# Create clean_train_reviews and clean_test_reviews as we did before
#
# Read data from files
train = pd.read_csv( os.path.join(os.path.dirname(__file__), 'data', 'labeledTrainData.tsv'), header=0, delimiter="\t", quoting=3 )
test = pd.read_csv(os.path.join(os.path.dirname(__file__), 'data', 'testData.tsv'), header=0, delimiter="\t", quoting=3 )
print("Cleaning training reviews")
clean_train_reviews = []
for review in train["review"]:
clean_train_reviews.append( KaggleWord2VecUtility.review_to_wordlist( review, \
remove_stopwords=True ))
print("Cleaning test reviews")
clean_test_reviews = []
for review in test["review"]:
clean_test_reviews.append( KaggleWord2VecUtility.review_to_wordlist( review, \
remove_stopwords=True ))
# ****** Create bags of centroids
#
# Pre-allocate an array for the training set bags of centroids (for speed)
train_centroids = np.zeros( (train["review"].size, num_clusters), \
dtype="float32" )
# Transform the training set reviews into bags of centroids
import pandas as pd
import numpy as np
path = 'D:/dataset/word2vec/'
train = pd.read_csv(path + 'labeledTrainData.tsv',
header=0,
delimiter="\t",
quoting=3)
test = pd.read_csv(path + 'testData.tsv', header=0, delimiter="\t", quoting=3)
y = train["sentiment"]
print("Cleaning and parsing movie reviews...\n")
traindata = []
for i in range(0, len(train["review"])):
traindata.append(" ".join(
KaggleWord2VecUtility.review_to_wordlist(train["review"][i], False)))
testdata = []
for i in range(0, len(test["review"])):
testdata.append(" ".join(
KaggleWord2VecUtility.review_to_wordlist(test["review"][i], False)))
print('vectorizing... ')
tfv = TfidfVectorizer(min_df=3,
max_features=None,
strip_accents='unicode',
analyzer='word',
token_pattern=r'\w{1,}',
ngram_range=(1, 2),
use_idf=1,
smooth_idf=1,
sublinear_tf=1,
# Read data from files
train = pd.read_csv(os.path.join(os.path.dirname(__file__), 'data',
'labeledTrainData.tsv'),
header=0,
delimiter="\t",
quoting=3)
test = pd.read_csv(os.path.join(os.path.dirname(__file__), 'data',
'testData.tsv'),
header=0,
delimiter="\t",
quoting=3)
print("Cleaning training reviews")
clean_train_reviews = []
for review in train["review"]:
clean_train_reviews.append( KaggleWord2VecUtility.review_to_wordlist( review, \
remove_stopwords=True ))
print("Cleaning test reviews")
clean_test_reviews = []
for review in test["review"]:
clean_test_reviews.append( KaggleWord2VecUtility.review_to_wordlist( review, \
remove_stopwords=True ))
# ****** Create bags of centroids
#
# Pre-allocate an array for the training set bags of centroids (for speed)
train_centroids = np.zeros( (train["review"].size, num_clusters), \
dtype="float32" )
# Transform the training set reviews into bags of centroids
counter = 0
def getCleanReviews(reviews):
clean_reviews = []
for review in reviews["review"]:
clean_reviews.append( KaggleWord2VecUtility.review_to_wordlist( review, remove_stopwords=True ))
return clean_reviews
test["review"].size, unlabeled_train["review"].size ))
# Load the punkt tokenizer
tokenizer = nltk.data.load('tokenizers/punkt/english.pickle')
# ****** Split the labeled and unlabeled training sets into clean sentences
#
sentences = [] # Initialize an empty list of sentences
print("Parsing sentences from training set")
for review in train["review"]:
sentences += KaggleWord2VecUtility.review_to_sentences(review, tokenizer)
print("Parsing sentences from unlabeled set")
for review in unlabeled_train["review"]:
sentences += KaggleWord2VecUtility.review_to_sentences(review, tokenizer)
# ****** Set parameters and train the word2vec model
#
# Import the built-in logging module and configure it so that Word2Vec
# creates nice output messages
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s',\
level=logging.INFO)
# Set values for various parameters
num_features = 300 # Word vector dimensionality
min_word_count = 40 # Minimum word count
from Kaggle_bag_of_words.KaggleWord2VecUtility import KaggleWord2VecUtility
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn import cross_validation
import pandas as pd
import numpy as np
path = 'D:/dataset/word2vec/'
train = pd.read_csv(path+'labeledTrainData.tsv', header=0, delimiter="\t", quoting=3)
test = pd.read_csv(path+'testData.tsv', header=0, delimiter="\t", quoting=3 )
y = train["sentiment"]
print("Cleaning and parsing movie reviews...\n")
traindata = []
for i in range( 0, len(train["review"])):
traindata.append(" ".join(KaggleWord2VecUtility.review_to_wordlist(train["review"][i], False)))
testdata = []
for i in range(0,len(test["review"])):
testdata.append(" ".join(KaggleWord2VecUtility.review_to_wordlist(test["review"][i], False)))
print('vectorizing... ')
tfv = TfidfVectorizer(min_df=3, max_features=None,
strip_accents='unicode', analyzer='word',token_pattern=r'\w{1,}',
ngram_range=(1, 2), use_idf=1,smooth_idf=1,sublinear_tf=1,
stop_words = 'english')
X_all = traindata + testdata
lentrain = len(traindata)
print("fitting pipeline... ")
tfv.fit(X_all)
X_all = tfv.transform(X_all)
input("Press Enter to continue...")
print(
"Download text data sets. If you already have NLTK datasets downloaded, just close the Python download window..."
)
# nltk.download() # Download text data sets, including stop words
# Initialize an empty list to hold the clean reviews
clean_train_reviews = []
# Loop over each review; create an index i that goes from 0 to the length
# of the movie review list
print("Cleaning and parsing the training set movie reviews...\n")
for i in range(0, len(train["review"])):
clean_train_reviews.append(" ".join(KaggleWord2VecUtility.review_to_wordlist(train["review"][i], False)))
# ****** Create a bag of words from the training set
#
print("Creating the bag of words...\n")
# Initialize the "CountVectorizer" object, which is scikit-learn's
# bag of words tool.
vectorizer = CountVectorizer(analyzer="word", tokenizer=None, preprocessor=None, stop_words=None, max_features=5000)
# fit_transform() does two functions: First, it fits the model
# and learns the vocabulary; second, it transforms our training data
# into feature vectors. The data to fit_transform should be a list of
# strings.
train_data_features = vectorizer.fit_transform(clean_train_reviews)
