import os

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestRegressor


def analyze_feature_importance(self):
    """分析特征重要性"""
    try:
        self._log_step("Analyzing feature importance...")

        if not (hasattr(self, 'data') and self.data is not None and len(self.data.columns) > 1):
            self._log_step("Not enough data for feature importance analysis", "warning")
            return None, "Not enough data for feature importance analysis", None

        X = self.data
        y = self.data.iloc[:, 0]  # 使用第一列作为目标变量

        model = RandomForestRegressor(n_estimators=50, random_state=42)  # 减少树的数量
        model.fit(X, y)

        feature_importance = pd.Series(model.feature_importances_, index=X.columns)
        feature_importance = feature_importance.sort_values(ascending=False)

        fi_df = feature_importance.reset_index()
        fi_df.columns = ['feature', 'importance']

        summary = f"Feature importance analysis completed, top feature: {fi_df.iloc[0]['feature']}"

        if not self.generate_plots:
            self._log_step("Feature importance analysis completed (data only)", "success")
            return None, summary, fi_df

        plt.figure(figsize=(8, 6))
        feature_importance.head(10).plot(kind='bar')
        plt.title('Feature Importance Analysis')
        plt.ylabel('Importance Score')
        plt.tight_layout()

        img_path = os.path.join(self.temp_dir.name, 'feature_importance.png')
        plt.savefig(img_path, dpi=150, bbox_inches='tight')
        plt.close()

        self._log_step("Feature importance analysis completed", "success")
        return img_path, summary, fi_df

    except Exception as e:
        self._log_step(f"Feature importance analysis failed: {e}", "error")
        return None, f"Feature importance analysis failed: {e}", None


def perform_var_analysis(self):
    """执行向量自回归分析"""
    try:
        self._log_step("Performing VAR analysis...")

        if not (hasattr(self, 'data') and self.data is not None and len(self.data.columns) > 1):
            self._log_step("Not enough data for VAR analysis", "warning")
            return None, "数据不足，无法进行VAR分析", None

        from statsmodels.tsa.api import VAR

        numeric_data = self.data.select_dtypes(include=[np.number])
        if len(numeric_data.columns) < 2:
            self._log_step("Not enough numeric columns for VAR analysis", "warning")
            return None, "数值变量不足，无法进行VAR分析", None

        var_data = numeric_data.iloc[:, : min(3, len(numeric_data.columns))]

        model = VAR(var_data)
        results = model.fit(maxlags=2, ic='aic')

        lag_order = results.k_ar
        forecast = results.forecast(var_data.values[-lag_order:], steps=10)

        forecast_df = pd.DataFrame(data=forecast, columns=[f"{col}_forecast" for col in var_data.columns])
        summary = f"VAR分析完成，使用滞后阶数: {results.k_ar}，生成了10期预测"

        if not self.generate_plots:
            self._log_step("VAR analysis completed (data only)", "success")
            return None, summary, forecast_df

        plt.figure(figsize=(12, 8))
        for i, col in enumerate(var_data.columns):
            plt.plot(range(len(var_data)), var_data[col].values, label=f'{col} (actual)', alpha=0.7)
            plt.plot(
                range(len(var_data), len(var_data) + 10),
                forecast[:, i],
                label=f'{col} (forecast)',
                linestyle='--',
            )

        plt.axvline(x=len(var_data), color='red', linestyle=':', alpha=0.7, label='Forecast Start')
        plt.xlabel('Time')
        plt.ylabel('Value')
        plt.title('Vector Autoregression (VAR) Forecast')
        plt.legend()
        plt.grid(True, alpha=0.3)
        plt.tight_layout()

        img_path = os.path.join(self.temp_dir.name, 'var_analysis.png')
        plt.savefig(img_path, dpi=150, bbox_inches='tight')
        plt.close()

        self._log_step("VAR analysis completed", "success")
        return img_path, summary, forecast_df

    except Exception as e:
        self._log_step(f"VAR analysis failed: {e}", "error")
        return None, f"VAR分析失败: {e}", None