Created
November 21, 2015 16:17
-
-
Save gbersac/a16c2191d58c20de03a9 to your computer and use it in GitHub Desktop.
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
# example from http://www.johnwittenauer.net/machine-learning-exercises-in-python-part-1/ | |
import numpy as np | |
import pandas as pd | |
import matplotlib.pyplot as plt | |
import os, sys | |
def computeCost(X, y, theta): | |
inner = np.power(((X * theta.T) - y), 2) | |
return np.sum(inner) / (2 * len(X)) | |
def gradientDescent(X, y, theta, alpha, iters): | |
temp = np.matrix(np.zeros(theta.shape)) | |
parameters = int(theta.ravel().shape[1]) | |
cost = np.zeros(iters) | |
for i in range(iters): | |
error = (X * theta.T) - y | |
for j in range(parameters): | |
term = np.multiply(error, X[:,j]) | |
temp[0,j] = theta[0,j] - ((alpha / len(X)) * np.sum(term)) | |
theta = temp | |
cost[i] = computeCost(X, y, theta) | |
return theta, cost | |
def scale(to_scale): | |
minimum = to_scale.min() | |
maximum = to_scale.max() | |
return (to_scale - minimum) / (maximum - minimum) | |
def unscale(to_scale, original): | |
minimum = original.min() | |
maximum = original.max() | |
return (to_scale * (maximum - minimum)) + minimum | |
# set path | |
path = os.getcwd() + '/' | |
if len(sys.argv) > 1: | |
path += sys.argv[1] | |
else: | |
path += 'example.csv' | |
# get data | |
data = pd.read_csv(path) | |
data.insert(0, 'Ones', 1) | |
# set X (training data) and y (target variable) | |
cols = data.shape[1] | |
X = data.iloc[:,cols-2] #population | |
y = data.iloc[:,cols-1:cols] #prices | |
X = np.matrix(X.values) | |
y = np.matrix(y.values) | |
X_original = X | |
y_original = y | |
X = scale(X) | |
y = scale(y) | |
ones = np.ones(shape = (X.shape[0] + 1, X.shape[1])) | |
ones[:-1,:] = X | |
X = ones | |
# variables for gradient descent | |
alpha = 0.01 | |
iters = 1000 | |
theta = np.matrix(np.array([0,0])) | |
# compute gradient descent | |
X = X.T | |
theta_result, cost = gradientDescent(X, y, theta, alpha, iters) | |
# theta_result = unscale(theta_result, y_original) | |
print "Theta: ", theta_result | |
print "Initial cost: ", computeCost(X, y, theta) | |
print "End cost: ", computeCost(X, y, theta_result) | |
# plotting data | |
x = np.linspace(data.Population.min(), data.Population.max(), 100) | |
f = theta_result[0, 0] + (theta_result[0, 1] * x) | |
fig, ax = plt.subplots(figsize = (12, 8)) | |
ax.plot(x, f, 'r', label = 'Prediction') | |
ax.scatter(data.Population, data.Profit, label = 'Traning Data') | |
ax.legend(loc = 2) | |
ax.set_xlabel('Population') | |
ax.set_ylabel('Profit') | |
ax.set_title('Predicted Profit vs. Population Size') | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment