ddi-fw 0.0.17__py3-none-any.whl → 0.0.18__py3-none-any.whl

ddi_fw/drugbank/drugbank_processor.py

@@ -40,7 +40,7 @@ class DrugBankProcessor():
             zip_helper = ZipHelper()
             zip_helper.extract(input_path=input_path, output_path=output_path)
 
-    def get_external_identifiers(self,input_path='drugs'):
+    def get_external_identifiers(self, input_path='drugs'):
         external_identifier_list = []
         all_json_files = input_path+'/*.json*'
 
@@ -50,14 +50,15 @@ class DrugBankProcessor():
                 data = json.load(f)
                 drug_1 = data['name']
                 drug_1_id = [d['value']
-                                     for d in data['drugbank-id'] if d['primary'] == True][0]
+                             for d in data['drugbank-id'] if d['primary'] == True][0]
                 external_identifiers = data['external-identifiers'] if "external-identifiers" in data else None
                 external_identifiers_dict = {}
                 external_identifiers_dict['name'] = drug_1
                 external_identifiers_dict['drugbank_id'] = drug_1_id
                 if external_identifiers is not None:
                     for p in external_identifiers['external-identifier']:
-                        external_identifiers_dict[p['resource'].lower().replace(" ","_")] = p['identifier']
+                        external_identifiers_dict[p['resource'].lower().replace(
+                            " ", "_")] = p['identifier']
                     # external_identifiers_dict = dict(
                     #     [(p['resource'].lower().replace(" ","_"), p['identifier']) for p in external_identifiers['external-identifier']])
                     # external_identifiers_dict['name'] = drug_1
@@ -65,11 +66,16 @@ class DrugBankProcessor():
                 external_identifier_list.append(external_identifiers_dict)
         return external_identifier_list
 
-
-    def process(self, input_path='drugs', output_path='output', save_as_sql=True, db_path =  r"./drugbank.db", zip_outputs=True):
+    def process(self,
+                input_path='drugs',
+                output_path='output',
+                save_as_sql=True,
+                db_path=r"./drugbank.db",
+                zip_outputs=True,
+                ner_data_path):
         if not os.path.exists(output_path):
             os.makedirs(output_path)
-        ner_df =CTakesNER().load()
+        ner_df = CTakesNER().load(ner_data_path)
         drugs_pickle_path = output_path+'/drugs.pkl'
         drugs_csv_path = output_path+'/drugs.gzip'
         ddi_pickle_path = output_path + '/ddi.pkl'
@@ -158,12 +164,12 @@ class DrugBankProcessor():
                             pathways = [
                                 d['smpdb-id'] for d in data['pathways']['pathway']]
 
-
                         if external_identifiers is not None:
                             external_identifiers_dict = dict(
                                 [(p['resource'], p['identifier']) for p in external_identifiers['external-identifier']])
                             external_identifiers_dict['drugbank_id'] = drug_1_id
-                            external_identifier_list.append(external_identifiers_dict)
+                            external_identifier_list.append(
+                                external_identifiers_dict)
 # add note column
                         smiles = None
                         morgan_hashed = None
@@ -182,19 +188,22 @@ class DrugBankProcessor():
                             morgan_hashed = np.zeros(881).tolist()
 
                         # TODO cui, tui, entities other types of texts, test it
-                        tuis_description = ner_df[ner_df['drugbank_id'] == drug_1_id]['tui_description'].values
+                        tuis_description = ner_df[ner_df['drugbank_id']
+                                                  == drug_1_id]['tui_description'].values
                         if len(tuis_description) > 0:
                             tuis_description = tuis_description[0]
                         else:
                             tuis_description = None
 
-                        cuis_description = ner_df[ner_df['drugbank_id'] == drug_1_id]['cui_description'].values
+                        cuis_description = ner_df[ner_df['drugbank_id']
+                                                  == drug_1_id]['cui_description'].values
                         if len(cuis_description) > 0:
                             cuis_description = cuis_description[0]
                         else:
                             cuis_description = None
 
-                        entities_description = ner_df[ner_df['drugbank_id'] == drug_1_id]['entities_description'].values
+                        entities_description = ner_df[ner_df['drugbank_id']
+                                                      == drug_1_id]['entities_description'].values
                         if len(entities_description) > 0:
                             entities_description = entities_description[0]
                         else:
@@ -225,10 +234,10 @@ class DrugBankProcessor():
                                'enzymes_polypeptides': '|'.join(enzymes_polypeptides) if enzymes_polypeptides is not None else None,
                                'targets_polypeptides': '|'.join(targets_polypeptides) if targets_polypeptides is not None else None,
                                'pathways': '|'.join(pathways) if pathways is not None else None,
-                               'tuis_description':'|'.join(tuis_description) if tuis_description is not None else None,
-                               'cuis_description':'|'.join(cuis_description) if cuis_description is not None else None,
-                               'entities_description':'|'.join(entities_description) if entities_description is not None else None
-                            #    'external_identifiers': external_identifiers_dict
+                               'tuis_description': '|'.join(tuis_description) if tuis_description is not None else None,
+                               'cuis_description': '|'.join(cuis_description) if cuis_description is not None else None,
+                               'entities_description': '|'.join(entities_description) if entities_description is not None else None
+                               #    'external_identifiers': external_identifiers_dict
                                }
                         drug_rows.append(row)
 
@@ -282,10 +291,13 @@ class DrugBankProcessor():
 
             if save_as_sql:
                 conn = sqlite3.connect(db_path)
-                # self.drugs_df.to_sql('_Drugs', conn, if_exists='replace', index=True)
-                # self.ddis_df.to_sql('_Interactions', conn, if_exists='replace', index=True)
-                ext_id_df= pd.DataFrame.from_records(external_identifier_list)
-                ext_id_df.to_sql('_ExternalIdentifiers', conn, if_exists='replace', index=True)
+                self.drugs_df.to_sql(
+                    '_Drugs', conn, if_exists='replace', index=True)
+                self.ddis_df.to_sql('_Interactions', conn,
+                                    if_exists='replace', index=True)
+                ext_id_df = pd.DataFrame.from_records(external_identifier_list)
+                ext_id_df.to_sql('_ExternalIdentifiers', conn,
+                                 if_exists='replace', index=True)
 
                 zip_helper.zip_single_file(
                     file_path=db_path, output_path=output_path+'/zips', name='db')

{ddi_fw-0.0.17.dist-info → ddi_fw-0.0.18.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ddi_fw
-Version: 0.0.17
+Version: 0.0.18
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.17.dist-info → ddi_fw-0.0.18.dist-info}/RECORD

@@ -53,7 +53,7 @@ ddi_fw/datasets/mdf_sa_ddi/indexes/validation_fold_4.txt,sha256=STKdpjRqA0Vi63RJ
 ddi_fw/drugbank/__init__.py,sha256=4_eKdZsnXUSJyr-TZpHwIn13JC6PqS5imeLJJbgt2-A,94
 ddi_fw/drugbank/drugbank.xsd,sha256=y-WzMHANyzmf5T_0ywlMOq63ft9uW41B5I1WfBKbh9c,43306
 ddi_fw/drugbank/drugbank_parser.py,sha256=lxUuhB0s8ef_aPNDs0V8ClKF7-KIWugNIV9gVsRvzrw,5610
-ddi_fw/drugbank/drugbank_processor.py,sha256=4Hs6cPmG_d0wDXA6979WMZQmFcDrGbCGLja-Nhs7gyQ,17692
+ddi_fw/drugbank/drugbank_processor.py,sha256=7I6YYnIagqm7tZGrRHAKTq9QoCxg5R3oS0CgjsyzMBY,18127
 ddi_fw/drugbank/drugbank_processor_org.py,sha256=eO5Yset50P91qkic79RUXPoEuxRxQKFkKW0l4G29Mas,13322
 ddi_fw/drugbank/event_extractor.py,sha256=6odoZohhK7OdLF-LF0l-5BFq0_NMG_5jrFJbHrBXsI8,4600
 ddi_fw/experiments/__init__.py,sha256=UJwd2i3QcuaI1YjC_2yGCiLuEMTT5Yo7rDFxw89chIw,108
@@ -79,7 +79,7 @@ ddi_fw/utils/__init__.py,sha256=nhNU_sEp55xsZ5VtvhozjKg6r4GWP6SJI13v8F_jbCg,217
 ddi_fw/utils/enums.py,sha256=19eJ3fX5eRK_xPvkYcukmug144jXPH4X9zQqtsFBj5A,671
 ddi_fw/utils/utils.py,sha256=Na6Y8mY-CFbQjrgd9xC8agcrjVvTj_7KIXqFm1H_3qU,3549
 ddi_fw/utils/zip_helper.py,sha256=DjtwcGBoYw8zOP-Ye5OxzeR1OgN3WfNkVx85nb0wbJA,2635
-ddi_fw-0.0.17.dist-info/METADATA,sha256=IbofIWh6wWq0LO-YT5qKARTnySunykPDHsK48OTc7lA,1508
-ddi_fw-0.0.17.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
-ddi_fw-0.0.17.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
-ddi_fw-0.0.17.dist-info/RECORD,,
+ddi_fw-0.0.18.dist-info/METADATA,sha256=tE1vK0fU12Rww6VOIqBShgWFPDqf-tndbEXF6YNkHlk,1508
+ddi_fw-0.0.18.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
+ddi_fw-0.0.18.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
+ddi_fw-0.0.18.dist-info/RECORD,,