使用tensorflow自定義線性分類器預測 良/惡性腫瘤

import tensorflow as tf

import numpy as np

import pandas as pd

train = pd.read_csv('../Datasets/Breast-Cancer/breast-cancer-train.csv')

test = pd.read_csv('../Datasets/Breast-Cancer/breast-cancer-test.csv')

X_train = np.float32(train[['Clump Thickness','Cell Size']].T)

y_train = np.float32(train['Type'].T)

X_test = np.float32(test[['Clump Thickness','Cell Size']].T)

y_test = np.float32(test['Type'].T)

#定義一個tensorflow的變量b作爲線性模型的截距，同時設置初始值爲 1 0
b = tf.Variable(tf.zeros([1]))

#定義一個tensorflow的變量w作爲線性模型的參數，並設置初始值爲-1.0至1.0之間均勻分佈的隨機數

W = tf.Variable(tf.random_uniform([1,2],-1.0,1.0))


#顯示定義這個線性函數

y = tf.matmul(W,X_train)+b

#使用tensorflow中的reduce_mean 取得訓練集上均方誤差

loss = tf.reduce_mean(tf.square(y-y_train))

#使用梯度下降法估計參數W， b,並且設置迭代步長爲0.01，這個與Scikit-learn中的SGDRegressor類似D

optimizer = tf.train.GradientDescentOptimizer(0.01)


#以最小二乘損失爲優化目標

train = optimizer.minimize(loss)


#初始化所有變量
init = tf.initialize_all_variables()

#開啓tensorflow中的會話
sess = tf.Session()

sess.run(init)

#迭代1000輪次，訓練參數


for  step in range(0,1000):
      sess.run(train)
      if step % 200 == 0:
           print(step,sess.run(W),sess.run(b))



test_negative = test.loc[test['Type'] == 0][['Clump Thickness','Cell Size']] 

test_positive = test.loc[test['Type'] == 1][['Clump Thickness','Cell Size']]

#以最終的參數作圖
import matplotlib.pyplot as plot
plot.scatter(test_negative['Clump Thickness'],test_negative['Cell Size'],marker='o',s=200,c='red')

plot.scatter(test_positive['Clump Thickness'],test_positive['Cell Size'],marker='x',s=150,c='black')

plot.xlabel('Clump Thickness')
plot.ylabel('Cell Size')

lx = np.arange(0,12)


ly = (0.5-sess.run(b)-lx*sess.run(W)[0][0])/sess.run(W)[0][1]


plot.plot(lx,ly,color='green')

plot.show()

效果圖如下