smiuser/hpos-data
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

remove duplicates

Browse Source
This commit is contained in:
Pritimay Sarkar
2023-10-06 00:17:24 +05:30
parent 8816fd537e
commit 6609faaec8
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
scripts/combine15.py
View File

@@ -17,10 +17,10 @@ print(df.columns)
df['Age'] = 2023 - df['birthYear']
df = df[["_id", "name", "abhaId", "aadharId", "Age", "gender", "category", "maritalStatus", "house", "district", "state", "pinCode", "phoneNumber", "classificationResult", "bloodGroup", "createdAt", "caste"]]
df = df[["_id", "name", "abhaId", "aadharId", "Age", "gender", "category", "maritalStatus", "house", "district", "state", "pinCode", "phoneNumber", "classificationResult", "bloodGroup", "testTime", "caste"]]
print(df)
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", "classificationResult": "Test Result", "bloodGroup": "Blood Group", "Age": "Age", "caste": "Caste"}, inplace = True)
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", "testTime": "Date", "classificationResult": "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'))
@@ -29,7 +29,7 @@ df = df.reindex(["Sample ID", "Name", "ABHA ID", "Aadhaar ID", "Age", "Gender",
df["Test Result"].fillna("Retest", inplace = True)
df = df[df["Test Result"] != "Retest"]
df_final = df
df_final = df.sort_values('Date').drop_duplicates('Sample ID', keep='last')
df_final.loc[df_final['Test Result'] == 'Normal', 'Test Result'] = 'Normal (HbA)'
df_final.loc[df_final['Test Result'] == 'Sickle Cell Trait', 'Test Result'] = 'Sickle Cell Trait (HbAS)'
@@ -44,7 +44,7 @@ print(df_final.groupby(["Test Result"]).describe())
df_count = df.groupby(["Test Result"]).describe()["ABHA ID"]["count"]
print(df.groupby(["Test Result"]).describe()["ABHA ID"]["count"])
writer = pd.ExcelWriter(curdir + path_delim + "data/Oct5.xlsx", engine = 'openpyxl')
writer = pd.ExcelWriter(curdir + path_delim + "data/Oct5c.xlsx", engine = 'openpyxl')
df_final.to_excel(writer, sheet_name = 'op', index=False)
df_count.to_excel(writer, sheet_name = "count")
writer.close()