Create report_generator.py

report_generator.py

@@ -0,0 +1,306 @@
+import matplotlib.pyplot as plt
+import matplotlib.gridspec as gridspec
+import librosa.display
+import numpy as np
+
+
+def create_report(audio_data, output_path):
+    """
+    Create a complete forensic PNG report.
+    Synthetic detection is informational only.
+    """
+
+    plt.style.use("default")
+
+    fig = plt.figure(figsize=(22, 16))
+    fig.patch.set_facecolor("white")
+
+    fig.suptitle(
+        f"AUDIO FORENSIC ANALYSIS REPORT\n{audio_data['filename']}",
+        fontsize=20,
+        fontweight="bold",
+        y=0.97
+    )
+
+    gs = gridspec.GridSpec(
+        5, 4,
+        figure=fig,
+        hspace=0.45,
+        wspace=0.4,
+        height_ratios=[1.5, 1, 0.8, 0.9, 0.7],
+        left=0.05,
+        right=0.95,
+        top=0.92,
+        bottom=0.05
+    )
+
+    # ============================================================
+    # 1. SPECTROGRAM PANEL
+    # ============================================================
+
+    ax_spec = fig.add_subplot(gs[0, :])
+
+    S_db = audio_data["spectral"]["S_db"]
+    sr = audio_data["info"]["samplerate"]
+    hop = audio_data["spectral"]["hop_length"]
+
+    img = librosa.display.specshow(
+        S_db,
+        sr=sr,
+        hop_length=hop,
+        y_axis="hz",
+        x_axis="time",
+        cmap="viridis",
+        ax=ax_spec,
+        vmin=-80,
+        vmax=0
+    )
+
+    ax_spec.set_title("Spectrogram", fontsize=14, fontweight="bold", pad=10)
+    ax_spec.grid(True, alpha=0.3, linestyle="--")
+    cbar = plt.colorbar(img, ax=ax_spec, pad=0.01)
+    cbar.set_label("Magnitude (dB)", fontsize=10, fontweight="bold")
+
+    # ============================================================
+    # 2. FILE INFORMATION PANEL
+    # ============================================================
+
+    ax_info = fig.add_subplot(gs[1, 0:2])
+    ax_info.axis("off")
+
+    info = audio_data["info"]
+    t = audio_data["time_stats"]
+
+    lines = [
+        "FILE INFORMATION",
+        "─" * 50,
+        f"Sample Rate:     {info['samplerate']:,} Hz",
+        f"Channels:        {info['channels']}",
+        f"Duration:        {info['duration']:.2f} sec",
+        f"Format:          {info['format']} ({info['subtype']})",
+        f"Frames:          {info['frames']:,}",
+        "",
+        "TIME ANALYSIS",
+        "─" * 50,
+        f"Peak:            {t['peak_db']:.2f} dBFS ({t['peak']:.6f})",
+        f"RMS:             {t['rms_db']:.2f} dBFS ({t['rms']:.6f})",
+        f"Crest Factor:    {t['crest_factor_db']:.2f} dB",
+        f"Noise Floor:     {t['noise_floor']:.6f}",
+        f"Est. SNR:        {t['snr_db']:.1f} dB",
+        f"Zero Cross Rate: {t['zero_crossing_rate']:.4f}",
+    ]
+
+    if audio_data.get("lufs") is not None:
+        lines += [
+            "",
+            "LOUDNESS",
+            "─" * 50,
+            f"Integrated LUFS: {audio_data['lufs']:.2f}"
+        ]
+
+    ax_info.text(
+        0.05, 0.95,
+        "\n".join(lines),
+        fontsize=10.8,
+        va="top",
+        family="monospace",
+        bbox=dict(
+            boxstyle="round,pad=1",
+            facecolor="#E8F4F8",
+            edgecolor="#0077BE",
+            linewidth=2
+        )
+    )
+
+    # ============================================================
+    # 3. SPECTRAL STATS PANEL
+    # ============================================================
+
+    ax_specstats = fig.add_subplot(gs[1, 2:4])
+    ax_specstats.axis("off")
+
+    spec = audio_data["spectral"]
+    e = spec["energy_distribution"]
+
+    text = [
+        "SPECTRAL ANALYSIS",
+        "─" * 50,
+        f"Centroid:        {spec['spectral_centroid']:.1f} Hz",
+        f"Bandwidth:       {spec['spectral_bandwidth']:.1f} Hz",
+        f"Flatness:        {spec['spectral_flatness']:.4f}",
+        f"Rolloff Mean:    {spec['spectral_rolloff']:.1f} Hz",
+        "",
+        "ROLLOFF POINTS",
+        "─" * 50,
+        f"85% Energy:      {spec['rolloff_85pct']:.1f} Hz",
+        f"95% Energy:      {spec['rolloff_95pct']:.1f} Hz",
+        f"Highest -60 dB:  {spec['highest_freq_minus60db']:.1f} Hz",
+        "",
+        "ENERGY DISTRIBUTION",
+        "─" * 50,
+        f"< 100 Hz:        {e['below_100hz']:.2f}%",
+        f"100–500 Hz:      {e['100_500hz']:.2f}%",
+        f"500–2k Hz:       {e['500_2khz']:.2f}%",
+        f"2k–8k Hz:        {e['2k_8khz']:.2f}%",
+        f"8k–12k Hz:       {e['8k_12khz']:.2f}%",
+        f"12k–16k Hz:      {e['12k_16khz']:.2f}%",
+        f"> 16k Hz:        {e['above_16khz']:.2f}%",
+    ]
+
+    ax_specstats.text(
+        0.05, 0.95,
+        "\n".join(text),
+        fontsize=10.8,
+        va="top",
+        family="monospace",
+        bbox=dict(
+            boxstyle="round,pad=1",
+            facecolor="#FFF4E6",
+            edgecolor="#FF8C00",
+            linewidth=2
+        )
+    )
+
+    # ============================================================
+    # 4. ENERGY DISTRIBUTION BARS
+    # ============================================================
+
+    ax_bar = fig.add_subplot(gs[2, :])
+
+    bands = [
+        "<100Hz", "100–500Hz", "500–2kHz",
+        "2k–8kHz", "8k–12kHz", "12k–16kHz", ">16kHz"
+    ]
+
+    vals = [
+        e["below_100hz"], e["100_500hz"], e["500_2khz"],
+        e["2k_8khz"], e["8k_12khz"], e["12k_16khz"], e["above_16khz"]
+    ]
+
+    colors = ["#2C3E50", "#E74C3C", "#E67E22", "#F39C12", "#2ECC71", "#3498DB", "#9B59B6"]
+
+    bars = ax_bar.bar(bands, vals, color=colors, edgecolor="black", alpha=0.85)
+
+    ax_bar.set_ylabel("Energy (%)", fontsize=12, fontweight="bold")
+    ax_bar.grid(axis="y", alpha=0.35, linestyle="--")
+
+    for b, v in zip(bars, vals):
+        ax_bar.text(b.get_x() + b.get_width()/2, v + 0.3, f"{v:.2f}%", ha="center", fontsize=10)
+
+    # ============================================================
+    # 5. ISSUES PANEL
+    # ============================================================
+
+    ax_issues = fig.add_subplot(gs[3, 0:3])
+    ax_issues.axis("off")
+
+    issues = audio_data["issues"]
+
+    lines = ["DETECTED ISSUES", "═" * 80]
+
+    if not issues:
+        lines.append("✅ No significant issues detected.")
+    else:
+        icons = {
+            "CRITICAL": "🔴",
+            "HIGH": "🟠",
+            "MEDIUM": "🟡",
+            "LOW": "🟢"
+        }
+        for issue, sev, desc in issues:
+            lines.append(f"{icons.get(sev,'⚪')} [{sev}] {issue}")
+            lines.append(f"   → {desc}")
+
+    if spec["spectral_notches"]:
+        lines += [
+            "",
+            f"🎵 Spectral Notches: {len(spec['spectral_notches'])}",
+        ]
+        for i, n in enumerate(spec["spectral_notches"][:5], 1):
+            lines.append(f"  {i}. {n['freq']:.1f} Hz (Depth {n['depth_db']:.1f} dB)")
+
+    ax_issues.text(
+        0.05, 0.95,
+        "\n".join(lines),
+        fontsize=10.8,
+        va="top",
+        family="monospace",
+        bbox=dict(
+            boxstyle="round,pad=1.2",
+            facecolor="#FFE6E6",
+            edgecolor="#DC143C",
+            linewidth=2
+        )
+    )
+
+    # ============================================================
+    # 6. QUALITY SCORE PANEL + SYNTHETIC BLOCK
+    # ============================================================
+
+    ax_score = fig.add_subplot(gs[3, 3])
+    ax_score.axis("off")
+
+    s = audio_data["score"]
+    syn = audio_data["synthetic"]
+
+    score_lines = [
+        "QUALITY ASSESSMENT",
+        "═" * 28,
+        f"SCORE: {s['score']}/100",
+        f"GRADE: {s['grade']}",
+        f"QUALITY: {s['quality']}",
+        "",
+        "RECOMMENDATION:",
+        s["recommendation"],
+        "",
+        "CLEANLINESS SCORE:",
+        f"{s['cleanliness_score']}/100",
+        "",
+        "PROCESSING SEVERITY:",
+        f"{s['processing_severity']}",
+        "",
+        "ISSUE SUMMARY",
+        "─" * 28,
+        f"Critical: {s['critical']}",
+        f"High:     {s['high']}",
+        f"Medium:   {s['medium']}",
+        f"Low:      {s['low']}",
+    ]
+
+    # Add synthetic visual block (your Option 3)
+    score_lines += [
+        "",
+        "━━━━━━━━━━━━━━━━━━━━━━━",
+        "     SYNTHETIC VOICE",
+        "━━━━━━━━━━━━━━━━━━━━━━━",
+        f"Probability : {syn['synthetic_probability']:.2f}",
+        f"Label       : {syn['synthetic_label']}",
+        "━━━━━━━━━━━━━━━━━━━━━━━",
+        "",
+        f"Generated: {audio_data['timestamp']}"
+    ]
+
+    ax_score.text(
+        0.5, 0.5,
+        "\n".join(score_lines),
+        fontsize=11,
+        ha="center",
+        va="center",
+        family="monospace",
+        bbox=dict(
+            boxstyle="round,pad=1.4",
+            facecolor=s["color"],
+            edgecolor="black",
+            linewidth=3,
+            alpha=0.70
+        )
+    )
+
+    # ============================================================
+    # SAVE REPORT
+    # ============================================================
+
+    plt.savefig(output_path, dpi=300, bbox_inches="tight")
+    plt.close()
+
+    return output_path