emotionanalysis.py

import librosa
import numpy as np
from scipy import signal
from collections import Counter
try:
    import matplotlib.pyplot as plt
except ImportError:
    plt = None
from scipy.stats import mode
import warnings
warnings.filterwarnings('ignore')  # Suppress librosa warnings

class MusicAnalyzer:
    def __init__(self):
        # Emotion feature mappings - these define characteristics of different emotions
        self.emotion_profiles = {
            'happy': {'tempo': (100, 180), 'energy': (0.6, 1.0), 'major_mode': True, 'brightness': (0.6, 1.0)},
            'sad': {'tempo': (40, 90), 'energy': (0, 0.5), 'major_mode': False, 'brightness': (0, 0.5)},
            'calm': {'tempo': (50, 90), 'energy': (0, 0.4), 'major_mode': True, 'brightness': (0.3, 0.6)},
            'energetic': {'tempo': (110, 200), 'energy': (0.7, 1.0), 'major_mode': True, 'brightness': (0.5, 0.9)},
            'tense': {'tempo': (70, 140), 'energy': (0.5, 0.9), 'major_mode': False, 'brightness': (0.3, 0.7)},
            'nostalgic': {'tempo': (60, 100), 'energy': (0.3, 0.7), 'major_mode': None, 'brightness': (0.4, 0.7)}
        }

        # Theme mappings based on musical features
        self.theme_profiles = {
            'love': {'emotion': ['happy', 'nostalgic', 'sad'], 'harmony_complexity': (0.3, 0.7)},
            'triumph': {'emotion': ['energetic', 'happy'], 'harmony_complexity': (0.4, 0.8)},
            'loss': {'emotion': ['sad', 'nostalgic'], 'harmony_complexity': (0.3, 0.7)},
            'adventure': {'emotion': ['energetic', 'tense'], 'harmony_complexity': (0.5, 0.9)},
            'reflection': {'emotion': ['calm', 'nostalgic'], 'harmony_complexity': (0.4, 0.8)},
            'conflict': {'emotion': ['tense', 'energetic'], 'harmony_complexity': (0.6, 1.0)}
        }

        # Musical key mapping
        self.key_names = ['C', 'C#', 'D', 'D#', 'E', 'F', 'F#', 'G', 'G#', 'A', 'A#', 'B']
        
        # Common time signatures and their beat patterns with weights for prior probability
        # Simplified to only include 4/4, 3/4, 2/4, and 6/8
        self.common_time_signatures = {
            "4/4": {"beats_per_bar": 4, "beat_pattern": [1.0, 0.2, 0.5, 0.2], "weight": 0.45},
            "3/4": {"beats_per_bar": 3, "beat_pattern": [1.0, 0.2, 0.3], "weight": 0.25},
            "2/4": {"beats_per_bar": 2, "beat_pattern": [1.0, 0.3], "weight": 0.15},
            "6/8": {"beats_per_bar": 6, "beat_pattern": [1.0, 0.2, 0.3, 0.8, 0.2, 0.3], "weight": 0.15}
        }
        
        # Add common accent patterns for different time signatures
        self.accent_patterns = {
            "4/4": [[1, 0, 0, 0], [1, 0, 2, 0], [1, 0, 2, 0, 3, 0, 2, 0]],
            "3/4": [[1, 0, 0], [1, 0, 2]],
            "2/4": [[1, 0], [1, 2]],
            "6/8": [[1, 0, 0, 2, 0, 0], [1, 0, 0, 2, 0, 3]]
        }
        
        # Expected rhythm density (relative note density per beat) for different time signatures
        self.rhythm_density = {
            "4/4": [1.0, 0.7, 0.8, 0.6],
            "3/4": [1.0, 0.6, 0.7],
            "6/8": [1.0, 0.5, 0.4, 0.8, 0.5, 0.4],
            "2/4": [1.0, 0.6]
        }

    def load_audio(self, file_path, sr=22050, duration=None):
        """Load audio file and return time series and sample rate"""
        try:
            y, sr = librosa.load(file_path, sr=sr, duration=duration)
            return y, sr
        except Exception as e:
            print(f"Error loading audio file: {e}")
            return None, None

    def analyze_rhythm(self, y, sr):
        """Analyze rhythm-related features: tempo, beats, time signature"""
        # Tempo and beat detection
        onset_env = librosa.onset.onset_strength(y=y, sr=sr)
        tempo, beat_frames = librosa.beat.beat_track(onset_envelope=onset_env, sr=sr)
        beat_times = librosa.frames_to_time(beat_frames, sr=sr)

        # Beat intervals and regularity
        beat_intervals = np.diff(beat_times) if len(beat_times) > 1 else np.array([0])
        beat_regularity = 1.0 / np.std(beat_intervals) if len(beat_intervals) > 0 and np.std(beat_intervals) > 0 else 0

        # Rhythm pattern analysis through autocorrelation
        ac = librosa.autocorrelate(onset_env, max_size=sr // 2)
        ac = librosa.util.normalize(ac, norm=np.inf)

        # Advanced time signature detection
        time_sig_result = self._detect_time_signature(y, sr)
        
        # Extract results from the time signature detection
        estimated_signature = time_sig_result["time_signature"]
        time_sig_confidence = time_sig_result["confidence"]

        # Compute onset strength to get a measure of rhythm intensity
        rhythm_intensity = np.mean(onset_env) / np.max(onset_env) if np.max(onset_env) > 0 else 0

        # Rhythm complexity based on variation in onset strength
        rhythm_complexity = np.std(onset_env) / np.mean(onset_env) if np.mean(onset_env) > 0 else 0

        # Convert numpy arrays to regular Python types for JSON serialization
        beat_times_list = [float(t) for t in beat_times.tolist()]
        beat_intervals_list = [float(i) for i in beat_intervals.tolist()]

        return {
            "tempo": float(tempo),
            "beat_times": beat_times_list,
            "beat_intervals": beat_intervals_list,
            "beat_regularity": float(beat_regularity),
            "rhythm_intensity": float(rhythm_intensity),
            "rhythm_complexity": float(rhythm_complexity),
            "estimated_time_signature": estimated_signature,
            "time_signature_confidence": float(time_sig_confidence),
            "time_signature_candidates": time_sig_result.get("all_candidates", {})
        }

    def _detect_time_signature(self, y, sr):
        """
        Multi-method approach to time signature detection
        
        Args:
            y: Audio signal
            sr: Sample rate
        
        Returns:
            dict with detected time signature and confidence
        """
        # 1. Compute onset envelope and beat positions
        onset_env = librosa.onset.onset_strength(y=y, sr=sr, hop_length=512)
        
        # Get tempo and beat frames
        tempo, beat_frames = librosa.beat.beat_track(onset_envelope=onset_env, sr=sr)
        beat_times = librosa.frames_to_time(beat_frames, sr=sr)
        
        # Return default if not enough beats detected
        if len(beat_times) < 8:
            return {"time_signature": "4/4", "confidence": 0.5}
        
        # 2. Extract beat strengths and normalize
        beat_strengths = self._get_beat_strengths(y, sr, beat_times, onset_env)
        
        # 3. Compute various time signature features using different methods
        results = {}
        
        # Method 1: Beat pattern autocorrelation
        autocorr_result = self._detect_by_autocorrelation(onset_env, sr)
        results["autocorrelation"] = autocorr_result
        
        # Method 2: Beat strength pattern matching
        pattern_result = self._detect_by_pattern_matching(beat_strengths)
        results["pattern_matching"] = pattern_result
        
        # Method 3: Spectral rhythmic analysis
        spectral_result = self._detect_by_spectral_analysis(onset_env, sr)
        results["spectral"] = spectral_result
        
        # Method 4: Note density analysis
        density_result = self._detect_by_note_density(y, sr, beat_times)
        results["note_density"] = density_result
        
        # Method 5: Tempo-based estimation
        tempo_result = self._estimate_from_tempo(tempo)
        results["tempo_based"] = tempo_result
        
        # 4. Combine results with weighted voting
        final_result = self._combine_detection_results(results, tempo)
        
        return final_result
    
    def _get_beat_strengths(self, y, sr, beat_times, onset_env):
        """Extract normalized strengths at beat positions"""
        # Convert beat times to frames
        beat_frames = librosa.time_to_frames(beat_times, sr=sr, hop_length=512)
        beat_frames = [min(f, len(onset_env)-1) for f in beat_frames]
        
        # Get beat strengths from onset envelope
        beat_strengths = np.array([onset_env[f] for f in beat_frames])
        
        # Also look at energy and spectral flux at beat positions
        hop_length = 512
        frame_length = 2048
        
        # Get energy at each beat
        energy = librosa.feature.rms(y=y, frame_length=frame_length, hop_length=hop_length)[0]
        beat_energy = np.array([energy[min(f, len(energy)-1)] for f in beat_frames])
        
        # Combine onset strength with energy (weighted average)
        beat_strengths = 0.7 * beat_strengths + 0.3 * beat_energy
        
        # Normalize
        if np.max(beat_strengths) > 0:
            beat_strengths = beat_strengths / np.max(beat_strengths)
            
        return beat_strengths
    
    def _detect_by_autocorrelation(self, onset_env, sr):
        """Detect meter using autocorrelation of onset strength"""
        # Calculate autocorrelation of onset envelope
        hop_length = 512
        ac = librosa.autocorrelate(onset_env, max_size=4 * sr // hop_length)
        ac = librosa.util.normalize(ac)
        
        # Find significant peaks in autocorrelation
        peaks = signal.find_peaks(ac, height=0.2, distance=sr//(8*hop_length))[0]
        
        if len(peaks) < 2:
            return {"time_signature": "4/4", "confidence": 0.4}
            
        # Analyze peak intervals in terms of beats
        peak_intervals = np.diff(peaks)
        
        # Convert peaks to time
        peak_times = peaks * hop_length / sr
        
        # Analyze for common time signature patterns
        time_sig_votes = {}
        
        # Check if peaks match expected bar lengths
        for ts, info in self.common_time_signatures.items():
            beats_per_bar = info["beats_per_bar"]
            
            # Check how well peaks match this meter
            score = 0
            for interval in peak_intervals:
                # Check if this interval corresponds to this time signature
                # Allow some tolerance around the expected value
                expected = beats_per_bar * (hop_length / sr)  # in seconds
                tolerance = 0.25 * expected
                
                if abs(interval * hop_length / sr - expected) < tolerance:
                    score += 1
            
            if len(peak_intervals) > 0:
                time_sig_votes[ts] = score / len(peak_intervals)
        
        # Return most likely time signature
        if time_sig_votes:
            best_ts = max(time_sig_votes.items(), key=lambda x: x[1])
            return {"time_signature": best_ts[0], "confidence": best_ts[1]}
        
        return {"time_signature": "4/4", "confidence": 0.4}
    
    def _detect_by_pattern_matching(self, beat_strengths):
        """Match beat strength patterns against known time signature patterns"""
        if len(beat_strengths) < 6:
            return {"time_signature": "4/4", "confidence": 0.4}
            
        results = {}
        
        # Try each possible time signature
        for ts, info in self.common_time_signatures.items():
            beats_per_bar = info["beats_per_bar"]
            expected_pattern = info["beat_pattern"]
            
            # Calculate correlation scores for overlapping segments
            scores = []
            
            # We need at least one complete pattern
            if len(beat_strengths) >= beats_per_bar:
                # Try different offsets to find best alignment
                for offset in range(min(beats_per_bar, len(beat_strengths) - beats_per_bar + 1)):
                    # Calculate scores for each complete pattern
                    pattern_scores = []
                    
                    for i in range(offset, len(beat_strengths) - beats_per_bar + 1, beats_per_bar):
                        segment = beat_strengths[i:i+beats_per_bar]
                        
                        # If expected pattern is longer than segment, truncate it
                        pattern = expected_pattern[:len(segment)]
                        
                        # Normalize segment and pattern
                        if np.std(segment) > 0 and np.std(pattern) > 0:
                            # Calculate correlation
                            corr = np.corrcoef(segment, pattern)[0, 1]
                            if not np.isnan(corr):
                                pattern_scores.append(corr)
                    
                    if pattern_scores:
                        scores.append(np.mean(pattern_scores))
            
            # Use the best score among different offsets
            if scores:
                confidence = max(scores)
                results[ts] = confidence
        
        # Find best match
        if results:
            best_ts = max(results.items(), key=lambda x: x[1])
            return {"time_signature": best_ts[0], "confidence": best_ts[1]}
        
        # Default
        return {"time_signature": "4/4", "confidence": 0.5}
    
    def _detect_by_spectral_analysis(self, onset_env, sr):
        """Analyze rhythm in frequency domain"""
        # Get rhythm periodicity through Fourier Transform
        # Focus on periods corresponding to typical bar lengths (1-8 seconds)
        hop_length = 512
        
        # Calculate rhythm periodicity
        fft_size = 2**13  # Large enough to give good frequency resolution
        S = np.abs(np.fft.rfft(onset_env, n=fft_size))
        
        # Convert frequency to tempo in BPM
        freqs = np.fft.rfftfreq(fft_size, d=hop_length/sr)
        tempos = 60 * freqs
        
        # Focus on reasonable tempo range (40-240 BPM)
        tempo_mask = (tempos >= 40) & (tempos <= 240)
        S_tempo = S[tempo_mask]
        tempos = tempos[tempo_mask]
        
        # Find peaks in spectrum
        peaks = signal.find_peaks(S_tempo, height=np.max(S_tempo)*0.1, distance=5)[0]

        if len(peaks) == 0:
            return {"time_signature": "4/4", "confidence": 0.4}
            
        # Get peak tempos and strengths
        peak_tempos = tempos[peaks]
        peak_strengths = S_tempo[peaks]
        
        # Sort by strength
        peak_indices = np.argsort(peak_strengths)[::-1]
        peak_tempos = peak_tempos[peak_indices]
        peak_strengths = peak_strengths[peak_indices]
        
        # Analyze relationships between peaks
        # For example, 3/4 typically has peaks at multiples of 3 beats
        # 4/4 has peaks at multiples of 4 beats
        
        time_sig_scores = {}
        
        # Check relationships between top peaks
        if len(peak_tempos) >= 2:
            tempo_ratios = []
            for i in range(len(peak_tempos)):
                for j in range(i+1, len(peak_tempos)):
                    if peak_tempos[j] > 0:
                        ratio = peak_tempos[i] / peak_tempos[j]
                        tempo_ratios.append(ratio)
            
            # Check for patterns indicative of different time signatures
            for ts in self.common_time_signatures:
                score = 0
                
                if ts == "4/4" or ts == "2/4":
                    # Look for ratios close to 2 or 4
                    for ratio in tempo_ratios:
                        if abs(ratio - 2) < 0.2 or abs(ratio - 4) < 0.2:
                            score += 1
                
                elif ts == "3/4" or ts == "6/8":
                    # Look for ratios close to 3 or 6
                    for ratio in tempo_ratios:
                        if abs(ratio - 3) < 0.2 or abs(ratio - 6) < 0.3:
                            score += 1
                
                # Normalize score
                if tempo_ratios:
                    time_sig_scores[ts] = min(1.0, score / len(tempo_ratios) + 0.4)
        
        # If we have meaningful scores, return best match
        if time_sig_scores:
            best_ts = max(time_sig_scores.items(), key=lambda x: x[1])
            return {"time_signature": best_ts[0], "confidence": best_ts[1]}
        
        # Default fallback
        return {"time_signature": "4/4", "confidence": 0.4}
    
    def _detect_by_note_density(self, y, sr, beat_times):
        """Analyze note density patterns between beats"""
        if len(beat_times) < 6:
            return {"time_signature": "4/4", "confidence": 0.4}
            
        # Extract note onsets (not just beats)
        onset_times = librosa.onset.onset_detect(y=y, sr=sr, units='time')
        
        if len(onset_times) < len(beat_times):
            return {"time_signature": "4/4", "confidence": 0.4}
            
        # Count onsets between consecutive beats
        note_counts = []
        for i in range(len(beat_times) - 1):
            start = beat_times[i]
            end = beat_times[i+1]
            
            # Count onsets in this beat
            count = sum(1 for t in onset_times if start <= t < end)
            note_counts.append(count)
        
        # Look for repeating patterns in the note counts
        time_sig_scores = {}
        
        for ts, info in self.common_time_signatures.items():
            beats_per_bar = info["beats_per_bar"]
            
            # Skip if we don't have enough data
            if len(note_counts) < beats_per_bar:
                continue
                
            # Calculate pattern similarity for this time signature
            scores = []
            
            for offset in range(min(beats_per_bar, len(note_counts) - beats_per_bar + 1)):
                similarities = []
                
                for i in range(offset, len(note_counts) - beats_per_bar + 1, beats_per_bar):
                    # Get current bar pattern
                    pattern = note_counts[i:i+beats_per_bar]
                    
                    # Compare with expected density pattern
                    expected = self.rhythm_density.get(ts, [1.0] * beats_per_bar)
                    expected = expected[:len(pattern)]  # Truncate if needed
                    
                    # Normalize both patterns
                    if sum(pattern) > 0 and sum(expected) > 0:
                        pattern_norm = [p/max(1, sum(pattern)) for p in pattern]
                        expected_norm = [e/sum(expected) for e in expected]
                        
                        # Calculate similarity (1 - distance)
                        distance = sum(abs(p - e) for p, e in zip(pattern_norm, expected_norm)) / len(pattern)
                        similarity = 1 - min(1.0, distance)
                        similarities.append(similarity)
                
                if similarities:
                    scores.append(np.mean(similarities))
            
            # Use the best score
            if scores:
                time_sig_scores[ts] = max(scores)
        
        # Return best match
        if time_sig_scores:
            best_ts = max(time_sig_scores.items(), key=lambda x: x[1])
            return {"time_signature": best_ts[0], "confidence": best_ts[1]}
        
        # Default
        return {"time_signature": "4/4", "confidence": 0.4}
    
    def _estimate_from_tempo(self, tempo):
        """Use tempo to help estimate likely time signature"""
        # Statistical tendencies: slower tempos often in compound meters (6/8)
        # Fast tempos often favor simple meters (2/4)
        
        scores = {}
        
        if tempo < 70:
            # Slow tempos favor compound meters
            scores = {
                "4/4": 0.5,
                "3/4": 0.4,
                "2/4": 0.3,
                "6/8": 0.7
            }
        elif 70 <= tempo <= 120:
            # Medium tempos favor 4/4, 3/4
            scores = {
                "4/4": 0.7,
                "3/4": 0.6,
                "2/4": 0.4,
                "6/8": 0.3
            }
        else:
            # Fast tempos favor simpler meters
            scores = {
                "4/4": 0.6,
                "2/4": 0.7,
                "3/4": 0.4,
                "6/8": 0.2
            }
        
        # Find best match
        best_ts = max(scores.items(), key=lambda x: x[1])
        return {"time_signature": best_ts[0], "confidence": best_ts[1]}
    
    def _combine_detection_results(self, results, tempo):
        """Combine results from different detection methods"""
        # Define weights for different methods
        method_weights = {
            "autocorrelation": 0.25,
            "pattern_matching": 0.30,
            "spectral": 0.20,
            "note_density": 0.20,
            "tempo_based": 0.05
        }
        
        # Prior probability (based on frequency in music)
        prior_weights = {ts: info["weight"] for ts, info in self.common_time_signatures.items()}
        
        # Combine votes
        total_votes = {ts: prior_weights.get(ts, 0.1) for ts in self.common_time_signatures}
        
        for method, result in results.items():
            ts = result["time_signature"]
            confidence = result["confidence"]
            weight = method_weights.get(method, 0.1)
            
            # Add weighted vote
            if ts in total_votes:
                total_votes[ts] += confidence * weight
            else:
                total_votes[ts] = confidence * weight
        
        # Special case: disambiguate between 3/4 and 6/8
        if "3/4" in total_votes and "6/8" in total_votes:
            # If the two are close, use tempo to break tie
            if abs(total_votes["3/4"] - total_votes["6/8"]) < 0.1:
                if tempo < 100:  # Slower tempo favors 6/8
                    total_votes["6/8"] += 0.1
                else:  # Faster tempo favors 3/4
                    total_votes["3/4"] += 0.1
        
        # Get highest scoring time signature
        best_ts = max(total_votes.items(), key=lambda x: x[1])
        
        # Calculate confidence score (normalize to 0-1)
        confidence = best_ts[1] / (sum(total_votes.values()) + 0.001)
        confidence = min(0.95, max(0.4, confidence))  # Bound confidence
        
        return {
            "time_signature": best_ts[0],
            "confidence": confidence,
            "all_candidates": {ts: float(score) for ts, score in total_votes.items()}
        }
    
    def _evaluate_beat_pattern(self, beat_strengths, pattern_length):
        """
        Evaluate how consistently a specific pattern length fits the beat strengths
        
        Args:
            beat_strengths: Array of normalized beat strengths
            pattern_length: Length of pattern to evaluate
            
        Returns:
            score: How well this pattern length explains the data (0-1)
        """
        if len(beat_strengths) < pattern_length * 2:
            return 0.0
            
        # Calculate correlation between consecutive patterns
        correlations = []
        
        num_full_patterns = len(beat_strengths) // pattern_length
        for i in range(num_full_patterns - 1):
            pattern1 = beat_strengths[i*pattern_length:(i+1)*pattern_length]
            pattern2 = beat_strengths[(i+1)*pattern_length:(i+2)*pattern_length]
            
            # Calculate similarity between consecutive patterns
            if len(pattern1) == len(pattern2) and len(pattern1) > 0:
                corr = np.corrcoef(pattern1, pattern2)[0, 1]
                if not np.isnan(corr):
                    correlations.append(corr)
        
        # Calculate variance of beat strengths within each position
        variance_score = 0
        if num_full_patterns >= 2:
            position_values = [[] for _ in range(pattern_length)]
            
            for i in range(num_full_patterns):
                for pos in range(pattern_length):
                    idx = i * pattern_length + pos
                    if idx < len(beat_strengths):
                        position_values[pos].append(beat_strengths[idx])
            
            # Calculate variance ratio (higher means consistent accent patterns)
            between_pos_var = np.var([np.mean(vals) for vals in position_values if vals])
            within_pos_var = np.mean([np.var(vals) for vals in position_values if len(vals) > 1])
            
            if within_pos_var > 0:
                variance_score = between_pos_var / within_pos_var
                variance_score = min(1.0, variance_score / 2.0)  # Normalize
        
        # Combine correlation and variance scores
        if correlations:
            correlation_score = np.mean(correlations)
            return 0.7 * correlation_score + 0.3 * variance_score
        
        return 0.5 * variance_score  # Lower confidence if we couldn't calculate correlations
    
    def _extract_average_pattern(self, beat_strengths, pattern_length):
        """
        Extract the average beat pattern of specified length
        
        Args:
            beat_strengths: Array of beat strengths
            pattern_length: Length of pattern to extract
            
        Returns:
            Average pattern of the specified length
        """
        if len(beat_strengths) < pattern_length:
            return np.array([])
            
        # Number of complete patterns
        num_patterns = len(beat_strengths) // pattern_length
        
        if num_patterns == 0:
            return np.array([])
            
        # Reshape to stack patterns and calculate average
        patterns = beat_strengths[:num_patterns * pattern_length].reshape((num_patterns, pattern_length))
        return np.mean(patterns, axis=0)

    def analyze_tonality(self, y, sr):
        """Analyze tonal features: key, mode, harmonic features"""
        # Compute chromagram
        chroma = librosa.feature.chroma_cqt(y=y, sr=sr)

        # Krumhansl-Schmuckler key-finding algorithm (simplified)
        # Major and minor profiles from music theory research
        major_profile = np.array([6.35, 2.23, 3.48, 2.33, 4.38, 4.09, 2.52, 5.19, 2.39, 3.66, 2.29, 2.88])
        minor_profile = np.array([6.33, 2.68, 3.52, 5.38, 2.60, 3.53, 2.54, 4.75, 3.98, 2.69, 3.34, 3.17])

        # Calculate the correlation of the chroma with each key profile
        chroma_avg = np.mean(chroma, axis=1)
        major_corr = np.zeros(12)
        minor_corr = np.zeros(12)

        for i in range(12):
            major_corr[i] = np.corrcoef(np.roll(chroma_avg, i), major_profile)[0, 1]
            minor_corr[i] = np.corrcoef(np.roll(chroma_avg, i), minor_profile)[0, 1]

        # Find the key with the highest correlation
        max_major_idx = np.argmax(major_corr)
        max_minor_idx = np.argmax(minor_corr)

        # Determine if the piece is in a major or minor key
        if major_corr[max_major_idx] > minor_corr[max_minor_idx]:
            mode = "major"
            key = self.key_names[max_major_idx]
        else:
            mode = "minor"
            key = self.key_names[max_minor_idx]

        # Calculate harmony complexity (variability in harmonic content)
        harmony_complexity = np.std(chroma) / np.mean(chroma) if np.mean(chroma) > 0 else 0

        # Calculate tonal stability (consistency of tonal center)
        tonal_stability = 1.0 / (np.std(chroma_avg) + 0.001)  # Add small value to avoid division by zero

        # Calculate spectral brightness (center of mass of the spectrum)
        spectral_centroid = librosa.feature.spectral_centroid(y=y, sr=sr)[0]
        brightness = np.mean(spectral_centroid) / (sr/2)  # Normalize by Nyquist frequency

        # Calculate dissonance using spectral contrast
        spectral_contrast = librosa.feature.spectral_contrast(y=y, sr=sr)
        dissonance = np.mean(spectral_contrast[0])  # Higher values may indicate more dissonance

        return {
            "key": key,
            "mode": mode,
            "is_major": mode == "major",
            "harmony_complexity": float(harmony_complexity),
            "tonal_stability": float(tonal_stability),
            "brightness": float(brightness),
            "dissonance": float(dissonance)
        }

    def analyze_energy(self, y, sr):
        """Analyze energy characteristics of the audio"""
        # RMS Energy (overall loudness)
        rms = librosa.feature.rms(y=y)[0]

        # Energy metrics
        mean_energy = np.mean(rms)
        energy_std = np.std(rms)
        energy_dynamic_range = np.max(rms) - np.min(rms) if len(rms) > 0 else 0

        # Energy distribution across frequency ranges
        spec = np.abs(librosa.stft(y))

        # Divide the spectrum into low, mid, and high ranges
        freq_bins = spec.shape[0]
        low_freq_energy = np.mean(spec[:int(freq_bins*0.2), :])
        mid_freq_energy = np.mean(spec[int(freq_bins*0.2):int(freq_bins*0.8), :])
        high_freq_energy = np.mean(spec[int(freq_bins*0.8):, :])

        # Normalize to create a distribution
        total_energy = low_freq_energy + mid_freq_energy + high_freq_energy
        if total_energy > 0:
            low_freq_ratio = low_freq_energy / total_energy
            mid_freq_ratio = mid_freq_energy / total_energy
            high_freq_ratio = high_freq_energy / total_energy
        else:
            low_freq_ratio = mid_freq_ratio = high_freq_ratio = 1/3

        return {
            "mean_energy": float(mean_energy),
            "energy_std": float(energy_std),
            "energy_dynamic_range": float(energy_dynamic_range),
            "frequency_distribution": {
                "low_freq": float(low_freq_ratio),
                "mid_freq": float(mid_freq_ratio),
                "high_freq": float(high_freq_ratio)
            }
        }

    def analyze_emotion(self, rhythm_data, tonal_data, energy_data):
        """Classify the emotion based on musical features"""
        # Extract key features for emotion detection
        tempo = rhythm_data["tempo"]
        is_major = tonal_data["is_major"]
        energy = energy_data["mean_energy"]
        brightness = tonal_data["brightness"]

        # Calculate scores for each emotion
        emotion_scores = {}
        for emotion, profile in self.emotion_profiles.items():
            score = 0.0

            # Tempo contribution (0-1 score)
            tempo_range = profile["tempo"]
            if tempo_range[0] <= tempo <= tempo_range[1]:
                score += 1.0
            else:
                # Partial score based on distance
                distance = min(abs(tempo - tempo_range[0]), abs(tempo - tempo_range[1]))
                max_distance = 40  # Maximum distance to consider
                score += max(0, 1 - (distance / max_distance))

            # Energy contribution (0-1 score)
            energy_range = profile["energy"]
            if energy_range[0] <= energy <= energy_range[1]:
                score += 1.0
            else:
                # Partial score based on distance
                distance = min(abs(energy - energy_range[0]), abs(energy - energy_range[1]))
                max_distance = 0.5  # Maximum distance to consider
                score += max(0, 1 - (distance / max_distance))

            # Mode contribution (0-1 score)
            if profile["major_mode"] is not None:  # Some emotions don't have strong mode preference
                score += 1.0 if profile["major_mode"] == is_major else 0.0
            else:
                score += 0.5  # Neutral contribution

            # Brightness contribution (0-1 score)
            brightness_range = profile["brightness"]
            if brightness_range[0] <= brightness <= brightness_range[1]:
                score += 1.0
            else:
                # Partial score based on distance
                distance = min(abs(brightness - brightness_range[0]), abs(brightness - brightness_range[1]))
                max_distance = 0.5  # Maximum distance to consider
                score += max(0, 1 - (distance / max_distance))

            # Normalize score (0-1 range)
            emotion_scores[emotion] = score / 4.0

        # Find primary emotion
        primary_emotion = max(emotion_scores.items(), key=lambda x: x[1])

        # Calculate valence and arousal (dimensional emotion model)
        # Mapping different emotions to valence-arousal space
        valence_map = {
            'happy': 0.8, 'sad': 0.2, 'calm': 0.6,
            'energetic': 0.7, 'tense': 0.3, 'nostalgic': 0.5
        }

        arousal_map = {
            'happy': 0.7, 'sad': 0.3, 'calm': 0.2,
            'energetic': 0.9, 'tense': 0.8, 'nostalgic': 0.4
        }

        # Calculate weighted valence and arousal
        total_weight = sum(emotion_scores.values())
        if total_weight > 0:
            valence = sum(score * valence_map[emotion] for emotion, score in emotion_scores.items()) / total_weight
            arousal = sum(score * arousal_map[emotion] for emotion, score in emotion_scores.items()) / total_weight
        else:
            valence = 0.5
            arousal = 0.5

        return {
            "primary_emotion": primary_emotion[0],
            "confidence": primary_emotion[1],
            "emotion_scores": emotion_scores,
            "valence": float(valence),    # Pleasure dimension (0-1)
            "arousal": float(arousal)     # Activity dimension (0-1)
        }

    def analyze_theme(self, rhythm_data, tonal_data, emotion_data):
        """Infer potential themes based on musical features and emotion"""
        # Extract relevant features
        primary_emotion = emotion_data["primary_emotion"]
        harmony_complexity = tonal_data["harmony_complexity"]

        # Calculate theme scores
        theme_scores = {}
        for theme, profile in self.theme_profiles.items():
            score = 0.0

            # Emotion contribution
            if primary_emotion in profile["emotion"]:
                # Emotions listed earlier have stronger connection to the theme
                position_weight = 1.0 / (profile["emotion"].index(primary_emotion) + 1)
                score += position_weight

            # Secondary emotions contribution
            secondary_emotions = [e for e, s in emotion_data["emotion_scores"].items()
                                 if s > 0.5 and e != primary_emotion]
            for emotion in secondary_emotions:
                if emotion in profile["emotion"]:
                    score += 0.3  # Less weight than primary emotion

            # Harmony complexity contribution
            complexity_range = profile["harmony_complexity"]
            if complexity_range[0] <= harmony_complexity <= complexity_range[1]:
                score += 1.0
            else:
                # Partial score based on distance
                distance = min(abs(harmony_complexity - complexity_range[0]),
                              abs(harmony_complexity - complexity_range[1]))
                max_distance = 0.5  # Maximum distance to consider
                score += max(0, 1 - (distance / max_distance))

            # Normalize score
            theme_scores[theme] = min(1.0, score / 2.5)

        # Find primary theme
        primary_theme = max(theme_scores.items(), key=lambda x: x[1])

        # Find secondary themes (scores > 0.5)
        secondary_themes = [(theme, score) for theme, score in theme_scores.items()
                          if score > 0.5 and theme != primary_theme[0]]
        secondary_themes.sort(key=lambda x: x[1], reverse=True)

        return {
            "primary_theme": primary_theme[0],
            "confidence": primary_theme[1],
            "secondary_themes": [t[0] for t in secondary_themes[:2]],  # Top 2 secondary themes
            "theme_scores": theme_scores
        }

    def analyze_music(self, file_path):
        """Main function to perform comprehensive music analysis"""
        # Load the audio file
        y, sr = self.load_audio(file_path)
        if y is None:
            return {"error": "Failed to load audio file"}

        # Run all analyses
        rhythm_data = self.analyze_rhythm(y, sr)
        tonal_data = self.analyze_tonality(y, sr)
        energy_data = self.analyze_energy(y, sr)

        # Higher-level analyses that depend on the basic features
        emotion_data = self.analyze_emotion(rhythm_data, tonal_data, energy_data)
        theme_data = self.analyze_theme(rhythm_data, tonal_data, emotion_data)

        # Convert any remaining numpy values to native Python types
        def convert_numpy_to_python(obj):
            if isinstance(obj, dict):
                return {k: convert_numpy_to_python(v) for k, v in obj.items()}
            elif isinstance(obj, list):
                return [convert_numpy_to_python(item) for item in obj]
            elif isinstance(obj, np.ndarray):
                return obj.tolist()
            elif isinstance(obj, np.number):
                return float(obj)
            else:
                return obj

        # Ensure all numpy values are converted
        rhythm_data = convert_numpy_to_python(rhythm_data)
        tonal_data = convert_numpy_to_python(tonal_data)
        energy_data = convert_numpy_to_python(energy_data)
        emotion_data = convert_numpy_to_python(emotion_data)
        theme_data = convert_numpy_to_python(theme_data)

        # Combine all results
        return {
            "file": file_path,
            "rhythm_analysis": rhythm_data,
            "tonal_analysis": tonal_data,
            "energy_analysis": energy_data,
            "emotion_analysis": emotion_data,
            "theme_analysis": theme_data,
            "summary": {
                "tempo": float(rhythm_data["tempo"]),
                "time_signature": rhythm_data["estimated_time_signature"],
                "key": tonal_data["key"],
                "mode": tonal_data["mode"],
                "primary_emotion": emotion_data["primary_emotion"],
                "primary_theme": theme_data["primary_theme"]
            }
        }

    # def visualize_analysis(self, file_path):
    #     """Create visualizations for the music analysis results"""
    #     # Check if matplotlib is available
    #     if plt is None:
    #         print("Error: matplotlib is not installed. Visualization is not available.")
    #         return
    #     
    #     # Load audio and run analysis
    #     y, sr = self.load_audio(file_path)
    #     if y is None:
    #         print("Error: Failed to load audio file")
    #         return
    #
    #     results = self.analyze_music(file_path)
    #
    #     # Create visualization
    #     plt.figure(figsize=(15, 12))

    #     # Waveform
    #     plt.subplot(3, 2, 1)
    #     librosa.display.waveshow(y, sr=sr, alpha=0.6)
    #     plt.title(f'Waveform (Tempo: {results["rhythm_analysis"]["tempo"]:.1f} BPM)')

    #     # Spectrogram
    #     plt.subplot(3, 2, 2)
    #     D = librosa.amplitude_to_db(np.abs(librosa.stft(y)), ref=np.max)
    #     librosa.display.specshow(D, sr=sr, x_axis='time', y_axis='log')
    #     plt.colorbar(format='%+2.0f dB')
    #     plt.title(f'Spectrogram (Key: {results["tonal_analysis"]["key"]} {results["tonal_analysis"]["mode"]})')

    #     # Chromagram
    #     plt.subplot(3, 2, 3)
    #     chroma = librosa.feature.chroma_cqt(y=y, sr=sr)
    #     librosa.display.specshow(chroma, y_axis='chroma', x_axis='time')
    #     plt.colorbar()
    #     plt.title('Chromagram')

    #     # Onset strength and beats
    #     plt.subplot(3, 2, 4)
    #     onset_env = librosa.onset.onset_strength(y=y, sr=sr)
    #     times = librosa.times_like(onset_env, sr=sr)
    #     plt.plot(times, librosa.util.normalize(onset_env), label='Onset strength')
    #     plt.vlines(results["rhythm_analysis"]["beat_times"], 0, 1, alpha=0.5, color='r',
    #               linestyle='--', label='Beats')
    #     plt.legend()
    #     plt.title('Rhythm Analysis')

    #     # Emotion scores
    #     plt.subplot(3, 2, 5)
    #     emotions = list(results["emotion_analysis"]["emotion_scores"].keys())
    #     scores = list(results["emotion_analysis"]["emotion_scores"].values())
    #     plt.bar(emotions, scores, color='skyblue')
    #     plt.ylim(0, 1)
    #     plt.title(f'Emotion Analysis (Primary: {results["emotion_analysis"]["primary_emotion"]})')
    #     plt.xticks(rotation=45)

    #     # Theme scores
    #     plt.subplot(3, 2, 6)
    #     themes = list(results["theme_analysis"]["theme_scores"].keys())
    #     scores = list(results["theme_analysis"]["theme_scores"].values())
    #     plt.bar(themes, scores, color='lightgreen')
    #     plt.ylim(0, 1)
    #     plt.title(f'Theme Analysis (Primary: {results["theme_analysis"]["primary_theme"]})')
    #     plt.xticks(rotation=45)

    #     plt.tight_layout()
    #     plt.show()


# Create an instance of the analyzer
analyzer = MusicAnalyzer()

# The following code is for demonstration purposes only
# and will only run if executed directly (not when imported)
if __name__ == "__main__":
    # Replace this with a real audio file path when running as a script
    demo_file = "path/to/your/audio/file.mp3"
    
    # Analyze the uploaded audio file
    results = analyzer.analyze_music(demo_file)
    
    # Print analysis summary
    print("\n=== MUSIC ANALYSIS SUMMARY ===")
    print(f"Tempo: {results['summary']['tempo']:.1f} BPM")
    print(f"Time Signature: {results['summary']['time_signature']}")
    print(f"Key: {results['summary']['key']} {results['summary']['mode']}")
    print(f"Primary Emotion: {results['summary']['primary_emotion']}")
    print(f"Primary Theme: {results['summary']['primary_theme']}")
    
    # Show detailed results (optional)
    import json
    print("\n=== DETAILED ANALYSIS ===")
    print(json.dumps(results, indent=2))
    
    # Visualize the analysis
    # analyzer.visualize_analysis(demo_file)