| import warnings |
| warnings.filterwarnings("ignore") |
| import pandas as pd |
| import numpy as np |
| import pickle |
|
|
| MODEL_PATH = "genre_model.pkl" |
| SCALER_PATH = "genre_scaler.pkl" |
| ENCODER_PATH = "genre_encoder.pkl" |
|
|
| NUMERICAL_FEATURES = [ |
| "melody_complexity (vocals)", |
| "melody_range (vocals)", |
| "melody_variability (vocals)", |
| "tempo_bpm_original (mix)", |
| "danceability custom (mix)", |
| "loudness_integrated_lufs custom (mix)", |
| "loudness_range_lu custom (mix)", |
| "energy_librosa (mix)", |
| "energy_librosa_std (mix)", |
| "energy_essentia (mix)", |
| "energy_essentia_std (mix)", |
| "energy_combined (mix)", |
| "spectral_centroid_mean custom (mix)", |
| "mfcc_mean_1 (mix)", |
| "mfcc_mean_2 (mix)", |
| "chroma_mean (mix)", |
| "spectral_contrast_mean (mix)", |
| "repetition_score custom (mix)", |
| "pitch_mean (mix)", |
| "pitch_std (mix)", |
| "rms_energy_mean (mix)", |
| "rms_energy_std (mix)", |
| "zero_crossing_rate (mix)", |
| ] |
|
|
|
|
| def engineer_features(df, feature_cols): |
| df = df.copy() |
| df['energy_per_tempo'] = df['energy_combined (mix)'] / (df['tempo_bpm_original (mix)'] + 1) |
| df['dance_energy_ratio'] = df['danceability custom (mix)'] * df['energy_combined (mix)'] |
| df['loudness_range_ratio'] = df['loudness_range_lu custom (mix)'] / (abs(df['loudness_integrated_lufs custom (mix)']) + 1) |
| df['melody_energy'] = df['melody_variability (vocals)'] * df['energy_combined (mix)'] |
| df['spectral_complexity'] = df['spectral_centroid_mean custom (mix)'] * df['spectral_contrast_mean (mix)'] |
| df['mfcc_ratio'] = df['mfcc_mean_1 (mix)'] / (abs(df['mfcc_mean_2 (mix)']) + 1) |
| df['rhythm_strength'] = df['tempo_bpm_original (mix)'] * df['danceability custom (mix)'] |
| df['pitch_variation'] = df['pitch_std (mix)'] / (df['pitch_mean (mix)'] + 1) |
| df['rms_energy_ratio'] = df['rms_energy_mean (mix)'] / (df['rms_energy_std (mix)'] + 1) |
| df['chroma_energy'] = df['chroma_mean (mix)'] * df['energy_combined (mix)'] |
| df['zero_tempo'] = df['zero_crossing_rate (mix)'] * df['tempo_bpm_original (mix)'] |
| df['tempo_category'] = np.where(df['tempo_bpm_original (mix)'] < 100, 0, np.where(df['tempo_bpm_original (mix)'] < 130, 1, 2)) |
| df['energy_category'] = np.where(df['energy_combined (mix)'] < 0.3, 0, np.where(df['energy_combined (mix)'] < 0.6, 1, 2)) |
| df['dance_category'] = np.where(df['danceability custom (mix)'] < 0.5, 0, np.where(df['danceability custom (mix)'] < 0.75, 1, 2)) |
| engineered = ['energy_per_tempo', 'dance_energy_ratio', 'loudness_range_ratio', 'melody_energy', 'spectral_complexity', |
| 'mfcc_ratio', 'rhythm_strength', 'pitch_variation', 'rms_energy_ratio', 'chroma_energy', 'zero_tempo', |
| 'tempo_category', 'energy_category', 'dance_category'] |
| return df, feature_cols + engineered |
|
|
|
|
| class GenrePredictor: |
| def __init__(self): |
| with open(MODEL_PATH, "rb") as f: |
| self.model = pickle.load(f) |
| with open(SCALER_PATH, "rb") as f: |
| self.scaler = pickle.load(f) |
| with open(ENCODER_PATH, "rb") as f: |
| self.genre_encoder, self.all_subgenres, self.all_features = pickle.load(f) |
| |
| def predict(self, feature_dict): |
| df = pd.DataFrame([feature_dict]) |
| df, _ = engineer_features(df, NUMERICAL_FEATURES) |
| |
| for col in self.all_features: |
| if col not in df.columns: |
| df[col] = 0 |
| |
| values = df[self.all_features].values[0] |
| values = np.nan_to_num(values, nan=0, posinf=0, neginf=0) |
| |
| input_scaled = self.scaler.transform(values.reshape(1, -1)) |
| genre_idx = self.model.predict(input_scaled)[0] |
| genre = self.genre_encoder.inverse_transform([genre_idx])[0] |
| |
| genre_probs = self.model.predict_proba(input_scaled)[0] |
| top_indices = np.argsort(genre_probs)[::-1][:5] |
| similar = [(self.genre_encoder.classes_[i], genre_probs[i]) for i in top_indices] |
| |
| related_subs = [s for s in self.all_subgenres if genre.lower() in s.lower()] |
| if not related_subs: |
| related_subs = self.all_subgenres[:10] |
| |
| return { |
| "genre": genre, |
| "similar_genres": similar, |
| "subgenres": related_subs |
| } |
|
|
|
|
| if __name__ == "__main__": |
| predictor = GenrePredictor() |
| |
| |
| song_features = { |
| "melody_complexity (vocals)": 2.5, |
| "melody_range (vocals)": 30.0, |
| "melody_variability (vocals)": 0.55, |
| "tempo_bpm_original (mix)": 140.0, |
| "danceability custom (mix)": 0.70, |
| "loudness_integrated_lufs custom (mix)": -12.0, |
| "loudness_range_lu custom (mix)": 5.0, |
| "energy_librosa (mix)": 0.5, |
| "energy_librosa_std (mix)": 0.15, |
| "energy_essentia (mix)": 0.3, |
| "energy_essentia_std (mix)": 0.15, |
| "energy_combined (mix)": 0.45, |
| "spectral_centroid_mean custom (mix)": 0.13, |
| "mfcc_mean_1 (mix)": 150.0, |
| "mfcc_mean_2 (mix)": -20.0, |
| "chroma_mean (mix)": 0.45, |
| "spectral_contrast_mean (mix)": 20.0, |
| "repetition_score custom (mix)": 0.007, |
| "pitch_mean (mix)": 200.0, |
| "pitch_std (mix)": 80.0, |
| "rms_energy_mean (mix)": 0.5, |
| "rms_energy_std (mix)": 0.15, |
| "zero_crossing_rate (mix)": 0.05, |
| } |
| |
| print("\n" + "=" * 60) |
| print("GENRE PREDICTION WITH DICT INPUT") |
| print("=" * 60) |
| print("\nInput Dictionary:") |
| for k, v in song_features.items(): |
| print(f" {k}: {v}") |
| |
| result = predictor.predict(song_features) |
| |
| print("\n" + "=" * 60) |
| print("PREDICTION RESULT") |
| print("=" * 60) |
| print(f"\n GENRE: {result['genre']}") |
| print("\n Similar Genres:") |
| for g, prob in result['similar_genres']: |
| print(f" - {g}: {prob:.1%}") |
| print("\n Sub-genres:") |
| for sub in result['subgenres'][:8]: |
| print(f" - {sub}") |
|
|
