Created
April 25, 2014 00:53
-
-
Save MartinBodocky/11274564 to your computer and use it in GitHub Desktop.
First linear regression in Python
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
__author__ = 'martinbodocky' | |
from numpy import * | |
import matplotlib.pyplot as plt | |
import csv | |
def loadDataSet(filename): | |
"""Load CSV comma formatted file without header, | |
which contains features values and target value in last column | |
""" | |
with open(filename) as csvfile: | |
csvlines = csv.reader(csvfile, delimiter=',', quoting=csv.QUOTE_MINIMAL) | |
dataMat = [] | |
targetMat = [] | |
for row in csvlines: | |
numfeatures = len(row) - 1 | |
dataRow = [] | |
for num in row[:numfeatures]: | |
dataRow.append(float(num)) | |
dataMat.append(dataRow) | |
targetMat.append(float(row[-1])) | |
return dataMat, targetMat | |
def normalEquation(xArr, yArr): | |
""" | |
Functions applies normal equation for find optimal thetas | |
""" | |
xMat = mat(xArr) | |
yMat = mat(yArr).T | |
xTx = xMat.T * xMat | |
if linalg.det(xTx) == 0.0: | |
print "This matrix is singular, cannot do inverse" | |
return | |
ws = xTx.I * (xMat.T * yMat) | |
return ws | |
def showData(filename): | |
x, y = loadDataSet(filename) | |
xMat = mat(x) | |
yMat = mat(y) | |
#Basic scatter which displays data | |
fig = plt.figure() | |
ax = fig.add_subplot(111) | |
ax.scatter(xMat[:, 0].flatten().A[0], yMat.T[:, 0].flatten().A[0]) | |
plt.show() | |
def showDataWithRegression(filename): | |
x, y = loadDataSet(filename) | |
xMat = mat(x) | |
yMat = mat(y) | |
# Linear regression by use Normal Equation | |
theta = normalEquation(x, y) | |
#compute target values | |
fig = plt.figure() | |
ax = fig.add_subplot(111) | |
ax.scatter(xMat[:, 0].flatten().A[0], yMat.T[:, 0].flatten().A[0]) | |
xCopy = xMat.copy() | |
xCopy.sort(0) | |
yTarget = xCopy * theta | |
ax.plot(xCopy[:, 0], yTarget) | |
plt.show() | |
showData("Data/ex1data1.txt") | |
showDataWithRegression("Data/ex1data1.txt") | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment