# Python快速实战机器学习(4) 逻辑回归

Python快速实战机器学习(1) 教材准备

Python快速实战机器学习(2) 数据预处理

1、认识sigmoid函数，了解其性质；

2、学会推导逻辑回归的损失函数以及梯度；

3、学会用sklearn应用逻辑回归进行分类任务。

sigmoid函数

import matplotlib.pyplot as plt
import numpy as np

def sigmoid(z):
return 1.0 / (1.0 + np.exp(-z))

z = np.arange(-7, 7, 0.1)
phi_z = sigmoid(z)

plt.plot(z, phi_z)
plt.axvline(0.0, color='k')
plt.ylim(-0.1, 1.1)
plt.xlabel('z')
plt.ylabel('$\phi (z)$')

# y axis ticks and gridline
plt.yticks([0.0, 0.5, 1.0])
ax = plt.gca()
ax.yaxis.grid(True)

plt.tight_layout()
# plt.savefig('./figures/sigmoid.png', dpi=300)
plt.show()

def cost_1(z):
return - np.log(sigmoid(z))

def cost_0(z):
return - np.log(1 - sigmoid(z))

z = np.arange(-10, 10, 0.1)
phi_z = sigmoid(z)

c1 = [cost_1(x) for x in z]
plt.plot(phi_z, c1, label='J(w) if y=1')

c0 = [cost_0(x) for x in z]
plt.plot(phi_z, c0, linestyle='--', label='J(w) if y=0')

plt.ylim(0.0, 5.1)
plt.xlim([0, 1])
plt.xlabel('$\phi$(z)')
plt.ylabel('J(w)')
plt.legend(loc='best')
plt.tight_layout()
# plt.savefig('./figures/log_cost.png', dpi=300)
plt.show()

from matplotlib.colors import ListedColormap
import matplotlib.pyplot as plt
import warnings

def versiontuple(v):
return tuple(map(int, (v.split("."))))

def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02):

# setup marker generator and color map
markers = ('s', 'x', 'o', '^', 'v')
colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
cmap = ListedColormap(colors[:len(np.unique(y))])

# plot the decision surface
x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution),
np.arange(x2_min, x2_max, resolution))
Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
Z = Z.reshape(xx1.shape)
plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)
plt.xlim(xx1.min(), xx1.max())
plt.ylim(xx2.min(), xx2.max())

for idx, cl in enumerate(np.unique(y)):
plt.scatter(x=X[y == cl, 0],
y=X[y == cl, 1],
alpha=0.6,
c=cmap(idx),
edgecolor='black',
marker=markers[idx],
label=cl)

# highlight test samples
if test_idx:
# plot all samples
if not versiontuple(np.__version__) >= versiontuple('1.9.0'):
X_test, y_test = X[list(test_idx), :], y[list(test_idx)]
else:
X_test, y_test = X[test_idx, :], y[test_idx]

plt.scatter(X_test[:, 0],
X_test[:, 1],
c='',
alpha=1.0,
edgecolor='black',
linewidths=1,
marker='o',
s=55, label='test set')
from sklearn import datasets
import numpy as np

X = iris.data[:, [2, 3]]
y = iris.target

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.3, random_state=0)

from sklearn.preprocessing import StandardScaler

sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)

X_combined_std = np.vstack((X_train_std, X_test_std))
y_combined = np.hstack((y_train, y_test))

from sklearn.linear_model import LogisticRegression

lr = LogisticRegression(C=1000.0, random_state=0)
lr.fit(X_train_std, y_train)

plot_decision_regions(X_combined_std, y_combined,
classifier=lr, test_idx=range(105, 150))
plt.xlabel('petal length [standardized]')
plt.ylabel('petal width [standardized]')
plt.legend(loc='upper left')
plt.tight_layout()
# plt.savefig('./figures/logistic_regression.png', dpi=300)
plt.show()

121 篇文章24 人订阅

0 条评论

15530

9430

16640

7920

15720

11030

9620

20320

10760

11640