Python机器学习：逻辑回归006逻辑回归中添加多项式特征

import numpy as np
import matplotlib.pyplot as plt

生成数据并给数据分类。。第一次看到这个技巧

#生成数据
np.random.seed(666)
X = np.random.normal(0,1,size = (200,2))
y = np.array(X[:,0] ** 2 + X[:,1] ** 2 < 1.5, dtype='int')#给数据加上标签了。。

print(y)
plt.scatter(X[y==0,0],X[y==0,1],color = 'red')
plt.scatter(X[y==1,0],X[y==1,1])

[1 0 1 1 1 1 1 1 0 0 0 1 0 0 1 1 1 1 1 1 1 1 0 1 0 0 1 0 0 0 0 1 1 1 1 1 1
 0 1 1 1 1 1 1 0 0 1 0 1 0 1 0 1 1 0 0 1 1 0 1 0 1 0 0 0 1 0 1 0 0 1 1 0 0
 1 1 0 1 1 1 1 1 0 0 0 1 0 0 1 1 1 0 1 0 1 0 1 0 1 0 0 1 1 0 0 1 1 1 0 0 1
 0 0 1 1 1 1 0 1 1 0 1 1 0 0 0 1 1 0 1 1 0 1 1 1 0 1 1 0 1 1 1 0 1 1 0 0 1
 1 0 1 0 0 1 0 1 0 1 0 0 0 0 1 1 1 0 1 1 1 1 0 0 0 0 1 0 1 0 0 0 1 1 0 0 0
 1 1 1 0 1 1 0 1 1 1 0 0 1 0 1]

使用逻辑回归

#使用逻辑回归
from sklearn.linear_model import LogisticRegression
log_reg = LogisticRegression()
log_reg.fit(X,y)

log_reg.score(X,y)

0.605

绘制决策边界

#绘制决策边界
def plot_decision_boundary(model, axis):

    x0, x1 = np.meshgrid(
        np.linspace(axis[0], axis[1], int((axis[1]-axis[0])*100)).reshape(-1, 1),
        np.linspace(axis[2], axis[3], int((axis[3]-axis[2])*100)).reshape(-1, 1),
    )
    X_new = np.c_[x0.ravel(), x1.ravel()]

    y_predict = model.predict(X_new)
    zz = y_predict.reshape(x0.shape)

    from matplotlib.colors import ListedColormap
    custom_cmap = ListedColormap(['#EF9A9A','#FFF59D','#90CAF9'])

    plt.contourf(x0, x1, zz, linewidth=5, cmap=custom_cmap)

plot_decision_boundary(log_reg,axis=[-4,4,-4,4])
plt.scatter(X[y==0,0],X[y==0,1])
plt.scatter(X[y==1,0],X[y==1,1])

效果并不好~~~~~~~~~~~~~~

添加多项式使用多项式回归

#添加多项式项
#使用多项式回归
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import PolynomialFeatures
def PolynomialLogisticRegression(degree):
    return Pipeline([('poly',PolynomialFeatures(degree=degree)),
                     ('std_scaler',StandardScaler()),
                     ('logistic_reg',LogisticRegression())
                     ])

poly_log_reg = PolynomialLogisticRegression(degree=2)
poly_log_reg.fit(X,y)

plot_decision_boundary(poly_log_reg,axis=[-4,4,-4,4])
plt.scatter(X[y==0,0],X[y==0,1])
plt.scatter(X[y==1,0],X[y==1,1])

效果很好~~~~~~~~~~~~~~~~