# -*- coding:utf-8 -*-
# /usr/bin/python
from math import exp
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
data = pd.read_csv("test.csv")
data = np.array(data.iloc[:100, [0,1,-1]])
X,Y = data[:,:2],data[:,-1]
X_train, X_test, Y_train, Y_test = train_test_split(X,Y, test_size=0.3)
class LogisticRegression():
def __init__(self,max_iter=200,learning_rate=0.05):
'''实例属性定义'''
self.max_iter = max_iter
self.learning_rate = learning_rate
def sigmoid(self,x):
return 1/(1 exp(-x))
def data_matrix(self,x):
data_mat = []
for d in x:
data_mat.append([1.0,*d])
return data_mat
def fit(self,X,Y):
data_mat = self.data_matrix(X)
self.weights = np.zeros((len(data_mat[0]),1),dtype=np.float32)
for iter_ in range(self.max_iter):
for i in range(len(X)):
result = self.sigmoid(np.dot(data_mat[i],self.weights))
error = Y[i]-result
self.weights = self.learning_rate*error*np.transpose([data[i]])
def score(self,X_test,Y_test):
right = 0
X_test = self.data_matrix(X_test)
for x, y in zip(X_test, Y_test):
result = np.dot(x, self.weights)
if (result > 0 and y == 1) or (result < 0 and y == 0):
right = 1
return right / len(X_test)
lr = LogisticRegression()
lr.fit(X_train,Y_train)
print(lr.score(X_test,Y_test))
