Cousera Machine Learning week 3 assignment python代码（一）

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
'''plot'''
print('''Plotting data with red indicating (y = 1) examples and blue indicating (y = 0) examples.\n''');
with open ('..\\ex2data1.txt','r'):
    data = pd.read_csv('..\\ex2data1.txt',names=['score1','score2','status'])
colors = np.where(data.status==1,"red", "blue")
plt.scatter(data.score1,data.score2,s=200,marker='+',c=colors)
plt.scatter(data.score1,data.score2,s=20,marker='o',c=colors) 
plt.savefig('aa.png')  
plt.show()    
'''define X and y'''
X = data.loc[:, lambda df: ['score1', 'score2']]
y = data.loc[:, lambda df: ['status']]
'''define sigmoid funtion'''
[m,n]=X.shape
ones=pd.DataFrame(np.ones((m,1)))
X=np.matrix(ones.join(X))
initial_theta =np.matrix(pd.DataFrame(np.zeros((n + 1, 1))))
# Compute and display initial cost and gradient
def sigmoid(z): #z is an np.arrapy tuple.
    g = 1/(1+np.exp(-z))
    return(g)
def costFunction(theta,X,y): #Initialize some useful values
    m=np.size(y)
    J = 0
    grad = np.zeros(theta.shape)
    h = sigmoid(X*theta)
    J = (1/m) * np.sum((-1) * y*np.log(h)-(1- y)*np.log(1 - h))
    grad = (1/m) * ((np.matrix(h)-y).T*X).T
    return(J, grad)

print('training samples Nr.:',m)    
print('Cost at initial theta (zeros)',costFunction(initial_theta,X,y))
test_theta = np.matrix([-24, 0.2, 0.2]).T
print('Cost at test theta',costFunction(test_theta, X, y))

尝试python处理，感觉流畅和octave相比较，如果熟的话，用python比较好，编程风格更强。欢迎留言评论！

原题：

%% Machine Learning Online Class - Exercise 2: Logistic Regression
%
%  Instructions
%  ------------
% 
%  This file contains code that helps you get started on the logistic
%  regression exercise. You will need to complete the following functions 
%  in this exericse:
%
%     sigmoid.m
%     costFunction.m
%     predict.m
%     costFunctionReg.m
%
%  For this exercise, you will not need to change any code in this file,
%  or any other files other than those mentioned above.
%


%% Initialization
clear ; close all; clc


%% Load Data
%  The first two columns contains the exam scores and the third column
%  contains the label.


data = load('ex2data1.txt');
X = data(:, [1, 2]); y = data(:, 3);


%% ==================== Part 1: Plotting ====================
%  We start the exercise by first plotting the data to understand the 
%  the problem we are working with.


fprintf(['Plotting data with + indicating (y = 1) examples and o ' ...
         'indicating (y = 0) examples.\n']);


plotData(X, y);


% Put some labels 
hold on;
% Labels and Legend
xlabel('Exam 1 score')
ylabel('Exam 2 score')


% Specified in plot order
legend('Admitted', 'Not admitted')
hold off;


fprintf('\nProgram paused. Press enter to continue.\n');
pause;




%% ============ Part 2: Compute Cost and Gradient ============
%  In this part of the exercise, you will implement the cost and gradient
%  for logistic regression. You neeed to complete the code in 
%  costFunction.m


%  Setup the data matrix appropriately, and add ones for the intercept term
[m, n] = size(X);


% Add intercept term to x and X_test
X = [ones(m, 1) X];


% Initialize fitting parameters
initial_theta = zeros(n + 1, 1);


% Compute and display initial cost and gradient
[cost, grad] = costFunction(initial_theta, X, y);
fprintf('Cost at initial theta (zeros): %f\n', cost);


fprintf('Expected cost (approx): 0.693\n');
fprintf('Gradient at initial theta (zeros): \n');
fprintf(' %f \n', grad);
fprintf('Expected gradients (approx):\n -0.1000\n -12.0092\n -11.2628\n');


% Compute and display cost and gradient with non-zero theta
test_theta = [-24; 0.2; 0.2];
[cost, grad] = costFunction(test_theta, X, y);


fprintf('\nCost at test theta: %f\n', cost);
fprintf('Expected cost (approx): 0.218\n');
fprintf('Gradient at test theta: \n');
fprintf(' %f \n', grad);
fprintf('Expected gradients (approx):\n 0.043\n 2.566\n 2.647\n');


fprintf('\nProgram paused. Press enter to continue.\n');
pause;




%% ============= Part 3: Optimizing using fminunc  =============
%  In this exercise, you will use a built-in function (fminunc) to find the
%  optimal parameters theta.


%  Set options for fminunc
options = optimset('GradObj', 'on', 'MaxIter', 400);


%  Run fminunc to obtain the optimal theta
%  This function will return theta and the cost 
[theta, cost] = ...
fminunc(@(t)(costFunction(t, X, y)), initial_theta, options);


% Print theta to screen
fprintf('Cost at theta found by fminunc: %f\n', cost);
fprintf('Expected cost (approx): 0.203\n');
fprintf('theta: \n');
fprintf(' %f \n', theta);
fprintf('Expected theta (approx):\n');
fprintf(' -25.161\n 0.206\n 0.201\n');


% Plot Boundary
plotDecisionBoundary(theta, X, y);


% Put some labels 
hold on;
% Labels and Legend
xlabel('Exam 1 score')
ylabel('Exam 2 score')


% Specified in plot order
legend('Admitted', 'Not admitted')
hold off;


fprintf('\nProgram paused. Press enter to continue.\n');
pause;


%% ============== Part 4: Predict and Accuracies ==============
%  After learning the parameters, you'll like to use it to predict the outcomes
%  on unseen data. In this part, you will use the logistic regression model
%  to predict the probability that a student with score 45 on exam 1 and 
%  score 85 on exam 2 will be admitted.
%
%  Furthermore, you will compute the training and test set accuracies of 
%  our model.
%
%  Your task is to complete the code in predict.m


%  Predict probability for a student with score 45 on exam 1 
%  and score 85 on exam 2 


prob = sigmoid([1 45 85] * theta);
fprintf(['For a student with scores 45 and 85, we predict an admission ' ...
         'probability of %f\n'], prob);
fprintf('Expected value: 0.775 +/- 0.002\n\n');


% Compute accuracy on our training set
p = predict(theta, X);


fprintf('Train Accuracy: %f\n', mean(double(p == y)) * 100);
fprintf('Expected accuracy (approx): 89.0\n');
fprintf('\n');