ddi-fw 0.0.1__py3-none-any.whl → 0.0.3__py3-none-any.whl

ddi_fw/ner/ner.py

@@ -0,0 +1,340 @@
+from collections import defaultdict
+import glob
+import json
+from pathlib import Path
+import pathlib
+from time import sleep
+import pandas as pd
+
+from tqdm import tqdm
+import os
+import requests
+# from mmlrestclient as metamapliteclient
+from enum import Enum
+from ddi_fw.utils import create_folder_if_not_exists
+
+
+# data = '''
+# Lepirudin is a recombinant hirudin formed by 65 amino acids that acts as a highly specific and direct thrombin inhibitor.
+# [L41539,L41569] Natural hirudin is an endogenous anticoagulant found in _Hirudo medicinalis_ leeches.
+# [L41539] Lepirudin is produced in yeast cells and is identical to natural hirudin except for the absence of sulfate
+# on the tyrosine residue at position 63 and the substitution of leucine for isoleucine at position 1 (N-terminal end).[A246609]
+
+# Lepirudin is used as an anticoagulant in patients with heparin-induced thrombocytopenia (HIT),
+# an immune reaction associated with a high risk of thromboembolic complications.[A3, L41539]
+# HIT is caused by the expression of immunoglobulin G (IgG) antibodies that bind to the complex formed by heparin and platelet factor 4.
+# This activates endothelial cells and platelets and enhances the formation of thrombi.
+# [A246609] Bayer ceased the production of lepirudin (Refludan) effective May 31, 2012.[L41574]'''
+
+# response = requests.post(url, data=data)
+
+# print(response.content)
+
+HERE = pathlib.Path(__file__).resolve().parent
+
+
+class CTakesNER:
+    def __init__(self, drugs_df = None,api_url= 'http://localhost:8080/ctakes-web-rest/service/analyze?pipeline=Default'
+                  , output_path='ner-output/ctakes', ids=[],
+                 columns=[]):
+        self.drugs_df =  drugs_df
+        self.api_url = api_url
+        self.columns = columns
+        self.ids = ids
+        self.output_path = output_path
+
+    def run(self, 
+            run_for=[]):
+
+        for column in self.columns:
+            if not os.path.exists(self.output_path+"/"+column):
+                os.makedirs(self.output_path+"/"+column)
+        for column in self.columns:
+            column_output_path = self.output_path+'/'+column
+            if not column in run_for:
+                continue
+            # not include
+            if self.ids:
+                self.drugs_df = self.drugs_df[~self.drugs_df['drugbank_id'].isin(
+                    self.ids)]
+            for index, row in self.drugs_df.iterrows():
+                drugbank_id = row['drugbank_id']
+                data = row[column]
+                if data is None or pd.isna(data) or (type(data) == str and len(data.strip()) == 0):  # or len(data) == 0:
+                    with open(f'{column_output_path}/{drugbank_id}.json', 'w', encoding='utf-8') as f:
+                        json.dump([], f, ensure_ascii=False, indent=4)
+                    continue
+                data = data.encode()
+                response = requests.post(self.api_url, data=data)
+
+                with open(f'{column_output_path}/{drugbank_id}.json', 'w', encoding='utf-8') as f:
+                    try:
+                        obj = json.loads(response.text)
+                        json.dump(obj, f, ensure_ascii=False, indent=4)
+                    except:
+                        # print(f'{drugbank_id} is not parsable')
+                        json.dump([], f, ensure_ascii=False, indent=4)
+                        continue
+
+                # if index % 10 == 0:
+                #     sleep(10)
+
+    def load(self, filename = None, group = True):
+        file_path=  filename if filename else HERE.joinpath('output/ctakes/ctakes_ner.pkl')
+        df = pd.read_pickle(file_path)
+
+        if group:
+            keys = list(df.columns.values)
+
+            df['tui'] = [[]] * df.shape[0]
+            df['cui'] = [[]] * df.shape[0]
+            df['entities'] = [[]] * df.shape[0]
+
+            tui_columns = [key for key in keys if key.startswith('tui')]
+            cui_columns = [key for key in keys if key.startswith('cui')]
+            entities_columns = [key for key in keys if key.startswith('entities')]
+            #bunu tek bir eşitlikle çöz
+            df['tui'] =  df[tui_columns].values.tolist()
+            df['tui'] = df['tui'].apply(lambda items:{i for item in items for i in item})  
+
+            df['cui'] =  df[cui_columns].values.tolist()
+            df['cui'] = df['cui'].apply(lambda items:{i for item in items for i in item})  
+
+            df['entities'] =  df[entities_columns].values.tolist()
+            df['entities'] = df['entities'].apply(lambda items:{i for item in items for i in item})  
+
+        return df
+
+    def create_dataframe(self, override = False):  # dataframe_columns=[]
+        filename='ctakes_ner.pkl'
+        if not override and os.path.exists(self.output_path+"/" + filename):
+            return self.load(self.output_path+"/" + filename)
+        
+        create_folder_if_not_exists(self.output_path+"/" + filename)
+        dict_of_dict = defaultdict(dict)
+        for column in self.columns:
+            all_json_files = f'{self.output_path}/{column}/'+'*.json*'
+            for filepath in tqdm(glob.glob(all_json_files)):
+                with open(filepath, 'r', encoding="utf8") as f:
+                    file_name = Path(f.name).stem
+                    t = dict_of_dict[file_name]
+                    data = json.load(f)
+                    entities = []
+                    cuis = []
+                    tuis = []
+                    if data is None or len(data) == 0:
+                        t['drugbank_id'] = file_name
+                        t[f'cui_{column}'] = []
+                        t[f'tui_{column}']= []
+                        t[f'entities_{column}'] = []
+                        dict_of_dict[file_name] = t
+                        continue
+                    for key, value in data.items():
+                        entities = [v['text'] for v in value]
+                        cuis = [attr['cui']
+                                for v in value for attr in v['conceptAttributes']]
+                        tuis = [attr['tui']
+                                for v in value for attr in v['conceptAttributes']]
+                        # codingScheme
+                    
+                    if 'drugbank_id' not in t:
+                        t['drugbank_id'] = file_name
+                    t[f'cui_{column}'] = cuis
+                    t[f'tui_{column}'] = tuis
+                    t[f'entities_{column}'] = entities
+                dict_of_dict[file_name] = t
+
+        df = pd.DataFrame(dict_of_dict.values(),
+                          #   orient='index',
+                          #   columns=columns
+                          )
+        df.to_pickle(self.output_path+"/" + filename)
+        # dataframe_columns.insert(0, 'drugbank_id')
+
+        # new_columns = {columns[i]: dataframe_columns[i]
+        #                for i in range(len(columns))}
+        # df.rename(columns=new_columns, inplace=True)
+        return df
+
+
+# no module named 'mmlrestclient'
+# class MMSLiteNER:
+
+#     # https://ii.nlm.nih.gov/metamaplite/js/formControls.js
+
+#     class Groups(Enum):
+
+#         activities_group = ['acty', 'bhvr', 'dora',
+#                             'evnt', 'gora', 'inbe', 'mcha', 'ocac', 'socb']
+
+#         anatomy_group = ['anst', 'blor', 'bpoc', 'bsoj', 'bdsu',
+#                          'bdsy', 'cell', 'celc', 'emst', 'ffas', 'tisu']
+
+#         checmicals_and_drugs_group = ['aapp', 'antb', 'bacs', 'bodm', 'carb', 'chem', 'chvf', 'chvs',
+#                                       'clnd', 'eico', 'elii', 'enzy', 'hops', 'horm', 'imft',
+#                                       'irda', 'inch', 'lipd', 'nsba', 'nnon', 'orch', 'opco',
+#                                       'phsu', 'rcpt', 'strd', 'vita']
+
+#         concept_and_ideas_group = ['clas', 'cnce', 'ftcn', 'grpa', 'idcn', 'inpr', 'lang',
+#                                    'qlco', 'rnlw', 'spco', 'tmco']
+
+#         devices_group = ['drdd', 'medd', 'resd']
+
+#         disorders_group = ['acab', 'anab', 'bact', 'comd', 'cgab', 'dsyn',
+#                            'emod', 'fndg', 'inpo', 'mobd', 'patf', 'sosy']
+
+#         # abbreviated disorders group, finding and congenital abnormality removed
+#         disorders_abbrev_group = ['acab', 'anab', 'bact', 'cgab', 'dsyn',
+#                                   'emod', 'inpo', 'mobd', 'patf', 'sosy']
+
+#         genes_and_molecular_sequences = [
+#             'amas', 'crbs', 'gngm', 'mosq', 'nusq']
+
+#         geographic_areas = ['geoa']
+
+#         living_being = ['aggp', 'amph', 'anim', 'arch', 'bact', 'bird', 'euka', 'fish',
+#                         'fngs', 'grup', 'humn', 'mamm', 'orgm', 'podg',
+#                         'plnt', 'popg', 'prog', 'rept', 'vtbt', 'virs']
+
+#         objects = ['enty', 'food', 'mnob', 'sbst']
+
+#         occupations = ['bmod', 'ocdi']
+
+#         organizations = ['hcro', 'orgt', 'pros', 'shro']
+
+#         phenomena = ['eehu' 'hcpp', 'lbtr', 'npop', 'phpr']
+
+#         physiology = ['celf', 'clna', 'clnd']
+
+#         procedures = ['diap', 'edac', 'hlca', 'lbpr', 'mbrt', 'resa', 'topp']
+
+#     def __init__(self, drugs_df, input_path='drugbank/output', output_path='ner-output/metamaplite', ids=[],
+#                  columns=[],
+#                  included_groups: Groups = [],
+#                  excluded_groups: Groups = [],
+#                  ):
+
+#         self.drugs_df = drugs_df
+#         self.columns = columns
+#         self.ids = ids
+#         self.output_path = output_path
+#         self.included_groups = set()
+#         for i, g in enumerate(included_groups):
+#             for v in g.value:
+#                 self.included_groups.add(v)
+
+#         self.excluded_groups = set()
+#         for i, g in enumerate(excluded_groups):
+#             for v in g.value:
+#                 self.excluded_groups.add(v)
+
+#         for column in columns:
+#             if not os.path.exists(output_path+"/"+column):
+#                 os.makedirs(output_path+"/"+column)
+
+#     def run_ner(self):
+#         # # url = 'https://ii-public1.nlm.nih.gov/metamaplite/rest/annotate'
+#         base_url = 'https://ii.nlm.nih.gov/metamaplite/rest/annotate'
+#         acceptfmt = 'text/plain'
+#         for column in self.columns:
+#             column_output_path = self.output_path+'/'+column
+
+#             if self.ids:
+#                 self.drugs_df = self.drugs_df[~self.drugs_df['drugbank_id'].isin(
+#                     self.ids)]
+#             for index, row in self.drugs_df.iterrows():
+#                 drugbank_id = row['drugbank_id']
+#                 input_text = row[column]
+#                 params = [('inputtext', input_text), ('docformat', 'freetext'),
+#                           ('resultformat', 'json'), ('sourceString', 'all'),
+#                           ('semanticTypeString', 'all')]
+#                 resp = metamapliteclient.handle_request(
+#                     base_url, acceptfmt, params)
+
+#                 with open(f'{column_output_path}/{drugbank_id}.json', 'w', encoding='utf-8') as f:
+#                     obj = json.loads(resp.text)
+#                     json.dump(obj, f, ensure_ascii=False, indent=4)
+
+#                 if index % 10 == 0:
+#                     sleep(10)
+
+#     def __dict_of_semantic_types__(self, path):
+#         m = dict()
+#         with open(path, 'r', encoding='utf-8') as f:
+#             data = f.read()
+#             rows = data.split("\n")
+#             for row in rows:
+#                 if row != "":
+#                     arr = row.split("|")
+#                     m[arr[0]] = arr[1]
+#         return m
+
+#     def load(self, semantic_type_path: str, dataframe_columns=[]):
+#         semantic_type_dict = self.__dict_of_semantic_types__(
+#             semantic_type_path)
+
+#         cui_dict = defaultdict(dict)
+#         tui_dict = defaultdict(dict)
+#         for column in self.columns:
+#             all_json_files = f'{self.output_path}/{column}/'+'*.json*'
+#             for filepath in tqdm(glob.glob(all_json_files)):
+#                 with open(filepath, 'r', encoding="utf8") as f:
+#                     file_name = Path(f.name).stem
+#                     data = json.load(f)
+#                     filtered_obj = [o for o in data if len(o['evlist']) == 1]
+#                     # filtered_obj = [o for o in data if len(o['evlist']) == 1 and set(
+#                     #     checmicals_and_drugs_group).intersection(set(o['evlist'][0]['conceptinfo']['semantictypes']))]
+
+#                     if self.included_groups:
+#                         evaluation = [o['evlist'][0]['conceptinfo'] for o in filtered_obj if len(o['evlist']) == 1
+#                                       and
+#                                       self.included_groups.intersection(
+#                             set(o['evlist'][0]['conceptinfo']['semantictypes']))]
+#                         # cuis = [o['evlist'][0]['conceptinfo']['cui'] for o in filtered_obj if len(o['evlist']) == 1
+#                         #         and
+#                         #         self.included_groups.intersection(
+#                         #             set(o['evlist'][0]['conceptinfo']['semantictypes']))]
+#                     elif self.excluded_groups:
+#                         evaluation = cuis = [o['evlist'][0]['conceptinfo'] for o in filtered_obj if len(o['evlist']) == 1
+#                                              and
+#                                              not self.excluded_groups.intersection(
+#                             set(o['evlist'][0]['conceptinfo']['semantictypes']))]
+#                         # cuis = [o['evlist'][0]['conceptinfo']['cui'] for o in filtered_obj if len(o['evlist']) == 1
+#                         #         and
+#                         #         not self.excluded_groups.intersection(
+#                         #             set(o['evlist'][0]['conceptinfo']['semantictypes']))]
+#                     else:
+#                         evaluation = [o['evlist'][0]['conceptinfo']
+#                                       for o in filtered_obj if len(o['evlist']) == 1]
+#                         # cuis = [o['evlist'][0]['conceptinfo']['cui']
+#                         #         for o in filtered_obj if len(o['evlist']) == 1]
+
+#                     # cuis = [o['evlist'][0]['conceptinfo']['cui'] for o in filtered_obj if len(o['evlist']) == 1 and set(
+#                     #     checmicals_and_drugs_group).intersection(set(o['evlist'][0]['conceptinfo']['semantictypes']))]
+#                     cuis = [ev['cui'] for ev in evaluation]
+#                     semantic_types = [ev['semantictypes'] for ev in evaluation]
+#                     tuis = [semantic_type_dict[s]
+#                             for semantic_type in semantic_types for s in semantic_type]
+
+#                     d = cui_dict[file_name]
+#                     d['drugbank_id'] = file_name
+#                     d[column] = set(cuis)
+
+#                     t = tui_dict[file_name]
+#                     t['drugbank_id'] = file_name
+#                     t[column] = set(tuis)
+#                     tui_dict[file_name] = t
+
+#         columns = self.columns
+#         columns.insert(0, 'drugbank_id')
+#         df = pd.DataFrame(tui_dict.values(),
+#                           #   orient='index',
+#                           columns=columns
+#                           )
+
+#         dataframe_columns.insert(0, 'drugbank_id')
+
+#         new_columns = {columns[i]: dataframe_columns[i]
+#                        for i in range(len(columns))}
+#         df.rename(columns=new_columns, inplace=True)
+#         return df

ddi_fw/utils/__init__.py

@@ -0,0 +1,3 @@
+from .utils import create_folder_if_not_exists, utc_time_as_string,utc_time_as_string_simple_format, compress_and_save_data
+from .zip_helper import ZipHelper
+from .enums import UMLSCodeTypes, DrugBankTextDataTypes

ddi_fw/utils/enums.py

@@ -0,0 +1,23 @@
+from enum import Enum
+
+
+class UMLSCodeTypes(Enum):
+    TUI = 'tui',
+    CUI = 'cui',
+    ENTITIES = 'entities',
+
+
+class DrugBankTextDataTypes(Enum):
+    DESCRIPTION = 'description',
+    INDICATION = 'indication',
+    SYNTHESIS_REFERENCE = 'synthesis_reference',
+    PHARMACODYNAMICS = 'pharmacodynamics',
+    MECHANISM_OF_ACTION = 'mechanism_of_action',
+    TOXICITY = 'toxicity',
+    METABOLISM = 'metabolism',
+    ABSORPTION = 'absorption',
+    HALF_LIFE = 'half_life',
+    PROTEIN_BINDING = 'protein_binding',
+    ROUTE_OF_ELIMINATION = 'route_of_elimination',
+    VOLUME_OF_DISTRIBUTION = 'volume_of_distribution',
+    CLEARANCE = 'clearance',

ddi_fw/utils/utils.py

@@ -0,0 +1,103 @@
+import gzip
+import json
+import os
+
+from datetime import datetime, timezone
+
+from matplotlib import pyplot as plt
+
+
+def create_folder_if_not_exists(path):
+    if not os.path.exists(path):
+        os.makedirs(path)
+
+
+def utc_time_as_string():
+    utc_datetime = datetime.now(timezone.utc)
+
+    return datetime.strftime(utc_datetime, "%Y-%m-%dT%H:%M:%S.%f")[:-3]
+
+def utc_time_as_string_simple_format():
+    utc_datetime = datetime.now(timezone.utc)
+
+    return datetime.strftime(utc_datetime, '%Y%m%d')
+
+# https://gist.github.com/LouisAmon/4bd79b8ab80d3851601f3f9016300ac4
+
+
+def compress_data(data):
+    # Convert to JSON
+    # json_data = json.dumps(data, indent=2)
+    json_data = json.dumps(data, separators=(',', ":"))
+    # Convert to bytes
+    encoded = json_data.encode('UTF-8')
+    # Compress
+    compressed = gzip.compress(encoded)
+    return compressed
+
+
+def compress_and_save_data(data, path, file_name):
+    compressed = compress_data(data)
+    create_folder_if_not_exists(path)
+    with gzip.open(path+f'/{file_name}', 'wb') as f:
+        f.write(compressed)
+
+def decompress(gzip_file):
+    with gzip.open(gzip_file, 'r') as fin:        # 4. gzip
+        json_bytes = fin.read()                      # 3. bytes (i.e. UTF-8)
+    json_bytes = gzip.decompress(json_bytes)
+    json_str = json_bytes.decode('UTF-8')            # 2. string (i.e. JSON)
+    data = json.loads(json_str)
+    return data
+
+
+if __name__ == "__main__":
+    # json_file = f'C:\\Users\\kivanc\\Downloads\\metrics.json'
+    # file_data = open(json_file, "r", 1).read()
+    # a = json.loads(file_data)  # store in json structure
+    # # a = {'key1':1, 'key2':2}
+    # compressed = compress_data(a)
+    # with gzip.open('deneme.gzip', 'wb') as f:
+    #     f.write(compressed)
+
+    # with gzip.open('deneme.gzip', 'r') as fin:        # 4. gzip
+    #     json_bytes = fin.read()                      # 3. bytes (i.e. UTF-8)
+    # json_bytes = gzip.decompress(json_bytes)
+    # json_str = json_bytes.decode('UTF-8')            # 2. string (i.e. JSON)
+    # data = json.loads(json_str)
+    # print(data)
+
+    gzip_file = f'C:\\Users\\kivanc\\Downloads\\metrics (2).gzip'
+    stored_file =  f'C:\\Users\\kivanc\\Downloads\\save.png'
+    metrics = decompress(gzip_file)
+    # print(metrics)
+
+    # Plot Precision-Recall curves for each class and micro-average
+    fig = plt.figure()
+    plt.step(metrics['recall']['micro_event'], metrics['precision']['micro_event'],
+             color='b', alpha=0.2, where='post')
+    plt.fill_between(
+        metrics['recall']["micro_event"], metrics['precision']["micro_event"], step='post', alpha=0.2, color='b')
+
+    # for i in range(65):
+    #     plt.step( metrics['recall'][str(i)],  metrics['precision'][str(i)], where='post',
+    #              label='Class {0} (AUC={1:0.2f})'.format(i, metrics['roc_aupr'][str(i)]))
+
+    plt.xlabel('Recall')
+    plt.ylabel('Precision')
+    plt.ylim([0.0, 1.05])
+    plt.xlim([0.0, 1.0])
+    plt.title(
+        'Micro-average Precision-Recall curve: AUC={0:0.2f}'.format(metrics['roc_aupr']["micro"]))
+    plt.legend(loc='best')
+    plt.savefig(stored_file)
+    # plt.show()
+
+    import plotly.express as px
+    import pandas as pd
+    df = pd.DataFrame(dict(
+    r=[1, 5, 2, 2, 3],
+    theta=['processing cost','mechanical properties','chemical stability',
+            'thermal stability', 'device integration']))
+    fig = px.line_polar(df, r='r', theta='theta', line_close=True)
+    fig.show()

ddi_fw/utils/zip_helper.py

@@ -0,0 +1,66 @@
+import zipfile as z
+import os
+from os.path import basename
+from collections import defaultdict
+import math
+
+
+class ZipHelper:
+    def __init__(self):
+        pass
+
+    def zip_single_file(self, name, file_path, output_path):
+        if not os.path.exists(output_path):
+            os.makedirs(output_path)
+        with z.ZipFile(f'{output_path}/{name}.zip', 'w', compression=z.ZIP_LZMA, compresslevel=z.ZIP_LZMA) as zipObj:
+            zipObj.write(file_path, basename(file_path))
+
+    def zip(self, zip_prefix, input_path, output_path, chunk_size):
+        files_paths = [input_path+'/' + p for p in os.listdir(input_path)]
+        count_of_chunks = math.ceil(len(files_paths) / chunk_size)
+        zero_padding_length = len(str(int(count_of_chunks))) + 2
+
+        if not os.path.exists(output_path):
+            os.makedirs(output_path)
+
+        part = 1
+        i = 0
+        zip_dict = defaultdict(list)
+        for filePath in files_paths:
+            padded_part = f'{part}'.zfill(zero_padding_length)
+            key = f'{zip_prefix}.{padded_part}'
+            zip_dict[key].append(filePath)
+            i += 1
+            if i % chunk_size == 0:
+                i = 0
+                part += 1
+
+        for key, value in zip_dict.items():
+            with z.ZipFile(f'{output_path}/{key}.zip', 'w', compression=z.ZIP_LZMA, compresslevel=z.ZIP_LZMA) as zipObj:
+                for file_path in value:
+                    zipObj.write(file_path, basename(file_path))
+
+    def extract(self, input_path, output_path):
+        files_paths = [input_path+'/' + p for p in os.listdir(input_path)]
+        if not os.path.exists(output_path):
+            os.makedirs(output_path)
+        for file_path in files_paths:
+            if file_path.endswith('zip'):
+                with z.ZipFile(file_path, 'r') as z1:
+                    z1.extractall(path=output_path)
+                    print(f'{file_path} has been extracted')
+
+
+# if __name__ == "__main__":
+#     helper = ZipHelper()
+    # helper.zip(zip_prefix='drugs', input_path='drugbank/drugs',
+    #            output_path='drugbank/drugs-zips', chunk_size=1000)
+    # helper.extract(input_path='drugbank/drugs-zips',
+    #                output_path='drugbank/drugs-extracted')
+    # path = ''
+    # import pandas as pd
+    # d = {'col1': [1, 2], 'col2': [3, 4]}
+    # df = pd.DataFrame(data=d)
+    # df.to_pickle('test/dataframe.pickle')
+    # helper.zip_single_file(file_path='test/dataframe.pickle',output_path='test/output', name='zip')
+    # helper.extract(input_path='test/output', output_path='test/output')

{ddi_fw-0.0.1.dist-info → ddi_fw-0.0.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ddi-fw
-Version: 0.0.1
+Version: 0.0.3
 Summary: Do not use :)
 Home-page: UNKNOWN
 Author: Kıvanç Bayraktar

ddi_fw-0.0.3.dist-info/RECORD

@@ -0,0 +1,28 @@
+ddi_fw/datasets/__init__.py,sha256=WmupqKInz9XMorCAUFS_iUZoSB56xasTrC8eb0UlCVk,540
+ddi_fw/datasets/core.py,sha256=4b8ai37BpQwFeE1x1saD-YP_RN_h8-LrG5o9Sh4lQik,18418
+ddi_fw/datasets/db_utils.py,sha256=OTsa3d-Iic7z3HmzSQK9UigedRbHDxYChJk0s4GfLnw,6191
+ddi_fw/datasets/embedding_generator.py,sha256=Jqrlv88RCu0Lg812KsA12X0cSaZuxbckJ4LNRKNy_qw,2173
+ddi_fw/datasets/embedding_generator_new.py,sha256=GExjmBysPWkmFxTZQPs2yEmDdFllZ-qC9lhZeRQAfbQ,4320
+ddi_fw/datasets/feature_vector_generation.py,sha256=dxTHvp6uTkao9PdThs116Q3bWw_WTo9T8WigVL4G01s,3245
+ddi_fw/datasets/idf_helper.py,sha256=_Gd1dtDSLaw8o-o0JugzSKMt9FpeXewTh4wGEaUd4VQ,2571
+ddi_fw/drugbank/__init__.py,sha256=4_eKdZsnXUSJyr-TZpHwIn13JC6PqS5imeLJJbgt2-A,94
+ddi_fw/drugbank/drugbank_parser.py,sha256=Zc-WXCqE6cjaPpXmDSFYZWZgckTrhEHl5PW9ZNxtbcs,5457
+ddi_fw/drugbank/drugbank_processor.py,sha256=guH586c92wBjVZlfpYQlJ4KxAewTLvte-vcpUSlqWZY,17685
+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
+ddi_fw/experiments/custom_torch_model.py,sha256=iQ_R_EApzD2JCcASN8cie6D21oh7VCxaOQ45_dkiGwc,2576
+ddi_fw/experiments/evaluation_helper.py,sha256=pY69cezV3WzrXw1bduIwRJfah1w3wXJ2YyTNim1J7ko,9349
+ddi_fw/experiments/tensorflow_helper.py,sha256=FnwF0UHb-5gUDC8FsXognq8gFyRaWMz9khASAUIe0Hk,12641
+ddi_fw/experiments/test.py,sha256=rf7UB2SUZR2-UL_IVOm8_8NOY9__2dVGlUbct5tqf-0,1981
+ddi_fw/ner/__init__.py,sha256=JwhGXrepomxPSsGsg2b_xPRC72AjvxOIn2CW5Mvscn0,26
+ddi_fw/ner/mmlrestclient.py,sha256=NZta7m2Qm6I_qtVguMZhqtAUjVBmmXn0-TMnsNp0jpg,6859
+ddi_fw/ner/ner.py,sha256=BEs9AFljAxOQrC2BEP1raSzRoypcfELS5UTdl4bjTqw,15863
+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-0.0.3.dist-info/METADATA,sha256=EpE1WfQ2EviFaJolYzdkAlBlmAMH-RDrrzx3SKk_Jws,391
+ddi_fw-0.0.3.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
+ddi_fw-0.0.3.dist-info/top_level.txt,sha256=Lfsqipq5Jm60ALnmFA_cdNfpVfzBJlKM0GiQ_sB8KGE,75
+ddi_fw-0.0.3.dist-info/RECORD,,

ddi_fw-0.0.3.dist-info/top_level.txt

@@ -0,0 +1,5 @@
+ddi_fw/datasets
+ddi_fw/drugbank
+ddi_fw/experiments
+ddi_fw/ner
+ddi_fw/utils

ddi_fw-0.0.1.dist-info/RECORD

@@ -1,4 +0,0 @@
-ddi_fw-0.0.1.dist-info/METADATA,sha256=G-yvgvniNCT677dkbA9kmW6mgFh43bIb71E6zxhqnmA,391
-ddi_fw-0.0.1.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
-ddi_fw-0.0.1.dist-info/top_level.txt,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-ddi_fw-0.0.1.dist-info/RECORD,,

ddi_fw-0.0.1.dist-info/top_level.txt

@@ -1 +0,0 @@
-