combine5

scripts/combine5.py

@@ -0,0 +1,31 @@
+import pandas as pd
+import os
+import numpy as np
+
+curdir = os.getcwd()
+path_delim = '/'
+df1 = pd.read_excel(curdir + path_delim + "data/July_Sept3.xlsx", sheet_name="op")
+df2 = pd.read_excel(curdir + path_delim + "data/diff_check.xlsx", sheet_name="op")
+
+print(df2)
+df = df2.merge(df1, on="_id", how='outer')
+print(df.columns)
+# df = pd.concat([df1, df3], ignore_index=True)
+df['Age'] = 2023 - df['birthYear']
+
+
+df = df[["_id", "name", "abhaId", "aadharId", "Age", "gender", "category", "maritalStatus", "house", "district", "state", "pinCode", "phoneNumber", "Test Result_x", "bloodGroup", "createdAt", "Caste"]]
+# print(df.columns)
+
+df.rename(columns={'_id': "Sample ID", "name": "Name", "abhaId": "ABHA ID", "aadharId": "Aadhaar ID", "gender": "Gender", "category": "Category", "maritalStatus": "Marital Status", "house": "Address", "district": "District", "state": "State", "pinCode": "Pincode", "phoneNumber": "Mobile Number", "createdAt": "Date", "Test Result_x": "Test Result", "bloodGroup": "Blood Group", "Age": "Age", "Caste": "Caste"}, inplace = True)
+df = df.reindex(["Sample ID", "Name", "ABHA ID", "Aadhaar ID", "Age", "Gender", "Caste", "Category", "Marital Status", "Address", "District", "State", "Pincode", "Mobile Number", "Date", "Test Result", "Blood Group"], axis=1)
+df['Date'] = pd.to_datetime(df["Date"].dt.strftime('%d-%m-%Y'))
+
+df.loc[df['Test Result'] == np.nan, 'Test Result'] = 'Retest'
+# df.loc[df['Test Result'] == "Inconclusive", 'Test Result'] = 'Retest'
+print(df)
+
+writer = pd.ExcelWriter(curdir + path_delim + "data/July_Sept4.xlsx", engine = 'openpyxl')
+df.to_excel(writer, sheet_name = 'op', index=False)
+writer.close()
+

scripts/consolidated_data.py

@@ -16,7 +16,7 @@ if __name__ == "__main__":
     else:
         path_delim = '/'
     
-    key_file_path = os.getcwd() + path_delim + "keys" + path_delim + "hpos-preprod-firebase-adminsdk-d6jjt-ae42ad0f67.json"
+    key_file_path = os.getcwd() + path_delim + "keys" + path_delim + "hpos-prod-firebase-adminsdk-bionp-3c041b2300.json"
     cred = credentials.Certificate(key_file_path)  # Replace with your own service account key path
     firebase_admin.initialize_app(cred)
 
@@ -79,7 +79,7 @@ if __name__ == "__main__":
     df = df[(df['testTime'] > start_date) & (df['testTime'] <= end_date)]
     df = df.sort_values(by=['testTime'], ascending=False)
     
-    df = df[["_id", "calculatedRatio", "deviceId", "deviceRatio", "deviceType", "kitSerial", "led1Average", "led1Buffer", "led1Sample", "led2Average", "led2Buffer", "led2Sample", "location", "deviceSerialNumber", "name", "testTime", "classificationResult"]]
+    df = df[["_id", "calculatedRatio", "deviceId", "deviceRatio", "deviceType", "kitSerial", "led1Average", "led1Buffer", "led1Sample", "led2Average", "led2Buffer", "led2Sample", "location", "deviceSerialNumber", "name", "testTime", "classificationResult", "resultData"]]
     # df.rename(columns={'deviceSerialNumber': "login_id", "calculatedRatio": "calibrated_ratio", "led1Buffer": "427_buffer_intensity", "led2Buffer": "555_buffer_intensity", "led1Sample": "427_sample_intensity", "led2Sample": "555_sample_intensity", "led1Average": "427_absorbance", "led2Average": "555_absorbance"}, inplace = True)
     
     df = df.reindex(sorted(df.columns), axis=1)

scripts/data_diff.py

@@ -0,0 +1,33 @@
+import pandas as pd
+import os
+
+curdir = os.getcwd()
+path_delim = '/'
+df1 = pd.read_excel(curdir + path_delim + "data/all_users_14_07_2023_to_12_09_2023.xlsx", sheet_name="Sheet1")
+df2 = pd.read_excel(curdir + path_delim + "data/all_users_14_07_2023_to_12_09_2023.xlsx", sheet_name="Sheet2")
+df3 = pd.read_excel(curdir + path_delim + "data/July_Sept2 copy.xlsx", sheet_name="op")
+
+### merging July 
+df = df1.merge(df2, on="_id", how='outer')
+# df = pd.concat([df1, df3], ignore_index=True)
+print(df)
+
+# sample_ids = df["_id"].tolist()
+# print(len(sample_ids))
+
+print(len(df['_id']) - len(df['_id'].drop_duplicates()))
+
+# df_dup = df['_id']-df['_id'].drop_duplicates()
+# print(df_dedup)
+
+# dfut = pd.merge(df1, df2, how='outer',
+#                 left_index=True, right_on=['_id', 'Sample ID'],
+#                 indicator=True)
+
+# print(dfut)
+# dfut.query('_merge != "both"')
+
+writer = pd.ExcelWriter(curdir + path_delim + "data/diff_check.xlsx", engine = 'openpyxl')
+df.to_excel(writer, sheet_name = 'op', index=False)
+writer.close()
+

scripts/describe1.py

@@ -0,0 +1,14 @@
+import pandas as pd
+import os
+import numpy as np
+
+curdir = os.getcwd()
+path_delim = '/'
+df1 = pd.read_excel(curdir + path_delim + "data/July_Sept4.xlsx", sheet_name="op")
+
+df1.loc[df1['Test Result'] == 'Sickle cell Trait (HbAS)', 'Test Result'] = 'Sickle Cell Trait (HbAS)'
+print(df1.groupby(['Test Result']).describe())
+
+writer = pd.ExcelWriter(curdir + path_delim + "data/July_Sept5.xlsx", engine = 'openpyxl')
+df1.to_excel(writer, sheet_name = 'op', index=False)
+writer.close()

scripts/test_collection.py

@@ -4,7 +4,7 @@ from firebase_admin import credentials
 from firebase_admin import firestore
 from google.cloud.firestore_v1.base_query import FieldFilter
 import pandas as pd
-import datetime
+from datetime import datetime
 import sys
 import os
 
@@ -53,13 +53,16 @@ df = pd.DataFrame(data)
 print(df)
 print(df.size)
 
+df = df[["_id", "classificationResult", "calculatedRatio", "deviceId", "deviceRatio", "deviceType", "kitSerial", "led1Average", "led1Buffer", "led1Sample", "led2Average", "led2Buffer", "led2Sample", "location", "deviceSerialNumber", "name", "testTime"]]
+
 # Save the DataFrame to a CSV file
-output_filename = "data.csv"
-df.to_csv(output_filename, index=False)
+output_filename = f'tests_{datetime.today().strftime("%d_%m_%Y_%H_%M")}.xlsx'
 
 downloads_dir = os.path.join(os.path.expanduser("~"), "Downloads")
 output_path = os.path.join(downloads_dir, output_filename)
-df.to_csv(output_path, index=False)
+writer = pd.ExcelWriter(output_path, engine = 'openpyxl')
+df.to_excel(writer, sheet_name = 'data', index=False)
+writer.close()
 
 print(f"Data saved to '{output_path}'")