11.30

import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, classification_report
from sklearn.preprocessing import KBinsDiscretizer
import matplotlib.pyplot as plt
from sklearn.metrics import ConfusionMatrixDisplay, confusion_matrix
import matplotlib as mpl

# 设置中文字体
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False

# 提供文件的绝对路径
file_path = r'D:\BP_R_Data.xlsx'  # 请替换为实际路径

# 尝试读取Excel文件
try:
    df = pd.read_excel(file_path, sheet_name='Sheet1', engine='openpyxl')

    # 假设最后一列为目标变量（混凝土抗压强度），其余为特征
    target_column = df.columns[-1]
    feature_columns = df.columns[:-1]

    # 将目标变量进行离散化处理，分为多个等级
    discretizer = KBinsDiscretizer(n_bins=5, encode='ordinal', strategy='uniform')
    y_discretized = discretizer.fit_transform(df[[target_column]]).astype(int).ravel()

    # 分离特征和目标变量
    X = df[feature_columns]
    y = y_discretized

    # 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)

    # 训练分类模型（这里使用随机森林分类器作为示例）
    model = RandomForestClassifier(n_estimators=100, random_state=42)
    model.fit(X_train, y_train)

    # 在测试集上进行预测
    y_pred = model.predict(X_test)

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

    # 打印评估指标，使用中文标签
    print(f"准确率 (Accuracy): {accuracy:.4f}")
    print(f"查准率 (Precision): {precision:.4f}")
    print(f"查全率 (Recall): {recall:.4f}")
    print(f"F1值 (F1 Score): {f1:.4f}")

    # 使用classification_report获得更详细的报告，并设置中文标签
    print("\n分类报告:")
    report = classification_report(y_test, y_pred, target_names=[f"等级{i}" for i in range(discretizer.n_bins)])
    print(report)

    # 生成混淆矩阵
    cm = confusion_matrix(y_test, y_pred)
    disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=[f"等级{i}" for i in range(discretizer.n_bins)])

    fig, ax = plt.subplots(figsize=(8, 6))
    disp.plot(ax=ax, cmap='Blues')
    plt.title('混凝土抗压强度等级的混淆矩阵')
    plt.xlabel('预测等级')
    plt.ylabel('真实等级')
    plt.show()

except FileNotFoundError:
    print(f"错误：无法找到文件，请检查路径是否正确：{file_path}")
except Exception as e:
    print(f"发生错误：{e}")