逻辑斯蒂回归 Logistic Regression（LR）的python实现

LR有两种实现方式，IRLS和GradDes ，前者是基于Newton–Raphson algorithm更新参数的，后者是梯度下降。
代码在Github上

IRLS :

iteratively reweighted least squares, using Newton–Raphson algorithm to update.

realized according to PRML section 4.3.3
代码：

# -*- coding:utf-8 -*-  

import numpy as np
import matplotlib.pyplot as plt
import csv
from sklearn import preprocessing

def load_data(filename,add_one = True):
    file = open(filename)
    csv_file = csv.reader(file)
    temp = next(csv_file)
    n_samples = int(temp[0]); n_features = int(temp[1])
    add = 1
    if not add_one:
        add = 0
    datamat = np.empty((n_samples,n_features+add),dtype = np.float64)
    labelmat = np.empty((n_samples,),dtype = np.int)
    if add_one:
        datamat[:,0] = 1
    for i,line