def __init__(self, path):
self.stemmer = PorterStemmer()
self.path = path
self.cur_idx = 0
self.batch = 2
self.sample = 0.001
self.vocab_size = 10000
self.total_count = 0
self.word_count = Counter()
self.word2idx = defaultdict(int)
self.idx2word = {}
self.word_sample = {}
self.batch_size = 128
self.embedding_size = 128 # Dimension of the embedding vector.
self.skip_window = 3 # How many words to consider left and right.
self.raw_sample_probs = [0.5, 0.3, 0.2]
self.sample_probs = []
sum = 0
for prob in self.raw_sample_probs:
sum += prob
self.sample_probs.append(sum)
self.num_skips = 2 # How many times to reuse an input to generate a label.
self.valid_size = 16 # Random set of words to evaluate similarity on.
self.valid_window = 100 # Only pick dev samples in the head of the distribution.
#self.valid_examples = np.random.choice(valid_window, valid_size, replace=False)
self.num_negative_sampled = 64 # Number of negative examples to sample.
self.batch_index = 0
self.get_stat()
def stemize(dictList): #STEMIZER FOR DICTIONARY porter = PorterStemmer() for dict in dictList: for token in dict.keys(): dict[porter.stem(token,0,len(token)-1)] = dict.pop(token) return dictList
def __init__(self,name,task_queue,result_queue):
self.name = name
self.r_stemmer = PorterStemmer()
self.queue = task_queue
self.queue2 = result_queue
#载入停词表
pre_worker.load_stopwords()
def tokenize(sText, pairing=False):
'''Given a string of text sText, returns a list of the individual stemmed tokens that
occur in that string (in order). This is my quick and dirty Tokenizer.
Satisfaction Not Guarenteed'''
import string
from stemmer import PorterStemmer
sText = sText.lower()
sText = re.sub("’", "'", sText)
sText = re.sub("&.{0,6};", " ", sText)
sText = re.sub("[\x80-\xff]", "", sText)
sText = sText.split(None)
for p in string.punctuation.replace("'", ""):
try:
sText = mapAndFold(lambda x: x.split(p), sText)
except TypeError: # empty string
return []
sText = mapAndFold(lambda x: x.split(), sText)
sText = map(lambda x: x.strip("\'"), sText)
sText = map(lambda x: x.strip("\""), sText)
sText = map(lambda x: x.strip("_"), sText)
sText = filter(lambda x: not re.match("\d+", x), sText)
sText = filter(lambda x: not x == "", sText)
sText = filter(lambda x: not x[0] == "@", sText)
stemmer = PorterStemmer()
if pairing:
#return original with token val in tuple
return [(w, stemmer.stem(w, 0, len(w) - 1)) for w in sText]
return [stemmer.stem(w, 0, len(w) - 1) for w in sText]
def ReadInfoFile(infoFile):
global text2pddl;
fin = open(infoFile)
lines = fin.readlines()
fin.close()
lines = [ line.strip() for line in lines ];
unitDict = {}
p = PorterStemmer()
for line in lines:
if len(line)==0: continue;
parts = line.split(':');
textName = parts[0];
words = [ p.stem(w.lower(),0,len(w)-1) for w in textName.split() ]
textName = ' '.join(words);
if len(parts)>1:
pddlName = parts[1];
else:
pddlName = parts[0];
assert(pddlName!='');
assert(textName!='');
for word in words:
unitDict[word] = True
#print unitDict.keys()
return unitDict
def stemizeQuery(query): # STEMIZER FOR QUERY porter = PorterStemmer() newList = [] for q in query: newList.append(porter.stem(q,0,len(q)-1)) return newList
def tokenize(sText, pairing = False):
'''Given a string of text sText, returns a list of the individual stemmed tokens that
occur in that string (in order). This is my quick and dirty Tokenizer.
Satisfaction Not Guarenteed'''
import string
from stemmer import PorterStemmer
sText = sText.lower()
sText = re.sub("’", "'", sText)
sText = re.sub("&.{0,6};", " ", sText)
sText = re.sub("[\x80-\xff]", "", sText)
sText = sText.split(None)
for p in string.punctuation.replace("'", ""):
try:
sText = mapAndFold(lambda x: x.split(p), sText)
except TypeError: # empty string
return []
sText = mapAndFold(lambda x: x.split(), sText)
sText = map(lambda x: x.strip("\'"), sText)
sText = map(lambda x: x.strip("\""), sText)
sText = map(lambda x: x.strip("_"), sText)
sText = filter(lambda x: not re.match("\d+", x), sText)
sText = filter(lambda x: not x == "", sText)
sText = filter(lambda x: not x[0] == "@", sText)
stemmer = PorterStemmer()
if pairing:
#return original with token val in tuple
return [(w,stemmer.stem(w, 0, len(w)-1)) for w in sText]
return [stemmer.stem(w, 0, len(w)-1) for w in sText]
def stemWords(listTokens): s = PorterStemmer() stemmedTerms = [] for x in listTokens: stemmedTerms.append(s.stem(x, 0, len(x) - 1)) return stemmedTerms
def stemWords(inList):
outList = []
ps = PorterStemmer()
for token in inList:
stemmed_token = ps.stem(token, 0, len(token) - 1)
outList.append(stemmed_token)
return outList
def stem_phrase(phrase):
words = phrase.lower().replace('.', '').replace("'", '').split()
# ignore stop words
words = [word for word in words if not word in STOP_WORDS]
p = PorterStemmer()
return [p.stem(word, 0, len(word)-1) for word in words]
def stemWords(tokens):
"""Function that stems the words. """
# use porter stemmer
# https://tartarus.org/martin/PorterStemmer/python.txt
p = PorterStemmer()
for index, word in enumerate(tokens):
tokens[index] = p.stem(word, 0, len(word) - 1)
return tokens
def stem(word):
# word needs to be all lowercase before being passed to stem
string.lower(word)
# fancy stuff to remove .,?!"
mymatch = re.compile('(\,|\.|\!|\?|\")')
word = mymatch.sub(r'',word)
p = PorterStemmer()
word = p.stem(word, 0,len(word)-1)
return word
def splitToken(token,isStem=True):
toks = token.split('_')
word = toks[0].lower()
tag = toks[1]
if not word.isalnum():
tag = 'PUNC'
if isStem:
# simple post stem
p = PorterStemmer()
#word = p.stem1(word,0,len(word)-1)
word = p.stem(word,0,len(word)-1)
return (word, tag)
def __init__(self, path):
self.stemmer = PorterStemmer()
self.path = path
self.cur_idx = 0
self.batch = 2
self.sample = 0.001
self.vocab_size = 10000
self.total_count = 0
self.word_count = Counter()
self.word2idx = defaultdict(int)
self.idx2word = {}
self.word_sample = {}
self.batch_size = 128
self.embedding_size = 128 # Dimension of the embedding vector.
self.skip_window = 3 # How many words to consider left and right.
self.raw_sample_probs = [0.5, 0.3, 0.2]
self.sample_probs = []
sum = 0
for prob in self.raw_sample_probs:
sum += prob
self.sample_probs.append(sum)
self.num_skips = 2 # How many times to reuse an input to generate a label.
self.valid_size = 16 # Random set of words to evaluate similarity on.
self.valid_window = 100 # Only pick dev samples in the head of the distribution.
#self.valid_examples = np.random.choice(valid_window, valid_size, replace=False)
self.num_negative_sampled = 64 # Number of negative examples to sample.
self.batch_index = 0
self.get_stat()
def GetWordDictionary(emails):
word_dict = {}
count = 0
stemmer = PorterStemmer()
for email_case in emails:
email = email_case[0]
body = SplitText(email['body'])
for word in body:
modified_word = word
if len(modified_word) > 1:
modified_word = stemmer.stem(word, 0, len(word) - 1)
if modified_word not in word_dict:
word_dict[modified_word] = count
count += 1
return word_dict
def GetDataset():
emails = None
x_vals = []
y_vals = []
stemmer = PorterStemmer()
with open("pickled_reduced_chains.txt", "rb") as fp1: # Unpickling
emails = pickle.load(fp1)
i = 0
text_data = []
for i in range(0, len(emails)):
print "Evaluation Email %d" % (i)
email, next_email, time_diff = emails[i]
print emails[i]
# Create feature array
features = []
# if np.round(time_diff / 60) > 72: continue;
#Feature 1: Number of to
features.append(len(email['to']))
# Feature 2: Num words
words = email['body'].split()
features.append(len(words))
# Feature 3: Number of CC
features.append(email['cc_count'])
# Feature 4: is reply
if email['is_re']:
features.append(1)
else:
features.append(0)
# Feature 5: Time of Day (minutes)
date = email['date']['local_date']
hour = date.hour
features.append(hour)
# Feature 6: Length of Subject Line
subject_words = email['subject'].split()
features.append(len(subject_words))
# Feature 7: Day of Week
features.append(date.weekday())
# Feature 8: Question marks in Body
features.append(email['body'].count('?'))
# Feature 9: Question marksin Subject
features.append(email['subject'].count('?'))
x_vals.append(features)
# Append y_value for training point
y_vals.append(int(np.round(time_diff / 60)))
a = np.array(x_vals)
b = np.array(y_vals)
return a, b
def main():
# Reading the document from the file
fileName = "cran.all.1400"
documents = readFromFile(fileName, "r")
# Reading stop words from the file
stopwordsList = readFromFile("stopwords.txt", "r")
stopwords = stopwordsList.split()
# List that maintains the document id number, number of unique terms in document, for each term in the document, its term and it's term frequency.
docId = 1
# InvFileHash
invFileHash = {}
# Splits the multiple documents of the same file into list
document = re.split(".I | \n.I", documents)[1:]
totalDocument = len(document)
print "Total documents:", totalDocument
for doc in enumerate(document):
startIndex = doc[1].index('.W\n')
text = doc[1][startIndex + 3:]
words = re.findall(r'\w+', text)
pObj = PorterStemmer()
listWords = {}
for word in words:
flagStopwords = word.lower() in stopwords
if (not flagStopwords and word.isalpha()):
stemWord = pObj.stem(word.lower(), 0, len(word) - 1)
listWords = addToDict(listWords, stemWord)
docList = addDoc(docId, listWords)
docId += 1
invFileHash = createInvFileHash(invFileHash, docList)
# Writes to the Inverted File Hash file
writeToFile(invFileHash)
# To read the queries list from the cran query file
queryFileRead = readFromFile("cran.qry", "r")
# Calculate the Vector Space Model (total number of documents, stopwords list)
vectorSpaceModel(totalDocument, queryFileRead, stopwords)
def classify(folds, nb_or_svm, ngrams, stemming, binary):
p = PorterStemmer()
vectorizer = CountVectorizer(input="filename", \
ngram_range=ngrams, \
tokenizer=(lambda d: [(p.stem(t, 0, len(t)-1) if stemming else t) for t in d.split()]), \
binary=binary, \
min_df=4, max_df=1.0)
X = vectorizer.fit_transform([f[0] for fold in folds for f in fold])
accuracies = []
for i in range(len(folds)):
classifier = SVC(gamma="auto", kernel="linear") if nb_or_svm[0] == "svm" \
else MultinomialNB(alpha=(1.0 if nb_or_svm[1] else 1.0e-10))
start_index = 0
for j in range(i):
start_index += len(folds[j])
end_index = start_index + len(folds[i])
test_set = X[start_index:end_index]
training_set = vstack([X[:start_index], X[end_index:]])
classifier.fit(
training_set,
[f[1] for fold in (folds[:i] + folds[i + 1:]) for f in fold])
correct_predictions = 0
results = classifier.predict(test_set)
for j in range(len(results)):
correct_predictions += int(results[j] == folds[i][j][1])
accuracies.append(100 * correct_predictions / len(results))
if nb_or_svm[0] != "svm":
print("smoothed" if nb_or_svm[1] else "unsmoothed", end=" ")
print("stemmed" if stemming else "unstemmed", \
"presence" if binary else "frequency", \
"unigrams" if ngrams == (1, 1) else \
("bigrams" if ngrams == (2, 2) else \
("uni + bi" if ngrams == (1, 2) else "unknown")), \
"accuracy:", sum(accuracies)/len(accuracies))
def GetPddlObj(_sWord):
global text2pddl;
if text2pddl == None:
ReadMinecraftDict(minecraftDictFile);
setObjs = set();
p = PorterStemmer();
sLastWord = p.stem(_sWord.lower(), 0, len(_sWord)-1);
if sLastWord == 'block': return setObjs;
#print sLastWord;
for sTextName in text2pddl.keys():
if text2pddl[sTextName] == 'NULL': continue;
lstWords = sTextName.split(' ');
sLastTextWord = lstWords[len(lstWords)-1];
if sLastTextWord == 'block':
if len(lstWords) == 1: continue;
sLastTextWord = lstWords[len(lstWords)-2];
if sLastTextWord == sLastWord:
setObjs.add(text2pddl[sTextName]);
return list(setObjs);
def stemizeList(normalList):
# STEMIZER FOR LIST
porter = PorterStemmer()
newList = []
newDict = {}
count = 0;
for lists in normalList:
tokenList = []
for token in lists:
#print normalList.index(lists)," ",lists.index(token)
tokenList.append(porter.stem(token,0,len(token)-1))
if token in newDict:
count = newDict[token]
newDict[token] = count +1
else:
newDict[token] = 1
newList.append(tokenList)
#token = porter.stem(token,0,len(token)-1)
return newList,newDict
def get_postlist(stop_answer, stem_answer, dict_terms):
if stop_answer == 'no':
stopwords = []
if stop_answer == 'yes':
stopwords = [
'i', 'a', 'about', 'an', 'and', 'are', 'as', 'at', 'be', 'by',
'for', 'from', 'how', 'in', 'is', 'it', 'of', 'on', 'or',
'that', 'the', 'this', 'to', 'was', 'what', 'when', 'where',
'who', 'will', 'with', 'the'
]
ps = PorterStemmer()
position_list = []
dict_posting = {}
counter = 0
for key, value in dict_terms.items():
if isinstance(value, dict):
for k, v in value.items():
if k == 'abstract':
val = v.replace(',', '').lower().split()
for index, word in enumerate(val):
if stem_answer == 'no':
stem_word = word
if stem_answer == 'yes':
stem_word = ps.stem(word, 0, len(word) - 1)
if stem_word not in stopwords:
if stem_word not in dict_posting:
dict_posting[stem_word] = {}
if key not in dict_posting[stem_word]:
dict_posting[stem_word][key] = {}
dict_posting[stem_word][key][
'frequency'] = 0
dict_posting[stem_word][key][
'position'] = []
dict_posting[stem_word][key]['frequency'] += 1
dict_posting[stem_word][key][
'position'].append(index)
with open('posting_list.json', 'w') as outfile:
json.dump(dict_posting, outfile)
print("Finished writing the posting list")
return dict_posting
def __init__(self, fileA, fileB):
self.__allWords = set()
self.__wordsA = dict()
self.__wordsB = dict()
with open(fileA, 'r') as document:
for line in document:
words = line.strip().split()
for word in words:
p = PorterStemmer()
word = p.stem(word, 0, len(word) - 1)
if word in self.__wordsA.keys():
self.__wordsA[word] += 1
else:
self.__wordsA[word] = 1
with open(fileB, 'r') as document:
for line in document:
words = line.strip().split()
for word in words:
p = PorterStemmer()
word = p.stem(word, 0, len(word) - 1)
if word in self.__wordsB.keys():
self.__wordsB[word] += 1
else:
self.__wordsB[word] = 1
self.__allWords = set(self.__wordsA.keys()) | set(self.__wordsB.keys())
self.__table = {t[1]: t[0] for t in enumerate(self.__allWords)}
def ReadMinecraftDict(infoFile):
global text2pddl;
fin = open(infoFile)
lines = fin.readlines()
fin.close()
lines = [ line.strip() for line in lines ];
text2pddl = {}
p = PorterStemmer()
for line in lines:
if len(line)==0: continue;
parts = line.split(':');
textName = parts[0];
words = [ p.stem(w.lower(),0,len(w)-1) for w in textName.split() ]
textName = ' '.join(words);
if len(parts)>1:
pddlName = parts[1];
else:
pddlName = parts[0];
assert(pddlName!='');
assert(textName!='');
text2pddl[textName] = pddlName;
def process(text):
'''Returns a list of words after carying out the
following text preprocessing and normalization steps'''
# Convert text to lower case
text = text.lower()
#Remove 'Subject'
text = re.sub(r'^sub(ject)?', ' ', text)
# Strip HTML
text = re.sub(r'<.*?>', ' ', text)
# Normalize URLs
text = re.sub(r'(http|https|ftp)://\S*', ' httpaddr ', text)
# Normalize email addresses
text = re.sub(r'[\w.+-]+@[\w.-]+', ' emailaddr ', text)
# Normalize numbers
text = re.sub(r'\b\d[\d,]*[.]*[\d]*\b', ' number ', text)
# Normalize Dollars/Rupees
text = re.sub(r'(\$|\brs\b|₹|£)+', ' dollar ', text)
# Remove non-word characters
text = re.sub(r'[^a-z]+', ' ', text)
# Strip all whitespace characters and generate list of words
# Stop Word Removal
# stop_words = pickle.load(open('stopwords_set.pyset', 'rb'))
text = [
word for word in text.split()
if word not in process.stop_words and len(word) > 2
]
# Word Stemming
p = PorterStemmer()
result = []
for word in text:
try:
stem_word = p.stem(word, 0, len(word) - 1)
if stem_word not in process.stop_words:
result.append(stem_word)
except:
pass
return result
def GetTFIDF():
emails = None
x_vals = []
y_vals = []
stemmer = PorterStemmer()
# Get email chains
with open("balanced_chains.pickle", "rb") as fp1: # Unpickling
emails = pickle.load(fp1)
np.random.shuffle(emails)
i = 0
text_data = []
for i in range(0, len(emails)):
print "Evaluation Email %d" % (i)
email, next_email, time_diff, bucket = emails[i]
# if int(np.round(time_diff / 60)) > 72:
# continue
# Create stemmed body and append to text_data
new_str = ""
words = email['body'].split()
for word in words:
new_word = stemmer.stem(word, 0, len(word) - 1)
new_str += new_word + " "
new_str = new_str[:-1]
text_data.append(new_str)
# Append hour
y_vals.append(int(np.round(time_diff / 60)))
#y_vals.append(int(time_diff)
b = np.array(y_vals)
count_vect = CountVectorizer()
X_train_counts = count_vect.fit_transform(text_data)
tf_transformer = TfidfTransformer(use_idf=True).fit(X_train_counts)
X_train_tf = tf_transformer.transform(X_train_counts)
return X_train_tf, b, count_vect, tf_transformer, text_data
def buildMatrix(self):
# use suffix-stripping algorithm to stem word
porter_strmmer = PorterStemmer()
for index in range(0,len(self.origin_documents)):
document = self.origin_documents[index]
# change document in origin_document array to array of stemmed word
self.origin_documents[index] = [porter_strmmer.stem(x, 0, len(x) - 1) for x in document.split()]
# use 2000 most frequent words to generate words array
temp_word = defaultdict(int)
for document in self.origin_documents:
for word in document:
temp_word[word] += 1
sorted_dict = sorted(temp_word.items(), key=operator.itemgetter(1))
sorted_dict.reverse()
self.words = [x[0] for x in sorted_dict[0:self.word_size]]
# build document array
for index in range(0, len(self.origin_documents)):
document = self.origin_documents[index]
self.documents.append([])
self.documents[index] = [document.count(word) for word in self.words]
# print(self.documents[0], sum(self.documents[0]))
# remove zero sum rows
zeros = [i for i, value in enumerate(self.documents) if sum(value) == 0]
for value in zeros[::-1]:
del self.labels[value]
del self.documents[value]
# zeros = [i for i, value in enumerate(self.documents) if sum(value) == 0]
print(len(self.origin_documents), len(self.words), len(self.documents), self.words)
def vectorSpaceModel(totalDocument, queryFileRead, stopwords):
"""
Query to calculate the cosine similarity between document d and Query Q
"""
# Loads the inverted File Hash
dic = loadFromFile()
#
queryList = processQueryList(queryFileRead)
# Calculation of Inverse Document Frequency
IDF = calculateIDF(dic, totalDocument)
# Calculation of Term Frequency
TF = calculateTFList(dic)
# Calculation of Wd from all the Term Frequency calculated
WD = calculateWD(TF, totalDocument)
pObj = PorterStemmer()
fileWrite = open("outputdocument.txt", "w")
for query in queryList:
fileWrite.write("\n---------------------------------------------------------------------------------------")
fileWrite.write("\nQuery: " + query)
# Separate the string of query into list of words
listQuery = re.findall(r'\w+', query)
# Remove the stopwords and numbers from the list of query words
queryWithoutStopword = [x for x in listQuery if x not in stopwords and x.isalpha()]
# Stem the list of query words
processedQuery = [pObj.stem(x.lower(), 0, len(x) - 1) for x in queryWithoutStopword]
# Calculate the cosine measure (Similarity) for the query
rankedDocList = calculateSimilarity(processedQuery, IDF, WD, totalDocument)
fileWrite.write("\nTotal number of documents retrieved: " + str(len(rankedDocList)))
fileWrite.write("\nDocument ID:\n")
fileWrite.write(''.join(str(rankedDocList)))
fileWrite.write("\n---------------------------------------------------------------------------------------")
fileWrite.close()
print "Writing to outputdocument.txt file completes."
def main():
# Reading the document from the file
file = open("cran.all.1400", "r")
documents = file.read()
# Reading stop words from the file
fileStopwords = open('stopwords.txt', 'r')
stopwordsList = fileStopwords.read()
stopwords = stopwordsList.split()
# List that maintains the document id number, number of unique terms in document, for each term in the document, its term and it's term frequency.
documentList = []
docId = 1
# Splits the multiple documents of the same file into list
document = re.split(".I | \n.I", documents)[1:]
for doc in enumerate(document):
startIndex = doc[1].index('.W\n')
text = doc[1][startIndex + 3:]
words = re.findall(r'\w+', text)
pObj = PorterStemmer()
listWords = {}
for word in words:
flagStopwords = word.lower() in stopwords
if (not flagStopwords and word.isalpha()):
stemWord = pObj.stem(word, 0, len(word) - 1)
listWords = addToDict(listWords, stemWord)
sortedList = sorted(listWords.items(), key=lambda t: t[0])
output = {'id': docId, 'unique': len(sortedList), 'terms': sortedList}
docId += 1
documentList.append(output)
for i in range(0, len(documentList)):
print "Document:", documentList[i][
'id'], "\nUnique Terms:", documentList[i][
'unique'], "\nTerms:\n", documentList[i]['terms']
def main():
array = []
array2 = []
p = PorterStemmer()
with open(sys.argv[1]) as f:
for line in f:
if len(line) > 1:
array.append(line[0:len(line) - 1])
word_dictionary, tag_dictionary, count = read_input(array, p)
with open(sys.argv[2]) as f:
for line in f:
if len(line) > 1:
array2.append(line[0:len(line) - 1])
read_test_data(array2, word_dictionary, tag_dictionary, count)
def main():
# Reading the document from the file
file = open("cran.all.1400", "r")
documents = file.read()
# Reading stop words from the file
fileStopwords = open('stopwords.txt', 'r')
stopwordsList = fileStopwords.read()
stopwords = stopwordsList.split()
# List that maintains the document id number, number of unique terms in document, for each term in the document, its term and it's term frequency.
docId = 1
#InvFileHash
invFileHash = {}
# Splits the multiple documents of the same file into list
document = re.split(".I | \n.I", documents)[1:]
for doc in enumerate(document):
startIndex = doc[1].index('.W\n')
text = doc[1][startIndex + 3:]
words = re.findall(r'\w+', text)
pObj = PorterStemmer()
listWords = {}
for word in words:
flagStopwords = word.lower() in stopwords
if (not flagStopwords and word.isalpha()):
stemWord = pObj.stem(word, 0, len(word) - 1)
listWords = addToDict(listWords, stemWord)
docList = addDoc(docId, listWords)
docId += 1
invFileHash = createInvFileHash(invFileHash, docList)
print "File written: output.json"
print "Number of terms:",len(invFileHash)
writeToFile(invFileHash)
def __init__(self):
"""
Author: Nicole
This method declares the list stopwords, dictionaries all_words and
all_words_freq, as well as the PorterStemmer object.
"""
self.stopwords = []
self.p = PorterStemmer()
self.all_words = {}
self.all_words_freq = {}
self.tfidf = {}
self.vocabulary = []
self.doc_term_matrix = [[0] * 23 for n in range(809)]
self.docs = {}
self.visited = []
class Cleaner(object):
def __init__(self, stopwords):
self.stopwords = stopwords
self.stemmer = PorterStemmer()
def clean_word(self, word):
word = word.strip().lower()
word = filter(lambda c: c.isalnum(), word)
if word in self.stopwords:
word = None
else:
word = self.stemmer.stem(word, 0, len(word) - 1)
return word
def clean_wordlist(self, wordlist):
wordlist = " ".join(wordlist).replace('-', ' ').split()
clean_list = map(lambda x: self.clean_word(x), wordlist)
return [word for word in clean_list if word]
@staticmethod
def make_printable(phrase):
return filter(lambda c: c in string.printable, phrase)
class Indexer():
# remove stop words and do stemming
STOP_WORD_LIST = ["a","a's","able","about","above","according","accordingly","across","actually","after","afterwards","again","against","ain't","all","allow","allows","almost","alone","along","already","also","although","always","am","among","amongst","an","and","another","any","anybody","anyhow","anyone","anything","anyway","anyways","anywhere","apart","appear","appreciate","appropriate","are","aren't","around","as","aside","ask","asking","associated","at","available","away","awfully","be","became","because","become","becomes","becoming","been","before","beforehand","behind","being","believe","below","beside","besides","best","better","between","beyond","both","brief","but","by","c'mon","c's","came","can","can't","cannot","cant","cause","causes","certain","certainly","changes","clearly","co","com","come","comes","concerning","consequently","consider","considering","contain","containing","contains","corresponding","could","couldn't","course","currently","definitely","described","despite","did","didn't","different","do","does","doesn't","doing","don't","done","down","downwards","during","each","edu","eg","eight","either","else","elsewhere","enough","entirely","especially","et","etc","even","ever","every","everybody","everyone","everything","everywhere","ex","exactly","example","except","far","few","fifth","first","five","followed","following","follows","for","former","formerly","forth","four","from","further","furthermore","get","gets","getting","given","gives","go","goes","going","gone","got","gotten","greetings","had","hadn't","happens","hardly","has","hasn't","have","haven't","having","he","he's","hello","help","hence","her","here","here's","hereafter","hereby","herein","hereupon","hers","herself","hi","him","himself","his","hither","hopefully","how","howbeit","however","i'd","i'll","i'm","i've","ie","if","ignored","immediate","in","inasmuch","inc","indeed","indicate","indicated","indicates","inner","insofar","instead","into","inward","is","isn't","it","it'd","it'll","it's","its","itself","just","keep","keeps","kept","know","knows","known","last","lately","later","latter","latterly","least","less","lest","let","let's","like","liked","likely","little","look","looking","looks","ltd","mainly","many","may","maybe","me","mean","meanwhile","merely","might","more","moreover","most","mostly","much","must","my","myself","name","namely","nd","near","nearly","necessary","need","needs","neither","never","nevertheless","new","next","nine","no","nobody","non","none","noone","nor","normally","not","nothing","novel","now","nowhere","obviously","of","off","often","oh","ok","okay","old","on","once","one","ones","only","onto","or","other","others","otherwise","ought","our","ours","ourselves","out","outside","over","overall","own","particular","particularly","per","perhaps","placed","please","plus","possible","presumably","probably","provides","que","quite","qv","rather","rd","re","really","reasonably","regarding","regardless","regards","relatively","respectively","right","said","same","saw","say","saying","says","second","secondly","see","seeing","seem","seemed","seeming","seems","seen","self","selves","sensible","sent","serious","seriously","seven","several","shall","she","should","shouldn't","since","six","so","some","somebody","somehow","someone","something","sometime","sometimes","somewhat","somewhere","soon","sorry","specified","specify","specifying","still","sub","such","sup","sure","t's","take","taken","tell","tends","th","than","thank","thanks","thanx","that","that's","thats","the","their","theirs","them","themselves","then","thence","there","there's","thereafter","thereby","therefore","therein","theres","thereupon","these","they","they'd","they'll","they're","they've","think","third","this","thorough","thoroughly","those","though","three","through","throughout","thru","thus","to","together","too","took","toward","towards","tried","tries","truly","try","trying","twice","two","un","under","unfortunately","unless","unlikely","until","unto","up","upon","us","use","used","useful","uses","using","usually","value","various","very","via","viz","vs","want","wants","was","wasn't","way","we","we'd","we'll","we're","we've","welcome","well","went","were","weren't","what","what's","whatever","when","whence","whenever","where","where's","whereafter","whereas","whereby","wherein","whereupon","wherever","whether","which","while","whither","who","who's","whoever","whole","whom","whose","why","will","willing","wish","with","within","without","won't","wonder","would","would","wouldn't","yes","yet","you","you'd","you'll","you're","you've","your","yours","yourself","yourselves","zero"]
def __init__(self):
logging.debug('Indexer => Init params:self')
self.idx_fields = [] # field of document to be indexed
#self.STOP_WORD_LIST = []
self.P = PorterStemmer()
# end of function
'''
def set_stop_words(self,stop_word_list):
self.STOP_WORD_LIST = stop_word_list
# end of function
'''
def set_idx_fields(self,fields):
logging.debug('Indexer => set_idx_fields fields:' + str(fields))
self.idx_fields = fields
def add_idx_field(self,field_name):
self.idx_fields.append(field_name)
def clean(self,word):
#preprocess word
word = word.lower()
word = word.strip("\n\t,.(){}?!;'")
if word not in self.STOP_WORD_LIST:
word = self.P.stem(word,0,len(word)-1)
else:
word = ""
return word
# end of function
def tokenize(self, text):
#list
word_idx = []
# split lines
lines = text.split('\n')
for line in lines:
# split words
words = line.split(' ')
for word in words:
word = self.clean(word)
if len(word) > 1:
word_idx.append(word)
# make a set (remove duplicate)
word_idx = set(word_idx)
return word_idx
# end of function
def index(self, document):
if isinstance(document,list): document = document[0]
text = ""
# get text from document to be indexed
for field in self.idx_fields:
text += document[field] + " "
return self.tokenize(text)
def stem(self, words):
return [self.tokenize(word) for word in words]
def __init__(self):
logging.debug('Indexer => Init params:self')
self.idx_fields = [] # field of document to be indexed
#self.STOP_WORD_LIST = []
self.P = PorterStemmer()
def stemming(self, term):
output = ""
stem1 = PorterStemmer()
output = stem1.stem(term)
return output
def stemWord(self, word):
return PorterStemmer.stem(self, word, 0, len(word) - 1)
def __init__(self, language):
PorterStemmer.__init__(self)
def stemWord(self, word):
return PorterStemmer.stem(self, word, 0, len(word) - 1)
class W2V:
def __init__(self, path):
self.stemmer = PorterStemmer()
self.path = path
self.cur_idx = 0
self.batch = 2
self.sample = 0.001
self.vocab_size = 10000
self.total_count = 0
self.word_count = Counter()
self.word2idx = defaultdict(int)
self.idx2word = {}
self.word_sample = {}
self.batch_size = 128
self.embedding_size = 128 # Dimension of the embedding vector.
self.skip_window = 3 # How many words to consider left and right.
self.raw_sample_probs = [0.5, 0.3, 0.2]
self.sample_probs = []
sum = 0
for prob in self.raw_sample_probs:
sum += prob
self.sample_probs.append(sum)
self.num_skips = 2 # How many times to reuse an input to generate a label.
self.valid_size = 16 # Random set of words to evaluate similarity on.
self.valid_window = 100 # Only pick dev samples in the head of the distribution.
#self.valid_examples = np.random.choice(valid_window, valid_size, replace=False)
self.num_negative_sampled = 64 # Number of negative examples to sample.
self.batch_index = 0
self.get_stat()
def get_stat(self):
import json
import collections
import os.path
filename = "stat"
if os.path.exists(filename):
f = open(filename, 'rb')
obj = pickle.load(f)
self.word2idx = obj["word2idx"]
self.idx2word = obj["idx2word"]
self.word_count = obj["word_count"]
self.word_sample = obj["word_sample"]
self.total_count = obj["total_count"]
return
line_idx = 0
text_data = ""
with open(self.path, "r") as ins:
for line in ins:
obj = json.loads(line)
reviewText = obj["reviewText"]
summary = obj["summary"]
reviewerID = obj["reviewerID"]
overall = obj["overall"]
asin = obj["asin"]
text_data = " ".join([text_data ,reviewText, summary])
line_idx += 1
if line_idx % 1000 == 0:
self.word_count + collections.Counter(self.stemmer.get_stem_wordlist(text_data.split()))
text_data = ""
self.word_count = self.word_count.most_common(self.vocab_size-1)
for word,cnt in self.word_count:
self.word2idx[word] = 1+len(self.word2idx)
#self.idx2word = dict(zip(self.word2idx.values(), self.word2idx.keys()))
#calculate the sample
#threshold_count = self.sample * self.total_count
#for word in self.word_count:
# word_probability = (sqrt(self.word_count[word] / threshold_count) + 1) * (threshold_count / self.word_count[word])
# self.word_sample[word] = int(round(word_probability * 2**32))
f = open(filename, 'wb')
pickle.dump({"word2idx":self.word2idx,"idx2word":self.idx2word,"word_count":self.word_count,"word_sample":self.word_sample,"total_count":self.total_count},f)
def get_batch(self):
#global batch_index
#calculate sample prob inside window
#sample_probs = []
#sum = (1<<(self.skip_window)) - 1
#prob = 0
#for idx in range(self.skip_window,0,-1):
# prob += (1<<(idx-1)) / sum
# sample_probs.append(prob)
#prepare buffer
span = 2 * self.skip_window + 1 # [ skip_window target skip_window ]
buffer = collections.deque(maxlen=span)
context_data = [] #list append is better than numpy append, so using list append first and then convert into numpy obj
target_data = [] # same as above
for i in range(1, self.batch_size):
idx = self.batch_index + i
#line = linecache.getline(self.path, idx)
line = '{ "reviewerID": "A2SUAM1J3GNN3B", "asin": "0000013714", "reviewerName": "J. McDonald", "helpful": [2, 3], "reviewText": "I bought this for my husband who plays the piano. He is having a wonderful time playing these old hymns. The music is at times hard to read because we think the book was published for singing from more than playing from. Great purchase though!", "overall": 5.0, "summary": "Heavenly Highway Hymns", "unixReviewTime": 1252800000, "reviewTime": "09 13, 2009" }'
if line is None or len(line) == 0:
print("current idx,", idx, " current batch_idx, ", self.batch_index, " line: ", line)
continue
obj = json.loads(line)
reviewText = obj["reviewText"]
summary = obj["summary"]
reviewerID = obj["reviewerID"]
overall = obj["overall"]
asin = obj["asin"]
text_data = " ".join([reviewText, summary]).split()
for word_idx in range(0, len(text_data)):
while len(buffer) < span:
buffer.append(self.word2idx[self.stemmer.get_stem_word(text_data[word_idx])])
target_word = self.word2idx[buffer[self.skip_window]]
context_word = target_word
avoid_context_word = [target_word]
r = rd.random()
for cnt_idx in range(0, int(self.skip_window/2)): #random pick up skip_window/2 context word
while context_word in avoid_context_word: #for avoid repeat sample
for rank_idx in range(0,self.skip_window): #from closest to farest
if r <= self.sample_probs[rank_idx]:
if rd.random() >= 0.5:
context_word = self.word2idx[buffer[self.skip_window - (rank_idx + 1)]]
else:
context_word = self.word2idx[buffer[self.skip_window + (rank_idx + 1)]]
break
if context_word not in avoid_context_word:
avoid_context_word.append(context_word)
context_data.append(context_word)
target_data.append(target_word)
#for next word
buffer.append(self.stemmer.get_stem_word(text_data[word_idx]))
#update global batch_index
self.batch_index += self.batch_size
context_data = np.ndarray(shape=(len(context_data)), dtype=np.int32)
target_data = np.ndarray(shape=(len(target_data), 1), dtype=np.int32)
return context_data, target_data
def train(self):
embedding_size = 128 # Dimension of the embedding vector.
graph = tf.Graph()
with graph.as_default():
# Input data.
train_inputs = tf.placeholder(tf.int32)
train_labels = tf.placeholder(tf.int32)
# Ops and variables pinned to the CPU because of missing GPU implementation
with tf.device('/cpu:0'):
# Look up embeddings for inputs.
embeddings = tf.Variable(
tf.random_uniform([self.vocab_size, embedding_size], -1.0, 1.0), name = "emb")
embed = tf.nn.embedding_lookup(embeddings, train_inputs)
# Construct the variables for the NCE loss
nce_weights = tf.Variable(
tf.truncated_normal([self.vocab_size, embedding_size],
stddev=1.0 / sqrt(embedding_size)))
nce_biases = tf.Variable(tf.zeros([self.vocab_size]))
# Compute the average NCE loss for the batch.
# tf.nce_loss automatically draws a new sample of the negative labels each
# time we evaluate the loss.
loss = tf.reduce_mean(
tf.nn.nce_loss(nce_weights, nce_biases, embed, train_labels,
self.num_negative_sampled, self.vocab_size))
# Construct the SGD optimizer using a learning rate of 1.0.
optimizer = tf.train.GradientDescentOptimizer(1.0).minimize(loss)
saver = tf.train.Saver()
init = tf.initialize_all_variables()
self.num_steps = 1000000
with tf.Session(graph=graph) as session:
# We must initialize all variables before we use them.
init.run()
print("Initialized")
average_loss = 0
for step in range(self.num_steps):
batch_inputs, batch_labels = self.get_batch()
feed_dict = {train_inputs: batch_inputs, train_labels: batch_labels}
# We perform one update step by evaluating the optimizer op (including it
# in the list of returned values for session.run()
_, loss_val = session.run([optimizer, loss], feed_dict=feed_dict)
average_loss += loss_val
if step % 2000 == 0:
if step > 0:
average_loss /= 50
# The average loss is an estimate of the loss over the last 2000 batches.
print("Average loss at step ", step, ": ", average_loss)
filename = "_".join(["embedding",str(step)])
saver.save(session, filename)
average_loss = 0
return
iter_ = regexObject.finditer(text)
for result in iter_:
if result.group('id') is not None:
docs.append(Doc(int(result.group('id')))) # add new doc to the `list` with the id
else:
# as far as we know, not both of these can be `not none` at the same time
if result.group('title') is not None:
docs[-1].appendText(result.group('title').lower() + '\n') # append to the last element docs `list`
if result.group('body') is not None:
docs[-1].appendText(result.group('body').lower()) # append to the last element docs `list`
return docs
stopWords = {'a', 'all', 'an', 'and', 'any', 'are', 'as', 'be', 'been', 'but', 'by ', 'few', 'for', 'have', 'he', 'her', 'here', 'him', 'his', 'how', 'i', 'in', 'is', 'it', 'its', 'many', 'me', 'my', 'none', 'of', 'on ', 'or', 'our', 'she', 'some', 'the', 'their', 'them', 'there', 'they', 'that ', 'this', 'us', 'was', 'what', 'when', 'where', 'which', 'who', 'why', 'will', 'with', 'you', 'your'}
portertStemmer = PorterStemmer()
ro= re.compile(r'\d+\.+\d+|\w+')
""" regex object for finding words and digits and floats containing dot IN them pre-cooked ready to eat"""
def regexStyleGenerator(text):
"""
A generator that returns tokens of given text
makes stopword removel and stemming
:param text: the text to tokenize
:return: None but yields tokens
"""
global total_num_words_before,total_num_words_after # for statistics
def run_train_test(training_file, testing_file):
# Set the variables, params, dicts, sets
alpha = 0.5
stop_words = {'the', 'and'}
logic_negation = {'t', 'not', 'no', 'never', 'dont', 'didnt', 'doesnt'}
Porter_Stemmer = PorterStemmer()
# Import training dataset
training_start_time = time.time()
vocab = set(['positive-words', 'negative-words'])
wordcount_class_0 = {'positive-words': 0, 'negative-words': 0}
wordcount_class_1 = {'positive-words': 0, 'negative-words': 0}
total_reviews = 0
reviewscount_0 = 0
reviewscount_1 = 0
train_labels = []
train_reviews = []
with training_file as f:
for line in f:
review, label = line.split(',')
words = review.split(' ')
del words[-1]
label = int(label.strip("\n"))
total_reviews += 1
# Implement negation: add NOT_ to words after logical negation
for i in range(len(words)):
words[i] = Porter_Stemmer.stem(words[i])
if words[i] in logic_negation:
try:
words[i + 1] = 'NOT_' + words[i + 1]
except:
continue
try:
words[i + 2] = 'NOT_' + words[i + 2]
except:
continue
try:
words[i + 3] = 'NOT_' + words[i + 3]
except:
continue
bigrams = []
for i in range(len(words) - 1):
bigram = words[i] + ' ' + words[i + 1]
bigrams.append(bigram)
words = set(bigrams)
# words = set(words)
vocab.update(words)
for word in words:
if word not in wordcount_class_0.keys():
wordcount_class_0[word] = 0
wordcount_class_1[word] = 0
if label == 0:
reviewscount_0 += 1
for word in words:
wordcount_class_0[word] += 1
# # Analyze Sentiment lexicons
# unigram1, unigram2 = word.split(' ')
# if unigram1 in lexicons.pos_words:
# wordcount_class_0['positive-words'] += 1
# if unigram1 in lexicons.neg_words:
# wordcount_class_0['negative-words'] += 1
# if unigram2 in lexicons.pos_words:
# wordcount_class_0['positive-words'] += 1
# if unigram2 in lexicons.neg_words:
# wordcount_class_0['negative-words'] += 1
if label == 1:
reviewscount_1 += 1
for word in words:
wordcount_class_1[word] += 1
# # Analyze Sentiment lexicons
# unigram1, unigram2 = word.split(' ')
# if unigram1 in lexicons.pos_words:
# wordcount_class_0['positive-words'] += 1
# if unigram1 in lexicons.neg_words:
# wordcount_class_0['negative-words'] += 1
# if unigram2 in lexicons.pos_words:
# wordcount_class_0['positive-words'] += 1
# if unigram2 in lexicons.neg_words:
# wordcount_class_0['negative-words'] += 1
train_labels.append(label)
train_reviews.append(words)
# Compute CPTs
P_class = [0, 0]
P_class[0] = reviewscount_0 / total_reviews
P_class[1] = reviewscount_1 / total_reviews
P_words_class_0 = {}
P_words_class_1 = {}
bottom_0 = sum(wordcount_class_0.values()) + alpha * len(vocab)
bottom_1 = sum(wordcount_class_1.values()) + alpha * len(vocab)
for word in vocab:
if word in stop_words:
P_words_class_0[word] = (0 + alpha) / bottom_0
P_words_class_1[word] = (0 + alpha) / bottom_1
else:
P_words_class_0[word] = (wordcount_class_0[word] +
alpha) / bottom_0
P_words_class_1[word] = (wordcount_class_1[word] +
alpha) / bottom_1
# Inference on the training dataset
predict_train_labels = []
for doc in train_reviews:
log_sum_0 = 0
log_sum_1 = 0
bag_of_words = set(doc)
for word in bag_of_words:
log_sum_0 += log(P_words_class_0[word])
log_sum_1 += log(P_words_class_1[word])
# # Sentiment Analysis
# unigram1, unigram2 = word.split(' ')
# if unigram1 in lexicons.pos_words:
# log_sum_0 += log(P_words_class_0['positive-words'])
# log_sum_1 += log(P_words_class_1['positive-words'])
# if unigram1 in lexicons.neg_words:
# log_sum_0 += log(P_words_class_0['negative-words'])
# log_sum_1 += log(P_words_class_1['negative-words'])
# if unigram2 in lexicons.pos_words:
# log_sum_0 += log(P_words_class_0['positive-words'])
# log_sum_1 += log(P_words_class_1['positive-words'])
# if unigram2 in lexicons.neg_words:
# log_sum_0 += log(P_words_class_0['negative-words'])
# log_sum_1 += log(P_words_class_1['negative-words'])
Prob_c0 = log(P_class[0]) + log_sum_0
Prob_c1 = log(P_class[1]) + log_sum_1
if Prob_c0 > Prob_c1:
c = 0
else:
c = 1
predict_train_labels.append(c)
# Compute training accuracy
correct = 0
for i in range(len(train_labels)):
if predict_train_labels[i] == train_labels[i]:
correct += 1
train_accuracy = correct / len(train_labels)
training_time = time.time() - training_start_time
# Import testing dataset
testing_start_time = time.time()
test_reviews = []
test_labels = []
with testing_file as f:
for line in f:
review, label = line.split(',')
words = review.split(' ')
del words[-1]
label = int(label.strip("\n"))
# Implement negation: add NOT_ to words after logical negation
for i in range(len(words)):
words[i] = Porter_Stemmer.stem(words[i])
if words[i] in logic_negation:
try:
words[i + 1] = 'NOT_' + words[i + 1]
except:
continue
try:
words[i + 2] = 'NOT_' + words[i + 2]
except:
continue
try:
words[i + 3] = 'NOT_' + words[i + 3]
except:
continue
bigrams = []
for i in range(len(words) - 1):
bigram = words[i] + ' ' + words[i + 1]
bigrams.append(bigram)
words = set(bigrams)
# words = set(words)
test_labels.append(label)
test_reviews.append(words)
# Inference on the testing dataset
predict_test_labels = []
for doc in test_reviews:
log_sum_0 = 0
log_sum_1 = 0
bag_of_words = set(doc)
bag_of_words = vocab.intersection(bag_of_words)
for word in bag_of_words:
log_sum_0 += log(P_words_class_0[word])
log_sum_1 += log(P_words_class_1[word])
# # Sentiment Analysis
# unigram1, unigram2 = word.split(' ')
# if unigram1 in lexicons.pos_words:
# log_sum_0 += log(P_words_class_0['positive-words'])
# log_sum_1 += log(P_words_class_1['positive-words'])
# if unigram1 in lexicons.neg_words:
# log_sum_0 += log(P_words_class_0['negative-words'])
# log_sum_1 += log(P_words_class_1['negative-words'])
# if unigram2 in lexicons.pos_words:
# log_sum_0 += log(P_words_class_0['positive-words'])
# log_sum_1 += log(P_words_class_1['positive-words'])
# if unigram2 in lexicons.neg_words:
# log_sum_0 += log(P_words_class_0['negative-words'])
# log_sum_1 += log(P_words_class_1['negative-words'])
Prob_c0 = log(P_class[0]) + log_sum_0
Prob_c1 = log(P_class[1]) + log_sum_1
if Prob_c0 > Prob_c1:
c = 0
else:
c = 1
# print(c)
predict_test_labels.append(c)
# Compute testing accuracy
correct = 0
for i in range(len(test_labels)):
if predict_test_labels[i] == test_labels[i]:
correct += 1
test_accuracy = correct / len(test_labels)
# Print results
testing_time = time.time() - testing_start_time
print(round(training_time), 'seconds (training)')
print(round(testing_time), 'seconds (labeling)')
print(round(train_accuracy, 3), '(training)')
print(round(test_accuracy, 3), '(testing)')
print(len(vocab))
return
'browser' : 1
},
'file' : {
'ls-time': 1
},
'ls' : {
'ls-time': 1,
'tag-time': 1
},
'refspec': {
'new-branch-push': 2
}
}
computed = {}
stemmer = PorterStemmer()
for word in sys.argv[1:]:
word = stemmer.stem(word.lower())
print word
if word in synonymMap:
word = synonymMap[word]
if word in weightMap:
for key, value in weightMap[word].iteritems():
if key in computed:
computed[key] += value
else:
computed[key] = value
sorted_computed = sorted(computed.iteritems(), key=operator.itemgetter(1))
from heapq import heappush, heappop
from collections import defaultdict
from stemmer import PorterStemmer
from pairwise import pairwise
here = lambda *x: os.path.abspath(os.path.join(os.path.dirname(__file__), *x))
stopwords_file = here('stopwords', )
index_file = here('index',)
lengths_file = here('lengths', )
top = 20
lambda_ = 0.5
query = sys.argv[1:]
inner_query = []
p = PorterStemmer()
index = {}
count_term = {}
start_time = time.time()
with open(stopwords_file, "r") as file:
stopwords = map(lambda line: line.strip(), file.readlines())
with open(index_file, "r") as index_file:
lines = index_file.readlines()
for line in lines:
entry = line.split(" ")
documents = entry[2:]
dictionary = defaultdict(int)
for document, count in pairwise(documents):
def __init__(self, stopwords):
self.stopwords = stopwords
self.stemmer = PorterStemmer()
def stem(word):
p = PorterStemmer()
return p.stem(word, 0, len(word)-1)
DATASETS = "datasets"
TRAINING = DATASETS + "/training.txt"
VALIDATION = DATASETS + "/validation.txt"
SPORTS = 2
POLITICS = 1
HASHTAGS = re.compile("\#([^\s\,\.\#\"\'\+\=\|\$\%\^\:]+)")
URLS1 = re.compile("https?\:\/\/([^\s]+)")
URLS2 = re.compile("www\.([^\s]+)")
REFS = re.compile("\@([^\s\,\.\#\"\'\+\=\|\$\%\^\:\-]+)")
KEYWORDS = re.compile("(\w+)")
WHITESPACE = re.compile(
"[\s\.\,\'\"\[\]\{\}\;\:\/\&\=\+\-\)\(\*\&\^\%\$\`\|\?\!]+")
STEMMER = PorterStemmer()
idtable = {}
def get_id(table, key, write=True):
if table.has_key(key): return table[key]
else:
if write:
table[key] = len(table)
return table[key]
else:
return None
def register(table, keys, write=True):
class Crawler:
def __init__(self):
"""
Author: Nicole
This method declares the list stopwords, dictionaries all_words and
all_words_freq, as well as the PorterStemmer object.
"""
self.stopwords = []
self.p = PorterStemmer()
self.all_words = {}
self.all_words_freq = {}
self.tfidf = {}
self.vocabulary = []
self.doc_term_matrix = [[0] * 23 for n in range(809)]
self.docs = {}
self.visited = []
def clean_url(self, url) :
"""
Author: Jason
This method removes the base url
EX. http://lyle.smu.edu/~fmoore/schedule.htm => schedule.htm
"""
url = re.compile(_ROOT_).sub('', url)
url = re.compile('http://lyle.smu.edu/~fmoore').sub('', url)
url = re.compile('index.*').sub('', url)
url = re.compile('.*.gif').sub('', url)
return re.compile('\.\./').sub('', url)
def fetch(self, url) :
"""
Author: Jason
This method will fetch the contents of the page.
"""
r = requests.get(urlparse.urljoin(_ROOT_, self.clean_url(url)))
return r.text
def extract_urls(self, text) :
"""
Author: Jason
This method will take the contents of a page and extract all of the URLs on it
"""
urls = []
soup = BeautifulSoup(text, 'html.parser')
for atag in soup.find_all('a'):
urls.append(atag.get('href'))
for img in soup.find_all('img'):
urls.append(img.get('src'))
return urls
def external_link(self, url) :
"""
Author: Jason
This method will check if the URL is an external link outside the root domain
"""
if url :
url = re.compile('https*://').sub('', url)
if re.compile('.*lyle.smu.edu/~fmoore.*').match(url) :
return False
elif re.compile('www.*').match(url) :
return True
elif re.compile('java-source.*').match(url) :
return True
elif re.compile('.*smu.edu.*').match(url) :
return True
elif re.compile('.*.aspx').match(url) :
return True
elif re.compile('mailto:').match(url) :
return True
elif re.compile('.*.xlsx').match(url) :
return False
elif requests.get(_ROOT_ + url).status_code == 200 :
return False
elif self.jpeg_link(url) :
return False
else :
return True
else :
return True
def jpeg_link(self, url) :
"""
Author: Jason
This method will check if the link is a JPEG
"""
return True if re.compile('.*.jpg').match(url) else False
def broken_link(self, url) :
"""
Author: Jason
This method will check if the link is broken.
"""
return False if requests.get(_ROOT_ + self.clean_url(url)).status_code == 200 else True
def excel_link(self,url) :
"""
Author: Jason
This method will check if the link is an excel file.
"""
return True if re.compile('.*.xlsx').match(url) else False
def add_root_to_links(self, urls) :
"""
Author: Jason
This method will add the root URL to all of the links for visual apperance
"""
new_urls = [_ROOT_ + re.compile('http://lyle.smu.edu/~fmoore/').sub('', link) for link in urls]
return new_urls
def remove_extra_whitespace(self, text) :
"""
Author: Nicole
This method removes more than one white space between words.
"""
p = re.compile(r'\s+')
return p.sub(' ', text)
def remove_punctuation(self, text) :
"""
Author: Nicole
This method uses regex to remove the punctuation in text.
http://stackoverflow.com/questions/265960/best-way-to-strip-punctuation-from-a-string-in-python
"""
exclude = set(string.punctuation)
return ''.join(ch for ch in text if ch not in exclude)
def load_stop_words(self, file) :
"""
Author: Nicole
This method stores the list of stopwords from a file to the class
variable list self.stopwords.
"""
self.stopwords = [line.rstrip(' \n').lower() for line in open(file)]
def prepare_text(self, text) :
"""
Author: Nicole
This method prepares the raw HTML text for it to be indexed by lowering
the letters, removing the HTML tags, removing the punctuation, removing
the extra white space, changing the list to ASCII from unicode, removing
the stop words, and stemming each word.
"""
text = strip_tags(text.lower())
text = self.remove_punctuation(text)
text = self.remove_extra_whitespace(text)
text = [word.encode('UTF8') for word in text.split()]
text = [word for word in text if word not in self.stopwords]
text = self.p.stem_word(text)
return text
def add_root_if_not_there(self, url) :
"""
Author: Jason
This method will add the root url to a single link if it isnt there
"""
url = re.compile('http://lyle.smu.edu/~fmoore/').sub('', url)
return _ROOT_ + url
def index(self, url, doc_words) :
"""
Author: Nicole
This method indexes all the words in a document and keeps track of
the frequency of a word in overall documents and overall occurrences.
"""
for key in doc_words :
if key not in self.all_words:
self.all_words[key] = [(url, doc_words[key])]
self.all_words_freq[key] = [1, doc_words[key]]
self.vocabulary.append(key)
# [word][docID] = word_freq
# print '['+str(self.vocabulary.index(key))+']['+str(self.docs[self.add_root_if_not_there(url)])+'] = ' + str(self.all_words[key][0][1])
self.doc_term_matrix[self.vocabulary.index(key)][self.docs[self.add_root_if_not_there(url)]] = self.all_words[key][0][1]
else:
self.all_words[key].append((url, doc_words[key]))
self.all_words_freq[key][0] += 1
self.all_words_freq[key][1] += doc_words[key]
for tup in self.all_words[key] :
if tup[0] == str(url) :
self.doc_term_matrix[self.vocabulary.index(key)][self.docs[self.add_root_if_not_there(url)]] = tup[1]
def calTFIDF(self, word, visited) :
"""
Author: Nicole
This method will calculate the TF-IDF for a given word.
1 + log(number of times word appears in a document) * log(total documents/ how many documents the word appears in)
"""
if word in self.all_words:
for i in self.all_words[word] :
return (1 + log10(i[1])) * log10(len(visited)/self.all_words_freq[word][0])
else :
return 0
def write_output(self, visited, external, jpeg, broken, dictionary) :
"""
Author: Jason and Nicole but mostly Jason except for lines 211 - 213
This method will write the output of the crawler and the 20 most common words to output.txt
"""
dictionary = sorted(dictionary.items(), key=lambda e: e[1][1], reverse=True)[:20]
f = open('output.txt', 'w')
f.write('Output of Jason and Nicole\'s web crawler.\n')
f.write('Current Time: ')
f.write(strftime("%Y-%m-%d %H:%M:%S", localtime()))
f.write('\n\n')
# Visited links
f.write('Visited Links: (' + str(len(visited)) + ' total)\n')
for link in visited :
f.write(link + '\n')
f.write('\n')
# External links
f.write('External Links: (' + str(len(external)) + ' total)\n')
for link in external :
f.write(link + '\n')
f.write('\n')
# JPEG links
f.write('JPEG Links: (' + str(len(jpeg)) + ' total)\n')
for link in jpeg :
f.write(link + '\n')
f.write('\n')
# Broken links
f.write('Broken Links: (' + str(len(broken)) + ' total)\n')
for link in broken :
f.write(link + '\n')
f.write('\n')
# Term Frequency
f.write('Top 20 Most Common Words with Document Frequency\n')
for i in dictionary:
f.write('The term ' + i[0] + ' occurs ' + str(i[1][1]) + ' times in ' + str(i[1][0]) + ' documents.\n')
f.close()
f = open('term_document_frequency_matrix.txt', 'w')
f.write('Term/Document Frequency Matrix for Jason and Nicole\'s web crawler.\n')
f.write('Current Time: ')
f.write(strftime("%Y-%m-%d %H:%M:%S", localtime()))
f.write('\n\n ') # 15 spaces
for key, val in self.docs.iteritems() :
f.write('{0:60}'.format(key))
f.write('\n')
for i in range(0,len(self.vocabulary)) :
f.write('{0:15}'.format(self.vocabulary[i]))
for j in range(0,23) :
f.write('{}'.format(self.appears(self.doc_term_matrix[i][j])).ljust(60))
f.write('\n')
f.close()
def appears(self, i) :
"""
Author: Jason
This method will return 1 if the frequency (i) is greater than 1. It is
used for writing the term/document frequency matrix
"""
if i >= 1 :
return 1
else:
return 0
def clean_external_links(self, external) :
"""
Author: Jason
This method will cremove the non links from the external links
"""
urls = []
for link in external :
if link == None :
return urls
else :
urls.append(link)
return urls
def query_engine(self, N):
"""
Author: Jason
This method will be the main query handler.
self.all_words format (var info below): [('spring'), [('url', 3), ('other_page', 4)] ]
word tuples(url, frequency)
"""
print "#################################################################"
print "################ Jason and Nicoles' Web Crawler #################"
print "#################################################################"
print
print "Please enter a query to search the lyle.smu.edu/~fmoore domain."
print "Search will display top " + str(N) + " results or all results that query is found on."
print "Type 'quit' to exit the search engine"
user_input = ""
while True :
user_input = raw_input("> ")
if user_input == "quit" or user_input == "Quit" or user_input == "QUIT":
break
query = self.p.stem_word(re.sub("[^\w]", " ", user_input).split())
query = [word.lower() for word in query]
for word in query :
if word in self.stopwords :
query.remove(word)
query_vector = [self.calTFIDF(word, self.visited) for word in query]
docs = {}
for doc_name, ID in self.docs.iteritems() :
vector = []
for word in query :
if word in self.vocabulary :
if self.doc_term_matrix[self.vocabulary.index(word)][self.docs[self.add_root_if_not_there(doc_name)]] >= 1 :
vector.append(1)
else :
vector.append(0)
docs[doc_name] = self.normalize_vector(vector)
rankings = {}
for url, doc_vec in docs.iteritems() :
rankings[url] = self.calculate_cosine_similarity(doc_vec, query_vector)
sorted_rankings = sorted(rankings.items(), key=operator.itemgetter(1), reverse=True)
i = 0
if sorted_rankings[0][1] == 0.0 :
print '%s not found in domain.\n' % user_input
continue
print ' Score: Document:'
while i < N :
if sorted_rankings[i][1] == 0.0 :
break
print ' {0:4f}'.format(sorted_rankings[i][1]) + ' {}'.format(sorted_rankings[i][0])
i += 1
print
return
def normalize_vector(self, vector) :
"""
Author: Jason
This method will nomalize the vector to prep for calculate_cosine_similarity
"""
if numpy.linalg.norm(vector) == 0.0 :
return [0.0 for i in vector]
else :
return [i / numpy.linalg.norm(vector) for i in vector]
def calculate_cosine_similarity(self, doc, query) :
"""
Author: Jason
This method will calculate the cosine similarity betwee two vectors of equal size
"""
if len(doc) != len(query) :
return 0.0
return numpy.dot(doc,query)
def crawl(self, pages_to_index) :
"""
Author: Jason and Nicole
This is the main worker method. It will parse the urls, add the words to
the index, get the next links, and continue looping through the queue until
the number of pages to index is met.
"""
parser = robotparser.RobotFileParser()
parser.set_url(urlparse.urljoin(_ROOT_, 'robots.txt'))
parser.read()
# Add _ROOT_ url to queue
urlqueue = [_ROOT_]
# visited, external, jpeg, and broken links
visited, external, jpeg, broken = [], [], [], []
# pages indexd
pages_indexed = 0
while urlqueue:
# get flast element in urlqueue
url = urlqueue.pop(-1)
if self.clean_url(url) in visited:
continue
# check if we can fetch the page first
if parser.can_fetch('*', urlparse.urljoin('/', url)) :
# remove the / at the beginning of the string
url = re.compile('^/').sub('',url)
# fetch the page
page = self.fetch(url)
# add page to visited links
visited.append(self.clean_url(url))
# get urls from page
new_urls = self.extract_urls(page)
for new_url in new_urls :
# check if we have already visited it or are going to
if new_url not in visited and new_url not in urlqueue and new_url not in jpeg and new_url not in broken and new_url not in external :
if self.external_link(new_url) :
external.append(new_url)
elif self.jpeg_link(new_url) :
jpeg.append(new_url)
elif self.excel_link(new_url) :
visited.append(new_url)
elif self.broken_link(new_url) :
broken.append(new_url)
else :
urlqueue.append(new_url)
# docs and page id
self.docs[self.add_root_if_not_there(url)] = pages_indexed
# checks to see if url is parsable aka .html, .htm, .txt
# if yes, then parse and index; if no, pass
filename, file_extension = os.path.splitext(url)
if not (file_extension == ".pdf" or file_extension == ".pptx") :
pagetext = requests.get(_ROOT_ + self.clean_url(url))
pagetext = pagetext.text
cleantext = self.prepare_text(pagetext)
doc_words = Counter(cleantext)
self.index(url, doc_words)
# increment the pages indexed
pages_indexed += 1
if int(pages_indexed) >= int(pages_to_index):
break
# end if
# end while
# clean the links for visual appearance
visited = set(self.add_root_to_links(visited))
self.visited = visited
jpeg = self.add_root_to_links(jpeg)
broken = self.add_root_to_links(broken)
external = self.clean_external_links(external)
# write to output file
self.write_output(visited, external, jpeg, broken, self.all_words_freq)
# query engine with N=5
self.query_engine(5)
#!/usr/bin/env python
import sys
sys.path.append('/home/yipei/Twitter/FeatureExtraction/code/util')
from collections import defaultdict
import os.path as path
from stemmer import PorterStemmer
import re
import TwitterParser as Tparse
stemmer = PorterStemmer()
filelist = sys.argv[1]
outputdir = sys.argv[2]
for line in open(filelist):
line = line.strip()
fin = open(line, 'r')
clip = path.basename(line).split(".")[0]
print "process ", clip
boffile = path.join(outputdir, clip+'.bof')
fout=open(boffile, 'w')
wordDict=defaultdict(int)
wordDict.clear()
#go through all tweets and count for the number of each term
while True:
def __init__(self, language):
PorterStemmer.__init__(self)
def GetDataset():
np.random.shuffle(emails)
x_vals = []
y_vals = []
stemmer = PorterStemmer()
word_mapping = GetWordDictionary(emails)
i = 0
text_data = []
for i in range(0, len(emails)):
#print "Evaluation Email %d" % (i)
# note: time diff in mins
email, next_email, time_diff, label = emails[i]
# Create feature array
features = []
#Feature 1: Number of to
features.append(len(email['to']))
# Feature 2: Num words
words = email['body'].split()
lower_case_body = [
stemmer.stem(x.lower(), 0,
len(x) - 1) for x in words
]
features.append(len(words))
# Feature 3: Number of CC
features.append(email['cc_count'])
# Feature 4: is reply
if email['is_re']:
features.append(1)
else:
features.append(0)
# Feature 5: Time of Day (hour)
date = email['date']['local_date']
hour = date.hour
features.append(hour)
# Feature 6: Length of Subject Line
subject_words = email['subject'].split()
lower_case_subject = [
stemmer.stem(x.lower(), 0,
len(x) - 1) for x in subject_words
]
features.append(len(subject_words))
# Feature 7: Day of Week
features.append(date.weekday())
# Feature 8: # Question marks in Body, bool in body
features.append(email['body'].count('?'))
# Feature 9: # Question marks in Subject, bool in subject
features.append(email['subject'].count('?'))
# NEW FEATURES
# boolean: presence of ? in body / header
features.append(1 if '?' in email['body'] else 0)
features.append(1 if '?' in email['subject'] else 0)
# Feature 12-13: "RESPONSE NEEDED" in subject or body
keywords = ['response', 'please', 'can', 'urgent', 'important', 'need']
for keyword in keywords:
stemmed_keyword = stemmer.stem(keyword, 0, len(keyword) - 1)
features.append(1 if stemmed_keyword in lower_case_subject else 0)
features.append(1 if stemmed_keyword in lower_case_body else 0)
x_vals.append(features)
y_vals.append(label)
X = np.array(x_vals)
Y = np.array(y_vals)
return X, Y
import glob
import os
import re
import string
from bs4 import BeautifulSoup
from stemmer import PorterStemmer
here = lambda *x: os.path.abspath(os.path.join(os.path.dirname(__file__), *x))
data_dir = here('data', )
corpus_dir = here('corpus', )
total_files = 0
p = PorterStemmer()
if not os.path.exists(corpus_dir):
os.makedirs(corpus_dir)
os.chdir(data_dir)
for file in glob.glob('*.sgm'):
current_file = os.path.join(data_dir, file)
print 'Extract files from file %s' % current_file
soup = BeautifulSoup(open(current_file))
for document in soup.find_all('reuters'):
new_file = os.path.join(corpus_dir, document.get('newid'))
with open(new_file, "wb") as extracted_file:
read_data = document.get_text().encode('utf-8')
clean_data = re.sub(r'/', ' / ', read_data)
clean_data = re.sub(r'-', ' - ', clean_data)
"""
The punctuations contained in the string.punctuation are
