Spaces:
Configuration error
Configuration error
| import pandas as pd | |
| from sklearn.feature_extraction.text import TfidfVectorizer | |
| from sklearn.metrics.pairwise import cosine_similarity | |
| import gradio as gr | |
| class BookRecommender: | |
| def __init__(self): | |
| self.df = None | |
| self.similarity_matrix = None | |
| def load_data(self, filepath): | |
| try: | |
| if filepath.endswith('.csv'): | |
| df = pd.read_csv(filepath) | |
| elif filepath.endswith(('.xls', '.xlsx')): | |
| df = pd.read_excel(filepath) | |
| else: | |
| raise ValueError("Unsupported file format. Please provide a CSV or Excel file.") | |
| return df | |
| except FileNotFoundError: | |
| raise FileNotFoundError(f"File not found at {filepath}") | |
| except ValueError as e: | |
| raise ValueError(f"Error loading data: {e}") | |
| except Exception as e: | |
| raise Exception(f"Error loading data: {e}") | |
| def preprocess_data(self, df, summary_column='summary', title_column='title'): | |
| if df[summary_column].isnull().any(): | |
| df[summary_column] = df[summary_column].fillna('') | |
| print("Handled missing values in summary column.") | |
| if df[title_column].isnull().any(): | |
| df[title_column] = df[title_column].fillna('') | |
| print("Handled missing values in title column.") | |
| df = df.drop_duplicates(subset=[title_column, summary_column], keep='first') | |
| print("Removed duplicate rows.") | |
| df = df[~(df[title_column] == '') | (df[summary_column] == '')] | |
| print("Removed rows with blank title and summary.") | |
| return df | |
| def create_tfidf_matrix(self, df, summary_column='summary'): | |
| tfidf = TfidfVectorizer(stop_words='english') | |
| tfidf_matrix = tfidf.fit_transform(df[summary_column]) | |
| return tfidf_matrix, tfidf | |
| def calculate_similarity(self, tfidf_matrix): | |
| similarity_matrix = cosine_similarity(tfidf_matrix) | |
| return similarity_matrix | |
| def recommend_books(self, book_title): | |
| try: | |
| book_index = self.df[self.df['title'] == book_title].index[0] | |
| except IndexError: | |
| return "Book title not found." | |
| except Exception as e: | |
| return f"An error occurred: {e}" | |
| similar_books_indices = self.similarity_matrix[book_index].argsort()[::-1][1:6] # Fixed top_n to 5 | |
| recommended_books = self.df['title'].iloc[similar_books_indices].tolist() | |
| return recommended_books | |
| def create_interface(self): | |
| def upload_and_process(file_obj): | |
| if file_obj is None: | |
| return "Please upload a file first.", None | |
| filepath = file_obj.name | |
| try: | |
| self.df = self.load_data(filepath) | |
| self.df = self.preprocess_data(self.df) | |
| tfidf_matrix, _ = self.create_tfidf_matrix(self.df) | |
| self.similarity_matrix = self.calculate_similarity(tfidf_matrix) | |
| return "File uploaded and processed successfully!", gr.update(interactive=True) | |
| except Exception as e: | |
| return f"Error: {e}", None | |
| def recommend_book_interface(book_title): | |
| if self.df is None or self.similarity_matrix is None: | |
| return "Please upload and process a file first." | |
| recommendations = self.recommend_books(book_title) | |
| formatted_recommendations = [[rec] for rec in recommendations] | |
| return formatted_recommendations | |
| with gr.Blocks() as iface: | |
| file_output = gr.File(label="Upload CSV or Excel file", file_types=[".csv", ".xls", ".xlsx"]) | |
| process_button = gr.Button("Process File") | |
| status_text = gr.Textbox(label="Status") | |
| text_input = gr.Textbox(lines=1, placeholder="Enter book title", interactive=False) | |
| output_list = gr.List(label="Recommended Books") | |
| process_button.click(upload_and_process, inputs=file_output, outputs=[status_text, text_input]) | |
| text_input.change(recommend_book_interface, inputs=text_input, outputs=output_list) | |
| return iface # Correct indentation here | |
| if __name__ == '__main__': | |
| recommender = BookRecommender() | |
| interface = recommender.create_interface() | |
| interface.launch() |