correlation_analysis.py

import pandas as pd
import scipy.stats as stats
import matplotlib.pyplot as plt
import numpy as np
import os

def interpret_correlation(rho):
    abs_rho = abs(rho)
    if abs_rho < 0.20:
        return 'sangat lemah'
    elif abs_rho < 0.40:
        return 'lemah'
    elif abs_rho < 0.60:
        return 'sedang'
    elif abs_rho < 0.80:
        return 'kuat'
    else:
        return 'sangat kuat'

def run_correlation_analysis(csv_path: str):
    df = pd.read_csv(csv_path)
    
    results = []
    
    for layer in range(1, 13):
        col_name = f'Score L{layer}'
        
        # Dropna just in case
        valid_data = df.dropna(subset=[col_name, 'rating'])
        
        spearman_rho, spearman_p = stats.spearmanr(valid_data[col_name], valid_data['rating'])
        pearson_r, pearson_p = stats.pearsonr(valid_data[col_name], valid_data['rating'])
        
        interpretation = interpret_correlation(spearman_rho)
        
        results.append({
            'layer': col_name,
            'spearman_rho': spearman_rho,
            'spearman_p': spearman_p,
            'pearson_r': pearson_r,
            'pearson_p': pearson_p,
            'interpretasi_spearman': interpretation
        })
        
    df_results = pd.DataFrame(results)
    return df, df_results

def plot_correlation_bar(df_corr):
    fig, ax = plt.subplots(figsize=(10, 6))
    
    ax.bar(df_corr['layer'], df_corr['spearman_rho'])
    ax.set_title('Korelasi Spearman (rho) per Layer vs Rating Ustadz')
    ax.set_xlabel('Layer')
    ax.set_ylabel('Spearman rho')
    plt.xticks(rotation=45)
    
    fig.tight_layout()
    return fig

def plot_scatter_best_layer(df, best_layer):
    fig, ax = plt.subplots(figsize=(8, 6))
    
    valid_data = df.dropna(subset=[best_layer, 'rating'])
    x = valid_data[best_layer]
    y = valid_data['rating']
    
    ax.scatter(x, y, alpha=0.5, label='Data points')
    
    # Linear regression line
    m, b = np.polyfit(x, y, 1)
    ax.plot(x, m*x + b, label=f'Trend line')
    
    ax.set_title(f'Scatter Plot: {best_layer} vs Rating Ustadz')
    ax.set_xlabel(f'Skor Sistem ({best_layer})')
    ax.set_ylabel('Rating Ustadz')
    ax.legend()
    
    fig.tight_layout()
    return fig

def plot_heatmap(df_corr):
    fig, ax = plt.subplots(figsize=(10, 4))
    
    # Create a simple heatmap
    data = df_corr[['spearman_rho', 'pearson_r']].values.T
    cax = ax.imshow(data, aspect='auto')
    
    # Add values
    for i in range(data.shape[0]):
        for j in range(data.shape[1]):
            ax.text(j, i, f'{data[i, j]:.2f}', ha='center', va='center', color='black')
            
    ax.set_yticks([0, 1])
    ax.set_yticklabels(['Spearman rho', 'Pearson r'])
    ax.set_xticks(range(len(df_corr)))
    ax.set_xticklabels(df_corr['layer'], rotation=45)
    ax.set_title('Heatmap Korelasi')
    
    fig.colorbar(cax)
    fig.tight_layout()
    return fig

def plot_pairing_diagram(df):
    # Get unique participants and files 
    participants = df['ID_Peserta'].unique()[:1]
    files = df['ID_Frasa'].unique()

    # Sesuaikan ukuran agar tidak terlalu bertumpuk jika datanya banyak
    height = max(5, max(len(participants), len(files)) * 0.4)
    fig, ax = plt.subplots(figsize=(12, height))
    
    # Positions
    x_peserta = 1
    x_frasa = 2
    x_ref = 3
    
    # Draw nodes
    y_peserta = np.linspace(len(files), 1, len(files))
    y_frasa = np.linspace(len(files), 1, len(files))
    y_ref = np.linspace(len(files), 1, len(files))
    
    # Peserta nodes
    ax.scatter([x_peserta]*len(files), y_peserta, s=200, zorder=2)
    if len(participants) > 0:
        p_name = participants[0]
        for i, f in enumerate(files):
            ax.annotate(f"Peserta {p_name} (Rekaman {i+1})", (x_peserta - 0.1, y_peserta[i]), ha='right', va='center', fontsize=10)
        
    # Frasa nodes
    ax.scatter([x_frasa]*len(files), y_frasa, s=200, zorder=2)
    for i, f in enumerate(files):
        # f is filename, format slightly for display e.g. "01.wav" -> "Frasa 1"
        frasa_label = f"Frasa {i+1}"
        ax.annotate(frasa_label, (x_frasa, y_frasa[i] + 0.15), ha='center', va='bottom', fontsize=10)
        
    # Referensi nodes
    ax.scatter([x_ref]*len(files), y_ref, s=200, zorder=2)
    for i, f in enumerate(files):
        ax.annotate(f"Referensi {i+1}", (x_ref + 0.1, y_ref[i]), ha='left', va='center', fontsize=10)
        
    # Draw lines
    for j, _ in enumerate(files):
        # Peserta to Frasa
        ax.plot([x_peserta, x_frasa], [y_peserta[j], y_frasa[j]], zorder=1, alpha=0.5)
            
    for j, _ in enumerate(files):
        # Frasa to Referensi
        ax.plot([x_frasa, x_ref], [y_frasa[j], y_ref[j]], zorder=1, alpha=0.5)
        
    peserta_name = participants[0] if len(participants) > 0 else "Peserta"
    ax.set_title(f"Ilustrasi Struktur Dataset Pasangan Frasa", fontsize=14)
    ax.set_xlim(0.5, 3.5)
    ax.set_ylim(0, len(files) + 1)
    ax.axis('off')
    
    fig.tight_layout()
    return fig