python机器学习库keras——线性回归、逻辑回归、一般逻辑回归

全栈工程师开发手册 （作者：栾鹏）
python数据挖掘系列教程

线性回归

import numpy as np

from keras.models import Sequential
from keras.layers import Dense
import matplotlib.pyplot as plt

# 样本数据集，第一列为x，第二列为y，在x和y之间建立回归模型
data=[
    [0.067732,3.176513],[0.427810,3.816464],[0.995731,4.550095],[0.738336,4.256571],[0.981083,4.560815],
    [0.526171,3.929515],[0.378887,3.526170],[0.033859,3.156393],[0.132791,3.110301],[0.138306,3.149813],
    [0.247809,3.476346],[0.648270,4.119688],[0.731209,4.282233],[0.236833,3.486582],[0.969788,4.655492],
    [0.607492,3.965162],[0.358622,3.514900],[0.147846,3.125947],[0.637820,4.094115],[0.230372,3.476039],
    [0.070237,3.210610],[0.067154,3.190612],[0.925577,4.631504],[0.717733,4.295890],[0.015371,3.085028],
    [0.335070,3.448080],[0.040486,3.167440],[0.212575,3.364266],[0.617218,3.993482],[0.541196,3.891471]
]
#生成X和y矩阵
dataMat = np.array(data)
X = dataMat[:,0:1]   # 变量x
y = dataMat[:,1]   #变量y


# 构建神经网络模型
model = Sequential()
model.add(Dense(input_dim=1, units=1))

# 选定loss函数和优化器
model.compile(loss='mse', optimizer='sgd')

# 训练过程
print('Training -----------')
for step in range(501):
    cost = model.train_on_batch(X, y)
    if step % 50 == 0:
        print("After %d trainings, the cost: %f" % (step, cost))

# 测试过程
print('\nTesting ------------')
cost = model.evaluate(X, y, batch_size=40)
print('test cost:', cost)
W, b = model.layers[0].get_weights()
print('Weights=', W, '\nbiases=', b)

# 将训练结果绘出
Y_pred = model.predict(X)
plt.scatter(X, y)
plt.plot(X, Y_pred)
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-6WzZRTCL-1606145353083)(//img-blog.csdn.net/20180429081624774?watermark/2/text/Ly9ibG9nLmNzZG4ubmV0L2x1YW5wZW5nODI1NDg1Njk3/font/5a6L5L2T/fontsize/400/fill/I0JBQkFCMA==/dissolve/70/gravity/SouthEast)]

二分类逻辑回归

import numpy as np

from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
import matplotlib.pyplot as plt
from sklearn import datasets

# 样本数据集，两个特征列，两个分类二分类不需要onehot编码，直接将类别转换为0和1，分别代表正样本的概率。
X,y=datasets.make_classification(n_samples=200, n_features=2, n_informative=2, n_redundant=0,n_repeated=0, n_classes=2, n_clusters_per_class=1)

# 构建神经网络模型
model = Sequential()
model.add(Dense(input_dim=2, units=1))
model.add(Activation('sigmoid'))

# 选定loss函数和优化器
model.compile(loss='binary_crossentropy', optimizer='sgd')

# 训练过程
print('Training -----------')
for step in range(501):
    cost = model.train_on_batch(X, y)
    if step % 50 == 0:
        print("After %d trainings, the cost: %f" % (step, cost))

# 测试过程
print('\nTesting ------------')
cost = model.evaluate(X, y, batch_size=40)
print('test cost:', cost)
W, b = model.layers[0].get_weights()
print('Weights=', W, '\nbiases=', b)

# 将训练结果绘出
Y_pred = model.predict(X)
Y_pred = (Y_pred*2).astype('int')  # 将概率转化为类标号，概率在0-0.5时，转为0，概率在0.5-1时转为1
# 绘制散点图 参数：x横轴 y纵轴
plt.subplot(2,1,1).scatter(X[:,0], X[:,1], c=Y_pred)
plt.subplot(2,1,2).scatter(X[:,0], X[:,1], c=y)
plt.show()

多分类逻辑回归

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
import matplotlib.pyplot as plt
from keras.utils import np_utils
from sklearn import datasets


# 样本数据集，两个特征列，两个分类二分类不需要onehot编码，直接将类别转换为0和1，分别代表正样本的概率。
X,y=datasets.make_classification(n_samples=200, n_features=2, n_informative=2, n_redundant=0,n_repeated=0, n_classes=3, n_clusters_per_class=1)
n_class=3

# 转换为one_hot类型
y = np_utils.to_categorical(y, n_class) # 将2分类类标号转化为one-hot编码


# 构建神经网络模型
model = Sequential()
model.add(Dense(input_dim=2, units=n_class))
model.add(Activation('softmax'))

# 选定loss函数和优化器
model.compile(loss='categorical_crossentropy', optimizer='sgd')

# 训练过程
print('Training -----------')
for step in range(501):
    cost = model.train_on_batch(X, y)
    if step % 50 == 0:
        print("After %d trainings, the cost: %f" % (step, cost))

# 测试过程
print('\nTesting ------------')
cost = model.evaluate(X, y, batch_size=40)
print('test cost:', cost)
W, b = model.layers[0].get_weights()
print('Weights=', W, '\nbiases=', b)

# 将训练结果绘出
Y_pred = model.predict(X)
Y_pred = Y_pred.argmax(axis=1)   # 获取概率最大的分类，获取每行最大值所在的列
print('分类结果：\n',Y_pred)
# 绘制散点图 参数：x横轴 y纵轴
plt.subplot(2,1,1).scatter(X[:,0], X[:,1], c=Y_pred)
plt.subplot(2,1,2).scatter(X[:,0], X[:,1], c=y)
plt.show()