鸢尾花逻辑回归分类项目实施

详细代码

本项目最后一步需要用图形表示模型的分类效果，而数据集中有四个特征，维度较高，难以直接用图形表示。
因此在特征提取中提取花瓣长度和花瓣宽度这两个特征作为训练模型的特征属性。

​

import numpy as np

from sklearn.datasets import load_iris

from sklearn.model_selection import train_test_split

x,y = load_iris().data[:,2:4],load_iris().target

x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=50)

from sklearn.linear_model import LogisticRegression

from sklearn.metrics import accuracy_score

mymodel= LogisticRegression()
#print(x_train)

mymodel.fit(x_train,y_train)

LogisticRegression()

ac=accuracy_score(y_test,mymodel.predict(x_test))

print(ac)

0.96

import matplotlib.pyplot as plt

from matplotlib.colors import ListedColormap

N,M = 500,500

t1 = np.linspace(0,8,N)

t2 = np.linspace(0,3,M)

x1,x2 = np.meshgrid(t1,t2)

x_new= np.stack((x1.flat,x2.flat),axis=1)

y_predict=mymodel.predict(x_new)

y_hat=y_predict.reshape(x1.shape)

plt.rcParams['font.sans-serif']='Simhei'

iris_cmap=ListedColormap(["#ACC6C0","#FF8080","#A0A0FF"])
plt.pcolormesh(x1,x2,y_hat,cmap=iris_cmap)
plt.scatter(x[y==0,0],x[y==0,1],s=30,c='g',marker='^')
plt.scatter(x[y==1,0],x[y==1,1],s=30,c='r',marker='o')
plt.scatter(x[y==2,0],x[y==2,1],s=30,c='b',marker='s')
plt.xlabel('花瓣长度')
plt.ylabel('花瓣宽度')
plt.show()