# app.py import gradio as gr import xgboost as xgb from xgboost import DMatrix from huggingface_hub import hf_hub_download from app_training_df_getter import create_app_user_training_df import pandas as pd from sklearn.model_selection import train_test_split from sklearn.preprocessing import LabelEncoder from helper import * import joblib # Define champion list for dropdowns CHAMPIONS = [ "Aatrox", "Ahri", "Akali", "Akshan", "Alistar", "Amumu", "Anivia", "Annie", "Aphelios", "Ashe", "Aurelion Sol", "Azir", "Bard", "Bel'Veth", "Blitzcrank", "Brand", "Braum", "Caitlyn", "Camille", "Cassiopeia", "Cho'Gath", "Corki", "Darius", "Diana", "Dr. Mundo", "Draven", "Ekko", "Elise", "Evelynn", "Ezreal", "Fiddlesticks", "Fiora", "Fizz", "Galio", "Gangplank", "Garen", "Gnar", "Gragas", "Graves", "Gwen", "Hecarim", "Heimerdinger", "Illaoi", "Irelia", "Ivern", "Janna", "Jarvan IV", "Jax", "Jayce", "Jhin", "Jinx", "Kai'Sa", "Kalista", "Karma", "Karthus", "Kassadin", "Katarina", "Kayle", "Kayn", "Kennen", "Kha'Zix", "Kindred", "Kled", "Kog'Maw", "KSante", "LeBlanc", "Lee Sin", "Leona", "Lillia", "Lissandra", "Lucian", "Lulu", "Lux", "Malphite", "Malzahar", "Maokai", "Master Yi", "Milio", "Miss Fortune", "Mordekaiser", "Morgana", "Naafiri", "Nami", "Nasus", "Nautilus", "Neeko", "Nidalee", "Nilah", "Nocturne", "Nunu & Willump", "Olaf", "Orianna", "Ornn", "Pantheon", "Poppy", "Pyke", "Qiyana", "Quinn", "Rakan", "Rammus", "Rek'Sai", "Rell", "Renata Glasc", "Renekton", "Rengar", "Riven", "Rumble", "Ryze", "Samira", "Sejuani", "Senna", "Seraphine", "Sett", "Shaco", "Shen", "Shyvana", "Singed", "Sion", "Sivir", "Skarner", "Sona", "Soraka", "Swain", "Sylas", "Syndra", "Tahm Kench", "Taliyah", "Talon", "Taric", "Teemo", "Thresh", "Tristana", "Trundle", "Tryndamere", "Twisted Fate", "Twitch", "Udyr", "Urgot", "Varus", "Vayne", "Veigar", "Vel'Koz", "Vex", "Vi", "Viego", "Viktor", "Vladimir", "Volibear", "Warwick", "Wukong", "Xayah", "Xerath", "Xin Zhao", "Yasuo", "Yone", "Yorick", "Yuumi", "Zac", "Zed", "Zeri", "Ziggs", "Zilean", "Zoe", "Zyra" ] # Load model try: model_path = hf_hub_download( repo_id="ivwhy/champion-predictor-model", filename="champion_predictor.json" ) model = xgb.Booster() model.load_model(model_path) except Exception as e: print(f"Error loading model: {e}") model = None try: label_encoder = joblib.load('util/label_encoder.joblib') print("Label encoder loaded successfully") except Exception as e: print(f"Error loading label encoder: {e}") label_encoder = None # Initialize champion name encoder champion_encoder = LabelEncoder() champion_encoder.fit(CHAMPIONS) #==================================== Functions ================================================= def get_user_training_df(player_opgg_url): try: print("========= Inside get_user_training_df(player_opgg_url) ============= \n") #print("player_opgg_url: ", player_opgg_url, "\n type(player_opgg_url): ", type(player_opgg_url), "\n") # Add input validation if not player_opgg_url or not isinstance(player_opgg_url, str): return "Invalid URL provided" training_df = create_app_user_training_df(player_opgg_url) return training_df except Exception as e: # Add more detailed error information import traceback error_trace = traceback.format_exc() print(f"Full error trace:\n{error_trace}") return f"Error getting training data: {str(e)}" #return f"Error getting training data: {e}" def show_stats(player_opgg_url): """Display player statistics and recent matches""" if not player_opgg_url: return "Please enter a player link to OPGG", None try: training_features = get_user_training_df(player_opgg_url) print("training_features: ", training_features, "\n") if isinstance(training_features, str): # Error message return training_features, None wins = training_features['result'].sum() losses = len(training_features) - wins winrate = f"{(wins / len(training_features)) * 100:.0f}%" favorite_champions = ( training_features['champion'] .value_counts() .head(3) .index.tolist() ) stats_html = f"""

Player's Recent Stats

Wins: {wins} | Losses: {losses}

Winrate: {winrate}

Favorite Champions: {', '.join(favorite_champions)}

""" return stats_html, None except Exception as e: return f"Error processing stats: {e}. ", None def predict_champion(player_opgg_url, *champions): """Make prediction based on selected champions""" if not player_opgg_url or None in champions: return "Please fill in all fields" try: if model is None: return "Model not loaded properly" if label_encoder is None: return "Label encoder not loaded properly" # Get and process the data training_df = get_user_training_df(player_opgg_url) if isinstance(training_df, str): return training_df training_df = convert_df(training_df) #print("type(training_df): ", type(training_df), "\n") print("check_datatypes(training_df) BEFORE feature eng: \n", check_datatypes(training_df), "\n") training_df = apply_feature_engineering(training_df) print("check_datatypes(training_df) AFTER feature eng: \n", check_datatypes(training_df), "\n") # Get feature columns feature_columns = [col for col in training_df.columns if col not in ['champion', 'region', 'stratify_label']] X = training_df[feature_columns] # Handle categorical features categorical_columns = X.select_dtypes(include=['category']).columns X_processed = X.copy() for col in categorical_columns: X_processed[col] = X_processed[col].cat.codes X_processed = X_processed.astype('float32') # Create DMatrix and predict dtest = DMatrix(X_processed, enable_categorical=True) predictions = model.predict(dtest) # Get prediction indices if len(predictions.shape) > 1: pred_indices = predictions.argmax(axis=1) else: pred_indices = predictions.astype(int) # First get the numeric ID from the original label encoder decoded_numeric = label_encoder.inverse_transform(pred_indices) # Map numeric ID to index in CHAMPIONS list # Since your label encoder seems to use champion IDs, we need to map these to list indices try: # Get the first prediction champion_id = int(decoded_numeric[0]) # Print debug information print(f"Champion ID from model: {champion_id}") # Find the closest matching index # Note: This assumes champion IDs roughly correspond to their position in the list champion_index = min(max(champion_id - 1, 0), len(CHAMPIONS) - 1) predicted_champion = CHAMPIONS[champion_index] print(f"Mapped to champion: {predicted_champion}") return f"{predicted_champion}" except Exception as e: print(f"Error mapping champion ID: {e}") return f"Error: Could not map champion ID {decoded_numeric[0]}" except Exception as e: import traceback print(f"Full error trace:\n{traceback.format_exc()}") return f"Error making prediction: {e}" ''' current working function!!!!!! def predict_champion(player_opgg_url, *champions): """Make prediction based on selected champions""" print("==================== Inside: predict_champion() ===================== \n") if not player_opgg_url or None in champions: return "Please fill in all fields" try: if model is None: return "Model not loaded properly" if label_encoder is None: return "Label encoder not loaded properly" # Print label encoder information print("\nLabel Encoder Information:") print("Classes in encoder:", label_encoder.classes_) print("Number of classes:", len(label_encoder.classes_)) # Get and process the data training_df = get_user_training_df(player_opgg_url) print("training_df retrieved: ", training_df, "\n") if isinstance(training_df, str): # Error message return training_df # Apply necessary transformations training_df = convert_df(training_df) training_df = apply_feature_engineering(training_df) print("training_df converted and feature engineered: ", training_df, "\n") # Get feature columns (excluding champion and region) feature_columns = [col for col in training_df.columns if col not in ['champion', 'region', 'stratify_label']] X = training_df[feature_columns] print("Got feature columns X: ", X, "\n") # Handle categorical features categorical_columns = X.select_dtypes(include=['category']).columns X_processed = X.copy() print("Handled categorical features, X_processed = ", X_processed, "\n") # Convert categorical columns to numeric for col in categorical_columns: X_processed[col] = X_processed[col].cat.codes print("Converted categorical columns to numeric: ", categorical_columns, "\n") # Convert to float32 X_processed = X_processed.astype('float32') print("Converted X_processed to float32: ", X_processed, "\n") # Create DMatrix with categorical feature support dtest = DMatrix(X_processed, enable_categorical=True) print("Converted to Dmatrix: ", dtest, "\n") # Make prediction print("Starting model prediction...\n") predictions = model.predict(dtest) print("Model prediction complete\n") print("\nPrediction Information:") print("Raw predictions shape:", predictions.shape) print("Raw predictions:", predictions) # Get the highest probability prediction if len(predictions.shape) > 1: pred_indices = predictions.argmax(axis=1) else: pred_indices = predictions.astype(int) print("\nPrediction Indices:") print("Indices shape:", pred_indices.shape) print("Indices:", pred_indices) # Check if indices are within valid range print("\nValidation:") print("Min index:", pred_indices.min()) print("Max index:", pred_indices.max()) print("Valid index range:", 0, len(label_encoder.classes_) - 1) # Try to decode predictions try: decoded_preds = label_encoder.inverse_transform(pred_indices) print("\nDecoded Predictions:") print("Type:", type(decoded_preds)) print("Value:", decoded_preds) print("==================== Exiting: predict_champion()===================\n") return f"Predicted champion: {decoded_preds[0]}" except Exception as e: print(f"\nError during decoding: {e}") # Fallback: try to directly index into classes try: champion = label_encoder.classes_[int(pred_indices[0])] return f"Predicted champion: {champion}" except Exception as e2: print(f"Fallback error: {e2}") return f"Error decoding prediction: {pred_indices[0]}" except Exception as e: import traceback print(f"Full error trace:\n{traceback.format_exc()}") return f"Error making prediction: {e}" ''' # Define your interface with gr.Blocks() as demo: gr.Markdown("# League of Legends Champion Prediction") with gr.Row(): player_opgg_url = gr.Textbox(label="OPGG Player URL") show_button = gr.Button("Show Player Stats") with gr.Row(): stats_output = gr.HTML(label="Player Statistics") recent_matches = gr.HTML(label="Recent Matches") with gr.Row(): champion_dropdowns = [ gr.Dropdown(choices=CHAMPIONS, label=f"Champion {i+1}") for i in range(9) ] with gr.Row(): predict_button = gr.Button("Predict") prediction_output = gr.Text(label="Prediction") # Set up event handlers show_button.click( fn=show_stats, inputs=[player_opgg_url], outputs=[stats_output, recent_matches] ) predict_button.click( fn=predict_champion, inputs=[player_opgg_url] + champion_dropdowns, outputs=prediction_output ) # Optional: Save the champion encoder for future use joblib.dump(champion_encoder, 'champion_encoder.joblib') # Enable queuing demo.launch(debug=True) # For local testing if __name__ == "__main__": demo.launch()