逻辑回归_线性

手写

import numpy as np
import matplotlib.pyplot as plt
from math import sqrt
from sklearn.linear_model import *
from sklearn.metrics import *
from sklearn import preprocessing
from numpy import genfromtxt
import random

def get_vertix(x_data,y_data):
    print ("get_vertix.\n")
    #******************类别为0********************
    x0=[]
    x1=[]
    #******************类别为1********************
    y0=[]
    y1=[]
    for i in range(len(y_data)):
        if y_data[i]==0:
            x0.append(x_data[i,0])
            x1.append(x_data[i,1])
        else:
            y0.append(x_data[i,0])
            y1.append(x_data[i,1]) 
    return [x0,x1],[y0,y1]
def draw_plot(x0,x1):
    #******************x0类别为0********************
    #******************x1类别为1********************
    print ("draw_plot.\n")
    scatter_0= plt.scatter(x0[0],x0[1],c='b',marker='o')
    scatter_1= plt.scatter(x1[0],x1[1],c='g',marker='x')
    plt.legend(handles=[scatter_0,scatter_1],labels=["l1","l2"],loc="best")
    #plt.show()
def sigmoid(x):
    return 1.0/(1+np.exp(-x))
def cost(x,y,ws):
    left  =  np.multiply(y,np.log(sigmoid(x*ws)))
    right =  np.multiply(1-y,np.log(1-sigmoid(x*ws)))
    return np.sum(left+right)/-(len(x))
def gradAscent(x,y,plot_=0):
    print (getattr(gradAscent,'__name__').center(20,"-"))
    if plot_ ==1:
        x = preprocessing.scale(x)
    x_=np.mat(x)
    y_=np.mat(y)
    lr=0.001
    epochs=10000
    cost_list=[]
    m,n =np.shape(x_)
    ws = np.mat(np.ones((n,1)))
    for i in range(epochs):
        h= sigmoid(x_*ws)
        ws_ =x_.T*(h-y_)/m
        ws = ws - lr*ws_
        if (i+1) % 50 == 0:
            cost_list.append(cost(x_,y_,ws))
    return ws,cost_list
        
        
def cost_draw(cost_list):
    print (len(cost_list))
    x = np.linspace(0,10000,200)
    plt.plot(x, cost_list, c='r')
    plt.title('Train')
    plt.xlabel('Epochs')
    plt.ylabel('Cost')
    plt.show()
    
def predict(x,ws,plot_):
    if plot_ ==1:
        x = preprocessing.scale(x)
    x_ = np.mat(x)
    ws = np.mat(ws)
    return [1 if x>=0.5 else 0 for x in sigmoid(x*ws)]
def main():
    data = genfromtxt("LR-testSet.csv",delimiter=",")
    x_data = data[:,:-1]
    y_data = data[:,-1]
    x_0,x_1 = get_vertix(x_data,y_data)
    #draw_plot(x_0,x_1)
    #plt.show()
    Y_data = data[:,-1,np.newaxis]
    print ("run".center(10,"-"))
    X_data =np.concatenate((np.ones((100,1)),x_data),axis=1)
    plot_= 0
    ws,cost_list = gradAscent( X_data,Y_data,plot_)
    if plot_ == 0 :
        draw_plot(x_0,x_1)
        x_test=[[-4],[3]]
        y_test=(-ws[0]-x_test*ws[1])/ws[2]
        plt.plot(x_test,y_test,"k")
        plt.show()
    cost_draw(cost_list)
    predict_ = predict(X_data,ws,plot_)
    print(classification_report(Y_data,predict_))
  
main()

plot_ = 0，未作归一化处理



plot_ = 1，进行归一化处理


明显看出，准确率有些许提高。

使用sklearn

import numpy as np
import matplotlib.pyplot as plt
from math import sqrt
from sklearn.linear_model import *
from sklearn.metrics import *
from sklearn import preprocessing
from numpy import genfromtxt
import random
from sklearn import *

def get_vertix(x_data,y_data):
    print ("get_vertix.\n")
    #******************类别为0********************
    x0=[]
    x1=[]
    #******************类别为1********************
    y0=[]
    y1=[]
    for i in range(len(y_data)):
        if y_data[i]==0:
            x0.append(x_data[i,0])
            x1.append(x_data[i,1])
        else:
            y0.append(x_data[i,0])
            y1.append(x_data[i,1]) 
    return [x0,x1],[y0,y1]
def draw_plot(x0,x1):
    #******************x0类别为0********************
    #******************x1类别为1********************
    print ("draw_plot.\n")
    scatter_0= plt.scatter(x0[0],x0[1],c='b',marker='o')
    scatter_1= plt.scatter(x1[0],x1[1],c='g',marker='x')
    plt.legend(handles=[scatter_0,scatter_1],labels=["l1","l2"],loc="best")
    #plt.show()

def main():
    plot_=0
    data = genfromtxt("LR-testSet.csv",delimiter=",")
    x_data = data[:,:-1]
    y_data = data[:,-1]
    x_0,x_1 = get_vertix(x_data,y_data)
    
    print ("run".center(10,"-"))
    logistic = linear_model.LogisticRegression()
    logistic.fit(x_data,y_data)
    print ("coef_:",logistic.coef_)
    print ("intercept_:",logistic.intercept_)
    if plot_ == 0 :
        draw_plot(x_0,x_1)
        x_test = np.matrix([[-4],[3]])
        y_test = (-logistic .intercept_ - x_test*logistic.coef_[0][0])/logistic.coef_[0][1]
        plt.plot(x_test,y_test,"k")
        plt.show()
    predictions = logistic.predict(x_data)
    print (classification_report(y_data,predictions))
    
main()

LR-testSet.csv(数据集)
-0.017612 14.053064 0
-1.395634 4.662541 1
-0.752157 6.53862 0
-1.322371 7.152853 0
0.423363 11.054677 0
0.406704 7.067335 1
0.667394 12.741452 0
-2.46015 6.866805 1
0.569411 9.548755 0
-0.026632 10.427743 0
0.850433 6.920334 1
1.347183 13.1755 0
1.176813 3.16702 1
-1.781871 9.097953 0
-0.566606 5.749003 1
0.931635 1.589505 1
-0.024205 6.151823 1
-0.036453 2.690988 1
-0.196949 0.444165 1
1.014459 5.754399 1
1.985298 3.230619 1
-1.693453 -0.55754 1
-0.576525 11.778922 0
-0.346811 -1.67873 1
-2.124484 2.672471 1
1.217916 9.597015 0
-0.733928 9.098687 0
-3.642001 -1.618087 1
0.315985 3.523953 1
1.416614 9.619232 0
-0.386323 3.989286 1
0.556921 8.294984 1
1.224863 11.58736 0
-1.347803 -2.406051 1
1.196604 4.951851 1
0.275221 9.543647 0
0.470575 9.332488 0
-1.889567 9.542662 0
-1.527893 12.150579 0
-1.185247 11.309318 0
-0.445678 3.297303 1
1.042222 6.105155 1
-0.618787 10.320986 0
1.152083 0.548467 1
0.828534 2.676045 1
-1.237728 10.549033 0
-0.683565 -2.166125 1
0.229456 5.921938 1
-0.959885 11.555336 0
0.492911 10.993324 0
0.184992 8.721488 0
-0.355715 10.325976 0
-0.397822 8.058397 0
0.824839 13.730343 0
1.507278 5.027866 1
0.099671 6.835839 1
-0.344008 10.717485 0
1.785928 7.718645 1
-0.918801 11.560217 0
-0.364009 4.7473 1
-0.841722 4.119083 1
0.490426 1.960539 1
-0.007194 9.075792 0
0.356107 12.447863 0
0.342578 12.281162 0
-0.810823 -1.466018 1
2.530777 6.476801 1
1.296683 11.607559 0
0.475487 12.040035 0
-0.783277 11.009725 0
0.074798 11.02365 0
-1.337472 0.468339 1
-0.102781 13.763651 0
-0.147324 2.874846 1
0.518389 9.887035 0
1.015399 7.571882 0
-1.658086 -0.027255 1
1.319944 2.171228 1
2.056216 5.019981 1
-0.851633 4.375691 1
-1.510047 6.061992 0
-1.076637 -3.181888 1
1.821096 10.28399 0
3.01015 8.401766 1
-1.099458 1.688274 1
-0.834872 -1.733869 1
-0.846637 3.849075 1
1.400102 12.628781 0
1.752842 5.468166 1
0.078557 0.059736 1
0.089392 -0.7153 1
1.825662 12.693808 0
0.197445 9.744638 0
0.126117 0.922311 1
-0.679797 1.22053 1
0.677983 2.556666 1
0.761349 10.693862 0
-2.168791 0.143632 1
1.38861 9.341997 0
0.317029 14.739025 0