python-Logistic回归实现鸢尾花分类

import numpy as np
import pandas as pd
import matplotlib as mpl
import matplotlib.pyplot as plt
from sklearn.datasets import data

pd.set_option("display.max_rows",None)
data = pd.read_csv(r"D:\Anaconda\ana\envs\python32\Lib\site-packages\sklearn\datasets\data\iris.csv")
data.drop_duplicates(inplace = True) #删除重复数据
#选取0和1进行二分类
data = data[data["species"] != 2]

class LogisticRegression:
    def __init__(self,alpha,times):
        self.alpha = alpha
        self.times = times

    def sigmoid(self,z):
        """ z为float类型 """
        return 1.0 / (1.0 + np.exp(-z))

    def fit(self,X,y):
        X = np.asarray(X)
        y = np.asarray(y)

        self.w_ = np.zeros(1 + X.shape[1])
        self.loss_ = []

        for i in range(self.times):
            z = np.dot(X,self.w_[1:]) + self.w_[0] #获得多项式输入z值
            p = self.sigmoid(z) #获得为1的概率值
            cost = -np.sum(y * np.log(p) + (1 - y) * np.log(1 - p))
            error = y - p
            self.loss_.append(cost)

            """ 调整权重值 """
            self.w_[0] += self.alpha * np.sum(error)
            self.w_[1:] += self.alpha * np.dot(X.T,error)

    def predict_pro(self,X):
        X = np.asarray(X)
        z = np.dot(X,self.w_[1:]) + self.w_[0]
        p = self.sigmoid(z)
        p = p.reshape(-1,1)
        return np.concatenate([1 - p,p],axis = 1)

    def predict(self,X):
        return np.argmax(self.predict_pro(X),axis = 1) #此时axis = 1为横向比较,返回数值较大的下标

data0 = data[data["species"] == 0]
data1 = data[data["species"] == 1]
data2 = data[data["species"] == 2]
data0 = data0.sample(len(data0),random_state = 0)
data1 = data1.sample(len(data1),random_state = 0)
data2 = data2.sample(len(data2),random_state = 0)

train_X = pd.concat([data1.iloc[:40,:-1],data0.iloc[:40,:-1]] , axis = 0)
train_y = pd.concat([data1.iloc[:40,-1],data0.iloc[:40,-1]] , axis = 0)

test_mix = pd.concat([data0.iloc[40:,:],data1.iloc[40:,:]],axis = 0)
test_mix = test_mix.sample(len(test_mix),random_state = 1)
test_X = test_mix.iloc[:,:-1]
test_y = test_mix.iloc[:,-1]

#训练
lr = LogisticRegression(0.01,20)
lr.fit(train_X,train_y)
result = lr.predict(test_X)

#输出准确率
accuracy = np.sum(result == test_y) / len(test_y)
print(accuracy)



"""
对于plot函数:
  I：ro:代表绘制红色圆圈
     ms:代表圆圈大小
  
    ro-:代表绘制红色实线
    ro--:代表绘制红色虚线
  
  II：
    在每个想要显示的图像前添加figure函数，再在后面添加show函数可以一次性展示多个函数

"""
mpl.rcParams["axes.unicode_minus"] = False
plt.figure(figsize = (15,15))
plt.plot(result,"ro",ms = 15,label = "predict")
plt.plot(test_y.values,"go",label = "real")
plt.title("Logistic Solve Classification",fontsize = 30)
plt.xlabel("Sample",fontsize = 20)
plt.ylabel("Sepices",fontsize = 20)
plt.legend(fontsize = 20)
plt.savefig(r"C:\Users\Y_ch\Desktop\Iris\Iris.png")
plt.show()

plt.figure(figsize = (15,15))
plt.plot(range(1,lr.times + 1),lr.loss_,"bo-")
plt.title("Loss Sigmoid Figure",fontsize = 30)
plt.ylabel("Loss",fontsize = 20)
plt.xlabel("Number of Training",fontsize = 20)
plt.savefig(r"C:\Users\Y_ch\Desktop\Iris\Iris_loss.png")
plt.show()