import tkinter as tk from tkinter import filedialog import pandas as pd from sklearn.preprocessing import StandardScaler from sklearn.linear_model import LinearRegression from sklearn.model_selection import train_test_split from sklearn.metrics import r2_score

GUI界面

root = tk.Tk() root.title('数据预处理和模型训练') root.geometry('400x400')

文件选择函数

def select_file(): filepath = filedialog.askopenfilename() file_entry.delete(0, tk.END) file_entry.insert(0, filepath)

数据读取和预处理函数

def process_data(): # 读入数据集 filepath = file_entry.get() df = pd.read_csv(filepath)

# 数据清洗
df.dropna(inplace=True)

# 数据标准化
scaler = StandardScaler()
scaled_data = scaler.fit_transform(df)

# 输出预处理后的数据
output_text.delete('1.0', tk.END)
output_text.insert(tk.END, str(scaled_data))

# 将数据分为特征和标签
X = scaled_data[:, :-1]
y = scaled_data[:, -1]

# 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)

# 训练线性回归模型
model = LinearRegression()
model.fit(X_train, y_train)

# 在测试集上评估模型
y_pred = model.predict(X_test)
r2 = r2_score(y_test, y_pred)
result_text.delete('1.0', tk.END)
result_text.insert(tk.END, '模型评估结果：R2 Score = {:.4f}'.format(r2))

文件选择按钮和输入框

file_label = tk.Label(root, text='请选择数据文件：') file_label.pack() file_entry = tk.Entry(root, width=30) file_entry.pack() file_button = tk.Button(root, text='选择', command=select_file) file_button.pack()

数据处理按钮和输出框

process_button = tk.Button(root, text='处理数据', command=process_data) process_button.pack() output_label = tk.Label(root, text='预处理后的数据：') output_label.pack() output_text = tk.Text(root, width=50, height=10) output_text.pack()

模型训练和评估界面

result_label = tk.Label(root, text='模型训练和评估') result_label.pack() result_text = tk.Text(root, width=50, height=2) result_text.pack()

root.mainloop()