Last active
May 22, 2018 08:09
-
-
Save yashhere/4f5b14192b2c968ea102c79116a14054 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
#!/usr/bin/python2.7 | |
spam=['free movie tickets','free watch offer','rolex watch discount'] | |
ham=['I watch movie','I am free'] | |
## function to calculate prior probability for SPAM ## | |
## how many SPAM seen out of all messages? ## | |
def get_prior_spam_probability(spam,ham): | |
return float(len(spam))/(len(spam)+len(ham)) | |
spam_prior=get_prior_spam_probability(spam,ham) | |
### define the function for calculating word frequencies ### | |
### input is a list of strings ### | |
def build_word_frequency(messages): | |
word_frequency={} | |
for message in messages: | |
message=message.replace('.','') #just stripoff dots in the message | |
tokens=message.split() | |
for token in tokens: | |
if token not in word_frequency: | |
word_frequency[token]=1 | |
else: | |
word_frequency[token]=word_frequency[token]+1 | |
return word_frequency | |
### build word fequencies ### | |
spam_map=build_word_frequency(spam) | |
ham_map=build_word_frequency(ham) | |
### function to calculate P(WORD|SPAM) and P(WORD|HAM) ### | |
def calculate_likelihoods(word,spam_frequency_map,ham_frequency_map,debug=True): | |
word_spam_frequency=0 | |
word_ham_frequency=0 | |
#count of total words in spam messages seen so far | |
total_spam_word_count = sum(spam_frequency_map.values()) | |
#count of total words in spam messages seen sofar | |
total_ham_word_count = sum(ham_frequency_map.values()) | |
## calculate vocabulary size for Laplace Smoothing; unique keys from both maps ## | |
vocabulary_size=len(set(spam_frequency_map.keys()+ham_frequency_map.keys())) | |
if word in spam_frequency_map: #if at all the word was used atleast once in a spam | |
word_spam_frequency=spam_frequency_map[word] | |
if word in ham_frequency_map: #if at all the word was used atleast once in a ham | |
word_ham_frequency=ham_frequency_map[word] | |
#calculate the probability of a word being spam using lapace smoothing so that # | |
# even if it is a new word, still some probability is there for it to be spam # | |
p_word_spam= (word_spam_frequency + 1.0)/ (total_spam_word_count + vocabulary_size) | |
p_word_ham= (word_ham_frequency + 1.0)/ (total_ham_word_count + vocabulary_size) | |
return p_word_spam,p_word_ham | |
## classify a text message using Naive Bayes formula | |
def classify_message(message,spam_prior=0.5,threshold=0.5): | |
posterior=0.0 | |
spam_likelihood=1.0 | |
ham_likelihood=1.0 | |
#convert to lower case and calculate total posterior probability | |
for word in message.lower().split(): | |
sl,hl=calculate_likelihoods(word,spam_map,ham_map) | |
spam_likelihood=spam_likelihood*sl | |
ham_likelihood=ham_likelihood*hl | |
posterior=spam_likelihood*spam_prior/((spam_likelihood*spam_prior)+(ham_likelihood*(1.0-spam_prior))) | |
if posterior>threshold: | |
return 'SPAM',posterior | |
return 'HAM',posterior | |
### test for a toy example | |
print classify_message('watch free movie',spam_prior) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment