OvR逻辑回归多分类算法

OvR

在二分类逻辑回归的基础上，采用One vs Rest的方法进行多分类。最终分类由概率最高的OvR决定。在二分类实验中，会发现对versicolor的分类准确性和覆盖率很差，对virginica的分类也不是很理想，只有对setosa的分类很准。采用OvR综合决策后，分类准确率极大提升，正确率达到95%左右。

# Author: Daniel Geng
# In this code, let's change the method to Gradient descent. We start from single feature.
import csv
import numpy as np
import matplotlib.pyplot as pl
import random
import scipy.special


# Import Iris raw data
def ImportData(filePath):
    X = []  # 2D arrays [[1, x11, x12, ...], [], ...[]], each item is a [] which contains columns of each row
    Y = []  # 1D vector Stands for class
    f = open(filePath)
    r = csv.reader(f, delimiter=',')
    r.__next__()  # Skip header row
    for row in r:
        rowX = [1.0]
        for i in row[1:5]:
            rowX.append(float(i))
        X.append(rowX)
        Y.append(row[5])
    return (X, Y)


# Random the order of the raw data
def RandomShuffle(X, Y, flag):
    # random the order of raw data
    if flag == True:
        for i, j in zip(X, Y):
            i.append(j)
        random.shuffle(X)
        Y = []     # clear Y, get Y item from X
        for i in X:
            Y.append(i[-1])
            i.pop(-1)
    else:
        pass
    return (X, Y)


# Format to Numpy
def FormatNumpy(X):
    Xformat = np.array(X[:])  # change to numpy format
    return Xformat


# Refill classification, change string to 1 or 0
def RefillClass(Y, char_positive):
    tempY = []
    for i, e in enumerate(Y):
        if Y[i] == char_positive: