使用sklearn 模块¶
In [1]:
#-*- coding: utf-8 -*-
import numpy as np
from sklearn import linear_model
from matplotlib import pyplot as plt
from sklearn.preprocessing import StandardScaler #引入归一化的包
% matplotlib inline
In [2]:
print u"加载数据...\n"
data = np.loadtxt("../data/1-linear_regression/data.txt",delimiter=",",dtype=np.float64) #读取数据
X = np.array(data[:,0:-1],dtype=np.float64) # X对应0到倒数第2列
y = np.array(data[:,-1],dtype=np.float64) # y对应最后一列
plt.scatter(X[:,0],X[:,1])
# 归一化操作
scaler = StandardScaler()
scaler.fit(X)
x_train = scaler.transform(X)
x_test = scaler.transform(np.array([1650.0,3.0]).reshape(1,-1))
# 线性模型拟合
model = linear_model.LinearRegression()
model.fit(x_train, y)
加载数据...
Out[2]:
LinearRegression(copy_X=True, fit_intercept=True, n_jobs=1, normalize=False)
预测结果¶
In [3]:
#预测结果
result = model.predict(x_test)
print model.coef_ # Coefficient of the features 决策函数中的特征系数
print model.intercept_ # 又名bias偏置,若设置为False，则为0
print result # 预测结果
[ 109447.79646964 -6578.35485416] 340412.659574 [ 293081.4643349]