Update app.py

app.py

@@ -1019,43 +1019,43 @@ if analysis_option == 'Machine Learning':
     token = os.environ["HUGGING_FACE_HUB_TOKEN"]
     local_file_1 = hf_hub_download(repo_id=repo_id, filename=filename_1,repo_type="dataset", token=token)
     filtered_data = pd.read_parquet(local_file_1)
-    if filtered_data['key_lab2'].notna().any():
-        column_list = ['PatientID', 'VisitID', 'GroupedICD'] + list(filtered_data['key_lab2'].iloc[0])
-        pivot_data = pd.pivot_table(filtered_data, values='ComponentValue', index=['PatientID', 'VisitID', 'GroupedICD'], columns='ComponentName', aggfunc=lambda x: ', '.join(map(str, x)))
-        pivot_data = pivot_data.reset_index(drop=False)
-        pivot_data = pivot_data[column_list].copy()
-        filtered_data = pd.merge(filtered_data, pivot_data, on=['PatientID', 'VisitID','GroupedICD'], how='left')
+    # if filtered_data['key_lab2'].notna().any():
+    #     column_list = ['PatientID', 'VisitID', 'GroupedICD'] + list(filtered_data['key_lab2'].iloc[0])
+    #     pivot_data = pd.pivot_table(filtered_data, values='ComponentValue', index=['PatientID', 'VisitID', 'GroupedICD'], columns='ComponentName', aggfunc=lambda x: ', '.join(map(str, x)))
+    #     pivot_data = pivot_data.reset_index(drop=False)
+    #     pivot_data = pivot_data[column_list].copy()
+    #     filtered_data = pd.merge(filtered_data, pivot_data, on=['PatientID', 'VisitID','GroupedICD'], how='left')
         
-        filtered_data.iloc[:, -20:] = filtered_data.iloc[:, -20:].convert_dtypes()
-        hmm = pd.DataFrame()
-        # num_columns = 20 
-        num_columns = len(list(filtered_data['key_lab2'].iloc[0]))
-        for i in range(1, num_columns+1):
-            existing_column = filtered_data.columns[-i]
-            new_column_name = f'{existing_column}_meanvalue'
-            hmm[new_column_name] = filtered_data[existing_column].apply(mean_of_values)
-        filtered_data = pd.concat([filtered_data, hmm], axis=1)
-        column_list = [
-        ## Necessary columns
-        'PatientID', 'VisitID', 'GroupedICD',
+    #     filtered_data.iloc[:, -20:] = filtered_data.iloc[:, -20:].convert_dtypes()
+    #     hmm = pd.DataFrame()
+    #     # num_columns = 20 
+    #     num_columns = len(list(filtered_data['key_lab2'].iloc[0]))
+    #     for i in range(1, num_columns+1):
+    #         existing_column = filtered_data.columns[-i]
+    #         new_column_name = f'{existing_column}_meanvalue'
+    #         hmm[new_column_name] = filtered_data[existing_column].apply(mean_of_values)
+    #     filtered_data = pd.concat([filtered_data, hmm], axis=1)
+    #     column_list = [
+    #     ## Necessary columns
+    #     'PatientID', 'VisitID', 'GroupedICD',
         
-        ## Numerical values
-        'Age', 'SystolicBP',
-        'DiastolicBP','Temperature',
-        'Pulse', 'Weight', 'Height', 'BMI', 'Respiration',
-        'SPO2', 'PHQ_9Score',
-        # 'PeakFlow'
+    #     ## Numerical values
+    #     'Age', 'SystolicBP',
+    #     'DiastolicBP','Temperature',
+    #     'Pulse', 'Weight', 'Height', 'BMI', 'Respiration',
+    #     'SPO2', 'PHQ_9Score',
+    #     # 'PeakFlow'
     
-        ## Categorial Values
-        'LegalSex','BPLocation', 'BPPosition', 'PregnancyStatus', 'LactationStatus', 'TemperatureSource',
-        'Age_Category','BP Severity','Depression Severity','weight_condition', 'Temp_condition', 'Pulse_condition',
-        'Respiration_condition', 'SPO2_condition', 'PeakF_condition']
-        # last = list(filtered_data.columns[-20:])
-        last = list(hmm.columns)
-        required_columns = column_list + last
-        filtered_data = filtered_data[required_columns].copy()
-        filtered_data = filtered_data.drop_duplicates().reset_index(drop=True)
-        filtered_data = filtered_data.dropna(axis=1, how='all')
+    #     ## Categorial Values
+    #     'LegalSex','BPLocation', 'BPPosition', 'PregnancyStatus', 'LactationStatus', 'TemperatureSource',
+    #     'Age_Category','BP Severity','Depression Severity','weight_condition', 'Temp_condition', 'Pulse_condition',
+    #     'Respiration_condition', 'SPO2_condition', 'PeakF_condition']
+    #     # last = list(filtered_data.columns[-20:])
+    #     last = list(hmm.columns)
+    #     required_columns = column_list + last
+    #     filtered_data = filtered_data[required_columns].copy()
+    #     filtered_data = filtered_data.drop_duplicates().reset_index(drop=True)
+    #     filtered_data = filtered_data.dropna(axis=1, how='all')
         imputer(filtered_data)