Update app.py

app.py

@@ -3,41 +3,62 @@ import pandas as pd
 
 def data_pre_processing(file_responses):
     # Financial Weights can be anything (ultimately the row-wise weights are aggregated and the corresponding fractions are obtained from that rows' total tax payed)
-
-    # Define the columns to be processed
-    try:
+    
+    try: # Define the columns to be processed
         
+        # Developing Numeric Columns
         # Convert columns to numeric and fill NaN values with 0
-        
-        
         file_responses['Personal_TaxDirection_1_TaxWeightageAllocated'] = pd.to_numeric(file_responses['Personal_TaxDirection_1_TaxWeightageAllocated'], errors='coerce').fillna(0)
         file_responses['Personal_TaxDirection_2_TaxWeightageAllocated'] = pd.to_numeric(file_responses['Personal_TaxDirection_2_TaxWeightageAllocated'], errors='coerce').fillna(0)
         file_responses['Personal_TaxDirection_3_TaxWeightageAllocated'] = pd.to_numeric(file_responses['Personal_TaxDirection_3_TaxWeightageAllocated'], errors='coerce').fillna(0)
         file_responses['Latest estimated Tax payment?'] = pd.to_numeric(file_responses['Latest estimated Tax payment?'], errors='coerce').fillna(0)
         
-        
-        
-
-
-
-
-        # Adding a new column 'Total Allocation' by summing specific columns by their names
+        # Adding a new column 'TotalWeightageAllocated' by summing specific columns by their names
         file_responses['TotalWeightageAllocated'] = file_responses['Personal_TaxDirection_1_TaxWeightageAllocated'] + file_responses['Personal_TaxDirection_2_TaxWeightageAllocated'] + file_responses['Personal_TaxDirection_3_TaxWeightageAllocated']
-        
-        # Calculating the actual TaxAmount to be allocated against each WISH (by rewriting the existing columns)
-        file_responses['Personal_TaxDirection_1_TaxWeightageAllocated'] = file_responses['Personal_TaxDirection_1_TaxWeightageAllocated'] * file_responses['Latest estimated Tax payment?'] / file_responses['TotalWeightageAllocated']
-        file_responses['Personal_TaxDirection_2_TaxWeightageAllocated'] = file_responses['Personal_TaxDirection_2_TaxWeightageAllocated'] * file_responses['Latest estimated Tax payment?'] / file_responses['TotalWeightageAllocated']
-        file_responses['Personal_TaxDirection_3_TaxWeightageAllocated'] = file_responses['Personal_TaxDirection_3_TaxWeightageAllocated'] * file_responses['Latest estimated Tax payment?'] / file_responses['TotalWeightageAllocated']
-
-
 
+        
 
+        # Creating Datasets (we assume everything has been provided to us in English, or the translations have been done already)
+        # Renaming the datasets into similar column headings
+        initial_dataset_1 = file_responses.rename(columns={
+            'Personal_TaxDirection_1_Wish': 'Problem_Description',
+            'Personal_TaxDirection_1_GeographicalLocation': 'Geographical_Location',
+            'Personal_TaxDirection_1_TaxWeightageAllocated': 'Financial_Weight'
+        })[['Problem_Description', 'Geographical_Location', 'Financial_Weight']]
+        
+        initial_dataset_2 = file_responses.rename(columns={
+            'Personal_TaxDirection_2_Wish': 'Problem_Description',
+            'Personal_TaxDirection_2_GeographicalLocation': 'Geographical_Location',
+            'Personal_TaxDirection_2_TaxWeightageAllocated': 'Financial_Weight'
+        })[['Problem_Description', 'Geographical_Location', 'Financial_Weight']]
+        
+        initial_dataset_3 = file_responses.rename(columns={
+            'Personal_TaxDirection_3_Wish': 'Problem_Description',
+            'Personal_TaxDirection_3_GeographicalLocation': 'Geographical_Location',
+            'Personal_TaxDirection_3_TaxWeightageAllocated': 'Financial_Weight'
+        })[['Problem_Description', 'Geographical_Location', 'Financial_Weight']]
 
 
-        file_responses = file_responses[[
-            "Personal_TaxDirection_1_Wish",
-            "Personal_TaxDirection_2_TaxWeightageAllocated"
-            ]]
+        
+        # Calculating the actual TaxAmount to be allocated against each WISH (by overwriting the newly created columns)
+        initial_dataset_1['Financial_Weight'] = file_responses['Personal_TaxDirection_1_TaxWeightageAllocated'] * file_responses['Latest estimated Tax payment?'] / file_responses['TotalWeightageAllocated']
+        initial_dataset_2['Financial_Weight'] = file_responses['Personal_TaxDirection_2_TaxWeightageAllocated'] * file_responses['Latest estimated Tax payment?'] / file_responses['TotalWeightageAllocated']
+        initial_dataset_3['Financial_Weight'] = file_responses['Personal_TaxDirection_3_TaxWeightageAllocated'] * file_responses['Latest estimated Tax payment?'] / file_responses['TotalWeightageAllocated']
+        
+        # Removing useless rows
+        # Drop rows where Problem_Description is NaN or an empty string
+        initial_dataset_1 = initial_dataset_1.dropna(subset=['Problem_Description'], axis=0)
+        initial_dataset_2 = initial_dataset_2.dropna(subset=['Problem_Description'], axis=0)
+        initial_dataset_3 = initial_dataset_3.dropna(subset=['Problem_Description'], axis=0)
+        
+        # Convert 'Problem_Description' column to string type
+        initial_dataset_1['Problem_Description'] = initial_dataset_1['Problem_Description'].astype(str)
+        initial_dataset_2['Problem_Description'] = initial_dataset_2['Problem_Description'].astype(str)
+        initial_dataset_3['Problem_Description'] = initial_dataset_3['Problem_Description'].astype(str)
+        
+        # Merging the Datasets
+        # Vertically concatenating (merging) the 3 DataFrames
+        merged_dataset = pd.concat([initial_dataset_1, initial_dataset_2, initial_dataset_3], ignore_index=True)
 
         
         
@@ -64,7 +85,7 @@ def data_pre_processing(file_responses):
         #         file_responses[tax_payment_col] * file_responses[col] / file_responses['Total Allocation']
         #     ).fillna(0)
         
-        return file_responses
+        return merged_dataset
     except Exception as e:
         return str(e)
 
@@ -119,20 +140,17 @@ interface = gr.Interface(
 
     description=(
         "<p style='font-weight: bold; font-size: 15px;'>Upload an Excel file to process and download the result or use the Example files:</p>"
-        "<p style='font-weight: bold; font-size: 15px;'>(click on any of them to directly process the file and Download the result)</p>"
         
         "<p style='font-weight: bold; font-size: 15px; text-align: right;'>Processed output contains a Project Proposal for each Location~Problem paired combination (i.e. each cell).</p>"
-        "<p style='font-weight: bold; font-size: 15px; text-align: right;'>Corresponding Budget Allocation and estimated Project Completion Time are provided in different sheets.</p>"
         
+        "<p style='font-weight: bold; font-size: 15px;'>(click on any of them to directly process the file and Download the result)</p>"
         
-        "<p style='font-weight: bold; font-size: 15px; text-align: justify;'>This tool allows for the systematic evaluation and proposal of solutions tailored to specific location-problem pairs, ensuring efficient resource allocation and project planning.</p>"
-
+        "<p style='font-weight: bold; font-size: 15px; text-align: right;'>Corresponding Budget Allocation and estimated Project Completion Time are provided in different sheets.</p>"
         
         
-        "<p style='font-size: 11px; color: gray; text-align: center'>Note: The example files provided above are for demonstration purposes. "
-        "Feel free to upload your own Excel files to see the results. If you have any questions, refer to the documentation-links or contact "
-        "<a href='https://www.change.org/p/democracy-evolution-ensuring-humanity-s-eternal-existence-through-taxdirection' target='_blank'>support</a>."
-        "\t For more information, visit <a href='https://santanban.github.io/TaxDirection/' target='_blank'>#TaxDirection weblink</a>.</p>"
+        "<p style='font-size: 12px; color: gray; text-align: center'>This tool allows for the systematic evaluation and proposal of solutions tailored to specific location-problem pairs, ensuring efficient resource allocation and project planning.</p>"
+        "<p style='font-size: 12px; color: gray; text-align: center'>Note: The example files provided above are for demonstration purposes. Feel free to upload your own Excel files to see the results. If you have any questions, refer to the documentation-links or contact <a href='https://www.change.org/p/democracy-evolution-ensuring-humanity-s-eternal-existence-through-taxdirection' target='_blank'>support</a>.</p>"
+        "<p style='font-size: 12px; color: gray; text-align: center'>For more information, visit <a href='https://santanban.github.io/TaxDirection/' target='_blank'>#TaxDirection weblink</a>.</p>"
     )  # Solid description with right-aligned second sentence
 
 )