classifier.train(document)
# We can now ask it questions about unknown e-mails:
print(classifier.classify("win money")) # False: most likely spam.
print(classifier.classify("fix bug")) # True: most likely a real message.
print()
# False: people don't talk like this on developer lists...
print(classifier.classify("customer"))
# True: because most likely everyone knows everyone.
print(classifier.classify("guys"))
print()
# To test the accuracy of a classifier,
# we typically use 10-fold cross validation.
# This means that 10 individual tests are performed,
# each with 90% of the corpus as training data and 10% as testing data.
from pattern.vector import k_fold_cv
print(k_fold_cv(NB, documents=m, folds=10))
# This yields 5 scores: (Accuracy, Precision, Recall, F-score, standard deviation).
# Accuracy in itself is not very useful,
# since some spam may have been regarded as real messages (false positives),
# and some real messages may have been regarded as spam (false negatives).
# Precision = how accurately false positives are discarded,
# Recall = how accurately false negatives are discarded.
# F-score = harmonic mean of precision and recall.
# stdev = folds' variation from average F-score.
# Each document has a type: True for actual e-mail, False for spam.
# This results in a "binary" classifier that either answers True or False
# for unknown documents.
classifier = NB()
for document in m:
classifier.train(document)
# We can now ask it questions about unknown e-mails:
print classifier.classify("win money") # False: most likely spam.
print classifier.classify("fix bug") # True: most likely a real message.
print
print classifier.classify("customer") # False: people don't talk like this on developer lists...
print classifier.classify("guys") # True: because most likely everyone knows everyone.
print
# To test the accuracy of a classifier,
# we typically use 10-fold cross validation.
# This means that 10 individual tests are performed,
# each with 90% of the corpus as training data and 10% as testing data.
from pattern.vector import k_fold_cv
print k_fold_cv(Bayes, documents=m, folds=10)
# This yields 4 scores: (Accuracy, Precision, Recall, F-score).
# Accuracy in itself is not very useful,
# since some spam may have been regarded as real messages (false positives),
# and some real messages may have been regarded as spam (false negatives).
# Precision = how accurately false positives are discarded,
# Recall = how accurately false negatives are discarded.
# F-score = harmonic mean of precision and recall.
# for unknown documents.
classifier = NB()
for document in m:
classifier.train(document)
# We can now ask it questions about unknown e-mails:
print classifier.classify("win money") # False: most likely spam.
print classifier.classify("fix bug") # True: most likely a real message.
print
print classifier.classify(
"customer") # False: people don't talk like this on developer lists...
print classifier.classify(
"guys") # True: because most likely everyone knows everyone.
print
# To test the accuracy of a classifier,
# we typically use 10-fold cross validation.
# This means that 10 individual tests are performed,
# each with 90% of the corpus as training data and 10% as testing data.
from pattern.vector import k_fold_cv
print k_fold_cv(Bayes, documents=m, folds=10)
# This yields 4 scores: (Accuracy, Precision, Recall, F-score).
# Accuracy in itself is not very useful,
# since some spam may have been regarded as real messages (false positives),
# and some real messages may have been regarded as spam (false negatives).
# Precision = how accurately false positives are discarded,
# Recall = how accurately false negatives are discarded.
# F-score = harmonic mean of precision and recall.
# This results in a "binary" classifier that either answers True or False
# for unknown documents.
classifier = NB()
for document in m:
classifier.train(document)
# We can now ask it questions about unknown e-mails:
print(classifier.classify("win money")) # False: most likely spam.
print(classifier.classify("fix bug")) # True: most likely a real message.
print()
print(classifier.classify("customer")) # False: people don't talk like this on developer lists...
print(classifier.classify("guys")) # True: because most likely everyone knows everyone.
print()
# To test the accuracy of a classifier,
# we typically use 10-fold cross validation.
# This means that 10 individual tests are performed,
# each with 90% of the corpus as training data and 10% as testing data.
from pattern.vector import k_fold_cv
print(k_fold_cv(NB, documents=m, folds=10))
# This yields 5 scores: (Accuracy, Precision, Recall, F-score, standard deviation).
# Accuracy in itself is not very useful,
# since some spam may have been regarded as real messages (false positives),
# and some real messages may have been regarded as spam (false negatives).
# Precision = how accurately false positives are discarded,
# Recall = how accurately false negatives are discarded.
# F-score = harmonic mean of precision and recall.
# stdev = folds' variation from average F-score.
# Each document has a type: True for real e-mail, False for spam.
# This results in a "binary" classifier that either answers True or False
# for unknown documents.
classifier = Bayes()
for document in corpus:
classifier.train(document)
# We can now ask it questions about unknown e-mails:
print classifier.classify("win money") # False: most likely spam.
print classifier.classify("fix bug") # True: most likely a real message.
print
print classifier.classify("customer") # False: people don't talk like this on developer lists...
print classifier.classify("guys") # True: because most likely everyone knows everyone.
print
# To test the accuracy of a classifier,
# we typically use 10-fold cross validation.
# This means that 10 individual tests are performed,
# each with 90% of the corpus as training data and 10% as testing data.
from pattern.vector import k_fold_cv
print k_fold_cv(Bayes, folds=10, documents=corpus)
# This yields 4 scores: Accuracy, Precision, Recall and F-score.
# Accuracy in itself is not very useful,
# since some spam may have been regarded as real messages (false positives),
# and some real messages may have been regarded as spam (false negatives).
# Precision = how accurate false positives are discarded,
# Recall = how accurate false negatives are discarded.