Update app.py

app.py

@@ -3,13 +3,95 @@ import pandas as pd
 
 
 
+def data_pre_processing(file_responses):
+    # Financial Weights are in per decas and NOT per cents
+    
+    ### GPT: Assuming 'Your financial allocation for Problem (in $)' column contains numerical values
+    
+    file_responses['''Your financial allocation for Problem 1:
+    Mention the percentage of your Tax Amount which you wish the Government would allocate through their annual budget, to implement a specific solution for your 1st problem.'''] = pd.to_numeric(file_responses['''Your financial allocation for Problem 1:
+    Mention the percentage of your Tax Amount which you wish the Government would allocate through their annual budget, to implement a specific solution for your 1st problem.'''], errors='coerce').fillna(0)
+    
+    file_responses['''Your financial allocation for Problem 2:
+    Mention the percentage of your Tax Amount which you wish the Government would allocate through their annual budget, to implement a solution specifically to your 2nd problem.'''] = pd.to_numeric(file_responses['''Your financial allocation for Problem 2:
+    Mention the percentage of your Tax Amount which you wish the Government would allocate through their annual budget, to implement a solution specifically to your 2nd problem.'''], errors='coerce').fillna(0)
+    
+    file_responses['''Your financial allocation for Problem 3:
+    Mention the percentage of your Tax Amount which you wish the Government would allocate through their annual budget, to implement a solution specifically to your 3rd problem.'''] = pd.to_numeric(file_responses['''Your financial allocation for Problem 3:
+    Mention the percentage of your Tax Amount which you wish the Government would allocate through their annual budget, to implement a solution specifically to your 3rd problem.'''], errors='coerce').fillna(0)    
+    
+    file_responses['''How much was your latest Tax payment (in U$D) ?
+    
+    Please try to be as accurate as possible:
+    Eg.: If your last tax amount was INR 25,785/-; then convert it in U$D and enter only the amount as: 310.
+    
+    If you have never paid tax, consider putting in a realistic donation amount which wish to contribute towards helping yourself obtain the desired relief.'''
+    ] = pd.to_numeric(file_responses['''How much was your latest Tax payment (in U$D) ?
+    
+    Please try to be as accurate as possible:
+    Eg.: If your last tax amount was INR 25,785/-; then convert it in U$D and enter only the amount as: 310.
+    
+    If you have never paid tax, consider putting in a realistic donation amount which wish to contribute towards helping yourself obtain the desired relief.'''
+    ], errors='coerce').fillna(0)
+    
+    
+    
+    
+    
+    # Adding a new column 'Total Allocation' by summing specific columns by their names
+    file_responses['Total Allocation'] = file_responses[['''Your financial allocation for Problem 1:
+    Mention the percentage of your Tax Amount which you wish the Government would allocate through their annual budget, to implement a specific solution for your 1st problem.''' , '''Your financial allocation for Problem 2:
+    Mention the percentage of your Tax Amount which you wish the Government would allocate through their annual budget, to implement a solution specifically to your 2nd problem.''' , '''Your financial allocation for Problem 3:
+    Mention the percentage of your Tax Amount which you wish the Government would allocate through their annual budget, to implement a solution specifically to your 3rd problem.''']].apply(lambda x: x.clip(lower=10)).sum(axis=1)
+    
+    
+    
+    
+    
+    # Creating 'Financial Weight' column by dividing 'Your financial allocation for Problem 1' by 'Total Allocation' and multiplying this with the assigned decage (similar to percentage but for 10) for Problem 1
+    file_responses['Financial Token Weight for Problem 1'] = file_responses['''How much was your latest Tax payment (in U$D) ?
+    
+    Please try to be as accurate as possible:
+    Eg.: If your last tax amount was INR 25,785/-; then convert it in U$D and enter only the amount as: 310.
+    
+    If you have never paid tax, consider putting in a realistic donation amount which wish to contribute towards helping yourself obtain the desired relief.'''
+    ] * file_responses['''Your financial allocation for Problem 1:
+    Mention the percentage of your Tax Amount which you wish the Government would allocate through their annual budget, to implement a specific solution for your 1st problem.'''] / file_responses['Total Allocation']
+    
+    
+    file_responses['Financial Token Weight for Problem 2'] = file_responses['''How much was your latest Tax payment (in U$D) ?
+    
+    Please try to be as accurate as possible:
+    Eg.: If your last tax amount was INR 25,785/-; then convert it in U$D and enter only the amount as: 310.
+    
+    If you have never paid tax, consider putting in a realistic donation amount which wish to contribute towards helping yourself obtain the desired relief.'''
+    ] * file_responses['''Your financial allocation for Problem 2:
+    Mention the percentage of your Tax Amount which you wish the Government would allocate through their annual budget, to implement a solution specifically to your 2nd problem.'''] / file_responses['Total Allocation']
+    
+    
+    file_responses['Financial Token Weight for Problem 3'] = file_responses['''How much was your latest Tax payment (in U$D) ?
+    
+    Please try to be as accurate as possible:
+    Eg.: If your last tax amount was INR 25,785/-; then convert it in U$D and enter only the amount as: 310.
+    
+    If you have never paid tax, consider putting in a realistic donation amount which wish to contribute towards helping yourself obtain the desired relief.'''
+    ] * file_responses['''Your financial allocation for Problem 3:
+    Mention the percentage of your Tax Amount which you wish the Government would allocate through their annual budget, to implement a solution specifically to your 3rd problem.'''] / file_responses['Total Allocation']
+
+    return file_responses
+    
+
+
+
+
+
+
 
 
 def nlp_pipeline(original_df):
-    print("Inside the NLP Pipeline")
-    original_df['Sum'] = original_df['a'] + original_df['b']
-    print(original_df)
-    return original_df
+    processed_df = data_pre_processing(original_df)
+    #original_df['Sum'] = original_df['a'] + original_df['b']
+    return processed_df
     
 
 
@@ -22,8 +104,6 @@ def process_excel(file):
         
         # Perform any processing on the DataFrame here
         # Example: adding a new column with the sum of two other columns
-        # df['Sum'] = df['Column1'] + df['Column2']
-        print("Hello")
         result_df = nlp_pipeline(df)