{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "Kütüphanelerin Yüklenmesi" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "ename": "ModuleNotFoundError", "evalue": "No module named 'datasets'", "output_type": "error", "traceback": [ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[1;31mModuleNotFoundError\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;01mimport\u001b[39;00m \u001b[38;5;21;01mdatasets\u001b[39;00m\n\u001b[0;32m 2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mdatasets\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m load_dataset\n\u001b[0;32m 3\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[1;31mModuleNotFoundError\u001b[0m: No module named 'datasets'" ] } ], "source": [ "import datasets\n", "from datasets import load_dataset\n", "import pandas as pd \n" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "ename": "OSError", "evalue": "[WinError 126] Belirtilen modül bulunamadı. Error loading \"c:\\gitProjects\\deneme\\.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[7], line 3\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[38;5;66;03m#verileri bart ile eğitme burada koleksiyon içerisindeki veriler tanımlanmalı \u001b[39;00m\n\u001b[0;32m 2\u001b[0m \u001b[38;5;66;03m# Load model directly\u001b[39;00m\n\u001b[1;32m----> 3\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 AutoModel,AutoTokenizer\n\u001b[0;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 (WEIGHTS_NAME, BertConfig,\n\u001b[0;32m 5\u001b[0m BertForQuestionAnswering, BertTokenizer)\n\u001b[0;32m 6\u001b[0m \u001b[38;5;28;01mfrom\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;01mdata\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m DataLoader, SequentialSampler, TensorDataset\n", "File \u001b[1;32mc:\\gitProjects\\deneme\\.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\\deneme\\.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\\deneme\\.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\\deneme\\.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\\deneme\\.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\\deneme\\.venv\\Lib\\site-packages\\torch\\lib\\fbgemm.dll\" or one of its dependencies." ] } ], "source": [ "#verileri bart ile eğitme burada koleksiyon içerisindeki veriler tanımlanmalı \n", "# Load model directly\n", "from transformers import AutoModel,AutoTokenizer\n", "from transformers import (WEIGHTS_NAME, BertConfig,\n", " BertForQuestionAnswering, BertTokenizer)\n", "from torch.utils.data import DataLoader, SequentialSampler, TensorDataset\n", "\n", "#from utils import (get_answer, input_to_squad_example,squad_examples_to_features, to_list)\n", "import collections\n", "# Load model directly\n", "from transformers import AutoTokenizer, AutoModelForSeq2SeqLM" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Train ve Test Verilerine İlişkin Databaselerin İçerisindeki Bilgilerin Alınması " ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "#birleştirilcek dosyaların listesi \n", "train_files=['C:\\\\gitProjects\\\\oak\\\\data\\\\train-00000-of-00007.parquet','C:\\\\gitProjects\\\\oak\\\\data\\\\train-00001-of-00007.parquet','C:\\\\gitProjects\\\\oak\\\\data\\\\train-00002-of-00007.parquet','C:\\\\gitProjects\\\\oak\\\\data\\\\train-00003-of-00007.parquet','C:\\\\gitProjects\\\\oak\\\\data\\\\train-00004-of-00007.parquet']\n", "test_files=['C:\\\\gitProjects\\\\oak\\\\data\\\\train-00005-of-00007.parquet','C:\\\\gitProjects\\\\oak\\\\data\\\\train-00006-of-00007.parquet']" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "#dosyaları yükleyin ve birleştirin\n", "train_dfs=[pd.read_parquet(file) for file in train_files]\n", "test_dfs=[pd.read_parquet(file) for file in test_files]" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "#parque dosyalarının birleştirilmesi\n", "train_df=pd.concat(train_dfs,ignore_index=True)\n", "test_df=pd.concat(test_dfs,ignore_index=True)\n", "\n", "print(train_df.head())\n", "print(train_df.head())" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "ename": "NameError", "evalue": "name 'train_df' 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[9], line 2\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[38;5;66;03m#train ve test dosyaları oluşturma \u001b[39;00m\n\u001b[1;32m----> 2\u001b[0m \u001b[43mtrain_df\u001b[49m\u001b[38;5;241m.\u001b[39mto_parquet(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mC:\u001b[39m\u001b[38;5;130;01m\\\\\u001b[39;00m\u001b[38;5;124mgitProjects\u001b[39m\u001b[38;5;130;01m\\\\\u001b[39;00m\u001b[38;5;124mdeneme\u001b[39m\u001b[38;5;130;01m\\\\\u001b[39;00m\u001b[38;5;124megitim\u001b[39m\u001b[38;5;130;01m\\\\\u001b[39;00m\u001b[38;5;124mtrain_Egitim\u001b[39m\u001b[38;5;130;01m\\\\\u001b[39;00m\u001b[38;5;124mmerged_train.parquet\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[0;32m 3\u001b[0m test_df\u001b[38;5;241m.\u001b[39mto_parquet(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mC:\u001b[39m\u001b[38;5;130;01m\\\\\u001b[39;00m\u001b[38;5;124mgitProjects\u001b[39m\u001b[38;5;130;01m\\\\\u001b[39;00m\u001b[38;5;124mdeneme\u001b[39m\u001b[38;5;130;01m\\\\\u001b[39;00m\u001b[38;5;124mtest_Egitim\u001b[39m\u001b[38;5;130;01m\\\\\u001b[39;00m\u001b[38;5;124mmerged_train.parquet\u001b[39m\u001b[38;5;124m'\u001b[39m)\n", "\u001b[1;31mNameError\u001b[0m: name 'train_df' is not defined" ] } ], "source": [ "#train ve test dosyaları oluşturma \n", "train_df.to_parquet('C:\\\\gitProjects\\\\deneme\\\\egitim\\\\train_Egitim\\\\merged_train.parquet')\n", "test_df.to_parquet('C:\\\\gitProjects\\\\deneme\\\\test_Egitim\\\\merged_train.parquet')" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Prompt_ID \\\n", "0 bb26c95639b18fd88857bf0964cd1fb5 \n", "1 56743c1870327184e058292a34ce12a8 \n", "2 88aa2f72d37cb8671ff68a6f481e382b \n", "3 703c086f7ffd9d8cc0497e82732860c7 \n", "4 a310cb6ed3f48e721473ec0525239e4e \n", "\n", " Prompt \\\n", "0 What were the crucial factors that contributed... \n", "1 Create a comprehensive guide to understanding ... \n", "2 Explore the historical significance and impact... \n", "3 How can advanced data analytics be leveraged t... \n", "4 Design a comprehensive diversity training prog... \n", "\n", " Response \\\n", "0 **Crucial Factors Contributing to the Success ... \n", "1 ## Comprehensive Guide to Weather Front Types:... \n", "2 ## The Fall of the Berlin Wall: Historical Sig... \n", "3 **1. Real-Time Sentiment Analysis:**\\n\\n* Anal... \n", "4 **Phase 1: Awareness and Self-Reflection**\\n\\n... \n", "\n", " Category Subcategory \\\n", "0 Voskhod program Voskhod 1 mission \n", "1 Science mnemonics Weather front types \n", "2 Political history The Fall of the Berlin Wall \n", "3 Test matches Data analytics \n", "4 Majority–minority relations Diversity training \n", "\n", " Prompt_token_length \n", "0 34 \n", "1 48 \n", "2 67 \n", "3 78 \n", "4 55 \n", " Prompt_ID \\\n", "0 e75b977d9abe55f0d4b33d7ee6a77e43 \n", "1 da7b42506d0c24c5f1d2371e0f53b8fe \n", "2 dc1e302eb77f44f32623f958bdf5b1f5 \n", "3 3e276bb9e578d719809b9654d710d6f5 \n", "4 3efc98322cc67bcf32abcf25576d6ba1 \n", "\n", " Prompt \\\n", "0 In the grand arena of intellectual discourse, ... \n", "1 Amidst the tapestry of human knowledge, we inv... \n", "2 In a world teeming with ideas and viewpoints, ... \n", "3 Amidst the tapestry of human knowledge, we inv... \n", "4 In the grand odyssey of intellectual discourse... \n", "\n", " Response Category Subcategory \\\n", "0 In the spirit of the renowned English physicia... None None \n", "1 Title: The Interplay of Politics and Psycholog... None None \n", "2 Energy conservation has become a critical topi... None None \n", "3 Title: Workplace Bullying: A Silent Epidemic\\n... None None \n", "4 Title: The Grand Odyssey of Grito: A Historica... None None \n", "\n", " Prompt_token_length \n", "0 134 \n", "1 121 \n", "2 191 \n", "3 128 \n", "4 190 \n" ] } ], "source": [ "#test ve train yollarını belirleme ve test, traindeki önemli sütunları alma\n", "train_file_path=('C:\\\\gitProjects\\\\deneme\\\\egitim\\\\train_Egitim\\\\merged_train.parquet')\n", "test_file_path=('C:\\\\gitProjects\\\\deneme\\\\egitim\\\\test_Egitim\\\\merged_train.parquet')\n", "\n", "train_df=pd.read_parquet(train_file_path,columns=['Prompt_ID','Prompt','Response','Category','Subcategory','Prompt_token_length'])\n", "test_df=pd.read_parquet(test_file_path,columns=['Prompt_ID','Prompt','Response','Category','Subcategory','Prompt_token_length'])\n", "\n", "print(train_df.head())\n", "print(test_df.head())" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Modelin Tokenizer ve İsminin Girilmesi" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "ename": "OSError", "evalue": "[WinError 126] Belirtilen modül bulunamadı. Error loading \"c:\\gitProjects\\deneme\\.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[13], 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 AutoModel,AutoTokenizer,AutoModelForSeq2SeqLM\n\u001b[0;32m 2\u001b[0m tokenizer \u001b[38;5;241m=\u001b[39m AutoTokenizer\u001b[38;5;241m.\u001b[39mfrom_pretrained(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mphilschmid/bart-large-cnn-samsum\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 3\u001b[0m model \u001b[38;5;241m=\u001b[39m AutoModelForSeq2SeqLM\u001b[38;5;241m.\u001b[39mfrom_pretrained(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mphilschmid/bart-large-cnn-samsum\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n", "File \u001b[1;32mc:\\gitProjects\\deneme\\.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\\deneme\\.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\\deneme\\.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\\deneme\\.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\\deneme\\.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\\deneme\\.venv\\Lib\\site-packages\\torch\\lib\\fbgemm.dll\" or one of its dependencies." ] } ], "source": [ "from transformers import AutoModel,AutoTokenizer,AutoModelForSeq2SeqLM\n", "tokenizer = AutoTokenizer.from_pretrained(\"philschmid/bart-large-cnn-samsum\")\n", "model = AutoModelForSeq2SeqLM.from_pretrained(\"philschmid/bart-large-cnn-samsum\")\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "MongoDb üzerinden önemli sütunların çekilmesi" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Train verilerinin moongodb yhe yüklenmesi " ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Data successfully loaded into MongoDB.\n" ] } ], "source": [ "from pymongo import MongoClient\n", "import pandas as pd\n", "\n", "# MongoDB connection settings\n", "\n", "def get_mongodb(database_name='yeniDatabase', collection_name='train', host='localhost', port=27017):\n", " \"\"\"\n", " MongoDB connection and collection selection\n", " \"\"\"\n", " client = MongoClient(f'mongodb://{host}:{port}/')\n", " db = client[database_name]\n", " collection = db[collection_name]\n", " return collection\n", "\n", "# Function to load dataset into MongoDB\n", "def dataset_read():\n", " train_file_path = ('C:\\\\gitProjects\\\\deneme\\\\egitim\\\\train_Egitim\\\\merged_train.parquet')\n", " data = pd.read_parquet(train_file_path, columns=['Prompt_ID', 'Prompt', 'Response', 'Category', 'Subcategory', 'Prompt_token_length'])\n", " data_dict = data.to_dict(\"records\")\n", "\n", " # Get the MongoDB collection\n", " source_collection = get_mongodb(database_name='yeniDatabase', collection_name='train') # Collection for translation\n", "\n", " # Insert data into MongoDB\n", " source_collection.insert_many(data_dict)\n", "\n", " print(\"Data successfully loaded into MongoDB.\")\n", " return source_collection\n", "\n", "# Call the function to load the dataset into MongoDB\n", "source_collection = dataset_read()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Test verilerinin monngodb yhe eklenmesi " ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Data successfully loaded into MongoDB.\n" ] } ], "source": [ "from pymongo import MongoClient\n", "import pandas as pd\n", "\n", "# MongoDB connection settings\n", "\n", "def get_mongodb(database_name='yeniDatabase', collection_name='test', host='localhost', port=27017):\n", " \"\"\"\n", " MongoDB connection and collection selection\n", " \"\"\"\n", " client = MongoClient(f'mongodb://{host}:{port}/')\n", " db = client[database_name]\n", " collection = db[collection_name]\n", " return collection\n", "\n", "# Function to load dataset into MongoDB\n", "def dataset_read():\n", " train_file_path = ('C:\\\\gitProjects\\\\deneme\\\\egitim\\\\test_Egitim\\\\merged_train.parquet')\n", " data = pd.read_parquet(train_file_path, columns=['Prompt_ID', 'Prompt', 'Response', 'Category', 'Subcategory', 'Prompt_token_length'])\n", " data_dict = data.to_dict(\"records\")\n", "\n", " # Get the MongoDB collection\n", " source_collection = get_mongodb(database_name='yeniDatabase', collection_name='test') # Collection for translation\n", "\n", " # Insert data into MongoDB\n", " source_collection.insert_many(data_dict)\n", "\n", " print(\"Data successfully loaded into MongoDB.\")\n", " return source_collection\n", "\n", "# Call the function to load the dataset into MongoDB\n", "source_collection = dataset_read()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Model eğitimi için tokenleştirme " ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from pymongo import MongoClient\n", "\n", "def get_mongodb():\n", " # MongoDB bağlantı bilgilerini döndürecek şekilde tanımlanmalıdır.\n", " return 'mongodb://localhost:27017/', 'yeniDatabase', 'test'\n", "\n", "def get_average_prompt_token_length():\n", " # MongoDB bağlantı bilgilerini alma\n", " mongo_url, db_name, collection_name = get_mongodb()\n", "\n", " # MongoDB'ye bağlanma\n", " client = MongoClient(mongo_url)\n", " db = client[db_name]\n", " collection = db[collection_name]\n", "\n", " # Tüm dökümanları çekme ve 'prompt_token_length' alanını alma\n", " docs = collection.find({}, {'Prompt_token_length': 1})\n", "\n", " # 'prompt_token_length' değerlerini toplama ve sayma\n", " total_length = 0\n", " count = 0\n", "\n", " for doc in docs:\n", " if 'Prompt_token_length' in doc:\n", " total_length += doc['Prompt_token_length']\n", " count += 1\n", " \n", " # Ortalama hesaplama\n", " if count > 0:\n", " average_length = total_length / count\n", " else:\n", " average_length = 0 # Eğer 'prompt_token_length' alanı olan döküman yoksa\n", "\n", " return int(average_length)\n", "\n", "# Ortalama prompt token uzunluğunu al ve yazdır\n", "average_length = get_average_prompt_token_length()\n", "print(f\"Ortalama prompt token uzunluğu: {average_length}\")\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# uygulama için kullanılcak olan özelliklerin tanımlanması\n", "from transformers import BertTokenizer,BertForQuestionAnswering,BertConfig\n", "class QA:\n", " def __init__(self,model_path: str):\n", " self.max_seq_length = 200 #max seq\n", " self.doc_stride = 128 #stride \n", " self.do_lower_case = False\n", " self.max_query_length = 30\n", " self.n_best_size = 3\n", " self.max_answer_length = 30\n", " self.version_2_with_negative = False\n", " #modelin yüklenmesi\n", " self.model, self.tokenizer = self.load_model(model_path)\n", " #hangi işlmecinin kullanıldığının belirlenmesi\n", " if torch.cuda.is_available():\n", " self.device = 'cuda'\n", " else:\n", " self.device = 'cpu'\n", " self.model.to(self.device)\n", " self.model.eval()\n", " \n", " # This function is used to load the model\n", " def load_model(self,model_path: str,do_lower_case=False):\n", " config = BertConfig.from_pretrained(model_path + \"C:\\\\gitProjects\\\\train_Egitim\")\n", " tokenizer = BertTokenizer.from_pretrained(model_path, do_lower_case=do_lower_case)\n", " model = BertForQuestionAnswering.from_pretrained(model_path, from_tf=False, config=config)\n", " return model, tokenizer" ] }, { "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": "3.11.9" } }, "nbformat": 4, "nbformat_minor": 2 }