import csv import sys # Increase CSV field size limit csv.field_size_limit(sys.maxsize) import gradio as gr import pandas as pd def data_pre_processing(file_responses): consoleMessage_and_Print("Starting data pre-processing...") # 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) # Different return can be used to check the processing consoleMessage_and_Print("Data pre-processing completed.") return merged_dataset except Exception as e: consoleMessage_and_Print(f"Error during data pre-processing: {str(e)}") return None import spacy from transformers import AutoTokenizer, AutoModel import torch # Load SpaCy model # Install the 'en_core_web_sm' model if it isn't already installed try: nlp = spacy.load('en_core_web_sm') except OSError: # Instead of this try~catch, we could also include this < https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.5.0/en_core_web_sm-3.5.0.tar.gz > in the requirements.txt to directly load it from spacy.cli import download download('en_core_web_sm') nlp = spacy.load('en_core_web_sm') # Load Hugging Face Transformers model tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/all-mpnet-base-v2") model = AutoModel.from_pretrained("sentence-transformers/all-mpnet-base-v2") import re import nltk from nltk.corpus import stopwords from nltk.tokenize import word_tokenize # Download necessary NLTK data nltk.download('punkt') nltk.download('stopwords') nltk.download('averaged_perceptron_tagger') import numpy as np import sentencepiece as sp from transformers import pipeline # Load a summarization model summarizer = pipeline("summarization") def Summarized_text(passed_text): try: # Summarization summarize_text = summarizer(passed_text, max_length=70, min_length=30, do_sample=False)[0]['summary_text'] return summarize_text except Exception as e: print(f"Summarization failed: {e}") return passed_text ###### Will uncomment Summarization during final deployment... as it takes a lot of time def Lemmatize_text(text): # Text Cleaning text = re.sub(r'[^\w\s]', '', text) text = re.sub(r'\d+', '', text) text = re.sub(r'http\S+', '', text) # Remove https URLs text = re.sub(r'www\.\S+', '', text) # Remove www URLs # Tokenize and remove stopwords tokens = word_tokenize(text.lower()) stop_words = set(stopwords.words('english')) custom_stopwords = {'example', 'another'} # Add custom stopwords tokens = [word for word in tokens if word not in stop_words and word not in custom_stopwords] # NER - Remove named entities doc = nlp(' '.join(tokens)) tokens = [token.text for token in doc if not token.ent_type_] # POS Tagging (optional) pos_tags = nltk.pos_tag(tokens) tokens = [word for word, pos in pos_tags if pos in ['NN', 'NNS']] # Filter nouns # Lemmatize tokens using SpaCy doc = nlp(' '.join(tokens)) lemmatized_text = ' '.join([token.lemma_ for token in doc]) return lemmatized_text # Return the cleaned and lemmatized text from random import random def text_processing_for_domain(text): # First, get the summarized text summarized_text = "" # summarized_text = Summarized_text(text) # Then, lemmatize the original text lemmatized_text = "" lemmatized_text = Lemmatize_text(text) if lemmatized_text and summarized_text: # Join both the summarized and lemmatized text if random() > 0.5: combined_text = summarized_text + " " + lemmatized_text else: combined_text = lemmatized_text + " " + summarized_text return combined_text elif summarized_text: return summarized_text elif lemmatized_text: return lemmatized_text else: return "Sustainability and Longevity" # Default FailSafe from sentence_transformers import SentenceTransformer from sklearn.cluster import AgglomerativeClustering, KMeans from sklearn.feature_extraction.text import TfidfVectorizer from sklearn.metrics import silhouette_score from bertopic import BERTopic from collections import Counter def extract_problem_domains(df, text_column='Processed_ProblemDescription_forDomainExtraction', cluster_range=(2, 10), top_words=10): consoleMessage_and_Print("Extracting Problem Domains...") # Sentence Transformers approach model = SentenceTransformer('all-mpnet-base-v2') embeddings = model.encode(df[text_column].tolist()) # Perform hierarchical clustering with Silhouette Analysis silhouette_scores = [] for n_clusters in range(cluster_range[0], cluster_range[1] + 1): clustering = AgglomerativeClustering(n_clusters=n_clusters) cluster_labels = clustering.fit_predict(embeddings) silhouette_avg = silhouette_score(embeddings, cluster_labels) silhouette_scores.append(silhouette_avg) # Determine the optimal number of clusters optimal_n_clusters = cluster_range[0] + silhouette_scores.index(max(silhouette_scores)) # Perform clustering with the optimal number of clusters clustering = AgglomerativeClustering(n_clusters=optimal_n_clusters) cluster_labels = clustering.fit_predict(embeddings) # Get representative words for each cluster cluster_representations = {} for i in range(optimal_n_clusters): cluster_words = df.loc[cluster_labels == i, text_column].str.cat(sep=' ').split() cluster_representations[i] = [word for word, _ in Counter(cluster_words).most_common(top_words)] # Map cluster labels to representative words df["Problem_Cluster"] = cluster_labels df['Problem_Category_Words'] = [cluster_representations[label] for label in cluster_labels] consoleMessage_and_Print("Problem Domain Extraction completed. Returning from Problem Domain Extraction function.") return df, optimal_n_clusters, cluster_representations def Extract_Location(text): doc = nlp(text) locations = [ent.text for ent in doc.ents if ent.label_ in ['GPE', 'LOC']] return ' '.join(locations) def text_processing_for_location(text): # Extract locations locations_text = Extract_Location(text) # Perform further text cleaning if necessary processed_locations_text = Lemmatize_text(locations_text) # Remove special characters, digits, and punctuation processed_locations_text = re.sub(r'[^a-zA-Z\s]', '', processed_locations_text) # Tokenize and remove stopwords tokens = word_tokenize(processed_locations_text.lower()) stop_words = set(stopwords.words('english')) tokens = [word for word in tokens if word not in stop_words] # Join location words into a single string final_locations_text = ' '.join(tokens) return final_locations_text if final_locations_text else "India" def extract_location_clusters(df, text_column1='Processed_LocationText_forClustering', # Extracted through NLP text_column2='Geographical_Location', # User Input cluster_range=(2, 10), top_words=10): # Combine the two text columns text_column = "Combined_Location_Text" df[text_column] = df[text_column1] + ' ' + df[text_column2] consoleMessage_and_Print("Extracting Location Clusters...") # Sentence Transformers approach for embeddings model = SentenceTransformer('all-mpnet-base-v2') embeddings = model.encode(df[text_column].tolist()) # Perform hierarchical clustering with Silhouette Analysis silhouette_scores = [] for n_clusters in range(cluster_range[0], cluster_range[1] + 1): clustering = AgglomerativeClustering(n_clusters=n_clusters) cluster_labels = clustering.fit_predict(embeddings) silhouette_avg = silhouette_score(embeddings, cluster_labels) silhouette_scores.append(silhouette_avg) # Determine the optimal number of clusters optimal_n_clusters = cluster_range[0] + silhouette_scores.index(max(silhouette_scores)) # Perform clustering with the optimal number of clusters clustering = AgglomerativeClustering(n_clusters=optimal_n_clusters) cluster_labels = clustering.fit_predict(embeddings) # Get representative words for each cluster cluster_representations = {} for i in range(optimal_n_clusters): cluster_words = df.loc[cluster_labels == i, text_column].str.cat(sep=' ').split() cluster_representations[i] = [word for word, _ in Counter(cluster_words).most_common(top_words)] # Map cluster labels to representative words df["Location_Cluster"] = cluster_labels df['Location_Category_Words'] = [cluster_representations[label] for label in cluster_labels] df = df.drop(text_column, axis=1) consoleMessage_and_Print("Location Clustering completed.") return df, optimal_n_clusters, cluster_representations def create_cluster_dataframes(processed_df): # Create a dataframe for Financial Weights budget_cluster_df = processed_df.pivot_table( values='Financial_Weight', index='Location_Cluster', columns='Problem_Cluster', aggfunc='sum', fill_value=0) # Create a dataframe for Problem Descriptions problem_cluster_df = processed_df.groupby(['Location_Cluster', 'Problem_Cluster'])['Problem_Description'].apply(list).unstack() return budget_cluster_df, problem_cluster_df from random import uniform from transformers import GPTNeoForCausalLM, GPT2Tokenizer def generate_project_proposal(prompt): # Generate the proposal default_proposal = "Hyper-local Sustainability Projects would lead to Longevity of the self and Prosperity of the community. Therefore UNSDGs coupled with Longevity initiatives should be focused upon." # model_Name = "EleutherAI/gpt-neo-2.7B" # tempareCHUR = uniform(0.3,0.6) model_Name = "EleutherAI/gpt-neo-1.3B" tempareCHUR = uniform(0.5,0.8) consoleMessage_and_Print(f"Trying to access {model_Name} model. The Prompt is: \n{prompt}") model = GPTNeoForCausalLM.from_pretrained(model_Name) tokenizer = GPT2Tokenizer.from_pretrained(model_Name) model_max_token_limit = 2000 #2048 #1500 try: # input_ids = tokenizer.encode(prompt, return_tensors="pt") # Truncate the prompt to fit within the model's input limits # Adjust as per your model's limit input_ids = tokenizer.encode(prompt, return_tensors="pt", truncation=True, max_length = int(2*model_max_token_limit/3) ) print("Input IDs shape:", input_ids.shape) input_length = input_ids.shape[1] # Slice off the input part if the input length is known pad_tokenId = tokenizer.pad_token_id if tokenizer.pad_token_id is not None else tokenizer.eos_token_id # Padding with EOS token may always be great attentionMask = input_ids.ne(pad_tokenId).long() # Generate the output output = model.generate( input_ids, min_length = int(model_max_token_limit/7), # minimum length of the generated output max_new_tokens = int(model_max_token_limit/3), num_return_sequences=1, no_repeat_ngram_size=2, temperature=tempareCHUR, attention_mask=attentionMask, # This was previously not being used pad_token_id=pad_tokenId ) print("Output shape:", output.shape) # Decode the output to text full_returned_segment = tokenizer.decode(output[0], skip_special_tokens=True) PP_in_fullReturn = "Project Proposal:" in full_returned_segment if output is not None and output.shape[1] > 0: # Decode the output if output.shape[1] > input_length and PP_in_fullReturn: generated_part = tokenizer.decode(output[0][input_length:], skip_special_tokens=True) else: generated_part = tokenizer.decode(output[0], skip_special_tokens=True) else: # Handle the error case, e.g., return an empty string or a default value raise Exception("Error generating proposal: output is empty or None") proposal = generated_part.strip() # if "Project Proposal:" in proposal: # proposal = proposal.split("Project Proposal:", 1)[1].strip() print("Generated Proposal: \n", proposal,"\n\n") return proposal except Exception as e: print("Error generating proposal:", str(e)) return default_proposal import copy def create_project_proposals(budget_cluster_df, problem_cluster_df, location_clusters, problem_clusters): consoleMessage_and_Print("\n Starting function: create_project_proposals") proposals = {} for loc in budget_cluster_df.index: consoleMessage_and_Print(f"\n loc: {loc}") for prob in budget_cluster_df.columns: consoleMessage_and_Print(f"\n prob: {prob}") location = ", ".join([item.strip() for item in location_clusters[loc] if item]) # Clean and join problem_domain = ", ".join([item.strip() for item in problem_clusters[prob] if item]) # Clean and join shuffled_descriptions = copy.deepcopy(problem_cluster_df.loc[loc, prob]) # Create a deep copy of the problem descriptions, shuffle it, and join the first 10 print("location: ", location) print("problem_domain: ", problem_domain) print("problem_descriptions: ", shuffled_descriptions) # Check if problem_descriptions is valid (not NaN and not an empty list) if isinstance(shuffled_descriptions, list) and shuffled_descriptions: # print(f"\nGenerating proposal for location: {location}, problem domain: {problem_domain}") consoleMessage_and_Print(f"Generating PP") random.shuffle(shuffled_descriptions) # Prepare the prompt # problems_summary = "; \n".join(shuffled_descriptions[:3]) # Limit to first 3 for brevity # problems_summary = "; \n".join([f"Problem: {desc}" for desc in shuffled_descriptions[:5]]) problems_summary = "; \n".join([f"Problem {i+1}: {desc}" for i, desc in enumerate(shuffled_descriptions[:7])]) # problems_summary = "; \n".join(shuffled_descriptions) # Join all problem descriptions # prompt = f"Generate a solution oriented project proposal for the following:\n\nLocation: {location}\nProblem Domain: {problem_domain}\nProblems: {problems_summary}\n\nProject Proposal:" # prompt = f"Generate a solution-oriented project proposal for the following public problem (only output the proposal):\n\n Geographical/Digital Location: {location}\nProblem Category: {problem_domain}\nProblems: {problems_summary}\n\nProject Proposal:" # prompt = f"Generate a singular solution-oriented project proposal bespoke to the following Location~Domain cluster of public problems:\n\n Geographical/Digital Location: {location}\nProblem Domain: {problem_domain}\nProblems: {problems_summary}\n\nProject Proposal: \t" prompt = f"Generate a singular solution-oriented project proposal bespoke to the following Location~Domain cluster of public problems:\n\n Geographical/Digital Location: {location}\nProblem Domain: {problem_domain}\n\n {problems_summary}\n\nSingle Combined Project Proposal: \t" proposal = generate_project_proposal(prompt) # Check if proposal is valid if isinstance(proposal, str) and proposal.strip(): # Valid string that's not empty proposals[(loc, prob)] = proposal else: print(f"Skipping empty problem descriptions for location: {location}, problem domain: {problem_domain}") return proposals # def create_project_proposals(budget_cluster_df, problem_cluster_df, location_clusters, problem_clusters): # print("\n Starting function: create_project_proposals") # console_messages.append("\n Starting function: create_project_proposals") # proposals = {} # for loc in budget_cluster_df.index: # print("\n loc: ", loc) # console_messages.append(f"\n loc: {loc}") # for prob in budget_cluster_df.columns: # console_messages.append(f"\n prob: {prob}") # print("\n prob: ", prob) # location = ", ".join([item.strip() for item in location_clusters[loc] if item]) # Clean and join # problem_domain = ", ".join([item.strip() for item in problem_clusters[prob] if item]) # Clean and join # problem_descriptions = problem_cluster_df.loc[loc, prob] # print("location: ",location) # print("problem_domain: ",problem_domain) # print("problem_descriptions: ",problem_descriptions) # if problem_descriptions:# and not pd.isna(problem_descriptions): # print(f"\nGenerating proposal for location: {location}, problem domain: {problem_domain}") # # console_messages.append(f"\nGenerating proposal for location: {location}, problem domain: {problem_domain}") # # Prepare the prompt # problems_summary = "; \n".join(problem_descriptions[:3]) # Limit to first 3 for brevity # # problems_summary = "; ".join(problem_descriptions) # # prompt = f"Generate a project proposal for the following:\n\nLocation: {location}\nProblem Domain: {problem_domain}\nProblems: {problems_summary}\nBudget: ${financial_weight:.2f}\n\nProject Proposal:" # prompt = f"Generate a solution oriented project proposal for the following:\n\nLocation: {location}\nProblem Domain: {problem_domain}\nProblems: {problems_summary}\n\nProject Proposal:" # proposal = generate_project_proposal(prompt) # proposals[(loc, prob)] = proposal # print("Generated Proposal: ", proposal) # else: # print(f"Skipping empty problem descriptions for location: {location}, problem domain: {problem_domain}") # return proposals # def create_project_proposals(budget_cluster_df, problem_cluster_df, location_clusters, problem_clusters): # print("\n Starting function: create_project_proposals") # console_messages.append("\n Starting function: create_project_proposals") # proposals = {} # for loc in budget_cluster_df.index: # for prob in budget_cluster_df.columns: # location = ", ".join(location_clusters[loc]) # problem_domain = ", ".join(problem_clusters[prob]) # problem_descriptions = problem_cluster_df.loc[loc, prob] # if problem_descriptions: # proposal = generate_project_proposal( # problem_descriptions, # location, # problem_domain) # proposals[(loc, prob)] = proposal # console_messages.append("\n Exiting function: create_project_proposals") # return proposals def nlp_pipeline(original_df): consoleMessage_and_Print("Starting NLP pipeline...") # Data Preprocessing processed_df = data_pre_processing(original_df) # merged_dataset # Starting the Pipeline for Domain Extraction consoleMessage_and_Print("Executing Text processing function for Domain identification") # Apply the text_processing_for_domain function to the DataFrame processed_df['Processed_ProblemDescription_forDomainExtraction'] = processed_df['Problem_Description'].apply(text_processing_for_domain) consoleMessage_and_Print("Removing entries which could not be allocated to any Problem Domain") # processed_df = processed_df.dropna(subset=['Processed_ProblemDescription_forDomainExtraction'], axis=0) # Drop rows where 'Processed_ProblemDescription_forDomainExtraction' contains empty arrays processed_df = processed_df[processed_df['Processed_ProblemDescription_forDomainExtraction'].apply(lambda x: len(x) > 0)] # Domain Clustering try: processed_df, optimal_n_clusters, problem_clusters = extract_problem_domains(processed_df) consoleMessage_and_Print(f"Optimal clusters for Domain extraction: {optimal_n_clusters}") except Exception as e: consoleMessage_and_Print(f"Error in extract_problem_domains: {str(e)}") consoleMessage_and_Print("NLP pipeline for Problem Domain extraction completed.") consoleMessage_and_Print("Starting NLP pipeline for Location extraction with text processing.") # Apply the text_processing_for_location function to the DataFrame processed_df['Processed_LocationText_forClustering'] = processed_df['Problem_Description'].apply(text_processing_for_location) # processed_df['Processed_LocationText_forClustering'], processed_df['Extracted_Locations'] = zip(*processed_df.apply(text_processing_for_location, axis=1)) # Location Clustering try: processed_df, optimal_n_clusters, location_clusters = extract_location_clusters(processed_df) consoleMessage_and_Print(f"Optimal clusters for Location extraction: {optimal_n_clusters}") except Exception as e: consoleMessage_and_Print(f"Error in extract_location_clusters: {str(e)}") consoleMessage_and_Print("NLP pipeline for location extraction completed.") # Create cluster dataframes budget_cluster_df, problem_cluster_df = create_cluster_dataframes(processed_df) print("Clustering Done...") # return processed_df, budget_cluster_df, problem_cluster_df, location_clusters, problem_clusters print("\n location_clusters: ", location_clusters) print("\n problem_clusters: ", problem_clusters) # # Generate project proposals # location_clusters = dict(enumerate(processed_df['Location_Category_Words'].unique())) # problem_clusters = dict(enumerate(processed_df['Problem_Category_Words'].unique())) # print("\n location_clusters_2: ", location_clusters) # print("\n problem_clusters_2: ", problem_clusters) project_proposals = create_project_proposals(budget_cluster_df, problem_cluster_df, location_clusters, problem_clusters) consoleMessage_and_Print("NLP pipeline completed.") return processed_df, budget_cluster_df, problem_cluster_df, project_proposals, location_clusters, problem_clusters console_messages = [] def consoleMessage_and_Print(some_text = ""): console_messages.append(some_text) print(some_text) def process_excel(file): consoleMessage_and_Print("Processing starts. Reading the uploaded Excel file...") # 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) try: # Process the DataFrame consoleMessage_and_Print("Processing the DataFrame...") processed_df, budget_cluster_df, problem_cluster_df, project_proposals, location_clusters, problem_clusters = nlp_pipeline(df) # processed_df, budget_cluster_df, problem_cluster_df, location_clusters, problem_clusters = nlp_pipeline(df) consoleMessage_and_Print("Error was here") #This code first converts the dictionary to a DataFrame with a single column for the composite key. #Then, it splits the composite key into separate columns for Location_Cluster and Problem_Cluster. #Finally, it reorders the columns and writes the DataFrame to an Excel sheet. try: # Meta AI Solution # Convert project_proposals dictionary to DataFrame project_proposals_df = pd.DataFrame(list(project_proposals.items()), columns=['Location_Cluster_Problem_Cluster', 'Solutions Proposed']) # consoleMessage_and_Print("CheckPoint 1") # Split the composite key into separate columns project_proposals_df[['Location_Cluster', 'Problem_Cluster']] = project_proposals_df['Location_Cluster_Problem_Cluster'].apply(pd.Series) # consoleMessage_and_Print("CheckPoint 2") # Drop the composite key column project_proposals_df.drop('Location_Cluster_Problem_Cluster', axis=1, inplace=True) # consoleMessage_and_Print("CheckPoint 3") # Reorder the columns project_proposals_df = project_proposals_df[['Location_Cluster', 'Problem_Cluster', 'Solutions Proposed']] # consoleMessage_and_Print("CheckPoint 4") except Exception as e: consoleMessage_and_Print("Meta AI Solution did not work, trying CHATGPT solution") try: # Convert project_proposals dictionary to DataFrame project_proposals_df = pd.DataFrame.from_dict( proposals, orient='index', columns=['Solutions Proposed'] ) # If the index is a tuple, it automatically becomes a MultiIndex, so we handle naming correctly: if isinstance(project_proposals_df.index, pd.MultiIndex): project_proposals_df.index.names = ['Location_Cluster', 'Problem_Cluster'] else: # If for some reason it's not a MultiIndex, we name it appropriately project_proposals_df.index.name = 'Cluster' # Reset index to have Location_Cluster and Problem_Cluster as columns project_proposals_df.reset_index(inplace=True) except Exception as e: print(e) # ### Convert project_proposals dictionary to DataFrame # project_proposals_df = pd.DataFrame.from_dict(project_proposals, orient='index', columns=['Solutions Proposed']) # project_proposals_df.index.names = ['Location_Cluster', 'Problem_Cluster'] # project_proposals_df.reset_index(inplace=True) consoleMessage_and_Print("Creating the Excel file.") output_filename = "OutPut_PPs.xlsx" with pd.ExcelWriter(output_filename) as writer: processed_df.to_excel(writer, sheet_name='Input_Processed', index=False) budget_cluster_df.to_excel(writer, sheet_name='Financial_Weights') problem_cluster_df.to_excel(writer, sheet_name='Problem_Descriptions') try: project_proposals_df.to_excel(writer, sheet_name='Project_Proposals', index=False) except Exception as e: consoleMessage_and_Print(f"Error during Project Proposal excelling at the end: {e}") try: location_clusters_df = pd.DataFrame({'Cluster_Id': list(location_clusters.keys()), 'Location_Cluster': list(location_clusters.values())}) location_clusters_df.to_excel(writer, sheet_name='Location_Clusters', index=False) except Exception as e: consoleMessage_and_Print(f"Error during Location Cluster Dataframing: {e}") try: problem_clusters_df = pd.DataFrame({'Cluster_Id': list(problem_clusters.keys()), 'Problem_Cluster': list(problem_clusters.values())}) problem_clusters_df.to_excel(writer, sheet_name='Problem_Clusters', index=False) except Exception as e: consoleMessage_and_Print(f"Error during Problem Cluster Dataframing: {e}") # # Ensure location_clusters and problem_clusters are in DataFrame format # if isinstance(location_clusters, pd.DataFrame): # location_clusters.to_excel(writer, sheet_name='Location_Clusters', index=False) # else: # consoleMessage_and_Print("Converting Location Clusters to df") # pd.DataFrame(location_clusters).to_excel(writer, sheet_name='Location_Clusters', index=False) # if isinstance(problem_clusters, pd.DataFrame): # problem_clusters.to_excel(writer, sheet_name='Problem_Clusters', index=False) # else: # consoleMessage_and_Print("Converting Problem Clusters to df") # pd.DataFrame(problem_clusters).to_excel(writer, sheet_name='Problem_Clusters', index=False) consoleMessage_and_Print("Processing completed. Ready for download.") return output_filename, "\n".join(console_messages) # Return the processed DataFrame as Excel file except Exception as e: # return str(e) # Return the error message # error_message = f"Error processing file: {str(e)}" # print(error_message) # Log the error consoleMessage_and_Print(f"Error during processing: {str(e)}") # return error_message, "Santanu Banerjee" # Return the error message to the user return None, "\n".join(console_messages) example_files = [] example_files.append('#TaxDirection (Responses)_BasicExample.xlsx') # example_files.append('#TaxDirection (Responses)_IntermediateExample.xlsx') # example_files.append('#TaxDirection (Responses)_UltimateExample.xlsx') import random a_random_object = random.choice(["⇒", "↣", "↠", "→"]) # 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 the processed Excel File containing the ** Project Proposals ** for each Location~Problem paired combination"), # File download output gr.Textbox(label="Console Messages", lines=7, interactive=False) # Console messages output ], # title="Excel File Uploader", # title="Upload Excel file containing #TaxDirections → Download HyperLocal Project Proposals\n", title = ( "

" "Upload Excel file containing #TaxDirections " # "→ " # "⇒ ↣ ↠ " " " +a_random_object +" " "Download HyperLocal Project Proposals" "

\n" ), description=( "

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 #TaxDirection weblink.

" "

Upload an Excel file to process and download the result or use the Example files:

" "

(click on any of them to directly process the file and Download the result)

" "

Processed output contains a Project Proposal for each Location~Problem paired combination (i.e. each cell).

" "

Corresponding Budget Allocation and estimated Project Completion Time are provided in different sheets.

" "

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 support.

" ) # Solid description with right-aligned second sentence ) # Launch the interface if __name__ == "__main__": interface.launch()