"""Visualization tools for data version comparisons."""

from pathlib import Path
from typing import Any, Dict, List

import matplotlib.pyplot as plt
import numpy as np


def plot_id_changes(comparison: Dict[str, Any], output_path: Path) -> None:
    """Create bar chart showing ID changes between versions.

    Args:
        comparison: Comparison results dictionary
        output_path: Path to save the plot
    """
    summary = comparison["summary"]
    id_changes = comparison["id_changes"]

    fig, ax = plt.subplots(figsize=(10, 6))

    categories = ["Added", "Removed", "Common"]
    counts = [
        id_changes["added_count"],
        id_changes["removed_count"],
        id_changes["common_count"],
    ]
    colors = ["#2ecc71", "#e74c3c", "#3498db"]

    bars = ax.bar(categories, counts, color=colors, alpha=0.7, edgecolor="black")

    # Add value labels on bars
    for bar in bars:
        height = bar.get_height()
        ax.text(
            bar.get_x() + bar.get_width() / 2.0,
            height,
            f"{int(height):,}",
            ha="center",
            va="bottom",
            fontsize=10,
            fontweight="bold",
        )

    ax.set_ylabel("Number of Records", fontsize=12)
    ax.set_title(
        f"ID Changes: {summary['old_version']} → {summary['new_version']}",
        fontsize=14,
        fontweight="bold",
    )
    ax.set_ylim(0, max(counts) * 1.15)
    ax.yaxis.set_major_formatter(plt.FuncFormatter(lambda x, p: f"{int(x):,}"))
    ax.grid(axis="y", alpha=0.3)

    plt.tight_layout()
    plt.savefig(output_path, dpi=150, bbox_inches="tight")
    plt.close()

    print(f"ID changes plot saved to {output_path}")


def plot_tag_changes(comparison: Dict[str, Any], output_path: Path) -> None:
    """Create bar chart showing top tag count changes.

    Args:
        comparison: Comparison results dictionary
        output_path: Path to save the plot
    """
    tag_changes = comparison["tag_changes"]
    top_movers = tag_changes.get("top_movers", {})

    if not top_movers:
        print("No tag changes to plot")
        return

    # Get top 15 movers by absolute change
    top_items = list(top_movers.items())[:15]
    tags = [item[0] for item in top_items]
    changes = [item[1]["change"] for item in top_items]

    # Color bars by positive/negative change
    colors = ["#2ecc71" if c > 0 else "#e74c3c" for c in changes]

    fig, ax = plt.subplots(figsize=(12, 8))

    y_pos = np.arange(len(tags))
    bars = ax.barh(y_pos, changes, color=colors, alpha=0.7, edgecolor="black")

    # Add value labels
    for i, (bar, change) in enumerate(zip(bars, changes)):
        width = bar.get_width()
        label_x = width + (max(abs(c) for c in changes) * 0.02)
        if width < 0:
            label_x = width - (max(abs(c) for c in changes) * 0.02)
            ha = "right"
        else:
            ha = "left"

        ax.text(
            label_x,
            i,
            f"{int(change):+,}",
            ha=ha,
            va="center",
            fontsize=9,
            fontweight="bold",
        )

    ax.set_yticks(y_pos)
    ax.set_yticklabels(tags, fontsize=9)
    ax.set_xlabel("Change in Count", fontsize=12)
    ax.set_title(
        f"Top Tag Count Changes: {comparison['summary']['old_version']} → {comparison['summary']['new_version']}",
        fontsize=14,
        fontweight="bold",
    )
    ax.axvline(x=0, color="black", linestyle="-", linewidth=0.8)
    ax.xaxis.set_major_formatter(plt.FuncFormatter(lambda x, p: f"{int(x):,}"))
    ax.grid(axis="x", alpha=0.3)

    plt.tight_layout()
    plt.savefig(output_path, dpi=150, bbox_inches="tight")
    plt.close()

    print(f"Tag changes plot saved to {output_path}")


def plot_quality_metrics(comparison: Dict[str, Any], output_path: Path) -> None:
    """Create grouped bar chart for quality metrics.

    Args:
        comparison: Comparison results dictionary
        output_path: Path to save the plot
    """
    quality = comparison["quality_metrics"]

    metrics = ["Duplicates", "Mismatch Rate\n(×10000)", "Path Anomalies", "Empty Texts"]
    old_values = [
        quality["duplicates"]["old"],
        quality["language_mismatch_rate"]["old"] * 10000,  # Scale for visibility
        quality["path_anomalies"]["old"],
        quality["empty_texts"]["old"],
    ]
    new_values = [
        quality["duplicates"]["new"],
        quality["language_mismatch_rate"]["new"] * 10000,
        quality["path_anomalies"]["new"],
        quality["empty_texts"]["new"],
    ]

    x = np.arange(len(metrics))
    width = 0.35

    fig, ax = plt.subplots(figsize=(12, 6))

    bars1 = ax.bar(
        x - width / 2,
        old_values,
        width,
        label=comparison["summary"]["old_version"],
        color="#3498db",
        alpha=0.7,
        edgecolor="black",
    )
    bars2 = ax.bar(
        x + width / 2,
        new_values,
        width,
        label=comparison["summary"]["new_version"],
        color="#e67e22",
        alpha=0.7,
        edgecolor="black",
    )

    # Add value labels
    for bars in [bars1, bars2]:
        for bar in bars:
            height = bar.get_height()
            if height > 0:
                ax.text(
                    bar.get_x() + bar.get_width() / 2.0,
                    height,
                    f"{height:,.0f}",
                    ha="center",
                    va="bottom",
                    fontsize=9,
                )

    ax.set_ylabel("Count / Rate", fontsize=12)
    ax.set_title(
        f"Quality Metrics Comparison: {comparison['summary']['old_version']} → {comparison['summary']['new_version']}",
        fontsize=14,
        fontweight="bold",
    )
    ax.set_xticks(x)
    ax.set_xticklabels(metrics, fontsize=10)
    ax.legend(fontsize=11)
    ax.grid(axis="y", alpha=0.3)

    plt.tight_layout()
    plt.savefig(output_path, dpi=150, bbox_inches="tight")
    plt.close()

    print(f"Quality metrics plot saved to {output_path}")


def plot_coverage_metrics(comparison: Dict[str, Any], output_path: Path) -> None:
    """Create grouped bar chart for coverage metrics.

    Args:
        comparison: Comparison results dictionary
        output_path: Path to save the plot
    """
    old_summary = comparison["old_summary"]
    new_summary = comparison["new_summary"]

    total_old = old_summary["total_records"]
    total_new = new_summary["total_records"]

    metrics = ["Tags", "Text", "Language", "Weight", "Stems"]
    old_pct = [
        (old_summary["records_with_tags"] / total_old * 100) if total_old > 0 else 0,
        (old_summary["records_with_text"] / total_old * 100) if total_old > 0 else 0,
        (old_summary["records_with_lang"] / total_old * 100) if total_old > 0 else 0,
        (old_summary["records_with_weight"] / total_old * 100) if total_old > 0 else 0,
        (old_summary["records_with_stems"] / total_old * 100) if total_old > 0 else 0,
    ]
    new_pct = [
        (new_summary["records_with_tags"] / total_new * 100) if total_new > 0 else 0,
        (new_summary["records_with_text"] / total_new * 100) if total_new > 0 else 0,
        (new_summary["records_with_lang"] / total_new * 100) if total_new > 0 else 0,
        (new_summary["records_with_weight"] / total_new * 100) if total_new > 0 else 0,
        (new_summary["records_with_stems"] / total_new * 100) if total_new > 0 else 0,
    ]

    x = np.arange(len(metrics))
    width = 0.35

    fig, ax = plt.subplots(figsize=(12, 6))

    bars1 = ax.bar(
        x - width / 2,
        old_pct,
        width,
        label=comparison["summary"]["old_version"],
        color="#9b59b6",
        alpha=0.7,
        edgecolor="black",
    )
    bars2 = ax.bar(
        x + width / 2,
        new_pct,
        width,
        label=comparison["summary"]["new_version"],
        color="#1abc9c",
        alpha=0.7,
        edgecolor="black",
    )

    # Add value labels
    for bars in [bars1, bars2]:
        for bar in bars:
            height = bar.get_height()
            ax.text(
                bar.get_x() + bar.get_width() / 2.0,
                height,
                f"{height:.1f}%",
                ha="center",
                va="bottom",
                fontsize=9,
            )

    ax.set_ylabel("Coverage (%)", fontsize=12)
    ax.set_title(
        f"Field Coverage Comparison: {comparison['summary']['old_version']} → {comparison['summary']['new_version']}",
        fontsize=14,
        fontweight="bold",
    )
    ax.set_xticks(x)
    ax.set_xticklabels(metrics, fontsize=10)
    ax.set_ylim(0, 105)
    ax.legend(fontsize=11)
    ax.grid(axis="y", alpha=0.3)

    plt.tight_layout()
    plt.savefig(output_path, dpi=150, bbox_inches="tight")
    plt.close()

    print(f"Coverage metrics plot saved to {output_path}")


def create_all_plots(comparison: Dict[str, Any], output_dir: Path) -> None:
    """Create all visualization plots for a comparison.

    Args:
        comparison: Comparison results dictionary
        output_dir: Directory to save plots
    """
    plots_dir = output_dir / "plots"
    plots_dir.mkdir(parents=True, exist_ok=True)

    print("\n" + "=" * 60)
    print("CREATING PLOTS")
    print("=" * 60)

    # ID changes plot
    plot_id_changes(comparison, plots_dir / "id_changes.png")

    # Tag changes plot
    plot_tag_changes(comparison, plots_dir / "tag_changes.png")

    # Quality metrics plot
    plot_quality_metrics(comparison, plots_dir / "quality_metrics.png")

    # Coverage metrics plot
    plot_coverage_metrics(comparison, plots_dir / "coverage_metrics.png")


def plot_overall_trends(all_comparisons: List[Dict[str, Any]], output_dir: Path) -> None:
    """Create line plots showing trends across all versions.

    Args:
        all_comparisons: List of comparison dictionaries
        output_dir: Directory to save plots
    """
    if not all_comparisons:
        print("No comparisons to plot")
        return

    plots_dir = output_dir / "plots"
    plots_dir.mkdir(parents=True, exist_ok=True)

    # Extract version labels and data
    versions = [all_comparisons[0]["summary"]["old_version"]]
    for comp in all_comparisons:
        versions.append(comp["summary"]["new_version"])

    total_records = [all_comparisons[0]["old_summary"]["total_records"]]
    for comp in all_comparisons:
        total_records.append(comp["new_summary"]["total_records"])

    duplicates = [all_comparisons[0]["quality_metrics"]["duplicates"]["old"]]
    for comp in all_comparisons:
        duplicates.append(comp["quality_metrics"]["duplicates"]["new"])

    mismatch_rates = [all_comparisons[0]["quality_metrics"]["language_mismatch_rate"]["old"]]
    for comp in all_comparisons:
        mismatch_rates.append(comp["quality_metrics"]["language_mismatch_rate"]["new"])

    # Plot 1: Dataset size trend
    fig, ax = plt.subplots(figsize=(12, 6))
    ax.plot(
        versions,
        [r / 1e6 for r in total_records],
        marker="o",
        linewidth=2,
        markersize=8,
        color="#3498db",
    )
    ax.set_ylabel("Total Records (Millions)", fontsize=12)
    ax.set_xlabel("Version", fontsize=12)
    ax.set_title("Dataset Size Trend Across Versions", fontsize=14, fontweight="bold")
    ax.grid(True, alpha=0.3)
    plt.xticks(rotation=45)
    plt.tight_layout()
    plt.savefig(plots_dir / "dataset_size_trend.png", dpi=150, bbox_inches="tight")
    plt.close()

    print(f"Dataset size trend plot saved to {plots_dir / 'dataset_size_trend.png'}")

    # Plot 2: Quality metrics trend
    fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(12, 10))

    # Duplicates
    ax1.plot(versions, duplicates, marker="o", linewidth=2, markersize=8, color="#e74c3c")
    ax1.set_ylabel("Duplicate IDs", fontsize=12)
    ax1.set_title("Quality Metrics Trends Across Versions", fontsize=14, fontweight="bold")
    ax1.grid(True, alpha=0.3)
    plt.setp(ax1.xaxis.get_majorticklabels(), rotation=45)

    # Mismatch rates
    ax2.plot(
        versions,
        [r * 100 for r in mismatch_rates],
        marker="s",
        linewidth=2,
        markersize=8,
        color="#f39c12",
    )
    ax2.set_ylabel("Language Mismatch Rate (%)", fontsize=12)
    ax2.set_xlabel("Version", fontsize=12)
    ax2.grid(True, alpha=0.3)
    plt.setp(ax2.xaxis.get_majorticklabels(), rotation=45)

    plt.tight_layout()
    plt.savefig(plots_dir / "quality_trends.png", dpi=150, bbox_inches="tight")
    plt.close()

    print(f"Quality trends plot saved to {plots_dir / 'quality_trends.png'}")