使用Python进行回归分析和最佳拟合直线

# Import the libraries
import numpy as np
import math
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

# Generate random data with numpy, and plot it with matplotlib:
ranstate = np.random.RandomState(1)
x = 10 * ranstate.rand(100)
y = 2 * x - 5 + ranstate.randn(100)
plt.scatter(x, y);
plt.show()

# Creating a linear regression model based on the positioning of the data and Intercepting, and predicting a Best Fit:
lr_model = LinearRegression(fit_intercept=True)
lr_model.fit(x[:70, np.newaxis], y[:70])
y_fit = lr_model.predict(x[70:, np.newaxis])

mse = mean_squared_error(y[70:], y_fit)
rmse = math.sqrt(mse)

print("Mean Square Error : ",mse)
print("Root Mean Square Error : ",rmse)

# Plot the estimated linear regression line using matplotlib:
plt.scatter(x, y)
plt.plot(x[70:], y_fit);
plt.show()

Mean Square Error : 1.0859922470998231 Root Mean Square Error : 1.0421095178050257