实验二逻辑回归与算法实验

import pandas as pd
import matplotlib.pyplot as plt
path = 'D:/ex2data1.txt'
data = pd.read_csv(path, header=None, names=['score1', 'score2', 'result'])
data


import matplotlib.pyplot as plt
positive=Data[Data["Admitted"]==1]
negative=Data[Data["Admitted"]==0]
fig,ax=plt.subplots(figsize=(12,8))
ax.scatter(positive['Exam1'],positive['Exam2'],s=30,c='b',marker='o',label='Admitted')
ax.scatter(negative['Exam1'],negative['Exam2'],s=30,c='r',marker='x',label='Not Admitted')
ax.legend()
ax.set_xlabel('Exam1 Score')
ax.set_ylabel('Exam2 Score')


import numpy as np
def sigmoid(z):
return 1/(1+np.exp(-z))
nums=np.arange(-10,10,step=1)
fig,ax=plt.subplots(figsize=(12,8))
ax.plot(nums,sigmoid(nums),"r")


def model(x,theta):
return sigmoid(np.dot(x,theta.T))
def cost(theta,x,y):
theta = np.matrix(theta)
L1=np.multiply(-y,np.log(model(x,theta)))
L2=np.multiply(1-y,np.log(1-model(x,theta)))
return np.sum(L1-L2)/(len(x))
Data.insert(0, 'Ones', 1)
cols=Data.shape[1]
x=np.array(Data.iloc[:,0:cols-1])
y=np.array(Data.iloc[:,cols-1:cols])
theta=np.zeros(x.shape[1])
print(cost(theta,x,y))


def gradient(theta,x,y):
theta = np.matrix(theta) #要先把theta转化为矩阵
grad=np.dot(((model(x,theta)-y).T),x)/len(x)
return np.array(grad).flatten()#因为下面寻找最优化参数的函数（opt.fmin_tnc())要求传入的gradient函返回值需要是一维数组，
#因此需要利用flatten（）将grad进行转换以下
gradient(theta,x,y)


import scipy.optimize as opt
result = opt.fmin_tnc(func=cost, x0=theta, fprime=gradient, args=(X, y))
result


def predict(theta,x):
theta=np.matrix(theta)
temp=sigmoid(x*theta.T)
return [1 if x >= 0.5 else 0 for x in temp]
theta=result[0]
predictValues=predict(theta,x)
hypothesis=[1 if a==b else 0 for (a,b)in zip(predictValues,y)]
accuracy=hypothesis.count(1)/len(hypothesis)
print ('accuracy = {0}%'.format(accuracy*100))


import numpy as np
def find_x2(x1,theta):
return [(-theta[0]-theta[1]*x_1)/theta[2] for x_1 in x1]
x1 = np.linspace(30, 100, 1000)
x2=find_x2(x1,theta)
admittedData=data[data['result'].isin([1])]
noAdmittedData=data[data['result'].isin([0])]
fig,ax=plt.subplots(figsize=(12,8))
ax.scatter(admittedData['score1'],admittedData['score2'],marker='+',label='addmitted')
ax.scatter(noAdmittedData['score2'],noAdmittedData['score1'],marker='o',label="not addmitted")
ax.plot(x1,x2,color='r',label="decision boundary")
ax.legend(loc=1)
ax.set_xlabel('Exam1 score')
ax.set_ylabel('Exam2 score')
ax.set_title("Training data with decision boundary")
plt.show()


import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.datasets import load_iris
data = load_iris() # 得到数据特征
iris_target = data.target # 得到数据对应的标签
iris_features = pd.DataFrame(data=data.data, columns=data.feature_names) # 利用Pandas转化为DataFrame格式
# 合并标签和特征信息
iris_all = iris_features.copy() ## 进行浅拷贝，防止对于原始数据的修改
iris_all['target'] = iris_target
# 特征与标签组合的散点可视化
# 在2D情况下不同的特征组合对于不同类别的花的散点分布，以及大概的区分能力。
sns.pairplot(data=iris_all,diag_kind='hist', hue= 'target')
plt.savefig("iris.png")
plt.show()


from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(iris_features,iris_target,test_size=0.2,random_state=2020)
from sklearn.linear_model import LogisticRegression
clf=LogisticRegression(random_state=0,solver='lbfgs')
# 在训练集上训练逻辑回归模型
clf.fit(X_train,y_train)
print('the weight of Logistic Regression:\n',clf.coef_)
print('the intercept(w0) of Logistic Regression:\n',clf.intercept_)
train_predict=clf.predict(X_train)
test_predict=clf.predict(X_test)


from sklearn import metrics
#利用accuracy（准确度）【预测正确的样本数目占总预测样本数目的比例】评估模型效果
print('The accuracy of the Logistic Regression is:',metrics.accuracy_score(y_train,train_predict))
print('The accuracy of the Logistic Regression is:',metrics.accuracy_score(y_test,test_predict))
#查看混淆矩阵(预测值和真实值的各类情况统计矩阵)
confusion_matrix_result=metrics.confusion_matrix(y_test,test_predict)
print('The confusion matrix result:\n',confusion_matrix_result)
# 利用热力图对于结果进行可视化,画混淆矩阵
plt.figure(figsize=(8,6))
sns.heatmap(confusion_matrix_result,annot=True,cmap='Reds')
plt.xlabel('Predictedlabels')
plt.ylabel('Truelabels')
plt.show()