diff --git a/scripts/combine25.py b/scripts/combine25.py
new file mode 100644
index 0000000..91c3482
--- /dev/null
+++ b/scripts/combine25.py
@@ -0,0 +1,83 @@
+import pandas as pd
+import os
+import numpy as np
+import matplotlib.pyplot as plt
+
+curdir = os.getcwd()
+path_delim = '/'
+df1 = pd.read_excel(curdir + path_delim + "data/users_19_10_2023_19_57.xlsx", sheet_name="Sheet1")
+df2 = pd.read_excel(curdir + path_delim + "data/19 Oct 2023 Final Results.xlsx")
+
+df2 = df2.sort_values('testTime')
+
+variance_column = df2["led2Buffer"].var(ddof=0)
+print(variance_column)
+
+# df2.plot(kind = 'scatter', x = 'testTime', y = 'calculatedRatio')
+# plt.show()
+
+
+# df2.plot(kind = 'scatter', x = 'testTime', y = 'led1Buffer')
+# plt.show()
+
+# df2.plot(kind = 'scatter', x = 'testTime', y = 'led2Buffer')
+# plt.show()
+
+# df2.plot(kind = 'scatter', x = 'testTime', y = 'led1Sample')
+# plt.show()
+
+# df2.plot(kind = 'scatter', x = 'testTime', y = 'led2Sample')
+# plt.show()
+
+df = df1.merge(df2, on="_id", how="outer")
+print(df.columns)
+# # df = pd.concat([df1, df3], ignore_index=True)
+df['Age'] = 2023 - df['birthYear_x']
+
+df['deviceId'].hist()
+plt.show()
+
+# df['led2Sample'].plot.box()
+# plt.show()
+
+# df['led2Sample'].plot.kde()
+# plt.show()
+
+# df['led2Sample'].plot.density()
+# plt.show()
+
+# df['category'].plot.pie()
+# plt.show()
+
+df = df[["_id", "name_x", "abhaId_x", "aadharId_x", "Age", "gender_x", "category_x", "maritalStatus_x", "house_x", "district_x", "state_x", "pinCode_x", "phoneNumber_x", "classificationResult", "bloodGroup_x", "createdAt_x", "caste_x", "registrationCenterName_x"]]
+print(df)
+
+df.rename(columns={'_id': "Sample ID", "name_x": "Name", "abhaId_x": "ABHA ID", "aadharId_x": "Aadhaar ID", "gender_x": "Gender", "category_x": "Category", "maritalStatus_x": "Marital Status", "house_x": "Address", "district_x": "District", "state_x": "State", "pinCode_x": "Pincode", "phoneNumber_x": "Mobile Number", "createdAt_x": "Date", "classificationResult": "Test Result", "bloodGroup_x": "Blood Group", "Age": "Age", "caste_x": "Caste", "registrationCenterName_x": "Center"}, 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", "Center"], axis=1)
+# df['Date'] = pd.to_datetime(df["Date"].dt.strftime('%d-%m-%Y'))
+
+# df = df.sort_values(by=['Date'], ascending=True)
+
+df["Test Result"].fillna("NOTEST", inplace = True)
+print("NOTEST: ", len(df[df["Test Result"] == "NOTEST"]))
+df = df[df["Test Result"] != "NOTEST"]
+
+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)'
+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'
+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/Oct19.xlsx", engine = 'openpyxl')
+df_final.to_excel(writer, sheet_name = 'op', index=False)
+df_count.to_excel(writer, sheet_name = "count")
+writer.close()