def output(partId):
# Random Test Cases
x1 = np.sin(np.arange(1, 11))
x2 = np.cos(np.arange(1, 11))
ec = 'the quick brown fox jumped over the lazy dog'
wi = np.abs(np.round(x1 * 1863)).astype(int)
wi = np.concatenate([wi, wi])
if partId == '1':
sim = gaussianKernel(x1, x2, 2)
out = formatter('%0.5f ', sim)
elif partId == '2':
mat = scipy.io.loadmat('ex6data3.mat')
X = mat['X']
y = mat['y'].ravel()
Xval = mat['Xval']
yval = mat['yval'].ravel()
C, sigma = dataset3Params(X, y, Xval, yval)
out = formatter('%0.5f ', C)
out += formatter('%0.5f ', sigma)
elif partId == '3':
word_indices = processEmail(ec) + 1
out = formatter('%d ', word_indices)
elif partId == '4':
x = emailFeatures(wi)
out = formatter('%d ', x)
return out
from emailFeatures import emailFeatures
from getVocabList import getVocabList
## ==================== Part 1: Email Preprocessing ====================
# To use an SVM to classify emails into Spam v.s. Non-Spam, you first need
# to convert each email into a vector of features. In this part, you will
# implement the preprocessing steps for each email. You should
# complete the code in processEmail.m to produce a word indices vector
# for a given email.
print 'Preprocessing sample email (emailSample1.txt)'
# Extract Features
file = open('emailSample1.txt', 'r')
file_contents = file.readlines()
word_indices = processEmail(''.join(file_contents))
# Print Stats
print 'Word Indices: '
print word_indices
raw_input("Program paused. Press Enter to continue...")
## ==================== Part 2: Feature Extraction ====================
# Now, you will convert each email into a vector of features in R^n.
# You should complete the code in emailFeatures.m to produce a feature
# vector for a given email.
print 'Extracting features from sample email (emailSample1.txt)'
# Extract Features
from linearKernel import linearKernel
from svmPredict import svmPredict
## ==================== Part 1: Email Preprocessing ====================
# To use an SVM to classify emails into Spam v.s. Non-Spam, you first need
# to convert each email into a vector of features. In this part, you will
# implement the preprocessing steps for each email. You should
# complete the code in processEmail.m to produce a word indices vector
# for a given email.
print 'Preprocessing sample email (emailSample1.txt)'
# Extract Features
with open('emailSample1.txt') as f:
file_contents = f.read()
word_indices = processEmail(file_contents)
# Print Stats
print 'Word Indices:'
print word_indices
print
print 'Program paused. Press enter to continue.'
raw_input()
## ==================== Part 2: Feature Extraction ====================
# Now, you will convert each email into a vector of features in R^n.
# You should complete the code in emailFeatures.py to produce a feature
# vector for a given email.
print '\nExtracting features from sample email (emailSample1.txt)'
import numpy as np
import scipy.io as sio # Used to load the OCTAVE *.mat files
from sklearn import svm
from processEmail import processEmail, getVocabList
## ==================== Part 1: Email Preprocessing ====================
# To use an SVM to classify emails into Spam v.s. Non-Spam, you first need
# to convert each email into a vector of features. In this part, you will
# implement the preprocessing steps for each email. You should
# complete the code in processEmail.m to produce a word indices vector
# for a given email.
print("Preprocessing and extracting features sample email (emailSample1.txt)")
# Extract Features
with open('emailSample1.txt', 'r') as f:
features =processEmail(f.read())
print('length of vector = {}\nnum of non-zero = {}'
.format(len(features), int(features.sum())))
print(features.shape)
## =========== Part 2: Train Linear SVM for Spam Classification ========
# In this section, you will train a linear classifier to determine if an
# email is Spam or Not-Spam.
# Load the Spam Email dataset
# You will have X, y in your environment
mat = sio.loadmat('spamTrain.mat')
X, y = mat['X'], mat['y']
print("\nTraining Linear SVM (Spam Classification)")
from emailFeatures import emailFeatures
#2.1
email_contents = open("emailSample1.txt","r").read()
vocabList = open("vocab.txt","r").read()
#2.1.1
vocabList=vocabList.split("\n")[:-1]
vocabList_d={}
for ea in vocabList:
value,key = ea.split("\t")[:]
vocabList_d[key] = value
word_indices = processEmail(email_contents , vocabList_d)
#2.2
featureVector = emailFeatures(word_indices)
#print(np.sum(featureVector))
#2.3
spamTrainData = loadmat('spamTrain.mat')
#print(spamTrainData)
X = spamTrainData['X']
y = spamTrainData['y']
print('> ' ,spamTrainData)
import numpy as np
def emailFeatures(word_indices):
n = 1899
x = np.zeros((n, 1))
for word_indice in word_indices:
x[word_indice] = 1
return x.T
if __name__ == '__main__':
f = open('emailSample1.txt')
email_contents = f.read()
from processEmail import processEmail
word_indices = processEmail(email_contents)
print word_indices
print len(word_indices)
features = emailFeatures(word_indices)
print len(features)
print np.sum(features)
def extractFeature(mails):
return np.array([processEmail(mail, vocabList) for mail in mails])
#
# ==================== Part 1: Email Preprocessing ====================
# To use an SVM to classify emails into Spam v.s. Non-Spam, you first need
# to convert each email into a vector of features. In this part, you will
# implement the preprocessing steps for each email. You should
# complete the code in processEmail.m to produce a word indices vector
# for a given email.
ml_dir = '/Users/gregory/Desktop/me/coursera/machine_learning/ml_python/machine-learning-ex6/ex6/'
fname = ml_dir + 'emailSample1.txt'
with open(fname) as f:
file_contents = f.readlines()
# Extract Features
word_indices = processEmail(file_contents)
# Print Stats
print('Word Indices: \n')
print(word_indices)
# ==================== Part 2: Feature Extraction ====================
# Now, you will convert each email into a vector of features in R^n.
# You should complete the code in emailFeatures.m to produce a feature
# vector for a given email.
# Extract Features
#file_contents = readFile('emailSample1.txt');
#word_indices = processEmail(file_contents);
vocab_length = len(getVocabList())
def main() :
path = os.getcwd()
path = os.path.join(path,'dataSets')
# =============== Part 1 ====================
# To use an SVM to classify emails into Spam v.s. Non-Spam, we first need
# to convert each email into a vector of features. In this part, we
# implement the preprocessing steps for each email.
f = open(os.path.join(path,"emailSample1.txt"),'r')
email_contents = f.read()
f.close()
print(email_contents)
word_indices = processEmail.processEmail(email_contents)
features = emailFeatures(word_indices)
print('Word Indices :\n')
print(word_indices, "\n")
#============= Part 2 =======================
# Print Stats
print('Length of feature vector: %d\n' % len(features))
print('Number of non-zero entries: %d\n' % sum(features))
# ============= Part 3 ======================
# In this section, we will train a linear classifier to determine if an
# email is Spam or Not-Spam.
print('\n\nRunning SVM on training set...')
mat = io.loadmat(os.path.join(path,'spamTrain.mat'))
X = mat['X']
y = mat['y']
y = numpy.ravel(y)
model = svm.SVC(C = 0.1, kernel='linear')
model.fit(X, y)
p = model.predict(X)
accuracy = model.score(X, y)
accuracy *= 100.0
print('\nTraining Accuracy: %.2f' % accuracy)
#================ Part 4 ========================
# Xtest and ytest are the env. variables
mat = io.loadmat(os.path.join(path,'spamTest.mat'))
XTest = mat['Xtest']
yTest = mat['ytest']
yTest = numpy.ravel(yTest)
p = model.predict(XTest)
accuracy = model.score(XTest,yTest)
accuracy *= 100.0
print('\nTest Accuracy: %.2f' % accuracy)
#================ Part 5 ============================
# Since the model we are training is a linear SVM, we can inspect the
# weights learned by the model to understand better how it is determining
# whether an email is spam or not. The following code finds the words with
# the highest weights in the classifier. Informally, the classifier
# 'thinks' that these words are the most likely indicators of spam.
print('\nTop spam predictors (keywords) \n')
z = model.coef_
z = numpy.ravel(z)
vocabList = getVocabList.getVocabList()
dic = {}
for i in range(len(z)) :
dic[ vocabList[i] ] = z[i]
cnt = 0
for w in sorted(dic, key=dic.get, reverse=True):
if cnt == 15 :
break
cnt = cnt + 1
print('{0:10} - {1:10f}'.format(w, dic[w]))
print('\n\n')
# ============ Part 6: Test a sample Email =====================
# Now that we have trained the spam classifier, we can use it on our own
# emails!
# The following code reads in one of these emails and then uses our
# learned SVM classifier to determine whether the email is Spam or
# Not Spam
f = open(os.path.join(path, "spamSample1.txt"),'r')
email_contents = f.read()
f.close()
print('Sample Email : ')
print(email_contents)
word_indices = processEmail.processEmail(email_contents)
features = emailFeatures(word_indices)
X = emailFeatures(word_indices);
p = model.predict(X)
print('\nEmail Processed\n\nSpam Classification: %d\n' % p);
print('(1 indicates spam, 0 indicates not spam)\n\n');
from emailFeatures import emailFeatures
from getVocabList import getVocabList
## ==================== Part 1: Email Preprocessing ====================
# To use an SVM to classify emails into Spam v.s. Non-Spam, you first need
# to convert each email into a vector of features. In this part, you will
# implement the preprocessing steps for each email. You should
# complete the code in processEmail.m to produce a word indices vector
# for a given email.
print 'Preprocessing sample email (emailSample1.txt)'
# Extract Features
file = open('ex6/emailSample1.txt', 'r')
file_contents = file.readlines()
word_indices = processEmail(''.join(file_contents))
# Print Stats
print 'Word Indices: '
print word_indices
#raw_input("Program paused. Press Enter to continue...")
## ==================== Part 2: Feature Extraction ====================
# Now, you will convert each email into a vector of features in R^n.
# You should complete the code in emailFeatures.m to produce a feature
# vector for a given email.
print 'Extracting features from sample email (emailSample1.txt)'
# Extract Features
# Empty dictionary
vocabList_d={}
for element_of_list in vocabList:
value, key = element_of_list.split("\t")[:]
vocabList_d[key] = value
print(file_contents)
word_indices= processEmail.processEmail(file_contents,vocabList_d)
features = emailFeatures.emailFeatures(word_indices,vocabList_d)
print("Length of feature vector: ", len(features))
print("Number of non-zero entries: ", np.sum(features))
spam_mat = loadmat("Data/spamTrain.mat")
X_train =spam_mat["X"]
y_train = spam_mat["y"]
from processEmail import processEmail
file = open('data/spamSample2.txt', mode='r')
# read all lines at once
all_of_it = file.read()
processEmail(all_of_it)
def ex6_spam():
## Machine Learning Online Class
# Exercise 6 | Spam Classification with SVMs
#
# Instructions
# ------------
#
# This file contains code that helps you get started on the
# exercise. You will need to complete the following functions:
#
# gaussianKernel.m
# dataset3Params.m
# processEmail.m
# emailFeatures.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
## ==================== Part 1: Email Preprocessing ====================
# To use an SVM to classify emails into Spam v.s. Non-Spam, you first need
# to convert each email into a vector of features. In this part, you will
# implement the preprocessing steps for each email. You should
# complete the code in processEmail.m to produce a word indices vector
# for a given email.
print('\nPreprocessing sample email (emailSample1.txt)')
# Extract Features
file_contents = readFile('emailSample1.txt')
word_indices = processEmail(file_contents)
# Print Stats
print('Word Indices: ')
print(formatter(' %d', np.array(word_indices) + 1))
print('\n')
print('Program paused. Press enter to continue.')
#pause;
## ==================== Part 2: Feature Extraction ====================
# Now, you will convert each email into a vector of features in R^n.
# You should complete the code in emailFeatures.m to produce a feature
# vector for a given email.
print('\nExtracting features from sample email (emailSample1.txt)')
# Extract Features
file_contents = readFile('emailSample1.txt')
word_indices = processEmail(file_contents)
features = emailFeatures(word_indices)
# Print Stats
print('Length of feature vector: %d' % features.size)
print('Number of non-zero entries: %d' % np.sum(features > 0))
print('Program paused. Press enter to continue.')
#pause;
## =========== Part 3: Train Linear SVM for Spam Classification ========
# In this section, you will train a linear classifier to determine if an
# email is Spam or Not-Spam.
# Load the Spam Email dataset
# You will have X, y in your environment
mat = scipy.io.loadmat('spamTrain.mat')
X = mat['X'].astype(float)
y = mat['y'][:, 0]
print('\nTraining Linear SVM (Spam Classification)\n')
print('(this may take 1 to 2 minutes) ...\n')
C = 0.1
model = svmTrain(X, y, C, linearKernel)
p = svmPredict(model, X)
print('Training Accuracy: %f' % (np.mean(p == y) * 100))
## =================== Part 4: Test Spam Classification ================
# After training the classifier, we can evaluate it on a test set. We have
# included a test set in spamTest.mat
# Load the test dataset
# You will have Xtest, ytest in your environment
mat = scipy.io.loadmat('spamTest.mat')
Xtest = mat['Xtest'].astype(float)
ytest = mat['ytest'][:, 0]
print('\nEvaluating the trained Linear SVM on a test set ...\n')
p = svmPredict(model, Xtest)
print('Test Accuracy: %f\n' % (np.mean(p == ytest) * 100))
#pause;
## ================= Part 5: Top Predictors of Spam ====================
# Since the model we are training is a linear SVM, we can inspect the
# weights learned by the model to understand better how it is determining
# whether an email is spam or not. The following code finds the words with
# the highest weights in the classifier. Informally, the classifier
# 'thinks' that these words are the most likely indicators of spam.
#
# Sort the weights and obtin the vocabulary list
idx = np.argsort(model['w'])
top_idx = idx[-15:][::-1]
vocabList = getVocabList()
print('\nTop predictors of spam: ')
for word, w in zip(np.array(vocabList)[top_idx], model['w'][top_idx]):
print(' %-15s (%f)' % (word, w))
#end
print('\n')
print('\nProgram paused. Press enter to continue.')
#pause;
## =================== Part 6: Try Your Own Emails =====================
# Now that you've trained the spam classifier, you can use it on your own
# emails! In the starter code, we have included spamSample1.txt,
# spamSample2.txt, emailSample1.txt and emailSample2.txt as examples.
# The following code reads in one of these emails and then uses your
# learned SVM classifier to determine whether the email is Spam or
# Not Spam
# Set the file to be read in (change this to spamSample2.txt,
# emailSample1.txt or emailSample2.txt to see different predictions on
# different emails types). Try your own emails as well!
filename = 'spamSample1.txt'
# Read and predict
file_contents = readFile(filename)
word_indices = processEmail(file_contents)
x = emailFeatures(word_indices)
p = svmPredict(model, x.ravel())
print('\nProcessed %s\n\nSpam Classification: %d' % (filename, p))
print('(1 indicates spam, 0 indicates not spam)\n')
