Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| 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) | |
| 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 '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'] | |
| # 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']] | |
| # 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) | |
| # # Convert columns to numeric and fill NaN values with 0 | |
| # for col in columns: | |
| # file_responses[col] = pd.to_numeric(file_responses[col], errors='coerce').fillna(0) | |
| # # Calculate the Total Allocation | |
| # file_responses['Total Allocation'] = file_responses[columns].sum(axis=1) | |
| # # Convert the Tax Payment column to numeric | |
| # tax_payment_col = '''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[tax_payment_col] = pd.to_numeric(file_responses[tax_payment_col], errors='coerce').fillna(0) | |
| # # Calculate Financial Token Weights | |
| # for i, col in enumerate(columns, start=1): | |
| # file_responses[f'Financial Token Weight for Problem {i}'] = ( | |
| # file_responses[tax_payment_col] * file_responses[col] / file_responses['Total Allocation'] | |
| # ).fillna(0) | |
| # Different return can be used to check the processing | |
| # return file_responses | |
| return merged_dataset | |
| except Exception as e: | |
| return str(e) | |
| def nlp_pipeline(original_df): | |
| processed_df = data_pre_processing(original_df) | |
| return processed_df | |
| def process_excel(file): | |
| try: | |
| # Ensure the file path is correct | |
| file_path = file.name if hasattr(file, 'name') else file | |
| # Read the Excel file | |
| df = pd.read_excel(file_path) | |
| # Process the DataFrame | |
| result_df = nlp_pipeline(df) | |
| output_file = "Output_ProjectProposals.xlsx" | |
| result_df.to_excel(output_file, index=False) | |
| return output_file # Return the processed DataFrame as Excel file | |
| except Exception as e: | |
| return str(e) # Return the error message | |
| example_files = ['#TaxDirection (Responses)_BasicExample.xlsx', | |
| '#TaxDirection (Responses)_IntermediateExample.xlsx', | |
| '#TaxDirection (Responses)_UltimateExample.xlsx' | |
| ] | |
| # Define the Gradio interface | |
| interface = gr.Interface( | |
| fn=process_excel, # The function to process the uploaded file | |
| inputs=gr.File(type="filepath", label="Upload Excel File here. \t Be sure to check that the column headings in your upload are the same as in the Example files below. \t (Otherwise there will be Error during the processing)"), # File upload input | |
| examples=example_files, # Add the example files | |
| # outputs=gr.File(label="Download Processed Excel File"), # File download output | |
| outputs=gr.File(label="Download the processed Excel File containing the ** Project Proposals ** for each Location~Problem paired combination"), # File download output | |
| # title="Excel File Uploader", | |
| # title="Upload Excel file containing #TaxDirections → Download HyperLocal Project Proposals\n", | |
| # "<p style='font-weight: bold; font-size: 15px; color: red;'>Upload Excel file containing #TaxDirections → Download HyperLocal Project Proposals</p>\n" | |
| title = ( | |
| "<p style='font-weight: bold; font-size: 15px; text-align: center;'>" | |
| "<span style='color: red;'>Upload Excel file containing #TaxDirections</span> " | |
| "→ " | |
| "<span style='color: blue;'>Download HyperLocal Project Proposals</span>" | |
| "</p>\n" | |
| ), | |
| description=( | |
| "<p style='font-weight: bold; font-size: 15px; color: red;'>Upload an Excel file to process and download the result or use the Example files:</p>" | |
| "<p style='font-weight: bold; font-size: 15px; color: red;'>(click on any of them to directly process the file and Download the result)</p>" | |
| "<p style='font-weight: bold; font-size: 14px; color: blue; 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: 14px; color: blue; text-align: right;'>Corresponding Budget Allocation and estimated Project Completion Time are provided in different sheets.</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. 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'>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>" | |
| ) # Solid description with right-aligned second sentence | |
| ) | |
| # Launch the interface | |
| if __name__ == "__main__": | |
| interface.launch() |