def predict_email_spam(_filename):
_file_contents = open('../data/' + _filename).read()
_word_indices = process_email(_file_contents)
_features = email_features(_word_indices)
_p = Classification.predict(_features.T)
print('\nProcessed %s\n\nSpam Classification: %d\n' % (_filename, _p[0]))
print('(1 indicates spam, 0 indicates not spam)\n\n')
print('\nProcessed %s\n\nSpam Classification: %d\n' % (_filename, _p[0]))
print('(1 indicates spam, 0 indicates not spam)\n\n')
if __name__ == '__main__':
# ==================== 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)\n')
# Extract Features
file_contents = open('../data/emailSample1.txt').read()
word_indices = process_email(file_contents)
# Print Stats
print('Word Indices:\n')
print_index = 0
for print_value in word_indices:
print_index += 1
print("%4d" % print_value, end=' ')
if print_index % 10 == 0:
print('\n')
print('\n')
print('Program paused. Press enter to continue.\n')
# pause_func()
# ==================== 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
from processEmail import process_email
from vocabulary import map_words
# Pre-process email
words = process_email(
"<html>HELLO world pythoner! It's $100, how are \n you're \t doing? http://ya.ru</html>"
)
# For each word in the email find it's index in the vocabulary
words_indices = map_words(words)
# Train classifier
# todo
# Predict
# todo
# Analyze
# todo
def classify_email(filename):
x = email_features(process_email(read_file(filename), 'vocab.txt')).reshape(1, -1)
pred = model.predict(x)
print('\nProcessed {}\n\nSpam Classification: {}\n'.format(filename, pred))
print('(1 indicates spam, 0 indicates not spam)\n\n')
def pause():
input("")
"""## Part 1: Email Pre-processing
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 pre-processing steps for each email. You should
complete the code in processEmail.py to produce a word indices vector
for a given email."""
print('\nPre-processing sample email (emailSample1.txt)\n')
# Extract Features
file_contents = read_file('emailSample1.txt')
word_indices = process_email(file_contents, 'vocab.txt')
# Print Stats
print('Word Indices: \n')
print(word_indices)
print('\n\n')
print('Program paused. Press enter to continue.\n')
pause()
"""
## Part 2: Feature Extraction
Convert each email into a vector of features in R^n.
"""
print('\nExtracting features from sample email (emailSample1.txt)\n')
def classify_email(filename):
x = email_features(process_email(read_file(filename),
'vocab.txt')).reshape(1, -1)
pred = model.predict(x)
print('\nProcessed {}\n\nSpam Classification: {}\n'.format(filename, pred))
print('(1 indicates spam, 0 indicates not spam)\n\n')
def pause():
input("")
"""## Part 1: Email Pre-processing
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 pre-processing steps for each email. You should
complete the code in processEmail.py to produce a word indices vector
for a given email."""
print('\nPre-processing sample email (emailSample1.txt)\n')
# Extract Features
file_contents = read_file('emailSample1.txt')
word_indices = process_email(file_contents, 'vocab.txt')
# Print Stats
print('Word Indices: \n')
print(word_indices)
print('\n\n')
print('Program paused. Press enter to continue.\n')
pause()
"""
## Part 2: Feature Extraction
Convert each email into a vector of features in R^n.
"""
print('\nExtracting features from sample email (emailSample1.txt)\n')