逻辑回归解决鸢尾花问题

需要下载的第三方库有： matplotlib（用于可视化绘图），pandas（打开数据集），numpy（数组），sklearn（逻辑回归库）

直接上代码：

# Warning:the ownership of this code only belongs to Chen Yongyi
"""
    Author: Chen_Yong_Yi
    Data: 2021.10.22 21:29:45
"""
from sklearn.metrics import accuracy_score #准确率
import matplotlib.colors
import pandas as pd
pd.set_option('display.max_columns',None)
pd.set_option('display.max_rows',None)
pd.set_option('max_colwidth',200)
from pandas.plotting import parallel_coordinates
from matplotlib import pyplot as plt
import matplotlib as mpl
import numpy as np
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_iris
from sklearn import linear_model
import warnings
warnings.filterwarnings('ignore')
#提取数据集
IRIS = pd.read_csv('F:\MachineLearningCode\iris.data',header=None)

#将目标值进行参数化
IRIS.iloc[IRIS[4]=='Iris-setosa',4] = 0
IRIS.iloc[IRIS[4]=='Iris-versicolor',4] = 1
IRIS.iloc[IRIS[4]=='Iris-virginica',4] = 2
#将某种类型的花进行划分:分割数据集
iris_setosa_data = IRIS.loc[IRIS[4]==0]
Iris_ersicolor_data = IRIS.loc[IRIS[4]==1]
Iris_virginica_data = IRIS.loc[IRIS[4]==2]
#平行坐标可视化图
parallel_coordinates(IRIS,4)
plt.title('chenyongyi21181214291')
plt.legend(['Iris-setosa','Iris-versicolor','Iris-virginica'])
plt.show()
#提取训练值并进行画图(0列与2列作为训练值)
iris_setosa_data_lx = iris_setosa_data.iloc[:,[0]]
iris_setosa_data_ly =iris_setosa_data.iloc[:,[2]]
Iris_ersicolor_data_lx = Iris_ersicolor_data.iloc[:,[0]]
Iris_ersicolor_data_ly = Iris_ersicolor_data.iloc[:,[2]]
Iris_virginica_data_lx = Iris_virginica_data.iloc[:,[0]]
Iris_virginica_data_ly = Iris_virginica_data.iloc[:,[2]]
# print(Iris_virginica_data_ly)
plt.scatter(iris_setosa_data_lx,iris_setosa_data_ly,c='r',marker='o')

plt.scatter(Iris_ersicolor_data_lx,Iris_ersicolor_data_ly,c='black',marker='o')

plt.scatter(Iris_virginica_data_lx,Iris_virginica_data_ly,c='b',marker='o')
plt.legend(['Iris-setosa','Iris-versicolor','Iris-virginica'])
plt.xlabel('sepal length in cm')
plt.ylabel('petal length in cm')
plt.title('chenyongyi21181214291-iris_data')
plt.show()
#划分训练集与测试集
xtrain,xtest,ytrain,ytest = train_test_split(IRIS.iloc[:,[0,2]].astype('float64').values,IRIS.iloc[:,[4]].astype('float64').values,test_size=0.2,random_state=100)
#通过逻辑回归对训练集进行训练
yt = ytest.tolist()

log_res = linear_model.LogisticRegression(C=1)
log_res.fit(xtrain,ytrain)
acc = log_res.predict(xtest)
acc_x = []
for i in range(len(acc)):
    acc_x.append(acc[i])
print(f'测试集预测值为{acc_x}')

print(f'测试集实际值为{yt}')

print(f'逻辑回归模型在测试集中的准确率为{accuracy_score(acc_x,yt)}')
iris = load_iris()
X = iris.data[:,[0,2]]

x1min,x1max = X[:,0].min()-.5,X[:,0].max()+.5
x2min,x2max = X[:,1].min()-.5,X[:,1].max()+.5
h=.02
x1,x2=np.meshgrid(np.arange(x1min,x1max,h),np.arange(x2min,x2max,h))
gridtest = np.stack((x1.flat,x2.flat),axis=1)
gridhat = log_res.predict(gridtest)
gridhat = gridhat.reshape(x1.shape)
plt.figure(1,figsize=(6,5))
plt.pcolormesh(x1,x2,gridhat,cmap=plt.cm.Paired)
plt.scatter(X[:50,0],X[:50,1],c='r',marker='o',label = 'setosa')
plt.scatter(X[50:100,0],X[50:100,1],c='black',marker='o',label = 'versicolor')
plt.scatter(X[100:150,0],X[100:150,1],c='b',marker='o',label = 'virginica')
plt.xlabel('SL')
plt.ylabel('FW')
plt.legend(loc = 2)
plt.xlim(x1.min(),x1.max())
plt.ylim(x2.min(),x2.max())
plt.xticks(())
plt.yticks(())
plt.title('chenyongyi')
plt.show()