import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.calibration import CalibratedClassifierCV
from sklearn.metrics import (
    accuracy_score, f1_score, roc_auc_score,
    precision_recall_curve, classification_report
)
from sklearn.model_selection import train_test_split

if __name__ == '__main__':
    data = pd.read_csv('tr_user_tj.csv', header=0)
    data1 = data[['star_num', 'sign_num', 'coll_num', 'dna_num', 'task_num', 'word_num', 'balance_amt', 'earn_amt',
                  'season_point', 'point', 'star_score', 'term_amt', 'match_num']]

    # 分离特征和目标变量
    X = data1.drop('match_num', axis=1)
    y = data1['match_num']

    # 划分训练集和测试集
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

    # 创建随机森林分类器
    rf_classifier = RandomForestClassifier(n_estimators=100, random_state=42)

    # 训练模型
    rf_classifier.fit(X_train, y_train)

    # 预测
    y_pred = rf_classifier.predict(X_test)
    y_pred_proba = rf_classifier.predict_proba(X_test)[:, 1] if len(np.unique(y)) == 2 else rf_classifier.predict_proba(
        X_test)

    # 计算评估指标
    accuracy = accuracy_score(y_test, y_pred)
    f1 = f1_score(y_test, y_pred, average='weighted')

    print(f"Accuracy: {accuracy}")
    print(f"F1 Score: {f1}")
    print("\nClassification Report:")
    print(classification_report(y_test, y_pred))

    # 特征重要性
    feature_importance = pd.DataFrame({
        'feature': X.columns,
        'importance': rf_classifier.feature_importances_
    }).sort_values('importance', ascending=False)

    print("\nFeature Importance:")
    print(feature_importance)