From fa9c676094b68fe3d649e56436a9fea01de870df Mon Sep 17 00:00:00 2001
From: Pritimay Sarkar <pritimay@sminnovations.in>
Date: Wed, 20 Sep 2023 12:26:07 +0530
Subject: [PATCH] combine testright daat for aug

---
 scripts/combine3.py | 55 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)
 create mode 100644 scripts/combine3.py

diff --git a/scripts/combine3.py b/scripts/combine3.py
new file mode 100644
index 0000000..11c5ca6
--- /dev/null
+++ b/scripts/combine3.py
@@ -0,0 +1,55 @@
+import pandas as pd
+import os
+
+curdir = os.getcwd()
+path_delim = '/'
+df1 = pd.read_excel(curdir + path_delim + "data/Testright 05 unreported data to be shated.xlsx", sheet_name="Sheet1")
+df2 = pd.read_excel(curdir + path_delim + "data/Testright 05 unreported data to be shated.xlsx", sheet_name="Sheet2")
+df3 = pd.read_excel(curdir + path_delim + "data/July_Sept_12_shared.xlsx", sheet_name="op")
+
+### merging July 
+df1['Age'] = 2023 - df1['birthYear']
+df = df1[["_id", "name", "abhaId", "aadharId", "Age", "gender", "category", "maritalStatus", "house", "district", "state", "pinCode", "phoneNumber", "bloodGroup", "testTime", "Class"]]
+
+# df = df.sort_values(by=['testTime'], ascending=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": "Test Time", "Class": "Test Result", "bloodGroup": "Blood Group", "Age": "Age", "name": "Name"}, inplace = True)
+df = df.reindex(["Sample ID", "Name", "ABHA ID", "Aadhaar ID", "Age", "Gender", "Category", "Marital Status", "Address", "District", "State", "Pincode", "Mobile Number", "Test Time", "Test Result", "Blood Group"], axis=1)
+df_result_1 = df
+
+### merging Aug 5 to 30
+df2['Age'] = 2023 - df2['birthYear']
+df = df2[["_id", "name", "abhaId", "aadharId", "Age", "gender", "category", "maritalStatus", "house", "district", "state", "pinCode", "phoneNumber", "bloodGroup", "testTime", "Class"]]
+
+# df = df.sort_values(by=['testTime'], ascending=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": "Test Time", "Class": "Test Result", "bloodGroup": "Blood Group", "Age": "Age", "name": "Name"}, inplace = True)
+df = df.reindex(["Sample ID", "Name", "ABHA ID", "Aadhaar ID", "Age", "Gender", "Category", "Marital Status", "Address", "District", "State", "Pincode", "Mobile Number", "Test Time", "Test Result", "Blood Group"], axis=1)
+df_result_2 = df
+
+
+# ### append all results
+df_final = pd.concat([df_result_1, df_result_2, df3])
+print(df_final)
+
+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)'
+df_final.loc[df_final['Test Result'] == 'SCT', 'Test Result'] = 'Sickle Cell Trait (HbAS)'
+df_final.loc[df_final['Test Result'] == 'SCD', 'Test Result'] = 'Sickle cell Disease (HbSS)'
+df_final.loc[df_final['Test Result'] == 'PBL', 'Test Result'] = 'Positive Borderline'
+df_final.loc[df_final['Test Result'] == 'NBL', 'Test Result'] = 'Negative Borderline'
+df_final.loc[df_final['Gender'] == 'Male', 'Gender'] = 'MALE'
+df_final.loc[df_final['Gender'] == 'Female', 'Gender'] = 'FEMALE'
+
+# #df_final = df.drop_duplicates(subset=['Sample ID', "Test Time"], keep='last')
+
+# df_dedup = pd.read_excel(curdir + path_delim + "data/July_Sept_12_shared.xlsx", sheet_name="op")
+
+# print(df_dedup)
+# print(df_dedup.groupby(["Gender"]).describe())
+
+
+writer = pd.ExcelWriter(curdir + path_delim + "data/July_Sept.xlsx", engine = 'openpyxl')
+df_final.to_excel(writer, sheet_name = 'op', index=False)
+writer.close()
+