Use recursion and gradient ascent to solve logistic regression in Python

This post was kindly contributed by DATA ANALYSIS - go there to comment and to read the full post.

In his book Machine Learning in Action, Peter Harrington provides a solution for parameter estimation of logistic regression . I use pandas and ggplot to realize a recursive alternative. Comparing with the iterative method, the recursion costs more space but may bring the improvement of performance.

# -*- coding: utf-8 -*-
"""
Use recursion and gradient ascent to solve logistic regression in Python
"""

import pandas as pd
from ggplot import *

def sigmoid(inX):
    return 1.0/(1+exp(-inX))

def grad_ascent(dataMatrix, labelMat, cycle):
    """
    A function to use gradient ascent to calculate the coefficients
    """
    if isinstance(cycle, int) == False or cycle < 0:
        raise ValueError("Must be a valid value for the number of iterations")
    m, n = shape(dataMatrix)
    alpha = 0.001
    if cycle == 0:
        return ones((n, 1))
    else:
        weights = grad_ascent(dataMatrix, labelMat, cycle-1)
        h = sigmoid(dataMatrix * weights)
        errors = (labelMat - h)
        return weights + alpha * dataMatrix.transpose()* errors

def plot(vector):
    """
    A funtion to use ggplot to visualize the result
    """
    x = arange(-3, 3, 0.1)
    y = (-vector[0]-vector[1]*x) / vector[2]
    new = pd.DataFrame()
    new['x'] = x
    new['y'] = array(y).flatten()
    infile.classlab = infile.classlab.astype(str)
    p = ggplot(aes(x='x', y='y', colour='classlab'), data=infile) + geom_point()
    return p + geom_line

# Use pandas to manipulate data
if __name__ == '__main__':
    infile = pd.read_csv("https://raw.githubusercontent.com/pbharrin/machinelearninginaction/master/Ch05/testSet.txt", sep='\t', header=None, names=['x', 'y', 'classlab'])
    infile['one'] = 1
    mat1 = mat(infile[['one', 'x', 'y']])
    mat2 = mat(infile['classlab']).transpose()
    result1 = grad_ascent(mat1, mat2, 500)
    print plot(result1)

This post was kindly contributed by DATA ANALYSIS - go there to comment and to read the full post.

Post navigation