Generate result with LLM validation

app.py

@@ -33,7 +33,7 @@ uploaded_files = st.file_uploader("Upload Paper(s) here :", type="pdf", accept_m
 
 chunk_option = st.selectbox(
     'Tokens amounts per process :',
-    (32000, 16000, 8000, 0), key='table_hv'
+    (32000, 16000, 8000), key='table_hv'
 )
 chunk_overlap = 0
 
@@ -112,14 +112,15 @@ if uploaded_files:
                     dataframe = dataframe[['Genes', 'SNPs', 'Diseases', 'Title', 'Authors', 'Publisher Name', 'Publication Year', 'Population', 'Sample Size', 'Study Methodology', 'Study Level', 'Conclusion']]
                     dataframe.drop_duplicates(['Genes', 'SNPs'], inplace=True)
                     dataframe.reset_index(drop=True, inplace=True)
-                    cleaned_dataframe = validate(dataframe)
+                    cleaned_df, cleaned_llm_df = validate(dataframe)
 
                     end_time = datetime.now()
                     st.write("Success in ", round((end_time.timestamp() - start_time.timestamp()) / 60, 2), "minutes")
 
-                    st.dataframe(cleaned_dataframe)
+                    st.dataframe(cleaned_df)
                     with pd.ExcelWriter(buffer, engine='xlsxwriter') as writer:
-                        cleaned_dataframe.to_excel(writer, sheet_name='Result')
+                        cleaned_llm_df.to_excel(writer, sheet_name='Result with LLM')
+                        cleaned_df.to_excel(writer, sheet_name='Result')
                         dataframe.to_excel(writer, sheet_name='Original')
                         writer.close()
 

process.py

@@ -8,7 +8,7 @@ from langchain.chains.llm import LLMChain
 from langchain.prompts import PromptTemplate
 from langchain_openai import ChatOpenAI
 from pdf2image import convert_from_path
-from prompt import prompt_entity_gsd_chunk, prompt_entity_gsd_combine, prompt_entity_summ_chunk, prompt_entity_summ_combine, prompt_entities_chunk, prompt_entities_combine, prompt_entity_one_chunk, prompt_table
+from prompt import prompt_entity_gsd_chunk, prompt_entity_gsd_combine, prompt_entity_summ_chunk, prompt_entity_summ_combine, prompt_entities_chunk, prompt_entities_combine, prompt_entity_one_chunk, prompt_table, prompt_validation
 from table_detector import detection_transform, device, model, ocr, outputs_to_objects
 
 import io
@@ -180,6 +180,7 @@ def get_table(path):
 
 def validate(df):
 
+    df = df[df['Genes'].notna()].reset_index(drop=True)
     df = df.fillna('')
     df['Genes'] = df['Genes'].str.upper()
     df['SNPs'] = df['SNPs'].str.lower()
@@ -191,32 +192,48 @@ def validate(df):
         for s in sym:
             if s in gene:
                 genes = gene.split(s)
-                df.loc[len(df)] = df.loc[i]
-                df.loc[i, 'Genes'] = genes[0]
-                df.loc[len(df) - 1, 'Genes'] = genes[1]
+                df.loc[i + 0.5] = df.loc[i]
+                df = df.sort_index().reset_index(drop=True)
+                df.loc[i, 'Genes'], df.loc[i + 1, 'Genes'] = genes[0], genes[1]
 
     # Check if there is SNPs without 'rs'
     for i in df.index:
         safe = True
         snp = df.loc[i, 'SNPs']
-        if not re.fullmatch('rs(\d)+|', snp):
-            if not re.fullmatch('s(\d)+', snp):
-                if not re.fullmatch('(\d)+', snp):
-                    safe = False
-                    df = df.drop(i)
-                else:
-                    snp = 'rs' + snp
-            else:
-                snp = 'r' + snp
-
+        if re.fullmatch('rs(\d)+|', snp):
+            pass
+        elif re.fullmatch('ts(\d)+', snp):
+            snp = 't' + snp[1:]
+        elif re.fullmatch('s(\d)+', snp):
+            snp = 'r' + snp
+        elif re.fullmatch('(\d)+', snp):
+            snp = 'rs' + snp
+        else:
+            safe = False
+            df = df.drop(i)
+            
         if safe:
             df.loc[i, 'SNPs'] = snp
 
     df.reset_index(drop=True, inplace=True)
 
-    # TODO: How to validate genes and SNPs?
+    # Validate genes and diseases with LLM
+    json_table = df[['Genes', 'SNPs', 'Diseases']].to_json(orient='records')
+    str_json_table = json.dumps(json.loads(json_table), indent=2)
+
+    result = llm_p.invoke(model='mistral-7b-instruct', input=prompt_validation.format(str_json_table)).content
+    print('val')
+    print(result)
 
-    # TODO: Validate genes and diseases with LLM
-    result = llm_p.invoke(model='mistral-7b-instruct', input='How many stars?')
+    result = result[result.find('['):result.rfind(']')+1]
+    try:
+        result = eval(result)
+    except SyntaxError:
+        result = []
+
+    df_val = pd.DataFrame(result)
+    df_val = df_val.merge(df.head(1).drop(['Genes', 'SNPs', 'Diseases'], axis=1), 'cross')
+
+    # TODO: How to validate genes and SNPs?
 
-    return df
+    return df, df_val

prompt.py

@@ -265,8 +265,8 @@ If there is no specific extracted entities provided from the table, just leave t
 
 prompt_validation = """
 # CONTEXT #
-In my capacity as a genomics specialist, I have table data containing gene names with its corresponding SNPs and diseases. The data is provided in a list of JSONs format, with each JSON object representing a single row in a tabular structure. 
-The problem is because the data is extracetd using OCR, some gene names and SNPs maybe have a typo.
+In my capacity as a genomics specialist, I have table data containing gene names with their corresponding SNPs and diseases. The data is provided in a list of JSON format, with each JSON object representing a single row in a tabular structure. 
+The problem is because the data is extracted using OCR, some gene names and SNPs may have a typo.
 
 This is the data:
 {}
@@ -274,11 +274,13 @@ This is the data:
 # OBJECTIVE #
 Given the provided table data, the following tasks need to be completed:
 
-1. Check whether the gene name is a correct gene name. If the gene name is suspected to be a typo, fix it into a correct form. If not, eliminate this row data because the gene name is not valid. 
-2. If diseases not empty, check whether the gene name is correspond with the gene names. Fix it with the correct diseases if the original disease is wrong.
+1. Check whether the gene name is the correct gene name. If the gene name is suspected of a typo, fix it into the correct form. If the gene name seems like a mistake entirely or invalid, remove the data row. Common errors include:
+    - Combined Names: Two gene names erroneously merged into one. Separate these using "and": "A and B".
+    - OCR Errors: Similar characters misread by the system. Correct these to the intended form.
+2. If diseases are not empty, check whether the gene name corresponds with the gene names. Fix it with the correct diseases if the original disease is wrong.
 
 # RESPONSE #
-The output should only be a string containing list of JSON objects, each representing an validated entry with the following structure:
+The output must be only a string containing a list of JSON objects, adhering to the identical structure present in the original input data. Each object representing a validated entry with the following structure:
 [
     {{
         "Genes": "A",

resources/experiment.ipynb

@@ -2316,6 +2316,59 @@
     "result = llm.invoke(model='llama-3-70b-instruct', input=prompt)\n",
     "print(result.content)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\Fadli\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\datasets\\load.py:1429: FutureWarning: The repository for bigbio/euadr contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/bigbio/euadr\n",
+      "You can avoid this message in future by passing the argument `trust_remote_code=True`.\n",
+      "Passing `trust_remote_code=True` will be mandatory to load this dataset from the next major release of `datasets`.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "ename": "ConnectionError",
+     "evalue": "Couldn't reach https://biosemantics.erasmusmc.nl/downloads/euadr.tgz (ConnectTimeout(MaxRetryError(\"HTTPSConnectionPool(host='biosemantics.erasmusmc.nl', port=443): Max retries exceeded with url: /downloads/euadr.tgz (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x000001CD0D00D060>, 'Connection to biosemantics.erasmusmc.nl timed out. (connect timeout=100)'))\")))",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mConnectionError\u001b[0m                           Traceback (most recent call last)",
+      "\u001b[1;32m<ipython-input-2-8057498175ab>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mdatasets\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mload_dataset\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      2\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 3\u001b[1;33m \u001b[0mdataset\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mload_dataset\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"bigbio/euadr\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[1;32mc:\\Users\\Fadli\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\datasets\\load.py\u001b[0m in \u001b[0;36mload_dataset\u001b[1;34m(path, name, data_dir, data_files, split, cache_dir, features, download_config, download_mode, verification_mode, ignore_verifications, keep_in_memory, save_infos, revision, token, use_auth_token, task, streaming, num_proc, storage_options, trust_remote_code, **config_kwargs)\u001b[0m\n\u001b[0;32m   2547\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2548\u001b[0m     \u001b[1;31m# Download and prepare data\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2549\u001b[1;33m     builder_instance.download_and_prepare(\n\u001b[0m\u001b[0;32m   2550\u001b[0m         \u001b[0mdownload_config\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdownload_config\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2551\u001b[0m         \u001b[0mdownload_mode\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdownload_mode\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\Fadli\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\datasets\\builder.py\u001b[0m in \u001b[0;36mdownload_and_prepare\u001b[1;34m(self, output_dir, download_config, download_mode, verification_mode, ignore_verifications, try_from_hf_gcs, dl_manager, base_path, use_auth_token, file_format, max_shard_size, num_proc, storage_options, **download_and_prepare_kwargs)\u001b[0m\n\u001b[0;32m   1003\u001b[0m                         \u001b[1;32mif\u001b[0m \u001b[0mnum_proc\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1004\u001b[0m                             \u001b[0mprepare_split_kwargs\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m\"num_proc\"\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnum_proc\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1005\u001b[1;33m                         self._download_and_prepare(\n\u001b[0m\u001b[0;32m   1006\u001b[0m                             \u001b[0mdl_manager\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdl_manager\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1007\u001b[0m                             \u001b[0mverification_mode\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mverification_mode\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\Fadli\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\datasets\\builder.py\u001b[0m in \u001b[0;36m_download_and_prepare\u001b[1;34m(self, dl_manager, verification_mode, **prepare_splits_kwargs)\u001b[0m\n\u001b[0;32m   1765\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1766\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m_download_and_prepare\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdl_manager\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mverification_mode\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mprepare_splits_kwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1767\u001b[1;33m         super()._download_and_prepare(\n\u001b[0m\u001b[0;32m   1768\u001b[0m             \u001b[0mdl_manager\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1769\u001b[0m             \u001b[0mverification_mode\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\Fadli\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\datasets\\builder.py\u001b[0m in \u001b[0;36m_download_and_prepare\u001b[1;34m(self, dl_manager, verification_mode, **prepare_split_kwargs)\u001b[0m\n\u001b[0;32m   1076\u001b[0m         \u001b[0msplit_dict\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mSplitDict\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdataset_name\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdataset_name\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1077\u001b[0m         \u001b[0msplit_generators_kwargs\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_make_split_generators_kwargs\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mprepare_split_kwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1078\u001b[1;33m         \u001b[0msplit_generators\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_split_generators\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdl_manager\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0msplit_generators_kwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1079\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1080\u001b[0m         \u001b[1;31m# Checksums verification\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32m~\\.cache\\huggingface\\modules\\datasets_modules\\datasets\\bigbio--euadr\\38388d88a335f2d91807b0f813bdfd809fec0e9dcbc32e2d9bfea7275d70f75c\\euadr.py\u001b[0m in \u001b[0;36m_split_generators\u001b[1;34m(self, dl_manager)\u001b[0m\n\u001b[0;32m    105\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m_split_generators\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdl_manager\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    106\u001b[0m         \u001b[0murls\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_URL\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 107\u001b[1;33m         \u001b[0mdatapath\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdl_manager\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdownload_and_extract\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0murls\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    108\u001b[0m         return [\n\u001b[0;32m    109\u001b[0m             datasets.SplitGenerator(\n",
+      "\u001b[1;32mc:\\Users\\Fadli\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\datasets\\download\\download_manager.py\u001b[0m in \u001b[0;36mdownload_and_extract\u001b[1;34m(self, url_or_urls)\u001b[0m\n\u001b[0;32m    560\u001b[0m             \u001b[0mextracted_path\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0ms\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[0;31m \u001b[0m\u001b[0;31m`\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;31m`\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mextracted\u001b[0m \u001b[0mpaths\u001b[0m \u001b[0mof\u001b[0m \u001b[0mgiven\u001b[0m \u001b[0mURL\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0ms\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    561\u001b[0m         \"\"\"\n\u001b[1;32m--> 562\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mextract\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdownload\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0murl_or_urls\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    563\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    564\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mget_recorded_sizes_checksums\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\Fadli\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\datasets\\download\\download_manager.py\u001b[0m in \u001b[0;36mdownload\u001b[1;34m(self, url_or_urls)\u001b[0m\n\u001b[0;32m    424\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    425\u001b[0m         \u001b[0mstart_time\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdatetime\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mnow\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 426\u001b[1;33m         downloaded_path_or_paths = map_nested(\n\u001b[0m\u001b[0;32m    427\u001b[0m             \u001b[0mdownload_func\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    428\u001b[0m             \u001b[0murl_or_urls\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\Fadli\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\datasets\\utils\\py_utils.py\u001b[0m in \u001b[0;36mmap_nested\u001b[1;34m(function, data_struct, dict_only, map_list, map_tuple, map_numpy, num_proc, parallel_min_length, types, disable_tqdm, desc)\u001b[0m\n\u001b[0;32m    457\u001b[0m     \u001b[1;31m# Singleton\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    458\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata_struct\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdict\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mand\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata_struct\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtypes\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 459\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0mfunction\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata_struct\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    460\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    461\u001b[0m     \u001b[0miterable\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlist\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata_struct\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata_struct\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdict\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32melse\u001b[0m \u001b[0mdata_struct\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\Fadli\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\datasets\\download\\download_manager.py\u001b[0m in \u001b[0;36m_download\u001b[1;34m(self, url_or_filename, download_config)\u001b[0m\n\u001b[0;32m    449\u001b[0m             \u001b[1;31m# append the relative path to the base_path\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    450\u001b[0m             \u001b[0murl_or_filename\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0murl_or_path_join\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_base_path\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl_or_filename\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 451\u001b[1;33m         \u001b[0mout\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcached_path\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0murl_or_filename\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdownload_config\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdownload_config\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    452\u001b[0m         \u001b[0mout\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtracked_str\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mout\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    453\u001b[0m         \u001b[0mout\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mset_origin\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0murl_or_filename\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\Fadli\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\datasets\\utils\\file_utils.py\u001b[0m in \u001b[0;36mcached_path\u001b[1;34m(url_or_filename, download_config, **download_kwargs)\u001b[0m\n\u001b[0;32m    186\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0mis_remote_url\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0murl_or_filename\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    187\u001b[0m         \u001b[1;31m# URL, so get it from the cache (downloading if necessary)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 188\u001b[1;33m         output_path = get_from_cache(\n\u001b[0m\u001b[0;32m    189\u001b[0m             \u001b[0murl_or_filename\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    190\u001b[0m             \u001b[0mcache_dir\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mcache_dir\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\Fadli\\AppData\\Local\\Programs\\Python\\Python310\\lib\\site-packages\\datasets\\utils\\file_utils.py\u001b[0m in \u001b[0;36mget_from_cache\u001b[1;34m(url, cache_dir, force_download, proxies, etag_timeout, resume_download, user_agent, local_files_only, use_etag, max_retries, token, use_auth_token, ignore_url_params, storage_options, download_desc)\u001b[0m\n\u001b[0;32m    571\u001b[0m         \u001b[0m_raise_if_offline_mode_is_enabled\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34mf\"Tried to reach {url}\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    572\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mhead_error\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 573\u001b[1;33m             \u001b[1;32mraise\u001b[0m \u001b[0mConnectionError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34mf\"Couldn't reach {url} ({repr(head_error)})\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    574\u001b[0m         \u001b[1;32melif\u001b[0m \u001b[0mresponse\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    575\u001b[0m             \u001b[1;32mraise\u001b[0m \u001b[0mConnectionError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34mf\"Couldn't reach {url} (error {response.status_code})\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;31mConnectionError\u001b[0m: Couldn't reach https://biosemantics.erasmusmc.nl/downloads/euadr.tgz (ConnectTimeout(MaxRetryError(\"HTTPSConnectionPool(host='biosemantics.erasmusmc.nl', port=443): Max retries exceeded with url: /downloads/euadr.tgz (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x000001CD0D00D060>, 'Connection to biosemantics.erasmusmc.nl timed out. (connect timeout=100)'))\")))"
+     ]
+    }
+   ],
+   "source": [
+    "from datasets import load_dataset\n",
+    "\n",
+    "dataset = load_dataset(\"bigbio/euadr\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dataset"
+   ]
   }
  ],
  "metadata": {