import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
# 读取数据
data = pd.read_csv('data.csv')
X = data.iloc[:, :-1].values
y = data.iloc[:, 1].values
# 将数据集分为训练集和测试集
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
# 创建模型并进行训练
regressor = LinearRegression()
regressor.fit(X_train, y_train)
# 进行预测
y_pred = regressor.predict(X_test)
# 可视化预测结果
plt.scatter(X_train, y_train, color='red')
plt.plot(X_train, regressor.predict(X_train), color='blue')
plt.title('Salary vs Experience (Training set)')
plt.xlabel('Years of Experience')
plt.ylabel('Salary')
plt.show()