主成分分析结合遗传算法优化的随机森林通用代码

import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor
from sklearn.metrics import accuracy_score, mean_squared_error, mean_absolute_error, r2_score
from sklearn.model_selection import train_test_split
from deap import base, creator, tools, algorithms
import numpy as np
from docx import Document
import matplotlib.pyplot as plt
import time

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

# 定义全局变量以便于调整和调试
DATA_SPLIT_RATIO = 0.2  # 数据划分比例（测试集占比）
DATA_SHUFFLE = True  # 是否进行数据洗牌
CROSS_VALIDATION = True  # 是否进行交叉验证
NGEN = 10  # 遗传算法迭代代数
POP_SIZE = 10  # 种群大小
MUTPB = 0.2  # 突变概率
CXPB = 0.5  # 交叉概率

def load_data():
    # 读取Excel数据
    data = pd.read_excel('附件1.xlsx')  # 替换为您的数据文件
    data = data.dropna()  # 清除缺失值
    return data

def pca_analysis(X):
    # 数据标准化
    scaler = StandardScaler()
    X_scaled = scaler.fit_transform(X)

    # 主成分分析（PCA）
    pca = PCA(n_components=min(X_scaled.shape))
    pca.fit(X_scaled)
    explained_variance = pca.explained_variance_
    explained_variance_ratio = pca.explained_variance_ratio_
    cumulative_variance = np.cumsum(explained_variance_ratio)

    # 总方差解释表格
    print("总方差解释表格：")
    print("成分\t特征根\t方差解释率(%)\t累积方差解释率(%)")
    for i in range(len(explained_variance)):
        print(f"{i + 1}\t{explained_variance[i]:.3f}\t{explained_variance_ratio[i] * 100:.3f}\t{cumulative_variance[i] * 100:.3f}")

    return X_scaled, pca

def ask_user_for_choices():
    print("\n请查看Excel数据的前几行：")
    data = load_data()
    print(data.head())

    preprocess = input("数据是否已完成预处理（数据清洗和标准化）？(是/否): ").strip().lower()
    if preprocess != '是':
        print("请先进行数据预处理。")
        return

    task_type = input("请选择任务类型（分类/回归）: ").strip().lower()
    target_column = input("请指定Excel中的因变量列名: ").strip()
    X = data.drop(columns=[target_column])
    y = data[target_column]

    if task_type == '分类':
        if not pd.api.types.is_numeric_dtype(y) or len(y.unique()) <= 2:
            model_class = RandomForestClassifier
            metrics_function = accuracy_score
        else:
            print("分类任务需要目标变量为类别标签。")