediate.dense.weight', 'bert_model.encoder.layer.2.output.LayerNorm.bias', 'bert_model.encoder.layer.2.output.LayerNorm.weight', 'bert_model.encoder.layer.2.output.dense.bias', 'bert_model.encoder.layer.2.output.dense.weight', 'bert_model.encoder.layer.3.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.3.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.3.attention.output.dense.bias', 'bert_model.encoder.layer.3.attention.output.dense.weight', 'bert_model.encoder.layer.3.attention.self.key.bias', 'bert_model.encoder.layer.3.attention.self.key.weight', 'bert_model.encoder.layer.3.attention.self.query.bias', 'bert_model.encoder.layer.3.attention.self.query.weight', 'bert_model.encoder.layer.3.attention.self.value.bias', 'bert_model.encoder.layer.3.attention.self.value.weight', 'bert_model.encoder.layer.3.intermediate.dense.bias', 'bert_model.encoder.layer.3.intermediate.dense.weight', 'bert_model.encoder.layer.3.output.LayerNorm.bias', 'bert_model.encoder.layer.3.output.LayerNorm.weight', 'bert_model.encoder.layer.3.output.dense.bias', 'bert_model.encoder.layer.3.output.dense.weight', 'bert_model.encoder.layer.4.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.4.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.4.attention.output.dense.bias', 'bert_model.encoder.layer.4.attention.output.dense.weight', 'bert_model.encoder.layer.4.attention.self.key.bias', 'bert_model.encoder.layer.4.attention.self.key.weight', 'bert_model.encoder.layer.4.attention.self.query.bias', 'bert_model.encoder.layer.4.attention.self.query.weight', 'bert_model.encoder.layer.4.attention.self.value.bias', 'bert_model.encoder.layer.4.attention.self.value.weight', 'bert_model.encoder.layer.4.intermediate.dense.bias', 'bert_model.encoder.layer.4.intermediate.dense.weight', 'bert_model.encoder.layer.4.output.LayerNorm.bias', 'bert_model.encoder.layer.4.output.LayerNorm.weight', 'bert_model.encoder.layer.4.output.dense.bias', 'bert_model.encoder.layer.4.output.dense.weight', 'bert_model.encoder.layer.5.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.5.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.5.attention.output.dense.bias', 'bert_model.encoder.layer.5.attention.output.dense.weight', 'bert_model.encoder.layer.5.attention.self.key.bias', 'bert_model.encoder.layer.5.attention.self.key.weight', 'bert_model.encoder.layer.5.attention.self.query.bias', 'bert_model.encoder.layer.5.attention.self.query.weight', 'bert_model.encoder.layer.5.attention.self.value.bias', 'bert_model.encoder.layer.5.attention.self.value.weight', 'bert_model.encoder.layer.5.intermediate.dense.bias', 'bert_model.encoder.layer.5.intermediate.dense.weight', 'bert_model.encoder.layer.5.output.LayerNorm.bias', 'bert_model.encoder.layer.5.output.LayerNorm.weight', 'bert_model.encoder.layer.5.output.dense.bias', 'bert_model.encoder.layer.5.output.dense.weight', 'bert_model.encoder.layer.6.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.6.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.6.attention.output.dense.bias', 'bert_model.encoder.layer.6.attention.output.dense.weight', 'bert_model.encoder.layer.6.attention.self.key.bias', 'bert_model.encoder.layer.6.attention.self.key.weight', 'bert_model.encoder.layer.6.attention.self.query.bias', 'bert_model.encoder.layer.6.attention.self.query.weight', 'bert_model.encoder.layer.6.attention.self.value.bias', 'bert_model.encoder.layer.6.attention.self.value.weight', 'bert_model.encoder.layer.6.intermediate.dense.bias', 'bert_model.encoder.layer.6.intermediate.dense.weight', 'bert_model.encoder.layer.6.output.LayerNorm.bias', 'bert_model.encoder.layer.6.output.LayerNorm.weight', 'bert_model.encoder.layer.6.output.dense.bias', 'bert_model.encoder.layer.6.output.dense.weight', 'bert_model.encoder.layer.7.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.7.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.7.attention.output.dense.bias', 'bert_model.encoder.layer.7.attention.output.dense.weight', 'bert_model.encoder.layer.7.attention.self.key.bias', 'bert_model.encoder.layer.7.attention.self.key.weight', 'bert_model.encoder.layer.7.attention.self.query.bias', 'bert_model.encoder.layer.7.attention.self.query.weight', 'bert_model.encoder.layer.7.attention.self.value.bias', 'bert_model.encoder.layer.7.attention.self.value.weight', 'bert_model.encoder.layer.7.intermediate.dense.bias', 'bert_model.encoder.layer.7.intermediate.dense.weight', 'bert_model.encoder.layer.7.output.LayerNorm.bias', 'bert_model.encoder.layer.7.output.LayerNorm.weight', 'bert_model.encoder.layer.7.output.dense.bias', 'bert_model.encoder.layer.7.output.dense.weight', 'bert_model.encoder.layer.8.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.8.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.8.attention.output.dense.bias', 'bert_model.encoder.layer.8.attention.output.dense.weight', 'bert_model.encoder.layer.8.attention.self.key.bias', 'bert_model.encoder.layer.8.attention.self.key.weight', 'bert_model.encoder.layer.8.attention.self.query.bias', 'bert_model.encoder.layer.8.attention.self.query.weight', 'bert_model.encoder.layer.8.attention.self.value.bias', 'bert_model.encoder.layer.8.attention.self.value.weight', 'bert_model.encoder.layer.8.intermediate.dense.bias', 'bert_model.encoder.layer.8.intermediate.dense.weight', 'bert_model.encoder.layer.8.output.LayerNorm.bias', 'bert_model.encoder.layer.8.output.LayerNorm.weight', 'bert_model.encoder.layer.8.output.dense.bias', 'bert_model.encoder.layer.8.output.dense.weight', 'bert_model.encoder.layer.9.attention.output.LayerNorm.bias', 'bert_model.encoder.layer.9.attention.output.LayerNorm.weight', 'bert_model.encoder.layer.9.attention.output.dense.bias', 'bert_model.encoder.layer.9.attention.output.dense.weight', 'bert_model.encoder.layer.9.attention.self.key.bias', 'bert_model.encoder.layer.9.attention.self.key.weight', 'bert_model.encoder.layer.9.attention.self.query.bias', 'bert_model.encoder.layer.9.attention.self.query.weight', 'bert_model.encoder.layer.9.attention.self.value.bias', 'bert_model.encoder.layer.9.attention.self.value.weight', 'bert_model.encoder.layer.9.intermediate.dense.bias', 'bert_model.encoder.layer.9.intermediate.dense.weight', 'bert_model.encoder.layer.9.output.LayerNorm.bias', 'bert_model.encoder.layer.9.output.LayerNorm.weight', 'bert_model.encoder.layer.9.output.dense.bias', 'bert_model.encoder.layer.9.output.dense.weight']\n",
+      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n",
+      "Some weights of the model checkpoint at facebook/dpr-question_encoder-single-nq-base were not used when initializing DPRQuestionEncoder: ['question_encoder.bert_model.pooler.dense.bias', 'question_encoder.bert_model.pooler.dense.weight']\n",
+      "- This IS expected if you are initializing DPRQuestionEncoder from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
+      "- This IS NOT expected if you are initializing DPRQuestionEncoder from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
+     ]
+    }
+   ],
+   "source": [
+    "from transformers import DPRQuestionEncoder, DPRQuestionEncoderTokenizer\n",
+    "\n",
+    "ctx_model=DPRQuestionEncoder.from_pretrained('facebook/dpr-ctx_encoder-single-nq-base')\n",
+    "ctx_tokenizer=DPRQuestionEncoder.from_pretrained('facebook/dpr-ctx_encoder-single-nq-base')\n",
+    "\n",
+    "question_tokenizer = DPRQuestionEncoderTokenizer.from_pretrained('facebook/dpr-question_encoder-single-nq-base')\n",
+    "question_model = DPRQuestionEncoder.from_pretrained('facebook/dpr-question_encoder-single-nq-base')\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\"\"\"title = [\"2024 Yılında Mobil Teknoloji Trendleri\"]\n",
+    "keywords = [\"mobil teknoloji\", \"2024 trendleri\", \"akıllı telefon yenilikleri\", \"5G teknolojisi\", \"giyilebilir cihazlar\"]\n",
+    "subheading = [\n",
+    "    \"2024'te Akıllı Telefonlardaki Yenilikler\",\n",
+    "    \"Giyilebilir Teknolojiler: Sağlık ve Fitness Trendleri\",\n",
+    "    \"5G'nin Mobil Cihazlar Üzerindeki Etkisi\",\n",
+    "    \"Mobil Güvenlikte Yeni Yaklaşımlar\"\n",
+    "]\"\"\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "xb_tokens=ctx_tokenizer()\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "myenv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

alternatif.txt

@@ -0,0 +1,10 @@
+Alternatif Yollar
+LDA (Latent Dirichlet Allocation): Konu modelleme yöntemlerinden biridir ve belgelerdeki ana temaları belirlemek için kullanılabilir.
+
+BERT ve Transformer Modelleri: Önerilen transformer tabanlı modeller, bağlam analizi için güçlüdür ve metinleri anlamak ve anahtar kelimeleri çıkarmak için kullanılabilir.
+
+TF-IDF ile Birlikte LDA: TF-IDF ve LDA’nın kombinasyonu, hem anahtar kelime hem de konu modellemesi için kullanılabilir.
+
+Sentence Embeddings ve Similitude Modeling: Sentence-BERT gibi modeller kullanarak metinler arasındaki benzerlikleri ölçebilir ve bu benzerlikleri anahtar kelime çıkarımı ile birleştirebilirsiniz.
+
+Pretrained Language Models: Hugging Face gibi kütüphaneler üzerinden önceden eğitilmiş modeller kullanarak, daha doğru ve bağlamlı anahtar kelime çıkarımı ve metin analizi yapılabilir.

combined_output.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d132586c17782ba7dabc58b6b8c11b797a65890e95a605b38b208caa08d984e
+size 1476218231

datasets.ipynb

@@ -437,9 +437,16 @@
     "TF-IDF HESAPLAMA"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Token vektörlerinin ortalamasını alarak metin düzeyinde özet oluşturacak şekilde k-means ve tf-ıdf algoritmalarını kullanarak keyword oluşturmak "
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 31,
    "metadata": {},
    "outputs": [
     {
@@ -447,165 +454,104 @@
      "output_type": "stream",
      "text": [
       "Tokens: ['[CLS]', 'Biy', '##ografi', 'İsim', 'P', '##şı', '##q', '##o', 'ismi', 'Ah', '##ec', '##a', '##q', '##o', 'soy', 'ismi', '##dir', '.', 'Çerkes', '##lerin', '\"', '-', 'q', '##o', '\"', 'son', '##eki', 'ile', 'biten', 'hem', 'soya', '##d', '##ları', 'hem', 'de', 'lak', '##ap', '##ları', 'vardı', '.', 'Bu', 'ek', 'Türkçe', 'ad', '##lardaki', '\"', '-', 'oğlu', '\"', 'eki', '##yle', 'eş', 'anlamlı', '##dır', '.', 'P', '##şı', '##q', '##o', 'Türkçe', '\"', 'Beyoğlu', '\"', 'anlamına', 'gelen', 'bir', 'lak', '##ap', '##tır', '.', 'Erken', 'dönem', 'Çerkes', '##ler', 'tarihleri', '##ni', 'yazma', '##dıkları', 've', 'tüm', 'bilgiler', 'Rus', 'kaynaklarından', 'geldiği', 'için', 'Ah', '##ec', '##a', '##q', '##o', 'hakkında', 'pek', 'bir', 'şey', 'kayded', '##ilme', '##di', '.', '177', '##7', \"'\", 'de', 'Çerkes', '##ya', \"'\", 'nın', 'B', '##je', '##duğ', 'bölgesinde', 'doğdu', '.', 'Asker', '##î', 'eğitim', 'ile', 'büyüt', '##üldü', '.', 'Rus', '-', 'Çerkes', 'Savaşı', '##na', 'Katılım', '##ı', 'Birkaç', 'kaynak', ',', 'Ah', '##ec', '##a', '##q', '##o', \"'\", 'nun', 'tüm', 'Çerkes', '##ya', \"'\", 'da', 'saygı', 'duyulan', 'bir', 'kişi', 'olduğunu', 'belirtir', '.', 'En', 'az', '6', '.', '000', 'at', '##lı', '##dan', 'oluşan', 'kalıcı', 'bir', 'ordusu', 'vardı', 've', 'çatışmalar', 'sırasında', 'müfre', '##ze', '##si', '12', '.', '000', 'at', '##lı', '##ya', 'ulaşıyor', '##du', '.', 'Rus', 'birlikleri', '##ne', 'karşı', 'kazandığı', 'zafer', '##lerle', 'ünlü', '##y', '##dü', '.', 'Askeri', 'becerisi', '##nin', 'yanı', 'sıra', 'yetenekli', 'bir', 'devlet', 'adamı', '##ydı', '.', 'Ölüm', '18', '##37', 'yılında', 'Rus', 'tarafına', 'geçti', 've', 'bir', 'yıl', 'sonra', 'hastalık', '##tan', 'öldü', '.', 'Kaynak', '##ça', 'Çerkes', 'soylu', '##lar', '177', '##7', 'doğumlu', '##lar', '18', '##38', 'yılında', 'ölen', '##ler', 'Kafkas', 'Savaşı', \"'\", 'nda', 'kişiler', '[SEP]']\n",
-      "Average Embedding Shape: torch.Size([768])\n",
-      "Average Embedding: tensor([ 3.1219e-01, -3.4488e-02,  1.1118e-02, -3.6194e-02,  1.3312e-02,\n",
-      "         8.7684e-02,  6.0835e-01, -5.8831e-03,  4.2102e-01,  3.7467e-01,\n",
-      "        -1.9954e-01,  2.5975e-01, -8.9819e-02,  6.8351e-02, -2.3226e-01,\n",
-      "        -6.4409e-02,  1.1375e-01,  6.9892e-02,  3.4909e-01, -2.0660e-01,\n",
-      "         4.2718e-02, -2.3758e-01, -1.2146e-01,  6.9431e-01,  8.2034e-02,\n",
-      "        -4.4726e-01, -3.9995e-01,  4.9043e-01, -5.3700e-01,  4.0028e-02,\n",
-      "         2.4516e-02, -1.9234e-01, -5.9901e-02,  4.0203e-01,  1.7956e-01,\n",
-      "         2.7692e-01,  4.2539e-01, -1.0046e-01, -1.9326e-01, -2.3722e-01,\n",
-      "         3.9989e-01,  1.1785e-01, -3.7475e-01, -4.7698e-01,  1.2440e-01,\n",
-      "         1.7583e-01,  4.7179e-01, -6.1670e-01,  3.4876e-01, -1.1977e-01,\n",
-      "         4.3870e-01, -4.7105e-01,  3.8414e-01,  3.6902e-01, -1.2121e-02,\n",
-      "        -3.3284e-02,  2.5584e-01,  2.0225e-01,  1.4411e-01,  2.9933e-01,\n",
-      "         3.6910e-01,  2.3893e-01,  6.0434e-01,  1.5669e-01, -8.5170e-01,\n",
-      "        -2.5171e-01,  3.6258e-01,  4.5186e-01, -2.9369e-01,  3.8370e-01,\n",
-      "         4.9858e-01, -7.5623e-02,  1.1362e-02, -1.3621e-01, -2.7373e-01,\n",
-      "        -3.1269e-01, -6.4951e-01, -6.9747e-02,  2.1302e-01,  3.4201e-01,\n",
-      "        -3.8148e-01, -3.2749e-02,  7.4201e-01, -6.0619e-01, -1.8069e-01,\n",
-      "        -1.5151e-01,  7.6336e-02, -4.0224e-02, -5.9742e-01, -1.7219e-02,\n",
-      "        -5.6787e-01,  2.6290e-01,  2.3984e-01,  4.8434e-01,  4.7557e-01,\n",
-      "         2.2432e-01, -1.0822e-01,  3.5924e-01, -4.4102e-01, -1.1613e+00,\n",
-      "         5.3896e-02, -2.8951e-01, -1.0792e+00, -2.2577e-02, -2.9868e-01,\n",
-      "        -2.7837e-01,  1.0477e-01,  3.8852e-01,  2.9142e-01, -4.2427e-01,\n",
-      "         3.6626e-01,  7.9898e-02,  2.2686e-01,  2.3253e-02, -6.9434e-01,\n",
-      "         3.2550e+00, -5.6280e-02,  1.1168e-01,  4.2853e-01,  7.7213e-02,\n",
-      "         3.1671e-01, -2.9387e-01, -2.1341e-01, -7.9131e-02, -1.0102e-01,\n",
-      "        -5.7301e-01,  5.6494e-01,  2.0392e-01, -2.6974e-01, -9.0448e-01,\n",
-      "        -7.6977e-01,  5.1432e-02, -1.3809e-01,  2.2806e-01, -3.8749e-01,\n",
-      "         4.0886e-01,  2.2627e-02, -2.4360e-02, -1.0032e-01, -8.8879e-03,\n",
-      "        -2.9814e-01,  2.4151e-01, -6.5038e-01,  5.5605e-01, -1.5214e-02,\n",
-      "        -4.4102e-01,  2.1589e-01,  8.9567e-02, -3.3454e-01,  4.1183e-01,\n",
-      "        -2.5177e-02, -4.8496e-01,  3.7691e-01,  6.1995e-02, -2.9426e-01,\n",
-      "        -1.5210e-01,  5.1504e-01,  4.9226e-01,  1.0083e-01,  1.9789e-01,\n",
-      "         6.5205e-01, -9.7679e-02,  3.4597e-02,  9.5440e-02,  6.5158e-01,\n",
-      "        -5.6019e-01, -1.1912e-01,  1.9009e-01,  1.1314e-01,  1.0752e-01,\n",
-      "         4.7765e-01,  2.5196e-01, -1.5925e-01,  1.3468e-01, -1.9441e-01,\n",
-      "        -5.0252e-02,  4.2977e-01,  2.7336e-01,  4.7672e-02,  2.3097e-01,\n",
-      "         1.5998e-01, -1.3434e-01,  3.8424e-01, -3.9759e-01, -2.6207e-02,\n",
-      "         2.9264e-02, -1.2846e-01, -3.9234e-01, -2.3295e-01, -1.4392e-01,\n",
-      "         7.9061e-02,  2.8095e-01, -1.6391e-01,  2.0505e-01, -1.2172e-01,\n",
-      "        -2.5179e-01,  8.8469e-02, -1.5946e+00, -6.6211e-01,  1.6993e-01,\n",
-      "        -1.6472e-02,  2.5519e-01, -2.4024e-02,  5.7010e-01,  6.1551e-03,\n",
-      "         7.0113e-02, -3.9507e-01, -2.2114e-02, -2.0259e-01, -8.9107e-03,\n",
-      "         1.1820e-01, -1.0522e-02,  5.2899e-01, -3.6007e-01, -5.6266e-01,\n",
-      "         1.3287e-01, -5.8443e-01, -2.5912e-01, -4.3816e-02, -1.1244e-01,\n",
-      "         1.0696e+00,  3.1219e-01, -4.1700e-01,  1.1373e-01, -2.2935e-01,\n",
-      "        -1.4058e-02,  2.6080e-01,  6.1457e-03,  5.5064e-02,  5.2089e-01,\n",
-      "         1.3195e-01, -6.0868e-01,  4.0164e-01, -1.8374e-01,  8.4919e-01,\n",
-      "        -4.2096e-01, -3.7411e-01,  1.8478e-02, -5.6272e-01, -2.5044e-01,\n",
-      "        -1.1385e-01,  1.6000e-01,  3.3307e-01, -5.7846e-02, -4.1887e-02,\n",
-      "        -1.7514e-01,  2.8522e-01, -3.3909e-01,  1.7133e-01,  2.4794e-02,\n",
-      "        -3.0897e-01,  1.7487e-01, -4.8215e-01, -1.0892e-01,  1.0915e-01,\n",
-      "        -2.9227e-02, -6.7439e-02, -3.6022e-01, -8.8648e-02,  2.5974e-01,\n",
-      "        -2.2780e-02,  1.8174e-02,  8.9919e-02,  1.6508e+00, -6.3506e-01,\n",
-      "         4.9391e-01,  7.9321e-02,  3.2023e-02,  3.1216e-01, -7.8220e-02,\n",
-      "         3.5055e-01, -2.8349e-01, -4.8787e-01, -5.3590e-01, -4.5163e-01,\n",
-      "         2.4602e-01,  4.0553e-01, -2.9002e-01, -1.6120e-01,  1.3428e-02,\n",
-      "         4.7906e-01,  2.2494e-01,  3.5909e-01,  1.2861e-01, -1.7966e-01,\n",
-      "         9.8253e-02, -9.9344e-02,  2.3110e-01,  3.1276e-01,  6.4092e-02,\n",
-      "         2.7386e-01, -3.8601e-01, -5.6480e-01, -5.6070e-01, -6.4271e-02,\n",
-      "        -2.8354e-01,  6.7687e-02, -5.7471e-01,  3.0518e-02, -1.3380e-02,\n",
-      "        -3.6718e-01,  3.8880e-01, -1.9569e-01,  2.8110e-01, -2.9406e-01,\n",
-      "        -2.5891e-01, -3.0043e-01, -3.3694e-01,  5.7723e-02, -1.2361e+00,\n",
-      "        -1.1917e-01, -2.6665e-01, -5.6574e-02, -3.8907e-01,  4.2425e-01,\n",
-      "        -6.5229e-02,  6.5768e-01, -1.0842e-01, -7.0508e-01,  8.4208e-02,\n",
-      "        -3.7736e-01,  3.2153e-01,  5.6956e-01,  1.2256e-01,  4.2261e-01,\n",
-      "        -2.7749e-01,  7.9419e-02, -8.1517e-02, -3.0462e-02,  1.5746e-01,\n",
-      "        -8.7179e-02,  1.8869e-01,  4.1413e-01,  3.7192e-01, -1.9835e-01,\n",
-      "        -2.5932e-01,  5.4023e-02, -3.8093e-01,  1.1605e-01, -1.4389e-01,\n",
-      "        -4.5509e-01, -6.0786e-01,  4.2643e-01,  1.6004e-01, -3.4740e-02,\n",
-      "        -4.4579e-01, -5.6887e-01, -1.1662e-01,  2.1577e-01,  6.6576e-03,\n",
-      "        -2.3879e-01,  4.4046e-01, -2.6281e-01,  2.4404e-01,  8.1931e-02,\n",
-      "         2.2825e-01, -1.5294e-01, -3.7482e-01,  8.8104e-02,  4.0676e-01,\n",
-      "         1.6295e-01,  5.8565e-01, -8.0144e-02, -4.1792e-01, -4.6798e-01,\n",
-      "         3.9977e-01, -3.7319e-01, -1.2999e-01, -4.4200e-01, -2.9825e-01,\n",
-      "        -1.2899e-01, -1.8651e-01, -2.0209e-02, -6.6213e-01,  5.0630e-02,\n",
-      "        -4.6655e-01, -4.3796e-01,  6.7476e-02,  3.4367e-01,  1.8640e-01,\n",
-      "         3.3172e-01, -4.1092e-01,  2.6630e-02, -4.9168e-02, -3.4948e-01,\n",
-      "         1.6500e-02, -4.3398e-01,  2.6911e-01,  3.4227e-02, -2.1475e-01,\n",
-      "         9.7154e-01, -2.9554e-01,  8.5149e-01, -6.0231e-01,  1.0421e-01,\n",
-      "         6.2897e-01,  1.8700e-02,  1.6866e-01, -7.0568e-03, -6.9820e-01,\n",
-      "        -1.3916e-01,  3.2686e-01, -1.5017e-01,  6.5600e-01,  2.9388e-02,\n",
-      "        -6.0431e-01,  3.8548e-02, -1.2187e-01, -4.8818e-01,  1.5922e-01,\n",
-      "        -2.1494e-02, -2.1316e-01, -1.5983e-01, -3.7928e-01,  5.6203e-01,\n",
-      "         3.1285e-01, -4.0310e-01,  3.8763e-01, -4.1886e-01,  1.6276e-01,\n",
-      "         1.2610e-01,  3.5952e-01,  1.3288e-01,  6.0504e-01, -3.4769e-01,\n",
-      "        -1.5976e-01,  2.9626e-01, -2.2079e-01, -1.5934e-01, -5.8491e-01,\n",
-      "        -5.7811e-02, -4.7510e-01,  2.7285e-03,  3.7191e-01,  4.7557e-01,\n",
-      "         9.2435e-02,  2.3198e-01, -5.8704e-01, -1.9506e-01, -5.3740e-01,\n",
-      "         1.8715e-01, -3.5691e-01,  2.5481e-01,  3.2795e-01, -9.4206e-02,\n",
-      "        -2.2492e-01, -3.1406e-01,  4.5814e-01, -1.7896e-01, -3.9470e-01,\n",
-      "         1.9183e-01, -4.3177e-01,  2.7146e-01,  1.9477e-01, -1.7568e-02,\n",
-      "        -2.0134e-01,  5.7984e-03,  3.0490e-01, -2.7846e-01,  9.8830e-03,\n",
-      "        -3.0119e-01, -4.1994e-01, -1.0905e-02,  6.9638e-01,  9.4965e-02,\n",
-      "        -2.6103e-01,  8.8206e-02, -1.0292e-01, -1.2342e-01, -2.2317e-03,\n",
-      "        -5.2474e-02, -2.1636e-01, -1.6554e-01,  2.3173e-01,  1.2170e-01,\n",
-      "         4.5793e-01, -1.1033e-01,  1.4489e-01,  2.2540e-01,  5.2360e-01,\n",
-      "        -3.6468e-01, -1.5081e-01, -2.3761e-02,  2.7475e-01,  5.3707e-01,\n",
-      "         9.3503e-02, -4.9759e-01,  1.5903e-01, -1.2017e-01,  3.4478e-01,\n",
-      "        -2.1399e-01,  3.9456e-01, -3.2861e-01,  1.7182e-01, -1.1697e-01,\n",
-      "         5.6727e-03, -1.9770e-01, -2.3682e-01,  2.7554e-01, -3.9236e-01,\n",
-      "         2.0691e-01,  1.6439e-01, -3.7138e-01, -7.8304e-01, -1.9874e-01,\n",
-      "         6.4637e-01, -2.4494e-01, -4.1920e-01, -3.7675e-01,  1.3178e-01,\n",
-      "         1.9076e-01, -1.2906e-01, -6.4864e-04, -9.7821e-03, -1.2172e-01,\n",
-      "        -5.5357e-02,  2.2997e-01, -3.2848e-01, -4.1649e-01,  9.9676e-04,\n",
-      "        -4.5320e-01, -2.2864e-01, -1.6760e-01, -7.9657e-02, -6.0780e-02,\n",
-      "        -1.7627e-01, -4.1947e-02,  2.3884e-01, -4.7784e-03, -3.1593e-01,\n",
-      "        -1.0243e-01,  5.3464e-01,  2.7388e-01, -4.2258e-02, -1.5521e-01,\n",
-      "        -1.0183e-01, -2.9342e-01, -1.0132e+00,  2.3122e-01, -3.3482e-01,\n",
-      "         3.2136e-01, -2.3603e-01, -1.4938e-01, -2.3986e-01,  6.1094e-02,\n",
-      "         1.6784e-01, -3.8075e-02,  5.6459e-01, -2.0828e-02, -1.7406e-01,\n",
-      "        -2.9475e-01, -5.0143e-01, -1.6885e-01,  4.4070e-01,  3.1866e-01,\n",
-      "        -2.7534e-01,  4.1410e-01, -7.2704e-02, -2.9659e-01,  3.0922e-01,\n",
-      "        -5.1553e-01, -2.7293e-01, -1.2403e-01,  5.3698e-01,  8.8994e-02,\n",
-      "         4.1334e-01,  2.5389e-01,  6.0110e-01, -2.3192e-01, -9.9463e+00,\n",
-      "         3.8342e-01, -3.4833e-01,  3.5175e-02, -3.3336e-01,  2.5660e-01,\n",
-      "         8.5744e-01, -3.4563e-01,  3.0483e-03,  3.4735e-01,  3.8450e-01,\n",
-      "         3.9665e-01,  2.2100e-01,  6.5109e-02, -5.5761e-01, -6.2348e-01,\n",
-      "        -1.8679e-01,  1.9003e-01,  7.4262e-02, -5.9655e-02, -3.9839e-01,\n",
-      "        -2.2625e-02, -7.6319e-02,  2.9763e-01,  1.4098e-01, -2.8759e-01,\n",
-      "        -4.0783e-01,  1.1544e-01,  3.2446e-01, -2.9828e-01,  1.4054e-02,\n",
-      "         1.6943e-01, -2.0345e-01, -2.1174e-02,  1.1417e-01,  3.3420e-01,\n",
-      "        -1.0892e-01, -3.1187e-01, -5.7087e-01, -1.1561e-02,  4.2107e-02,\n",
-      "         4.9406e-01, -3.7056e-01, -3.2354e-01,  5.4846e-02,  2.4392e-01,\n",
-      "        -1.2840e-01, -4.3743e-01,  2.4391e-01,  2.1046e-01, -6.3811e-01,\n",
-      "         3.5563e-01, -2.0561e-01, -3.0996e-01,  1.6479e-01, -5.1947e-02,\n",
-      "         3.2559e-01, -6.3670e-03, -2.7855e-01, -4.2847e-01, -1.2022e-01,\n",
-      "         4.0702e-01,  9.6086e-01,  1.3305e-01, -2.0369e-01,  7.5751e-02,\n",
-      "        -1.2915e-01, -8.5741e-02,  2.7087e-01,  9.1068e-02, -1.5946e-01,\n",
-      "         4.7289e-01,  1.0613e-01,  1.3504e-01,  2.7304e-01, -7.9823e-01,\n",
-      "         1.1986e-01,  4.7432e-01, -1.4133e-01,  3.9729e-01, -1.6949e-01,\n",
-      "        -9.2290e-01, -1.9302e-01, -7.9017e-02, -6.5796e-01,  1.3385e-02,\n",
-      "         1.6185e-01, -3.4487e-01,  5.8601e-01, -1.5023e-01,  5.8034e-01,\n",
-      "        -2.8326e-01, -1.6494e-01, -2.9796e-01,  6.7479e-03, -6.3622e-01,\n",
-      "        -1.7732e-02, -1.6043e-01, -8.2452e-01, -2.4934e-02, -1.3969e-01,\n",
-      "        -1.2475e-01,  2.1235e-01,  6.9211e-02,  1.1795e-01, -2.5098e-02,\n",
-      "         4.8630e-01,  3.5354e-01,  4.4272e-01,  2.5360e-01,  2.7441e-01,\n",
-      "        -2.6457e-01, -3.3007e-01, -3.1083e-01,  4.9623e-01, -2.7829e-01,\n",
-      "        -3.0000e-01, -2.5620e-01,  2.1623e-01, -1.0724e-01, -5.0995e-01,\n",
-      "        -4.9460e-01,  8.4283e-02, -3.2844e-01, -6.0080e-01, -1.1809e-01,\n",
-      "         1.1040e-01,  3.7749e-02,  3.9097e-01,  2.7157e-02, -3.5270e-01,\n",
-      "        -1.0008e-01, -3.1026e-01, -1.9041e-01,  3.7090e-01, -4.5056e-01,\n",
-      "        -8.3087e-02, -3.6450e-01, -1.0154e+00, -1.3134e-01, -5.0261e-02,\n",
-      "         3.6961e-01, -1.1989e-01, -1.2336e-01,  2.6829e-01, -6.0926e-01,\n",
-      "        -3.0037e-01, -1.0460e+00, -2.1501e-01,  1.7171e-01,  1.7970e-02,\n",
-      "        -2.0708e-01, -1.3656e-01, -3.2854e-01,  1.2158e-01, -3.0438e-01,\n",
-      "        -4.6487e-02,  1.8717e-01, -2.3236e-01, -1.4668e-01, -6.9169e-01,\n",
-      "        -2.1502e-01, -1.2722e-01,  3.5600e-01,  1.5203e-03, -3.7041e-01,\n",
-      "        -6.5877e-01,  2.1490e-01, -5.1359e-02,  2.2720e-01, -1.6363e-01,\n",
-      "        -1.0862e-01,  1.4914e-02,  3.7205e-01,  3.4950e-01, -2.5987e-01,\n",
-      "        -2.0222e-01,  3.4466e-02,  5.8733e-01, -1.6877e-01, -4.8642e-01,\n",
-      "        -7.8254e-03,  1.2950e-01, -5.6791e-01, -6.6342e-01, -1.5021e-01,\n",
-      "        -4.4367e-01, -2.8434e-01, -1.7593e-01, -4.2538e-01, -3.7350e-01,\n",
-      "        -4.0185e-02, -6.1727e-01,  2.3771e-01, -4.1247e-01,  3.9440e-01,\n",
-      "         1.0506e-01, -4.0222e-01,  5.9232e-01])\n",
-      "TF-IDF Keywords: [('rus', np.float64(0.33567254331867563)), ('ahecaqo', np.float64(0.25175440748900674)), ('000', np.float64(0.16783627165933782)), ('1777', np.float64(0.16783627165933782)), ('ile', np.float64(0.16783627165933782)), ('pşıqo', np.float64(0.16783627165933782)), ('türkçe', np.float64(0.16783627165933782)), ('vardı', np.float64(0.16783627165933782)), ('çerkes', np.float64(0.16783627165933782)), ('çerkesya', np.float64(0.16783627165933782)), ('12', np.float64(0.08391813582966891)), ('1837', np.float64(0.08391813582966891)), ('1838', np.float64(0.08391813582966891)), ('adamıydı', np.float64(0.08391813582966891)), ('adlardaki', np.float64(0.08391813582966891)), ('anlamlıdır', np.float64(0.08391813582966891)), ('anlamına', np.float64(0.08391813582966891)), ('askeri', np.float64(0.08391813582966891)), ('askerî', np.float64(0.08391813582966891)), ('atlıdan', np.float64(0.08391813582966891)), ('atlıya', np.float64(0.08391813582966891)), ('az', np.float64(0.08391813582966891)), ('becerisinin', np.float64(0.08391813582966891)), ('belirtir', np.float64(0.08391813582966891)), ('beyoğlu', np.float64(0.08391813582966891)), ('bilgiler', np.float64(0.08391813582966891)), ('birliklerine', np.float64(0.08391813582966891)), ('biyografi', np.float64(0.08391813582966891)), ('bjeduğ', np.float64(0.08391813582966891)), ('bölgesinde', np.float64(0.08391813582966891)), ('büyütüldü', np.float64(0.08391813582966891)), ('devlet', np.float64(0.08391813582966891)), ('doğdu', np.float64(0.08391813582966891)), ('doğumlular', np.float64(0.08391813582966891)), ('duyulan', np.float64(0.08391813582966891)), ('dönem', np.float64(0.08391813582966891)), ('ek', np.float64(0.08391813582966891)), ('ekiyle', np.float64(0.08391813582966891)), ('erken', np.float64(0.08391813582966891)), ('eğitim', np.float64(0.08391813582966891)), ('eş', np.float64(0.08391813582966891)), ('geldiği', np.float64(0.08391813582966891)), ('gelen', np.float64(0.08391813582966891)), ('geçti', np.float64(0.08391813582966891)), ('hakkında', np.float64(0.08391813582966891)), ('hastalıktan', np.float64(0.08391813582966891)), ('ismi', np.float64(0.08391813582966891)), ('ismidir', np.float64(0.08391813582966891)), ('için', np.float64(0.08391813582966891)), ('kafkas', np.float64(0.08391813582966891)), ('kalıcı', np.float64(0.08391813582966891)), ('katılımı', np.float64(0.08391813582966891)), ('kaydedilmedi', np.float64(0.08391813582966891)), ('kaynak', np.float64(0.08391813582966891)), ('kaynaklarından', np.float64(0.08391813582966891)), ('kaynakça', np.float64(0.08391813582966891)), ('kazandığı', np.float64(0.08391813582966891)), ('kişi', np.float64(0.08391813582966891)), ('kişiler', np.float64(0.08391813582966891)), ('lakapları', np.float64(0.08391813582966891)), ('lakaptır', np.float64(0.08391813582966891)), ('müfrezesi', np.float64(0.08391813582966891)), ('nda', np.float64(0.08391813582966891)), ('nun', np.float64(0.08391813582966891)), ('nın', np.float64(0.08391813582966891)), ('olduğunu', np.float64(0.08391813582966891)), ('oluşan', np.float64(0.08391813582966891)), ('ordusu', np.float64(0.08391813582966891)), ('oğlu', np.float64(0.08391813582966891)), ('pek', np.float64(0.08391813582966891)), ('qo', np.float64(0.08391813582966891)), ('savaşı', np.float64(0.08391813582966891)), ('savaşına', np.float64(0.08391813582966891)), ('saygı', np.float64(0.08391813582966891)), ('sim', np.float64(0.08391813582966891)), ('soneki', np.float64(0.08391813582966891)), ('sonra', np.float64(0.08391813582966891)), ('soy', np.float64(0.08391813582966891)), ('soyadları', np.float64(0.08391813582966891)), ('soylular', np.float64(0.08391813582966891)), ('sıra', np.float64(0.08391813582966891)), ('sırasında', np.float64(0.08391813582966891)), ('tarafına', np.float64(0.08391813582966891)), ('tarihlerini', np.float64(0.08391813582966891)), ('ulaşıyordu', np.float64(0.08391813582966891)), ('yazmadıkları', np.float64(0.08391813582966891)), ('yıl', np.float64(0.08391813582966891)), ('zaferlerle', np.float64(0.08391813582966891)), ('çatışmalar', np.float64(0.08391813582966891)), ('çerkesler', np.float64(0.08391813582966891)), ('çerkeslerin', np.float64(0.08391813582966891)), ('öldü', np.float64(0.08391813582966891)), ('ölenler', np.float64(0.08391813582966891)), ('ölüm', np.float64(0.08391813582966891)), ('ünlüydü', np.float64(0.08391813582966891))]\n",
+      "Positive Average Embedding Shape: torch.Size([353])\n",
+      "Positive Average Embedding: tensor([3.1219e-01, 1.1118e-02, 1.3312e-02, 8.7684e-02, 6.0835e-01, 4.2102e-01,\n",
+      "        3.7467e-01, 2.5975e-01, 6.8351e-02, 1.1375e-01, 6.9892e-02, 3.4909e-01,\n",
+      "        4.2718e-02, 6.9431e-01, 8.2034e-02, 4.9043e-01, 4.0028e-02, 2.4516e-02,\n",
+      "        4.0203e-01, 1.7956e-01, 2.7692e-01, 4.2539e-01, 3.9989e-01, 1.1785e-01,\n",
+      "        1.2440e-01, 1.7583e-01, 4.7179e-01, 3.4876e-01, 4.3870e-01, 3.8414e-01,\n",
+      "        3.6902e-01, 2.5584e-01, 2.0225e-01, 1.4411e-01, 2.9933e-01, 3.6910e-01,\n",
+      "        2.3893e-01, 6.0434e-01, 1.5669e-01, 3.6258e-01, 4.5186e-01, 3.8370e-01,\n",
+      "        4.9858e-01, 1.1362e-02, 2.1302e-01, 3.4201e-01, 7.4201e-01, 7.6336e-02,\n",
+      "        2.6290e-01, 2.3984e-01, 4.8434e-01, 4.7557e-01, 2.2432e-01, 3.5924e-01,\n",
+      "        5.3896e-02, 1.0477e-01, 3.8852e-01, 2.9142e-01, 3.6626e-01, 7.9898e-02,\n",
+      "        2.2686e-01, 2.3253e-02, 3.2550e+00, 1.1168e-01, 4.2853e-01, 7.7213e-02,\n",
+      "        3.1671e-01, 5.6494e-01, 2.0392e-01, 5.1432e-02, 2.2806e-01, 4.0886e-01,\n",
+      "        2.2627e-02, 2.4151e-01, 5.5605e-01, 2.1589e-01, 8.9567e-02, 4.1183e-01,\n",
+      "        3.7691e-01, 6.1995e-02, 5.1504e-01, 4.9226e-01, 1.0083e-01, 1.9789e-01,\n",
+      "        6.5205e-01, 3.4597e-02, 9.5440e-02, 6.5158e-01, 1.9009e-01, 1.1314e-01,\n",
+      "        1.0752e-01, 4.7765e-01, 2.5196e-01, 1.3468e-01, 4.2977e-01, 2.7336e-01,\n",
+      "        4.7672e-02, 2.3097e-01, 1.5998e-01, 3.8424e-01, 2.9264e-02, 7.9061e-02,\n",
+      "        2.8095e-01, 2.0505e-01, 8.8469e-02, 1.6993e-01, 2.5519e-01, 5.7010e-01,\n",
+      "        6.1551e-03, 7.0113e-02, 1.1820e-01, 5.2899e-01, 1.3287e-01, 1.0696e+00,\n",
+      "        3.1219e-01, 1.1373e-01, 2.6080e-01, 6.1457e-03, 5.5064e-02, 5.2089e-01,\n",
+      "        1.3195e-01, 4.0164e-01, 8.4919e-01, 1.8478e-02, 1.6000e-01, 3.3307e-01,\n",
+      "        2.8522e-01, 1.7133e-01, 2.4794e-02, 1.7487e-01, 1.0915e-01, 2.5974e-01,\n",
+      "        1.8174e-02, 8.9919e-02, 1.6508e+00, 4.9391e-01, 7.9321e-02, 3.2023e-02,\n",
+      "        3.1216e-01, 3.5055e-01, 2.4602e-01, 4.0553e-01, 1.3428e-02, 4.7906e-01,\n",
+      "        2.2494e-01, 3.5909e-01, 1.2861e-01, 9.8253e-02, 2.3110e-01, 3.1276e-01,\n",
+      "        6.4092e-02, 2.7386e-01, 6.7687e-02, 3.0518e-02, 3.8880e-01, 2.8110e-01,\n",
+      "        5.7723e-02, 4.2425e-01, 6.5768e-01, 8.4208e-02, 3.2153e-01, 5.6956e-01,\n",
+      "        1.2256e-01, 4.2261e-01, 7.9419e-02, 1.5746e-01, 1.8869e-01, 4.1413e-01,\n",
+      "        3.7192e-01, 5.4023e-02, 1.1605e-01, 4.2643e-01, 1.6004e-01, 2.1577e-01,\n",
+      "        6.6576e-03, 4.4046e-01, 2.4404e-01, 8.1931e-02, 2.2825e-01, 8.8104e-02,\n",
+      "        4.0676e-01, 1.6295e-01, 5.8565e-01, 3.9977e-01, 5.0630e-02, 6.7476e-02,\n",
+      "        3.4367e-01, 1.8640e-01, 3.3172e-01, 2.6630e-02, 1.6500e-02, 2.6911e-01,\n",
+      "        3.4227e-02, 9.7154e-01, 8.5149e-01, 1.0421e-01, 6.2897e-01, 1.8700e-02,\n",
+      "        1.6866e-01, 3.2686e-01, 6.5600e-01, 2.9388e-02, 3.8548e-02, 1.5922e-01,\n",
+      "        5.6203e-01, 3.1285e-01, 3.8763e-01, 1.6276e-01, 1.2610e-01, 3.5952e-01,\n",
+      "        1.3288e-01, 6.0504e-01, 2.9626e-01, 2.7285e-03, 3.7191e-01, 4.7557e-01,\n",
+      "        9.2435e-02, 2.3198e-01, 1.8715e-01, 2.5481e-01, 3.2795e-01, 4.5814e-01,\n",
+      "        1.9183e-01, 2.7146e-01, 1.9477e-01, 5.7984e-03, 3.0490e-01, 9.8830e-03,\n",
+      "        6.9638e-01, 9.4965e-02, 8.8206e-02, 2.3173e-01, 1.2170e-01, 4.5793e-01,\n",
+      "        1.4489e-01, 2.2540e-01, 5.2360e-01, 2.7475e-01, 5.3707e-01, 9.3503e-02,\n",
+      "        1.5903e-01, 3.4478e-01, 3.9456e-01, 1.7182e-01, 5.6727e-03, 2.7554e-01,\n",
+      "        2.0691e-01, 1.6439e-01, 6.4637e-01, 1.3178e-01, 1.9076e-01, 2.2997e-01,\n",
+      "        9.9676e-04, 2.3884e-01, 5.3464e-01, 2.7388e-01, 2.3122e-01, 3.2136e-01,\n",
+      "        6.1094e-02, 1.6784e-01, 5.6459e-01, 4.4070e-01, 3.1866e-01, 4.1410e-01,\n",
+      "        3.0922e-01, 5.3698e-01, 8.8994e-02, 4.1334e-01, 2.5389e-01, 6.0110e-01,\n",
+      "        3.8342e-01, 3.5175e-02, 2.5660e-01, 8.5744e-01, 3.0483e-03, 3.4735e-01,\n",
+      "        3.8450e-01, 3.9665e-01, 2.2100e-01, 6.5109e-02, 1.9003e-01, 7.4262e-02,\n",
+      "        2.9763e-01, 1.4098e-01, 1.1544e-01, 3.2446e-01, 1.4054e-02, 1.6943e-01,\n",
+      "        1.1417e-01, 3.3420e-01, 4.2107e-02, 4.9406e-01, 5.4846e-02, 2.4392e-01,\n",
+      "        2.4391e-01, 2.1046e-01, 3.5563e-01, 1.6479e-01, 3.2559e-01, 4.0702e-01,\n",
+      "        9.6086e-01, 1.3305e-01, 7.5751e-02, 2.7087e-01, 9.1068e-02, 4.7289e-01,\n",
+      "        1.0613e-01, 1.3504e-01, 2.7304e-01, 1.1986e-01, 4.7432e-01, 3.9729e-01,\n",
+      "        1.3385e-02, 1.6185e-01, 5.8601e-01, 5.8034e-01, 6.7479e-03, 2.1235e-01,\n",
+      "        6.9211e-02, 1.1795e-01, 4.8630e-01, 3.5354e-01, 4.4272e-01, 2.5360e-01,\n",
+      "        2.7441e-01, 4.9623e-01, 2.1623e-01, 8.4283e-02, 1.1040e-01, 3.7749e-02,\n",
+      "        3.9097e-01, 2.7157e-02, 3.7090e-01, 3.6961e-01, 2.6829e-01, 1.7171e-01,\n",
+      "        1.7970e-02, 1.2158e-01, 1.8717e-01, 3.5600e-01, 1.5203e-03, 2.1490e-01,\n",
+      "        2.2720e-01, 1.4914e-02, 3.7205e-01, 3.4950e-01, 3.4466e-02, 5.8733e-01,\n",
+      "        1.2950e-01, 2.3771e-01, 3.9440e-01, 1.0506e-01, 5.9232e-01])\n",
+      "TF-IDF Keywords: [array([['rus', 'ahecaqo', 'türkçe', 'pşıqo', '1777', 'çerkes', '000',\n",
+      "        'çerkesya', 'ölenler', 'ünlüydü', 'ölüm', 'yazmadıkları',\n",
+      "        'ulaşıyordu', 'tarihlerini', 'çerkeslerin', 'çerkesler',\n",
+      "        'çatışmalar', 'zaferlerle', 'öldü', 'soneki', 'soy', 'soyadları',\n",
+      "        'soylular', 'sıra', 'savaşı', 'sim', 'saygı', 'ordusu', 'oluşan',\n",
+      "        'olduğunu', 'müfrezesi', 'lakaptır', 'savaşına', 'qo', 'oğlu',\n",
+      "        'kazandığı', 'kaynakça', 'kaynaklarından', 'kaynak',\n",
+      "        'kaydedilmedi', 'katılımı', 'kalıcı', 'kafkas', 'ismidir',\n",
+      "        'ismi', 'hastalıktan', 'hakkında', 'geçti', 'lakapları',\n",
+      "        'kişiler', 'kişi', 'eş', 'geldiği', 'gelen', 'eğitim', 'dönem',\n",
+      "        'erken', 'ekiyle', 'ek', 'devlet', 'büyütüldü', 'bölgesinde',\n",
+      "        'bjeduğ', 'biyografi', 'duyulan', 'doğumlular', 'doğdu',\n",
+      "        'beyoğlu', 'bilgiler', 'birliklerine', 'belirtir', 'askerî',\n",
+      "        'becerisinin', 'atlıya', 'atlıdan', 'anlamlıdır', 'anlamına',\n",
+      "        'askeri', 'adlardaki', '1838', 'adamıydı', '1837', '12']],\n",
+      "      dtype=object)]\n",
       "BERT Embeddings:\n",
       "Text 1 embedding shape: torch.Size([233, 768])\n"
      ]
+    },
+    {
+     "ename": "ValueError",
+     "evalue": "setting an array element with a sequence.",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[1;31mTypeError\u001b[0m: float() argument must be a string or a real number, not 'csr_matrix'",
+      "\nThe above exception was the direct cause of the following exception:\n",
+      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[31], line 151\u001b[0m\n\u001b[0;32m    146\u001b[0m \u001b[38;5;124;03m\"\"\"# Liste halindeki TF-IDF değerlerini yazdırma\u001b[39;00m\n\u001b[0;32m    147\u001b[0m \u001b[38;5;124;03mprint(\"TF-IDF List:\")\u001b[39;00m\n\u001b[0;32m    148\u001b[0m \u001b[38;5;124;03mfor row in tfidf_list:\u001b[39;00m\n\u001b[0;32m    149\u001b[0m \u001b[38;5;124;03m    print(row)\"\"\"\u001b[39;00m\n\u001b[0;32m    150\u001b[0m \u001b[38;5;66;03m# Anahtar kelimeler ve metin arasındaki cosine similarity hesaplama\u001b[39;00m\n\u001b[1;32m--> 151\u001b[0m similarity_score \u001b[38;5;241m=\u001b[39m \u001b[43mcosine_similarity\u001b[49m\u001b[43m(\u001b[49m\u001b[43m[\u001b[49m\u001b[43mkeywords_vector\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[43mdocument_vector\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    153\u001b[0m \u001b[38;5;66;03m# Her bir kelime için TF-IDF değerlerini yazdırma\u001b[39;00m\n\u001b[0;32m    154\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m doc_idx, doc \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(tfidf_scores):\n",
+      "File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\sklearn\\utils\\_param_validation.py:213\u001b[0m, in \u001b[0;36mvalidate_params.<locals>.decorator.<locals>.wrapper\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m    207\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m    208\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m config_context(\n\u001b[0;32m    209\u001b[0m         skip_parameter_validation\u001b[38;5;241m=\u001b[39m(\n\u001b[0;32m    210\u001b[0m             prefer_skip_nested_validation \u001b[38;5;129;01mor\u001b[39;00m global_skip_validation\n\u001b[0;32m    211\u001b[0m         )\n\u001b[0;32m    212\u001b[0m     ):\n\u001b[1;32m--> 213\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m func(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m    214\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m InvalidParameterError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m    215\u001b[0m     \u001b[38;5;66;03m# When the function is just a wrapper around an estimator, we allow\u001b[39;00m\n\u001b[0;32m    216\u001b[0m     \u001b[38;5;66;03m# the function to delegate validation to the estimator, but we replace\u001b[39;00m\n\u001b[0;32m    217\u001b[0m     \u001b[38;5;66;03m# the name of the estimator by the name of the function in the error\u001b[39;00m\n\u001b[0;32m    218\u001b[0m     \u001b[38;5;66;03m# message to avoid confusion.\u001b[39;00m\n\u001b[0;32m    219\u001b[0m     msg \u001b[38;5;241m=\u001b[39m re\u001b[38;5;241m.\u001b[39msub(\n\u001b[0;32m    220\u001b[0m         \u001b[38;5;124mr\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mparameter of \u001b[39m\u001b[38;5;124m\\\u001b[39m\u001b[38;5;124mw+ must be\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m    221\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mparameter of \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfunc\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__qualname__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m must be\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m    222\u001b[0m         \u001b[38;5;28mstr\u001b[39m(e),\n\u001b[0;32m    223\u001b[0m     )\n",
+      "File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\sklearn\\metrics\\pairwise.py:1679\u001b[0m, in \u001b[0;36mcosine_similarity\u001b[1;34m(X, Y, dense_output)\u001b[0m\n\u001b[0;32m   1635\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Compute cosine similarity between samples in X and Y.\u001b[39;00m\n\u001b[0;32m   1636\u001b[0m \n\u001b[0;32m   1637\u001b[0m \u001b[38;5;124;03mCosine similarity, or the cosine kernel, computes similarity as the\u001b[39;00m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m   1675\u001b[0m \u001b[38;5;124;03m       [0.57..., 0.81...]])\u001b[39;00m\n\u001b[0;32m   1676\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m   1677\u001b[0m \u001b[38;5;66;03m# to avoid recursive import\u001b[39;00m\n\u001b[1;32m-> 1679\u001b[0m X, Y \u001b[38;5;241m=\u001b[39m \u001b[43mcheck_pairwise_arrays\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mY\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1681\u001b[0m X_normalized \u001b[38;5;241m=\u001b[39m normalize(X, copy\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m   1682\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m X \u001b[38;5;129;01mis\u001b[39;00m Y:\n",
+      "File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\sklearn\\metrics\\pairwise.py:185\u001b[0m, in \u001b[0;36mcheck_pairwise_arrays\u001b[1;34m(X, Y, precomputed, dtype, accept_sparse, force_all_finite, ensure_2d, copy)\u001b[0m\n\u001b[0;32m    175\u001b[0m     X \u001b[38;5;241m=\u001b[39m Y \u001b[38;5;241m=\u001b[39m check_array(\n\u001b[0;32m    176\u001b[0m         X,\n\u001b[0;32m    177\u001b[0m         accept_sparse\u001b[38;5;241m=\u001b[39maccept_sparse,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    182\u001b[0m         ensure_2d\u001b[38;5;241m=\u001b[39mensure_2d,\n\u001b[0;32m    183\u001b[0m     )\n\u001b[0;32m    184\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 185\u001b[0m     X \u001b[38;5;241m=\u001b[39m \u001b[43mcheck_array\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    186\u001b[0m \u001b[43m        \u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    187\u001b[0m \u001b[43m        \u001b[49m\u001b[43maccept_sparse\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maccept_sparse\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    188\u001b[0m \u001b[43m        \u001b[49m\u001b[43mdtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdtype\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    189\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcopy\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcopy\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    190\u001b[0m \u001b[43m        \u001b[49m\u001b[43mforce_all_finite\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_all_finite\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    191\u001b[0m \u001b[43m        \u001b[49m\u001b[43mestimator\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mestimator\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    192\u001b[0m \u001b[43m        \u001b[49m\u001b[43mensure_2d\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mensure_2d\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    193\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    194\u001b[0m     Y \u001b[38;5;241m=\u001b[39m check_array(\n\u001b[0;32m    195\u001b[0m         Y,\n\u001b[0;32m    196\u001b[0m         accept_sparse\u001b[38;5;241m=\u001b[39maccept_sparse,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    201\u001b[0m         ensure_2d\u001b[38;5;241m=\u001b[39mensure_2d,\n\u001b[0;32m    202\u001b[0m     )\n\u001b[0;32m    204\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m precomputed:\n",
+      "File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\sklearn\\utils\\validation.py:1012\u001b[0m, in \u001b[0;36mcheck_array\u001b[1;34m(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_writeable, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, estimator, input_name)\u001b[0m\n\u001b[0;32m   1010\u001b[0m         array \u001b[38;5;241m=\u001b[39m xp\u001b[38;5;241m.\u001b[39mastype(array, dtype, copy\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[0;32m   1011\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1012\u001b[0m         array \u001b[38;5;241m=\u001b[39m \u001b[43m_asarray_with_order\u001b[49m\u001b[43m(\u001b[49m\u001b[43marray\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43morder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43morder\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdtype\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mxp\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mxp\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1013\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m ComplexWarning \u001b[38;5;28;01mas\u001b[39;00m complex_warning:\n\u001b[0;32m   1014\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[0;32m   1015\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mComplex data not supported\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;132;01m{}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mformat(array)\n\u001b[0;32m   1016\u001b[0m     ) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mcomplex_warning\u001b[39;00m\n",
+      "File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\sklearn\\utils\\_array_api.py:751\u001b[0m, in \u001b[0;36m_asarray_with_order\u001b[1;34m(array, dtype, order, copy, xp, device)\u001b[0m\n\u001b[0;32m    749\u001b[0m     array \u001b[38;5;241m=\u001b[39m numpy\u001b[38;5;241m.\u001b[39marray(array, order\u001b[38;5;241m=\u001b[39morder, dtype\u001b[38;5;241m=\u001b[39mdtype)\n\u001b[0;32m    750\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 751\u001b[0m     array \u001b[38;5;241m=\u001b[39m \u001b[43mnumpy\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43masarray\u001b[49m\u001b[43m(\u001b[49m\u001b[43marray\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43morder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43morder\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdtype\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdtype\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    753\u001b[0m \u001b[38;5;66;03m# At this point array is a NumPy ndarray. We convert it to an array\u001b[39;00m\n\u001b[0;32m    754\u001b[0m \u001b[38;5;66;03m# container that is consistent with the input's namespace.\u001b[39;00m\n\u001b[0;32m    755\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m xp\u001b[38;5;241m.\u001b[39masarray(array)\n",
+      "\u001b[1;31mValueError\u001b[0m: setting an array element with a sequence."
+     ]
     }
    ],
    "source": [
@@ -617,7 +563,9 @@
     "from sklearn.feature_extraction.text import TfidfVectorizer\n",
     "from nltk.corpus import stopwords as nltk_stopwords\n",
     "from transformers import BertTokenizer, BertModel\n",
+    "from sklearn.metrics.pairwise import cosine_similarity\n",
     "import torch\n",
+    "import torch.nn.functional as F\n",
     "\n",
     "# BERT Tokenizer ve Model'i yükleyin\n",
     "tokenizer = BertTokenizer.from_pretrained('dbmdz/bert-base-turkish-cased')\n",
@@ -661,9 +609,10 @@
     "    vectorizer = TfidfVectorizer(stop_words=stop_words_list)\n",
     "    X = vectorizer.fit_transform(corpus)\n",
     "    feature_names = vectorizer.get_feature_names_out()\n",
-    "    scores = np.asarray(X.sum(axis=0)).flatten()\n",
-    "    keywords = {feature_names[i]: scores[i] for i in range(len(feature_names))}\n",
-    "    sorted_keywords = sorted(keywords.items(), key=lambda x: x[1], reverse=True)\n",
+    "    #scores = np.asarray(X.sum(axis=0)).flatten()\n",
+    "    sorted_keywords = [feature_names[i] for i in X.sum(axis=0).argsort()[0, ::-1]]\n",
+    "    #keywords = {feature_names[i]: scores[i] for i in range(len(feature_names))}\n",
+    "    #sorted_keywords = sorted(keywords.items(), key=lambda x: x[1], reverse=True)\n",
     "    return sorted_keywords\n",
     "\n",
     "#tokenleri kelimelere dönüştürür ve listeler \n",
@@ -695,9 +644,6 @@
     "         \n",
     "    \n",
     "\n",
-    "    \n",
-    "\n",
-    "\n",
     "#token ıd leri ve bert gömme vektörleri\n",
     "for text in texts:\n",
     "    input_ids,embeddings= get_bert_embeddings(text)\n",
@@ -708,10 +654,18 @@
     "    # Tokenları ve ortalama vektörleri al\n",
     "    tokens = decode_tokens(input_ids)\n",
     "    avg_embedding = average_embeddings(embeddings)\n",
+    "    #ortalama embedding değerlerinden sadece 0'dan büyük olanları alma\n",
+    "    positive_avg_embedding= avg_embedding[avg_embedding>0]\n",
+    "    # Eğer pozitif embedding değerleri varsa, çıktıyı yazdır\n",
+    "\n",
+    "if len(positive_avg_embedding) > 0:\n",
     "    print(f\"Tokens: {tokens}\")\n",
-    "    print(f\"Average Embedding Shape: {avg_embedding.shape}\")\n",
-    "    print(f\"Average Embedding: {avg_embedding}\")\n",
+    "    print(f\"Positive Average Embedding Shape: {positive_avg_embedding.shape}\")\n",
+    "    print(f\"Positive Average Embedding: {positive_avg_embedding}\")\n",
+    "else:\n",
+    "    print(\"No positive embedding values found.\")\n",
     "\n",
+    "        \n",
     "# TF-IDF anahtar kelimelerini çıkar\n",
     "keywords = extract_keywords_tfidf(texts,stop_words_list)\n",
     "print(\"TF-IDF Keywords:\", keywords)\n",
@@ -721,10 +675,566 @@
     "for i, emb in enumerate(embeddings):\n",
     "    print(f\"Text {i+1} embedding shape: {emb.shape}\")\n",
     "\n",
-    "\n",
+    "keywords_str = \" \".join([str(keyword) for keyword in keywords])\n",
+    "\n",
+    "\n",
+    "#metinleri birleştirip tf-ıdf matrisini oluşturma\n",
+    "# TF-IDF vektörleştirici oluşturma\n",
+    "tfidf_vectorizer = TfidfVectorizer(stop_words=stop_words_list)\n",
+    "corpus = [text, keywords_str]\n",
+    "tfidf_matrix = tfidf_vectorizer.fit_transform(corpus)\n",
+    "\n",
+    "# Anahtar kelimeler vektörünü ve diğer metin vektörünü ayırma\n",
+    "keywords_vector = tfidf_matrix[1]\n",
+    "document_vector = tfidf_matrix[0]\n",
+    "keywords_vector_dense = keywords_vector.toarray()\n",
+    "document_vector_dense = document_vector.toarray()\n",
+    "\n",
+    "# Kelimeleri ve TF-IDF değerlerini alma\n",
+    "feature_names = tfidf_vectorizer.get_feature_names_out()\n",
+    "tfidf_scores = tfidf_matrix.toarray()\n",
+    "similarity_score = cosine_similarity(keywords_vector_dense, document_vector_dense)\n",
+    "\n",
+    "# TF-IDF matrisini dense formata çevirme\n",
+    "dense_matrix = tfidf_matrix.todense()\n",
+    "# Dense matrisi liste haline getirme\n",
+    "tfidf_list = dense_matrix.tolist()\n",
+    "\n",
+    "\"\"\"# Liste halindeki TF-IDF değerlerini yazdırma\n",
+    "print(\"TF-IDF List:\")\n",
+    "for row in tfidf_list:\n",
+    "    print(row)\"\"\"\n",
+    "# Anahtar kelimeler ve metin arasındaki cosine similarity hesaplama\n",
+    "similarity_score = cosine_similarity([keywords_vector], [document_vector])\n",
+    "\n",
+    "# Her bir kelime için TF-IDF değerlerini yazdırma\n",
+    "for doc_idx, doc in enumerate(tfidf_scores):\n",
+    "    print(f\"Document {doc_idx + 1}:\")\n",
+    "    for word_idx, score in enumerate(doc):\n",
+    "        print(f\"Word: {feature_names[word_idx]}, TF-IDF: {score:.4f}\")\n",
+    "    print(\"\\n\")\n",
+    "\n",
+    "# Sonucu yazdırma\n",
+    "print(f\"Keywords ile metin arasındaki benzerlik: {similarity_score[0][0]}\")\n",
     "\n"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Tokens: ['[CLS]', 'Biy', '##ografi', 'İsim', 'P', '##şı', '##q', '##o', 'ismi', 'Ah', '##ec', '##a', '##q', '##o', 'soy', 'ismi', '##dir', '.', 'Çerkes', '##lerin', '\"', '-', 'q', '##o', '\"', 'son', '##eki', 'ile', 'biten', 'hem', 'soya', '##d', '##ları', 'hem', 'de', 'lak', '##ap', '##ları', 'vardı', '.', 'Bu', 'ek', 'Türkçe', 'ad', '##lardaki', '\"', '-', 'oğlu', '\"', 'eki', '##yle', 'eş', 'anlamlı', '##dır', '.', 'P', '##şı', '##q', '##o', 'Türkçe', '\"', 'Beyoğlu', '\"', 'anlamına', 'gelen', 'bir', 'lak', '##ap', '##tır', '.', 'Erken', 'dönem', 'Çerkes', '##ler', 'tarihleri', '##ni', 'yazma', '##dıkları', 've', 'tüm', 'bilgiler', 'Rus', 'kaynaklarından', 'geldiği', 'için', 'Ah', '##ec', '##a', '##q', '##o', 'hakkında', 'pek', 'bir', 'şey', 'kayded', '##ilme', '##di', '.', '177', '##7', \"'\", 'de', 'Çerkes', '##ya', \"'\", 'nın', 'B', '##je', '##duğ', 'bölgesinde', 'doğdu', '.', 'Asker', '##î', 'eğitim', 'ile', 'büyüt', '##üldü', '.', 'Rus', '-', 'Çerkes', 'Savaşı', '##na', 'Katılım', '##ı', 'Birkaç', 'kaynak', ',', 'Ah', '##ec', '##a', '##q', '##o', \"'\", 'nun', 'tüm', 'Çerkes', '##ya', \"'\", 'da', 'saygı', 'duyulan', 'bir', 'kişi', 'olduğunu', 'belirtir', '.', 'En', 'az', '6', '.', '000', 'at', '##lı', '##dan', 'oluşan', 'kalıcı', 'bir', 'ordusu', 'vardı', 've', 'çatışmalar', 'sırasında', 'müfre', '##ze', '##si', '12', '.', '000', 'at', '##lı', '##ya', 'ulaşıyor', '##du', '.', 'Rus', 'birlikleri', '##ne', 'karşı', 'kazandığı', 'zafer', '##lerle', 'ünlü', '##y', '##dü', '.', 'Askeri', 'becerisi', '##nin', 'yanı', 'sıra', 'yetenekli', 'bir', 'devlet', 'adamı', '##ydı', '.', 'Ölüm', '18', '##37', 'yılında', 'Rus', 'tarafına', 'geçti', 've', 'bir', 'yıl', 'sonra', 'hastalık', '##tan', 'öldü', '.', 'Kaynak', '##ça', 'Çerkes', 'soylu', '##lar', '177', '##7', 'doğumlu', '##lar', '18', '##38', 'yılında', 'ölen', '##ler', 'Kafkas', 'Savaşı', \"'\", 'nda', 'kişiler', '[SEP]']\n",
+      "Positive Average Embedding Shape: torch.Size([353])\n",
+      "Positive Average Embedding: tensor([3.1219e-01, 1.1118e-02, 1.3312e-02, 8.7684e-02, 6.0835e-01, 4.2102e-01,\n",
+      "        3.7467e-01, 2.5975e-01, 6.8351e-02, 1.1375e-01, 6.9892e-02, 3.4909e-01,\n",
+      "        4.2718e-02, 6.9431e-01, 8.2034e-02, 4.9043e-01, 4.0028e-02, 2.4516e-02,\n",
+      "        4.0203e-01, 1.7956e-01, 2.7692e-01, 4.2539e-01, 3.9989e-01, 1.1785e-01,\n",
+      "        1.2440e-01, 1.7583e-01, 4.7179e-01, 3.4876e-01, 4.3870e-01, 3.8414e-01,\n",
+      "        3.6902e-01, 2.5584e-01, 2.0225e-01, 1.4411e-01, 2.9933e-01, 3.6910e-01,\n",
+      "        2.3893e-01, 6.0434e-01, 1.5669e-01, 3.6258e-01, 4.5186e-01, 3.8370e-01,\n",
+      "        4.9858e-01, 1.1362e-02, 2.1302e-01, 3.4201e-01, 7.4201e-01, 7.6336e-02,\n",
+      "        2.6290e-01, 2.3984e-01, 4.8434e-01, 4.7557e-01, 2.2432e-01, 3.5924e-01,\n",
+      "        5.3896e-02, 1.0477e-01, 3.8852e-01, 2.9142e-01, 3.6626e-01, 7.9898e-02,\n",
+      "        2.2686e-01, 2.3253e-02, 3.2550e+00, 1.1168e-01, 4.2853e-01, 7.7213e-02,\n",
+      "        3.1671e-01, 5.6494e-01, 2.0392e-01, 5.1432e-02, 2.2806e-01, 4.0886e-01,\n",
+      "        2.2627e-02, 2.4151e-01, 5.5605e-01, 2.1589e-01, 8.9567e-02, 4.1183e-01,\n",
+      "        3.7691e-01, 6.1995e-02, 5.1504e-01, 4.9226e-01, 1.0083e-01, 1.9789e-01,\n",
+      "        6.5205e-01, 3.4597e-02, 9.5440e-02, 6.5158e-01, 1.9009e-01, 1.1314e-01,\n",
+      "        1.0752e-01, 4.7765e-01, 2.5196e-01, 1.3468e-01, 4.2977e-01, 2.7336e-01,\n",
+      "        4.7672e-02, 2.3097e-01, 1.5998e-01, 3.8424e-01, 2.9264e-02, 7.9061e-02,\n",
+      "        2.8095e-01, 2.0505e-01, 8.8469e-02, 1.6993e-01, 2.5519e-01, 5.7010e-01,\n",
+      "        6.1551e-03, 7.0113e-02, 1.1820e-01, 5.2899e-01, 1.3287e-01, 1.0696e+00,\n",
+      "        3.1219e-01, 1.1373e-01, 2.6080e-01, 6.1457e-03, 5.5064e-02, 5.2089e-01,\n",
+      "        1.3195e-01, 4.0164e-01, 8.4919e-01, 1.8478e-02, 1.6000e-01, 3.3307e-01,\n",
+      "        2.8522e-01, 1.7133e-01, 2.4794e-02, 1.7487e-01, 1.0915e-01, 2.5974e-01,\n",
+      "        1.8174e-02, 8.9919e-02, 1.6508e+00, 4.9391e-01, 7.9321e-02, 3.2023e-02,\n",
+      "        3.1216e-01, 3.5055e-01, 2.4602e-01, 4.0553e-01, 1.3428e-02, 4.7906e-01,\n",
+      "        2.2494e-01, 3.5909e-01, 1.2861e-01, 9.8253e-02, 2.3110e-01, 3.1276e-01,\n",
+      "        6.4092e-02, 2.7386e-01, 6.7687e-02, 3.0518e-02, 3.8880e-01, 2.8110e-01,\n",
+      "        5.7723e-02, 4.2425e-01, 6.5768e-01, 8.4208e-02, 3.2153e-01, 5.6956e-01,\n",
+      "        1.2256e-01, 4.2261e-01, 7.9419e-02, 1.5746e-01, 1.8869e-01, 4.1413e-01,\n",
+      "        3.7192e-01, 5.4023e-02, 1.1605e-01, 4.2643e-01, 1.6004e-01, 2.1577e-01,\n",
+      "        6.6576e-03, 4.4046e-01, 2.4404e-01, 8.1931e-02, 2.2825e-01, 8.8104e-02,\n",
+      "        4.0676e-01, 1.6295e-01, 5.8565e-01, 3.9977e-01, 5.0630e-02, 6.7476e-02,\n",
+      "        3.4367e-01, 1.8640e-01, 3.3172e-01, 2.6630e-02, 1.6500e-02, 2.6911e-01,\n",
+      "        3.4227e-02, 9.7154e-01, 8.5149e-01, 1.0421e-01, 6.2897e-01, 1.8700e-02,\n",
+      "        1.6866e-01, 3.2686e-01, 6.5600e-01, 2.9388e-02, 3.8548e-02, 1.5922e-01,\n",
+      "        5.6203e-01, 3.1285e-01, 3.8763e-01, 1.6276e-01, 1.2610e-01, 3.5952e-01,\n",
+      "        1.3288e-01, 6.0504e-01, 2.9626e-01, 2.7285e-03, 3.7191e-01, 4.7557e-01,\n",
+      "        9.2435e-02, 2.3198e-01, 1.8715e-01, 2.5481e-01, 3.2795e-01, 4.5814e-01,\n",
+      "        1.9183e-01, 2.7146e-01, 1.9477e-01, 5.7984e-03, 3.0490e-01, 9.8830e-03,\n",
+      "        6.9638e-01, 9.4965e-02, 8.8206e-02, 2.3173e-01, 1.2170e-01, 4.5793e-01,\n",
+      "        1.4489e-01, 2.2540e-01, 5.2360e-01, 2.7475e-01, 5.3707e-01, 9.3503e-02,\n",
+      "        1.5903e-01, 3.4478e-01, 3.9456e-01, 1.7182e-01, 5.6727e-03, 2.7554e-01,\n",
+      "        2.0691e-01, 1.6439e-01, 6.4637e-01, 1.3178e-01, 1.9076e-01, 2.2997e-01,\n",
+      "        9.9676e-04, 2.3884e-01, 5.3464e-01, 2.7388e-01, 2.3122e-01, 3.2136e-01,\n",
+      "        6.1094e-02, 1.6784e-01, 5.6459e-01, 4.4070e-01, 3.1866e-01, 4.1410e-01,\n",
+      "        3.0922e-01, 5.3698e-01, 8.8994e-02, 4.1334e-01, 2.5389e-01, 6.0110e-01,\n",
+      "        3.8342e-01, 3.5175e-02, 2.5660e-01, 8.5744e-01, 3.0483e-03, 3.4735e-01,\n",
+      "        3.8450e-01, 3.9665e-01, 2.2100e-01, 6.5109e-02, 1.9003e-01, 7.4262e-02,\n",
+      "        2.9763e-01, 1.4098e-01, 1.1544e-01, 3.2446e-01, 1.4054e-02, 1.6943e-01,\n",
+      "        1.1417e-01, 3.3420e-01, 4.2107e-02, 4.9406e-01, 5.4846e-02, 2.4392e-01,\n",
+      "        2.4391e-01, 2.1046e-01, 3.5563e-01, 1.6479e-01, 3.2559e-01, 4.0702e-01,\n",
+      "        9.6086e-01, 1.3305e-01, 7.5751e-02, 2.7087e-01, 9.1068e-02, 4.7289e-01,\n",
+      "        1.0613e-01, 1.3504e-01, 2.7304e-01, 1.1986e-01, 4.7432e-01, 3.9729e-01,\n",
+      "        1.3385e-02, 1.6185e-01, 5.8601e-01, 5.8034e-01, 6.7479e-03, 2.1235e-01,\n",
+      "        6.9211e-02, 1.1795e-01, 4.8630e-01, 3.5354e-01, 4.4272e-01, 2.5360e-01,\n",
+      "        2.7441e-01, 4.9623e-01, 2.1623e-01, 8.4283e-02, 1.1040e-01, 3.7749e-02,\n",
+      "        3.9097e-01, 2.7157e-02, 3.7090e-01, 3.6961e-01, 2.6829e-01, 1.7171e-01,\n",
+      "        1.7970e-02, 1.2158e-01, 1.8717e-01, 3.5600e-01, 1.5203e-03, 2.1490e-01,\n",
+      "        2.2720e-01, 1.4914e-02, 3.7205e-01, 3.4950e-01, 3.4466e-02, 5.8733e-01,\n",
+      "        1.2950e-01, 2.3771e-01, 3.9440e-01, 1.0506e-01, 5.9232e-01])\n",
+      "TF-IDF Keywords: [array([['rus', 'ahecaqo', 'türkçe', 'pşıqo', '1777', 'çerkes', '000',\n",
+      "        'çerkesya', 'ölenler', 'ünlüydü', 'ölüm', 'yazmadıkları',\n",
+      "        'ulaşıyordu', 'tarihlerini', 'çerkeslerin', 'çerkesler',\n",
+      "        'çatışmalar', 'zaferlerle', 'öldü', 'soneki', 'soy', 'soyadları',\n",
+      "        'soylular', 'sıra', 'savaşı', 'sim', 'saygı', 'ordusu', 'oluşan',\n",
+      "        'olduğunu', 'müfrezesi', 'lakaptır', 'savaşına', 'qo', 'oğlu',\n",
+      "        'kazandığı', 'kaynakça', 'kaynaklarından', 'kaynak',\n",
+      "        'kaydedilmedi', 'katılımı', 'kalıcı', 'kafkas', 'ismidir',\n",
+      "        'ismi', 'hastalıktan', 'hakkında', 'geçti', 'lakapları',\n",
+      "        'kişiler', 'kişi', 'eş', 'geldiği', 'gelen', 'eğitim', 'dönem',\n",
+      "        'erken', 'ekiyle', 'ek', 'devlet', 'büyütüldü', 'bölgesinde',\n",
+      "        'bjeduğ', 'biyografi', 'duyulan', 'doğumlular', 'doğdu',\n",
+      "        'beyoğlu', 'bilgiler', 'birliklerine', 'belirtir', 'askerî',\n",
+      "        'becerisinin', 'atlıya', 'atlıdan', 'anlamlıdır', 'anlamına',\n",
+      "        'askeri', 'adlardaki', '1838', 'adamıydı', '1837', '12']],\n",
+      "      dtype=object)]\n"
+     ]
+    },
+    {
+     "ename": "TypeError",
+     "evalue": "sequence item 0: expected str instance, numpy.ndarray found",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[32], line 96\u001b[0m\n\u001b[0;32m     94\u001b[0m \u001b[38;5;66;03m# TF-IDF matrisini oluşturma\u001b[39;00m\n\u001b[0;32m     95\u001b[0m tfidf_vectorizer \u001b[38;5;241m=\u001b[39m TfidfVectorizer(stop_words\u001b[38;5;241m=\u001b[39mstop_words_list)\n\u001b[1;32m---> 96\u001b[0m corpus \u001b[38;5;241m=\u001b[39m [\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m \u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mjoin\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkeywords\u001b[49m\u001b[43m)\u001b[49m]  \u001b[38;5;66;03m# Anahtar kelimeleri string olarak birleştir\u001b[39;00m\n\u001b[0;32m     97\u001b[0m tfidf_matrix \u001b[38;5;241m=\u001b[39m tfidf_vectorizer\u001b[38;5;241m.\u001b[39mfit_transform(corpus \u001b[38;5;241m+\u001b[39m texts)\n\u001b[0;32m     99\u001b[0m \u001b[38;5;66;03m# Anahtar kelimeler vektörünü ve diğer metin vektörünü ayırma\u001b[39;00m\n",
+      "\u001b[1;31mTypeError\u001b[0m: sequence item 0: expected str instance, numpy.ndarray found"
+     ]
+    }
+   ],
+   "source": [
+    "import re\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from nltk.stem import WordNetLemmatizer\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "from nltk.corpus import stopwords as nltk_stopwords\n",
+    "from transformers import BertTokenizer, BertModel\n",
+    "from sklearn.metrics.pairwise import cosine_similarity\n",
+    "import torch\n",
+    "import torch.nn.functional as F\n",
+    "\n",
+    "# BERT Tokenizer ve Model'i yükleyin\n",
+    "tokenizer = BertTokenizer.from_pretrained('dbmdz/bert-base-turkish-cased')\n",
+    "model = BertModel.from_pretrained('dbmdz/bert-base-turkish-cased')\n",
+    "\n",
+    "#-------------------------- burada turkish_stop_words'ü alıyoruz\n",
+    "def load_stop_words(file_path):\n",
+    "    \"\"\"Stop words'leri dosyadan okuyarak bir liste oluşturur.\"\"\"\n",
+    "    with open(file_path, 'r', encoding='utf-8') as file:\n",
+    "        stop_words = [line.strip() for line in file if line.strip()]\n",
+    "    return stop_words\n",
+    "\n",
+    "# Türkçe stop words dosyasını yükleyin\n",
+    "stop_words_list = load_stop_words('turkish_stop_words.txt')\n",
+    "\n",
+    "# Gömülü kelimeleri k-means ile kümeleyebiliriz , benzerlik oranını hesaplamak için farklı algoritmalardan yararlanabiliriz.\n",
+    "def get_bert_embeddings(text):\n",
+    "    inputs = tokenizer(text, return_tensors='pt', truncation=True, padding=True)\n",
+    "    with torch.no_grad():\n",
+    "        outputs = model(**inputs)\n",
+    "    # Son katmandaki gömme (embedding) çıktısını alın\n",
+    "    return inputs['input_ids'], outputs.last_hidden_state\n",
+    "\n",
+    "#------------------------------------ token verilerinin ortalaması (eşik değer için)\n",
+    "def average_embeddings(embeddings):\n",
+    "    # Token vektörlerinin ortalamasını alarak metin düzeyinde özet oluştur\n",
+    "    return torch.mean(embeddings, dim=1).squeeze()\n",
+    "\n",
+    "# Keywords çıkarma fonksiyonu\n",
+    "def extract_keywords_tfidf(corpus, stop_words_list):\n",
+    "    \"\"\"TF-IDF ile anahtar kelimeleri çıkarır, stop words listesi ile birlikte kullanır.\"\"\"\n",
+    "    vectorizer = TfidfVectorizer(stop_words=stop_words_list)\n",
+    "    X = vectorizer.fit_transform(corpus)\n",
+    "    feature_names = vectorizer.get_feature_names_out()\n",
+    "    sorted_keywords = [feature_names[i] for i in X.sum(axis=0).argsort()[0, ::-1]]\n",
+    "    return sorted_keywords\n",
+    "\n",
+    "# Tokenları kelimelere dönüştürür ve listeler \n",
+    "def decode_tokens(input_ids):\n",
+    "    tokens = tokenizer.convert_ids_to_tokens(input_ids.squeeze().tolist())\n",
+    "    return tokens\n",
+    "\n",
+    "# Örnek metinler (buranın yerine combined_text kullanılacak)\n",
+    "texts = [\"\"\"Biyografi\n",
+    "İsim \n",
+    "Pşıqo ismi Ahecaqo soy ismidir. Çerkeslerin \"-qo\" soneki ile biten hem soyadları hem de lakapları vardı. Bu ek Türkçe adlardaki \"-oğlu\" ekiyle eş anlamlıdır. Pşıqo Türkçe \"Beyoğlu\" anlamına gelen bir lakaptır.\n",
+    "\n",
+    "Erken dönem \n",
+    "Çerkesler tarihlerini yazmadıkları ve tüm bilgiler Rus kaynaklarından geldiği için Ahecaqo hakkında pek bir şey kaydedilmedi. 1777'de Çerkesya'nın Bjeduğ bölgesinde doğdu. Askerî eğitim ile büyütüldü.\n",
+    "\n",
+    "Rus-Çerkes Savaşına Katılımı \n",
+    "Birkaç kaynak, Ahecaqo'nun tüm Çerkesya'da saygı duyulan bir kişi olduğunu belirtir. En az 6.000 atlıdan oluşan kalıcı bir ordusu vardı ve çatışmalar sırasında müfrezesi 12.000 atlıya ulaşıyordu. Rus birliklerine karşı kazandığı zaferlerle ünlüydü. Askeri becerisinin yanı sıra yetenekli bir devlet adamıydı.\n",
+    "\n",
+    "Ölüm \n",
+    "1837 yılında Rus tarafına geçti ve bir yıl sonra hastalıktan öldü.\n",
+    "\n",
+    "Kaynakça \n",
+    "\n",
+    "Çerkes soylular\n",
+    "1777 doğumlular\n",
+    "1838 yılında ölenler\n",
+    "Kafkas Savaşı'nda kişiler \"\"\"]\n",
+    "\n",
+    "# Token id'leri ve BERT gömme vektörleri\n",
+    "for text in texts:\n",
+    "    input_ids, embeddings = get_bert_embeddings(text)\n",
+    "    tokens = decode_tokens(input_ids)\n",
+    "    avg_embedding = average_embeddings(embeddings)\n",
+    "\n",
+    "    # Ortalama embedding değerlerinden sadece 0'dan büyük olanları alma\n",
+    "    positive_avg_embedding = avg_embedding[avg_embedding > 0]\n",
+    "\n",
+    "    if len(positive_avg_embedding) > 0:\n",
+    "        print(f\"Tokens: {tokens}\")\n",
+    "        print(f\"Positive Average Embedding Shape: {positive_avg_embedding.shape}\")\n",
+    "        print(f\"Positive Average Embedding: {positive_avg_embedding}\")\n",
+    "    else:\n",
+    "        print(\"No positive embedding values found.\")\n",
+    "\n",
+    "# TF-IDF anahtar kelimelerini çıkar\n",
+    "keywords = extract_keywords_tfidf(texts, stop_words_list)\n",
+    "print(\"TF-IDF Keywords:\", keywords)\n",
+    "\n",
+    "# TF-IDF matrisini oluşturma\n",
+    "tfidf_vectorizer = TfidfVectorizer(stop_words=stop_words_list)\n",
+    "corpus = [\" \".join(keywords)]  # Anahtar kelimeleri string olarak birleştir\n",
+    "tfidf_matrix = tfidf_vectorizer.fit_transform(corpus + texts)\n",
+    "\n",
+    "# Anahtar kelimeler vektörünü ve diğer metin vektörünü ayırma\n",
+    "keywords_vector = tfidf_matrix[0]\n",
+    "document_vectors = tfidf_matrix[1:]\n",
+    "\n",
+    "# Kelimeleri ve TF-IDF değerlerini alma\n",
+    "feature_names = tfidf_vectorizer.get_feature_names_out()\n",
+    "tfidf_scores = tfidf_matrix.toarray()\n",
+    "\n",
+    "# Cosine similarity hesaplama\n",
+    "similarity_scores = cosine_similarity(keywords_vector, document_vectors)\n",
+    "\n",
+    "# Her bir kelime için TF-IDF değerlerini yazdırma\n",
+    "for doc_idx, doc in enumerate(tfidf_scores[1:], start=1):\n",
+    "    print(f\"Document {doc_idx}:\")\n",
+    "    for word_idx, score in enumerate(doc):\n",
+    "        print(f\"Word: {feature_names[word_idx]}, TF-IDF: {score:.4f}\")\n",
+    "    print(\"\\n\")\n",
+    "\n",
+    "# Sonucu yazdırma\n",
+    "print(f\"Keywords ile metin arasındaki benzerlik: {similarity_scores[0][0]}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "A module that was compiled using NumPy 1.x cannot be run in\n",
+      "NumPy 2.1.0 as it may crash. To support both 1.x and 2.x\n",
+      "versions of NumPy, modules must be compiled with NumPy 2.0.\n",
+      "Some module may need to rebuild instead e.g. with 'pybind11>=2.12'.\n",
+      "\n",
+      "If you are a user of the module, the easiest solution will be to\n",
+      "downgrade to 'numpy<2' or try to upgrade the affected module.\n",
+      "We expect that some modules will need time to support NumPy 2.\n",
+      "\n",
+      "Traceback (most recent call last):  File \"C:\\Users\\info\\AppData\\Local\\Programs\\Python\\Python310\\lib\\runpy.py\", line 196, in _run_module_as_main\n",
+      "    return _run_code(code, main_globals, None,\n",
+      "  File \"C:\\Users\\info\\AppData\\Local\\Programs\\Python\\Python310\\lib\\runpy.py\", line 86, in _run_code\n",
+      "    exec(code, run_globals)\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\ipykernel_launcher.py\", line 18, in <module>\n",
+      "    app.launch_new_instance()\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\traitlets\\config\\application.py\", line 1075, in launch_instance\n",
+      "    app.start()\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\ipykernel\\kernelapp.py\", line 739, in start\n",
+      "    self.io_loop.start()\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\tornado\\platform\\asyncio.py\", line 205, in start\n",
+      "    self.asyncio_loop.run_forever()\n",
+      "  File \"C:\\Users\\info\\AppData\\Local\\Programs\\Python\\Python310\\lib\\asyncio\\base_events.py\", line 603, in run_forever\n",
+      "    self._run_once()\n",
+      "  File \"C:\\Users\\info\\AppData\\Local\\Programs\\Python\\Python310\\lib\\asyncio\\base_events.py\", line 1909, in _run_once\n",
+      "    handle._run()\n",
+      "  File \"C:\\Users\\info\\AppData\\Local\\Programs\\Python\\Python310\\lib\\asyncio\\events.py\", line 80, in _run\n",
+      "    self._context.run(self._callback, *self._args)\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\ipykernel\\kernelbase.py\", line 545, in dispatch_queue\n",
+      "    await self.process_one()\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\ipykernel\\kernelbase.py\", line 534, in process_one\n",
+      "    await dispatch(*args)\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\ipykernel\\kernelbase.py\", line 437, in dispatch_shell\n",
+      "    await result\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\ipykernel\\ipkernel.py\", line 362, in execute_request\n",
+      "    await super().execute_request(stream, ident, parent)\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\ipykernel\\kernelbase.py\", line 778, in execute_request\n",
+      "    reply_content = await reply_content\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\ipykernel\\ipkernel.py\", line 449, in do_execute\n",
+      "    res = shell.run_cell(\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\ipykernel\\zmqshell.py\", line 549, in run_cell\n",
+      "    return super().run_cell(*args, **kwargs)\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\IPython\\core\\interactiveshell.py\", line 3075, in run_cell\n",
+      "    result = self._run_cell(\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\IPython\\core\\interactiveshell.py\", line 3130, in _run_cell\n",
+      "    result = runner(coro)\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\IPython\\core\\async_helpers.py\", line 128, in _pseudo_sync_runner\n",
+      "    coro.send(None)\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\IPython\\core\\interactiveshell.py\", line 3334, in run_cell_async\n",
+      "    has_raised = await self.run_ast_nodes(code_ast.body, cell_name,\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\IPython\\core\\interactiveshell.py\", line 3517, in run_ast_nodes\n",
+      "    if await self.run_code(code, result, async_=asy):\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\IPython\\core\\interactiveshell.py\", line 3577, in run_code\n",
+      "    exec(code_obj, self.user_global_ns, self.user_ns)\n",
+      "  File \"C:\\Users\\info\\AppData\\Local\\Temp\\ipykernel_17960\\3105833283.py\", line 7, in <module>\n",
+      "    from transformers import BertTokenizer, BertModel\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\transformers\\__init__.py\", line 26, in <module>\n",
+      "    from . import dependency_versions_check\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\transformers\\dependency_versions_check.py\", line 16, in <module>\n",
+      "    from .utils.versions import require_version, require_version_core\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\transformers\\utils\\__init__.py\", line 34, in <module>\n",
+      "    from .generic import (\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\transformers\\utils\\generic.py\", line 462, in <module>\n",
+      "    import torch.utils._pytree as _torch_pytree\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\__init__.py\", line 2120, in <module>\n",
+      "    from torch._higher_order_ops import cond\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\_higher_order_ops\\__init__.py\", line 1, in <module>\n",
+      "    from .cond import cond\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\_higher_order_ops\\cond.py\", line 5, in <module>\n",
+      "    import torch._subclasses.functional_tensor\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\_subclasses\\functional_tensor.py\", line 42, in <module>\n",
+      "    class FunctionalTensor(torch.Tensor):\n",
+      "  File \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\_subclasses\\functional_tensor.py\", line 258, in FunctionalTensor\n",
+      "    cpu = _conversion_method_template(device=torch.device(\"cpu\"))\n",
+      "c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\_subclasses\\functional_tensor.py:258: UserWarning: Failed to initialize NumPy: _ARRAY_API not found (Triggered internally at C:\\actions-runner\\_work\\pytorch\\pytorch\\builder\\windows\\pytorch\\torch\\csrc\\utils\\tensor_numpy.cpp:84.)\n",
+      "  cpu = _conversion_method_template(device=torch.device(\"cpu\"))\n"
+     ]
+    },
+    {
+     "ename": "NameError",
+     "evalue": "name 'texts' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[1], line 62\u001b[0m\n\u001b[0;32m     59\u001b[0m tfidf_vectorizer \u001b[38;5;241m=\u001b[39m TfidfVectorizer()\n\u001b[0;32m     61\u001b[0m \u001b[38;5;66;03m# TF-IDF anahtar kelimelerini çıkar\u001b[39;00m\n\u001b[1;32m---> 62\u001b[0m keywords \u001b[38;5;241m=\u001b[39m extract_keywords_tfidf(\u001b[43mtexts\u001b[49m, stop_words_list)\n\u001b[0;32m     63\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mTF-IDF Keywords:\u001b[39m\u001b[38;5;124m\"\u001b[39m, keywords)\n\u001b[0;32m     65\u001b[0m \u001b[38;5;66;03m# Transform the text and keywords into TF-IDF representations\u001b[39;00m\n",
+      "\u001b[1;31mNameError\u001b[0m: name 'texts' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "import numpy as np\n",
+    "import re\n",
+    "import pandas as pd\n",
+    "from nltk.stem import WordNetLemmatizer\n",
+    "from nltk.corpus import stopwords as nltk_stopwords\n",
+    "from transformers import BertTokenizer, BertModel\n",
+    "from sklearn.metrics.pairwise import cosine_similarity\n",
+    "import torch\n",
+    "import torch.nn.functional as F\n",
+    "\n",
+    "# BERT Tokenizer ve Model'i yükleyin\n",
+    "tokenizer = BertTokenizer.from_pretrained('dbmdz/bert-base-turkish-cased')\n",
+    "model = BertModel.from_pretrained('dbmdz/bert-base-turkish-cased')\n",
+    "\n",
+    "#-------------------------- burada turkish_stop_words'ü alıyoruz\n",
+    "def load_stop_words(file_path):\n",
+    "    \"\"\"Stop words'leri dosyadan okuyarak bir liste oluşturur.\"\"\"\n",
+    "    with open(file_path, 'r', encoding='utf-8') as file:\n",
+    "        stop_words = [line.strip() for line in file if line.strip()]\n",
+    "    return stop_words\n",
+    "\n",
+    "# Keywords çıkarma fonksiyonu\n",
+    "def extract_keywords_tfidf(corpus, stop_words_list):\n",
+    "    \"\"\"TF-IDF ile anahtar kelimeleri çıkarır, stop words listesi ile birlikte kullanır.\"\"\"\n",
+    "    vectorizer = TfidfVectorizer(stop_words=stop_words_list)\n",
+    "    X = vectorizer.fit_transform(corpus)\n",
+    "    feature_names = vectorizer.get_feature_names_out()\n",
+    "    sorted_keywords = [feature_names[i] for i in X.sum(axis=0).argsort()[0, ::-1]]\n",
+    "    return sorted_keywords\n",
+    "\n",
+    "# Türkçe stop words dosyasını yükleyin\n",
+    "stop_words_list = load_stop_words('turkish_stop_words.txt')\n",
+    "# Define the text\n",
+    "text = \"\"\"Biyografi\n",
+    "İsim \n",
+    "Pşıqo ismi Ahecaqo soy ismidir. Çerkeslerin \"-qo\" soneki ile biten hem soyadları hem de lakapları vardı. Bu ek Türkçe adlardaki \"-oğlu\" ekiyle eş anlamlıdır. Pşıqo Türkçe \"Beyoğlu\" anlamına gelen bir lakaptır.\n",
+    "\n",
+    "Erken dönem \n",
+    "Çerkesler tarihlerini yazmadıkları ve tüm bilgiler Rus kaynaklarından geldiği için Ahecaqo hakkında pek bir şey kaydedilmedi. 1777'de Çerkesya'nın Bjeduğ bölgesinde doğdu. Askerî eğitim ile büyütüldü.\n",
+    "\n",
+    "Rus-Çerkes Savaşına Katılımı \n",
+    "Birkaç kaynak, Ahecaqo'nun tüm Çerkesya'da saygı duyulan bir kişi olduğunu belirtir. En az 6.000 atlıdan oluşan kalıcı bir ordusu vardı ve çatışmalar sırasında müfrezesi 12.000 atlıya ulaşıyordu. Rus birliklerine karşı kazandığı zaferlerle ünlüydü. Askeri becerisinin yanı sıra yetenekli bir devlet adamıydı.\n",
+    "\n",
+    "Ölüm \n",
+    "1837 yılında Rus tarafına geçti ve bir yıl sonra hastalıktan öldü.\n",
+    "\n",
+    "Kaynakça \n",
+    "\n",
+    "Çerkes soylular\n",
+    "1777 doğumlular\n",
+    "1838 yılında ölenler\n",
+    "Kafkas Savaşı'nda kişiler \"\"\"\n",
+    "\n",
+    "# Define the keywords\n",
+    "#keywords = [\"rus\", \"ahecaqo\", \"türkçe\", \"pşıqo\", \"1777\", \"çerkes\", \"000\", \"çerkesya\", \"ölenler\", \"ünlüydü\"]\n",
+    "\n",
+    "# Create a TfidfVectorizer instance\n",
+    "tfidf_vectorizer = TfidfVectorizer()\n",
+    "\n",
+    "# TF-IDF anahtar kelimelerini çıkar\n",
+    "keywords = extract_keywords_tfidf(texts, stop_words_list)\n",
+    "print(\"TF-IDF Keywords:\", keywords)\n",
+    "\n",
+    "# Transform the text and keywords into TF-IDF representations\n",
+    "text_tfidf = tfidf_vectorizer.fit_transform([text]) #burada text'i de vetörize ediyoruz.\n",
+    "keywords_tfidf = tfidf_vectorizer.transform(keywords)\n",
+    "\n",
+    "# Calculate the cosine similarity between the text and each keyword\n",
+    "similarities = []\n",
+    "for i in range(keywords_tfidf.shape[0]): #keyword_tfidf matrisinin satırları üzerinde dönfü tanımlıyoruz \n",
+    "    keyword_tfidf = keywords_tfidf[i, :] # matrisin i. değerini alıyoruz \n",
+    "    # `text_tfidf` ile `keyword_tfidf` arasındaki kosinüs benzerliğini hesaplıyoruz\n",
+    "    similarity = np.dot(text_tfidf, keyword_tfidf.T).toarray()[0][0]\n",
+    "    similarities.append((keywords[i], similarity))\n",
+    "\n",
+    "# Sort the similarities in descending order\n",
+    "keyword_similarities = sorted(similarities, key=lambda x: x[1], reverse=True)\n",
+    "\n",
+    "\n",
+    "\n",
+    "# Print the top 10 keywords with their similarities\n",
+    "print(\"Top 10 Keywords with Similarities:\")\n",
+    "for keyword, similarity in keyword_similarities[:10]:\n",
+    "    print(f\"{keyword}: {similarity:.4f}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "AttributeError",
+     "evalue": "'list' object has no attribute 'lower'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[24], line 14\u001b[0m\n\u001b[0;32m     12\u001b[0m tfidf_vectorizer \u001b[38;5;241m=\u001b[39m TfidfVectorizer(stop_words\u001b[38;5;241m=\u001b[39mstop_words_list)\n\u001b[0;32m     13\u001b[0m corpus \u001b[38;5;241m=\u001b[39m [text, keywords]\n\u001b[1;32m---> 14\u001b[0m tfidf_matrix \u001b[38;5;241m=\u001b[39m \u001b[43mtfidf_vectorizer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit_transform\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcorpus\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     16\u001b[0m \u001b[38;5;66;03m# Anahtar kelimeler vektörünü ve diğer metin vektörünü ayırma\u001b[39;00m\n\u001b[0;32m     17\u001b[0m keywords_vector \u001b[38;5;241m=\u001b[39m tfidf_matrix[\u001b[38;5;241m1\u001b[39m]\n",
+      "File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\sklearn\\feature_extraction\\text.py:2091\u001b[0m, in \u001b[0;36mTfidfVectorizer.fit_transform\u001b[1;34m(self, raw_documents, y)\u001b[0m\n\u001b[0;32m   2084\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_check_params()\n\u001b[0;32m   2085\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_tfidf \u001b[38;5;241m=\u001b[39m TfidfTransformer(\n\u001b[0;32m   2086\u001b[0m     norm\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mnorm,\n\u001b[0;32m   2087\u001b[0m     use_idf\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39muse_idf,\n\u001b[0;32m   2088\u001b[0m     smooth_idf\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msmooth_idf,\n\u001b[0;32m   2089\u001b[0m     sublinear_tf\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msublinear_tf,\n\u001b[0;32m   2090\u001b[0m )\n\u001b[1;32m-> 2091\u001b[0m X \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit_transform\u001b[49m\u001b[43m(\u001b[49m\u001b[43mraw_documents\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   2092\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_tfidf\u001b[38;5;241m.\u001b[39mfit(X)\n\u001b[0;32m   2093\u001b[0m \u001b[38;5;66;03m# X is already a transformed view of raw_documents so\u001b[39;00m\n\u001b[0;32m   2094\u001b[0m \u001b[38;5;66;03m# we set copy to False\u001b[39;00m\n",
+      "File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\sklearn\\base.py:1473\u001b[0m, in \u001b[0;36m_fit_context.<locals>.decorator.<locals>.wrapper\u001b[1;34m(estimator, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1466\u001b[0m     estimator\u001b[38;5;241m.\u001b[39m_validate_params()\n\u001b[0;32m   1468\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m config_context(\n\u001b[0;32m   1469\u001b[0m     skip_parameter_validation\u001b[38;5;241m=\u001b[39m(\n\u001b[0;32m   1470\u001b[0m         prefer_skip_nested_validation \u001b[38;5;129;01mor\u001b[39;00m global_skip_validation\n\u001b[0;32m   1471\u001b[0m     )\n\u001b[0;32m   1472\u001b[0m ):\n\u001b[1;32m-> 1473\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m fit_method(estimator, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
+      "File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\sklearn\\feature_extraction\\text.py:1372\u001b[0m, in \u001b[0;36mCountVectorizer.fit_transform\u001b[1;34m(self, raw_documents, y)\u001b[0m\n\u001b[0;32m   1364\u001b[0m             warnings\u001b[38;5;241m.\u001b[39mwarn(\n\u001b[0;32m   1365\u001b[0m                 \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mUpper case characters found in\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m   1366\u001b[0m                 \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m vocabulary while \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mlowercase\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m   1367\u001b[0m                 \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m is True. These entries will not\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m   1368\u001b[0m                 \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m be matched with any documents\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m   1369\u001b[0m             )\n\u001b[0;32m   1370\u001b[0m             \u001b[38;5;28;01mbreak\u001b[39;00m\n\u001b[1;32m-> 1372\u001b[0m vocabulary, X \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_count_vocab\u001b[49m\u001b[43m(\u001b[49m\u001b[43mraw_documents\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfixed_vocabulary_\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1374\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbinary:\n\u001b[0;32m   1375\u001b[0m     X\u001b[38;5;241m.\u001b[39mdata\u001b[38;5;241m.\u001b[39mfill(\u001b[38;5;241m1\u001b[39m)\n",
+      "File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\sklearn\\feature_extraction\\text.py:1259\u001b[0m, in \u001b[0;36mCountVectorizer._count_vocab\u001b[1;34m(self, raw_documents, fixed_vocab)\u001b[0m\n\u001b[0;32m   1257\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m doc \u001b[38;5;129;01min\u001b[39;00m raw_documents:\n\u001b[0;32m   1258\u001b[0m     feature_counter \u001b[38;5;241m=\u001b[39m {}\n\u001b[1;32m-> 1259\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m feature \u001b[38;5;129;01min\u001b[39;00m \u001b[43manalyze\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdoc\u001b[49m\u001b[43m)\u001b[49m:\n\u001b[0;32m   1260\u001b[0m         \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   1261\u001b[0m             feature_idx \u001b[38;5;241m=\u001b[39m vocabulary[feature]\n",
+      "File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\sklearn\\feature_extraction\\text.py:108\u001b[0m, in \u001b[0;36m_analyze\u001b[1;34m(doc, analyzer, tokenizer, ngrams, preprocessor, decoder, stop_words)\u001b[0m\n\u001b[0;32m    106\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m    107\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m preprocessor \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m--> 108\u001b[0m         doc \u001b[38;5;241m=\u001b[39m \u001b[43mpreprocessor\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdoc\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    109\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m tokenizer \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m    110\u001b[0m         doc \u001b[38;5;241m=\u001b[39m tokenizer(doc)\n",
+      "File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\sklearn\\feature_extraction\\text.py:66\u001b[0m, in \u001b[0;36m_preprocess\u001b[1;34m(doc, accent_function, lower)\u001b[0m\n\u001b[0;32m     47\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Chain together an optional series of text preprocessing steps to\u001b[39;00m\n\u001b[0;32m     48\u001b[0m \u001b[38;5;124;03mapply to a document.\u001b[39;00m\n\u001b[0;32m     49\u001b[0m \n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m     63\u001b[0m \u001b[38;5;124;03m    preprocessed string\u001b[39;00m\n\u001b[0;32m     64\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m     65\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m lower:\n\u001b[1;32m---> 66\u001b[0m     doc \u001b[38;5;241m=\u001b[39m \u001b[43mdoc\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlower\u001b[49m()\n\u001b[0;32m     67\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m accent_function \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m     68\u001b[0m     doc \u001b[38;5;241m=\u001b[39m accent_function(doc)\n",
+      "\u001b[1;31mAttributeError\u001b[0m: 'list' object has no attribute 'lower'"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "from sklearn.metrics.pairwise import cosine_similarity\n",
+    "import numpy as np\n",
+    "\n",
+    "#metin ile keywordslerin benzerlik oranını hesaplama \n",
+    "text,keywords\n",
+    "\n",
+    "# Metinleri birleştirip TF-IDF matrisini oluşturma\n",
+    "# TF-IDF vektörleştirici oluşturma\n",
+    "# Türkçe stop words dosyasını yükleyin\n",
+    "stop_words_list = load_stop_words('turkish_stop_words.txt')\n",
+    "tfidf_vectorizer = TfidfVectorizer(stop_words=stop_words_list)\n",
+    "corpus = [text, keywords]\n",
+    "tfidf_matrix = tfidf_vectorizer.fit_transform(corpus)\n",
+    "\n",
+    "# Anahtar kelimeler vektörünü ve diğer metin vektörünü ayırma\n",
+    "keywords_vector = tfidf_matrix[1]\n",
+    "text_vector = tfidf_matrix[0]\n",
+    "\n",
+    "# Anahtar kelimeler ve metin arasındaki cosine similarity hesaplama\n",
+    "similarity_score = cosine_similarity(keywords_vector, text_vector)\n",
+    "\n",
+    "# Sonucu yazdırma\n",
+    "print(f\"Keywords ile metin arasındaki benzerlik: {similarity_score[0][0]}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "TypeError",
+     "evalue": "'function' object is not subscriptable",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[19], line 18\u001b[0m\n\u001b[0;32m     15\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m embeddings\n\u001b[0;32m     17\u001b[0m \u001b[38;5;66;03m# Compute BERT embeddings for the top 10 keywords\u001b[39;00m\n\u001b[1;32m---> 18\u001b[0m top_keywords \u001b[38;5;241m=\u001b[39m [keyword \u001b[38;5;28;01mfor\u001b[39;00m keyword, _ \u001b[38;5;129;01min\u001b[39;00m \u001b[43mextract_keywords_tfidf\u001b[49m\u001b[43m[\u001b[49m\u001b[43m:\u001b[49m\u001b[38;5;241;43m10\u001b[39;49m\u001b[43m]\u001b[49m]\n\u001b[0;32m     19\u001b[0m bert_embeddings \u001b[38;5;241m=\u001b[39m compute_bert_embeddings(top_keywords)\n\u001b[0;32m     21\u001b[0m \u001b[38;5;66;03m# Define a function to compute the similarity between two embeddings\u001b[39;00m\n",
+      "\u001b[1;31mTypeError\u001b[0m: 'function' object is not subscriptable"
+     ]
+    }
+   ],
+   "source": [
+    "#------------------------------ tf-ıdf ve embedding benzerlik \n",
+    "# Define a function to compute BERT embeddings for a list of keywords\n",
+    "\n",
+    "def compute_bert_embeddings(keywords):\n",
+    "    embeddings = []\n",
+    "    for keyword in keywords:\n",
+    "        inputs = tokenizer.encode_plus(\n",
+    "            keyword,\n",
+    "            add_special_tokens=True,\n",
+    "            max_length=512,\n",
+    "            return_attention_mask=True,\n",
+    "            return_tensors='pt'\n",
+    "        )\n",
+    "        outputs = model(inputs['input_ids'], attention_mask=inputs['attention_mask'])\n",
+    "        embeddings.append(outputs.last_hidden_state[:, 0, :])  # Take the embedding of the [CLS] token\n",
+    "    return embeddings\n",
+    "\n",
+    "# Compute BERT embeddings for the top 10 keywords\n",
+    "top_keywords = [keyword for keyword, score in extract_keywords_tfidf[:10]]\n",
+    "bert_embeddings = compute_bert_embeddings(top_keywords)\n",
+    "\n",
+    "# Define a function to compute the similarity between two embeddings\n",
+    "def compute_similarity(embedding1, embedding2):\n",
+    "    return F.cosine_similarity(embedding1, embedding2)\n",
+    "\n",
+    "# Compute the similarity between the text and each keyword\n",
+    "similarities = []\n",
+    "for keyword_embedding in enumerate(bert_embeddings):\n",
+    "\n",
+    "    keyword= top_keywords[i]\n",
+    "    score = extract_keywords_tfidf[i][1]\n",
+    "    similarity = compute_similarity(positive_avg_embedding, keyword_embedding)\n",
+    "    similarities.append(keyword,similarity.item()*score)\n",
+    "\n",
+    "# Combine the top 10 keywords with their similarities\n",
+    "keyword_similarities = sorted(similarities, key=lambda x: x[1], reverse=True)\n",
+    "# Combine the top 10 keywords with their similarities\n",
+    "#keyword_similarities = list(zip(top_keywords, similarities))"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 8,
@@ -790,6 +1300,79 @@
     "test_stop_words_effectiveness(texts, stop_words_list)\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "K-nn ile Cosine Similarity "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#tf-ıdf değeleri arasınadki en çok metinde tekrarlanan ve anlam ilşikisi en yüksek olan kelimeleri kıyaslama \n",
+    "model.most_similar(positive=[\"rus\",])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.metrics.pairwise import cosine_similarity\n",
+    "\n",
+    "# TF-IDF ile vektörleri oluştur\n",
+    "vectorizer = TfidfVectorizer(stop_words=stop_words_list)\n",
+    "tfidf_matrix = vectorizer.fit_transform(texts)\n",
+    "\n",
+    "# BERT ile elde edilen pozitif embedding'leri TF-IDF vektörlerine dönüştür\n",
+    "# Bu adımda, her kelimenin veya metnin TF-IDF ağırlıklarıyla karşılaştırılması yapılacak\n",
+    "\n",
+    "def get_tfidf_vector_for_query(query, vectorizer):\n",
+    "    \"\"\"Sorgu metni için TF-IDF vektörü alır\"\"\"\n",
+    "    return vectorizer.transform([query])\n",
+    "\n",
+    "def calculate_similarity(tfidf_vector, embeddings):\n",
+    "    \"\"\"TF-IDF vektörü ile embeddings arasındaki cosine similarity hesaplar\"\"\"\n",
+    "    return cosine_similarity(tfidf_vector, embeddings)\n",
+    "\n",
+    "# Sorgu metnini tanımlayın ve TF-IDF vektörünü alın\n",
+    "query_text = \"Nasılsın?\"\n",
+    "query_tfidf_vector = get_tfidf_vector_for_query(query_text, vectorizer)\n",
+    "\n",
+    "# Cosine similarity hesaplayın\n",
+    "similarity_scores = calculate_similarity(query_tfidf_vector, tfidf_matrix)\n",
+    "\n",
+    "# Sonuçları yazdırın\n",
+    "print(\"Cosine Similarity Scores:\", similarity_scores)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.neighbors import NearestNeighbors\n",
+    "\n",
+    "def fit_knn_model(embeddings,n_neighbors=5):\n",
+    "    knn = NearestNeighbors(n_neighbors=n_neighbors, metric='cosine')\n",
+    "    knn.fit(embeddings)\n",
+    "    return knn\n",
+    "\n",
+    "embeddings= np.array([get_bert_embeddings(text) for text in texts])\n",
+    "#knn\n",
+    "knn_model=fit_knn_model(embeddings)\n",
+    "\n",
+    "\n",
+    "#tf-ıdf değelriyle bert üzerinden elde ettiğimiz verlerin benzerliğini hesaplayacağız \n",
+    "keywords"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 20,

deneme.ipynb

@@ -0,0 +1,69 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    },
+    {
+     "ename": "OSError",
+     "evalue": "[WinError 126] Belirtilen modül bulunamadı. Error loading \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\lib\\fbgemm.dll\" or one of its dependencies.",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mOSError\u001b[0m                                   Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[3], line 4\u001b[0m\n\u001b[0;32m      2\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mpandas\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01mpd\u001b[39;00m \n\u001b[0;32m      3\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mpymongo\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m MongoClient\n\u001b[1;32m----> 4\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtransformers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m BertTokenizer, BertForMaskedLM, DPRContextEncoderTokenizer,DPRContextEncoder\n",
+      "File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\transformers\\__init__.py:26\u001b[0m\n\u001b[0;32m     23\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtyping\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m TYPE_CHECKING\n\u001b[0;32m     25\u001b[0m \u001b[38;5;66;03m# Check the dependencies satisfy the minimal versions required.\u001b[39;00m\n\u001b[1;32m---> 26\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m dependency_versions_check\n\u001b[0;32m     27\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[0;32m     28\u001b[0m     OptionalDependencyNotAvailable,\n\u001b[0;32m     29\u001b[0m     _LazyModule,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m     48\u001b[0m     logging,\n\u001b[0;32m     49\u001b[0m )\n\u001b[0;32m     52\u001b[0m logger \u001b[38;5;241m=\u001b[39m logging\u001b[38;5;241m.\u001b[39mget_logger(\u001b[38;5;18m__name__\u001b[39m)  \u001b[38;5;66;03m# pylint: disable=invalid-name\u001b[39;00m\n",
+      "File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\transformers\\dependency_versions_check.py:16\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[38;5;66;03m# Copyright 2020 The HuggingFace Team. All rights reserved.\u001b[39;00m\n\u001b[0;32m      2\u001b[0m \u001b[38;5;66;03m#\u001b[39;00m\n\u001b[0;32m      3\u001b[0m \u001b[38;5;66;03m# Licensed under the Apache License, Version 2.0 (the \"License\");\u001b[39;00m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m     12\u001b[0m \u001b[38;5;66;03m# See the License for the specific language governing permissions and\u001b[39;00m\n\u001b[0;32m     13\u001b[0m \u001b[38;5;66;03m# limitations under the License.\u001b[39;00m\n\u001b[0;32m     15\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mdependency_versions_table\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m deps\n\u001b[1;32m---> 16\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutils\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mversions\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m require_version, require_version_core\n\u001b[0;32m     19\u001b[0m \u001b[38;5;66;03m# define which module versions we always want to check at run time\u001b[39;00m\n\u001b[0;32m     20\u001b[0m \u001b[38;5;66;03m# (usually the ones defined in `install_requires` in setup.py)\u001b[39;00m\n\u001b[0;32m     21\u001b[0m \u001b[38;5;66;03m#\u001b[39;00m\n\u001b[0;32m     22\u001b[0m \u001b[38;5;66;03m# order specific notes:\u001b[39;00m\n\u001b[0;32m     23\u001b[0m \u001b[38;5;66;03m# - tqdm must be checked before tokenizers\u001b[39;00m\n\u001b[0;32m     25\u001b[0m pkgs_to_check_at_runtime \u001b[38;5;241m=\u001b[39m [\n\u001b[0;32m     26\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpython\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m     27\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtqdm\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m     37\u001b[0m     \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpyyaml\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m     38\u001b[0m ]\n",
+      "File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\transformers\\utils\\__init__.py:34\u001b[0m\n\u001b[0;32m     25\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mconstants\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD, IMAGENET_STANDARD_MEAN, IMAGENET_STANDARD_STD\n\u001b[0;32m     26\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mdoc\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[0;32m     27\u001b[0m     add_code_sample_docstrings,\n\u001b[0;32m     28\u001b[0m     add_end_docstrings,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m     32\u001b[0m     replace_return_docstrings,\n\u001b[0;32m     33\u001b[0m )\n\u001b[1;32m---> 34\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mgeneric\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[0;32m     35\u001b[0m     ContextManagers,\n\u001b[0;32m     36\u001b[0m     ExplicitEnum,\n\u001b[0;32m     37\u001b[0m     ModelOutput,\n\u001b[0;32m     38\u001b[0m     PaddingStrategy,\n\u001b[0;32m     39\u001b[0m     TensorType,\n\u001b[0;32m     40\u001b[0m     add_model_info_to_auto_map,\n\u001b[0;32m     41\u001b[0m     add_model_info_to_custom_pipelines,\n\u001b[0;32m     42\u001b[0m     cached_property,\n\u001b[0;32m     43\u001b[0m     can_return_loss,\n\u001b[0;32m     44\u001b[0m     expand_dims,\n\u001b[0;32m     45\u001b[0m     filter_out_non_signature_kwargs,\n\u001b[0;32m     46\u001b[0m     find_labels,\n\u001b[0;32m     47\u001b[0m     flatten_dict,\n\u001b[0;32m     48\u001b[0m     infer_framework,\n\u001b[0;32m     49\u001b[0m     is_jax_tensor,\n\u001b[0;32m     50\u001b[0m     is_numpy_array,\n\u001b[0;32m     51\u001b[0m     is_tensor,\n\u001b[0;32m     52\u001b[0m     is_tf_symbolic_tensor,\n\u001b[0;32m     53\u001b[0m     is_tf_tensor,\n\u001b[0;32m     54\u001b[0m     is_torch_device,\n\u001b[0;32m     55\u001b[0m     is_torch_dtype,\n\u001b[0;32m     56\u001b[0m     is_torch_tensor,\n\u001b[0;32m     57\u001b[0m     reshape,\n\u001b[0;32m     58\u001b[0m     squeeze,\n\u001b[0;32m     59\u001b[0m     strtobool,\n\u001b[0;32m     60\u001b[0m     tensor_size,\n\u001b[0;32m     61\u001b[0m     to_numpy,\n\u001b[0;32m     62\u001b[0m     to_py_obj,\n\u001b[0;32m     63\u001b[0m     torch_float,\n\u001b[0;32m     64\u001b[0m     torch_int,\n\u001b[0;32m     65\u001b[0m     transpose,\n\u001b[0;32m     66\u001b[0m     working_or_temp_dir,\n\u001b[0;32m     67\u001b[0m )\n\u001b[0;32m     68\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mhub\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[0;32m     69\u001b[0m     CLOUDFRONT_DISTRIB_PREFIX,\n\u001b[0;32m     70\u001b[0m     HF_MODULES_CACHE,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m     96\u001b[0m     try_to_load_from_cache,\n\u001b[0;32m     97\u001b[0m )\n\u001b[0;32m     98\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mimport_utils\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[0;32m     99\u001b[0m     ACCELERATE_MIN_VERSION,\n\u001b[0;32m    100\u001b[0m     ENV_VARS_TRUE_AND_AUTO_VALUES,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    219\u001b[0m     torch_only_method,\n\u001b[0;32m    220\u001b[0m )\n",
+      "File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\transformers\\utils\\generic.py:462\u001b[0m\n\u001b[0;32m    458\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mtuple\u001b[39m(\u001b[38;5;28mself\u001b[39m[k] \u001b[38;5;28;01mfor\u001b[39;00m k \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mkeys())\n\u001b[0;32m    461\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_torch_available():\n\u001b[1;32m--> 462\u001b[0m     \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mtorch\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutils\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01m_pytree\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m \u001b[38;5;21;01m_torch_pytree\u001b[39;00m\n\u001b[0;32m    464\u001b[0m     \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_model_output_flatten\u001b[39m(output: ModelOutput) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tuple[List[Any], \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_torch_pytree.Context\u001b[39m\u001b[38;5;124m\"\u001b[39m]:\n\u001b[0;32m    465\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mlist\u001b[39m(output\u001b[38;5;241m.\u001b[39mvalues()), \u001b[38;5;28mlist\u001b[39m(output\u001b[38;5;241m.\u001b[39mkeys())\n",
+      "File \u001b[1;32mc:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\__init__.py:148\u001b[0m\n\u001b[0;32m    146\u001b[0m                 err \u001b[38;5;241m=\u001b[39m ctypes\u001b[38;5;241m.\u001b[39mWinError(ctypes\u001b[38;5;241m.\u001b[39mget_last_error())\n\u001b[0;32m    147\u001b[0m                 err\u001b[38;5;241m.\u001b[39mstrerror \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m Error loading \u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mdll\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m or one of its dependencies.\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[1;32m--> 148\u001b[0m                 \u001b[38;5;28;01mraise\u001b[39;00m err\n\u001b[0;32m    150\u001b[0m     kernel32\u001b[38;5;241m.\u001b[39mSetErrorMode(prev_error_mode)\n\u001b[0;32m    153\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_preload_cuda_deps\u001b[39m(lib_folder, lib_name):\n",
+      "\u001b[1;31mOSError\u001b[0m: [WinError 126] Belirtilen modül bulunamadı. Error loading \"c:\\gitProjects\\yeni\\.venv\\lib\\site-packages\\torch\\lib\\fbgemm.dll\" or one of its dependencies."
+     ]
+    }
+   ],
+   "source": [
+    "from datasets import load_dataset\n",
+    "import pandas as pd \n",
+    "from pymongo import MongoClient\n",
+    "from transformers import BertTokenizer, BertForMaskedLM, DPRContextEncoderTokenizer,DPRContextEncoder"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

requirements.txt

@@ -1,6 +1,127 @@
-gradio==4.40.0.*
-pymongo==4.8.0.*
-pandas==2.2.2.*
-datasets==2.20.0.*
-torch
-transformers==4.43.4.*
+absl-py==2.1.0
+aiofiles==23.2.1
+aiohappyeyeballs==2.3.4
+aiohttp==3.10.1
+aiosignal==1.3.1
+annotated-types==0.7.0
+anyio==4.4.0
+asttokens==2.4.1
+astunparse==1.6.3
+attrs==24.1.0
+certifi==2024.7.4
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+comm==0.2.2
+contourpy==1.2.1
+cycler==0.12.1
+datasets==2.20.0
+debugpy==1.8.5
+decorator==5.1.1
+dill==0.3.8
+dnspython==2.6.1
+executing==2.0.1
+fastapi==0.112.0
+ffmpy==0.4.0
+filelock==3.15.4
+flatbuffers==24.3.25
+fonttools==4.53.1
+frozenlist==1.4.1
+fsspec==2024.5.0
+gast==0.6.0
+google-pasta==0.2.0
+gradio==4.40.0
+gradio_client==1.2.0
+grpcio==1.65.4
+h11==0.14.0
+h5py==3.11.0
+httpcore==1.0.5
+httpx==0.27.0
+huggingface-hub==0.24.5
+idna==3.7
+importlib_resources==6.4.0
+ipykernel==6.29.5
+ipython==8.26.0
+jedi==0.19.1
+Jinja2==3.1.4
+jupyter_client==8.6.2
+jupyter_core==5.7.2
+keras==3.4.1
+kiwisolver==1.4.5
+libclang==18.1.1
+Markdown==3.6
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.0
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+ml-dtypes==0.4.0
+mpmath==1.3.0
+multidict==6.0.5
+multiprocess==0.70.16
+namex==0.0.8
+nest-asyncio==1.6.0
+networkx==3.3
+numpy==1.26.4
+opt-einsum==3.3.0
+optree==0.12.1
+orjson==3.10.6
+packaging==24.1
+pandas==2.2.2
+parso==0.8.4
+pillow==10.4.0
+platformdirs==4.2.2
+prompt_toolkit==3.0.47
+protobuf==4.25.4
+psutil==6.0.0
+pure_eval==0.2.3
+pyarrow==17.0.0
+pyarrow-hotfix==0.6
+pydantic==2.8.2
+pydantic_core==2.20.1
+pydub==0.25.1
+Pygments==2.18.0
+pymongo==4.8.0
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+python-multipart==0.0.9
+pytz==2024.1
+pywin32==306
+PyYAML==6.0.1
+pyzmq==26.1.0
+regex==2024.7.24
+requests==2.32.3
+rich==13.7.1
+ruff==0.5.6
+safetensors==0.4.4
+semantic-version==2.10.0
+sentence-transformers==3.0.1
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+stack-data==0.6.3
+starlette==0.37.2
+sympy==1.13.1
+tensorboard==2.17.0
+tensorboard-data-server==0.7.2
+tensorflow==2.17.0
+tensorflow-intel==2.17.0
+tensorflow-io-gcs-filesystem==0.31.0
+termcolor==2.4.0
+tokenizers==0.19.1
+tomlkit==0.12.0
+tqdm==4.66.5
+traitlets==5.14.3
+transformers==4.43.4
+typer==0.12.3
+typing_extensions==4.12.2
+tzdata==2024.1
+urllib3==2.2.2
+uvicorn==0.30.5
+wcwidth==0.2.13
+websockets==12.0
+Werkzeug==3.0.3
+wrapt==1.16.0
+xxhash==3.4.1
+yarl==1.9.4
+

turkish_stop_words.txt

@@ -0,0 +1,428 @@
+ah
+ama
+an
+ancak
+araba
+aralar
+aslında
+az
+başlayan
+bağlı
+bazı
+belirli
+ben
+bence
+birkaç
+birlikte
+bunu
+burada
+biten
+bir
+birkaç
+biz
+bu
+buna
+çünkü
+da
+de
+demek
+den
+derken
+değil
+daha
+dolayı
+edilir
+eğer
+en
+fakat
+genellikle
+gibi
+hem
+her
+herhangi
+hiç
+için
+ile
+ise
+işte
+itibaren
+iyi
+kadar
+karşı
+ki
+kime
+kısaca
+mu
+mü
+nasıl
+ne
+neden
+niye
+nın
+nda
+nun
+o
+olasılıkla
+olabilir
+olarak
+olduğu
+oluşur
+önce
+pek
+peki
+şu
+sadece
+se
+şey
+sırasında
+şimdi
+sonra
+tabi
+tarafına
+tüm
+vardı
+ve
+ya
+ya da
+yanı
+yani
+yıl
+yılında
+yetenekli
+yine
+ama
+amma
+anca
+ancak
+belki
+çünkü
+dahi
+eğer
+emme
+fakat
+gah
+gerek
+hakeza
+halbuki
+hatta
+hele
+hem
+hoş
+ile
+ile
+imdi
+ister
+kah
+keşke
+keza
+kezalik
+kim
+lakin
+madem
+mademki
+mamafih
+meğer
+meğerki
+meğerse
+netekim
+neyse
+nitekim
+oysa
+oysaki
+şayet
+velev
+velhasıl
+velhasılıkelam
+veya
+veyahut
+yahut
+yalnız
+yani
+yok
+yoksa
+zira
+acaba
+acep
+açıkça
+açıkçası
+adamakıllı
+adeta
+bazen
+bazı
+bilcümle
+binaen
+binaenaleyh
+bir
+biraz
+birazdan
+birden
+birden
+birdenbire
+birice
+birlikte
+bitevi
+biteviye
+bittabi
+bizatihi
+bizce
+bizcileyin
+bizden
+bizzat
+boşuna
+böyle
+böylece
+böylecene
+böylelikle
+böylemesine
+böylesine
+buracıkta
+burada
+buradan
+büsbütün
+çabuk
+çabukça
+çeşitli
+çoğu
+çoğun
+çoğunca
+çoğunlukla
+çok
+çokça
+çokluk
+çoklukla
+cuk
+daha
+dahil
+dahilen
+daima
+demin
+demincek
+deminden
+derakap
+derhal
+derken
+diye
+elbet
+elbette
+enikonu
+epey
+epeyce
+epeyi
+esasen
+esnasında
+etraflı
+etraflıca
+evleviyetle
+evvel
+evvela
+evvelce
+evvelden
+evvelemirde
+evveli
+gayet
+gayetle
+gayri
+gayrı
+geçende
+geçenlerde
+gene
+gerçi
+gibi
+gibilerden
+gibisinden
+gine
+halen
+halihazırda
+haliyle
+handiyse
+hani
+hasılı
+hulasaten
+iken
+illa
+illaki
+itibarıyla
+iyice
+iyicene
+kala
+kez
+kısaca
+külliyen
+lütfen
+nasıl
+nasılsa
+nazaran
+neden
+nedeniyle
+nedense
+nerde
+nerden
+nerdeyse
+nerede
+nereden
+neredeyse
+nereye
+neye
+neyi
+nice
+niçin
+nihayet
+nihayetinde
+niye
+oldu
+oldukça
+olur
+onca
+önce
+önceden
+önceleri
+öncelikle
+onculayın
+ondan
+oracık
+oracıkta
+orada
+oradan
+oranca
+oranla
+oraya
+öyle
+öylece
+öylelikle
+öylemesine
+pek
+pekala
+pekçe
+peki
+peyderpey
+sadece
+sahi
+sahiden
+sanki
+sonra
+sonradan
+sonraları
+sonunda
+şöyle
+şuncacık
+şuracıkta
+tabii
+tam
+tamam
+tamamen
+tamamıyla
+tek
+vasıtasıyla
+yakinen
+yakında
+yakından
+yakınlarda
+yalnız
+yalnızca
+yeniden
+yenilerde
+yine
+yok
+yoluyla
+yüzünden
+zaten
+zati
+ait
+bari
+beri
+bile
+değin
+dek
+denli
+doğru
+dolayı
+dolayısıyla
+gelgelelim
+gibi
+gırla
+göre
+hasebiyle
+için
+ila
+ile
+ilen
+indinde
+inen
+kadar
+kaffesi
+karşın
+kelli
+Leh
+maada
+mebni
+naşi
+rağmen
+üzere
+zarfında
+öbür
+bana
+başkası
+ben
+beriki
+birbiri
+birçoğu
+biri
+birileri
+birisi
+birkaçı
+biz
+bizimki
+buna
+bunda
+bundan
+bunlar
+bunu
+bunun
+burası
+çoğu
+çoğu
+çokları
+çoklarınca
+cümlesi
+değil
+diğeri
+filanca
+hangisi
+hepsi
+hiçbiri
+iş
+kaçı
+kaynak
+kendi
+kim
+kimi
+kimisi
+kimse
+kimse
+kimsecik
+kimsecikler
+nere
+neresi
+öbürkü
+öbürü
+ona
+onda
+ondan
+onlar
+onu
+onun
+öteki
+ötekisi
+öz
+sana
+sen
+siz
+şuna
+şunda
+şundan
+şunlar
+şunu
+şunun
+şura
+şuracık
+şurası