def main():
data_dir = "C:\\Users\\John\\Documents\\Kaggle\\Word2Vec\\"
# Read data from files
train = pd.read_csv(data_dir + "labeledTrainData.tsv", header=0, delimiter="\t", quoting=3)
test = pd.read_csv(data_dir + "testData.tsv", header=0, delimiter="\t", quoting=3)
unlabeled_train = pd.read_csv(data_dir + "unlabeledTrainData.tsv", header=0, delimiter="\t", quoting=3)
# Verify the number of reviews that were read (100,000 in total)
print "Read %d labeled train reviews, %d labeled test reviews, and %d unlabeled reviews\n" % (
train["review"].size,
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
# Initialize an empty list of sentences
sentences = []
print "Parsing sentences from training set"
for review in train["review"]:
sentences += KaggleUtility.review_to_sentences(review, tokenizer)
print "Parsing sentences from unlabeled set"
for review in unlabeled_train["review"]:
sentences += KaggleUtility.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
num_workers = 4 # Number of threads to run in parallel
context = 10 # Context window size
downsampling = 1e-3 # Downsample setting for frequent words
# Initialize and train the model (this will take some time)
print "Training Word2Vec model..."
model = Word2Vec(
sentences,
workers=num_workers,
size=num_features,
min_count=min_word_count,
window=context,
sample=downsampling,
seed=1,
)
# If you don't plan to train the model any further, calling
# init_sims will make the model much more memory-efficient.
model.init_sims(replace=True)
# It can be helpful to create a meaningful model name and
# save the model for later use. You can load it later using Word2Vec.load()
model_name = "300features_40minwords_10context"
model.save(data_dir + model_name)
model.doesnt_match("man woman child kitchen".split())
model.doesnt_match("france england germany berlin".split())
model.doesnt_match("paris berlin london austria".split())
model.most_similar("man")
model.most_similar("queen")
model.most_similar("awful")
# Create average vectors for the training and test sets
print "Creating average feature vecs for training reviews"
train_data_vecs = get_avg_feature_vecs(get_clean_reviews(train), model, num_features)
print "Creating average feature vecs for test reviews"
test_data_vecs = get_avg_feature_vecs(get_clean_reviews(test), model, num_features)
# Fit a random forest to the training set, then make predictions
# Fit a random forest to the training data, using 100 trees
forest = RandomForestClassifier(n_estimators=100)
print "Fitting a random forest to labeled training data..."
forest = forest.fit(train_data_vecs, train["sentiment"])
# Test & extract results
result = forest.predict(test_data_vecs)
# Write the test results
output = pd.DataFrame(data={"id": test["id"], "sentiment": result})
output.to_csv(data_dir + "Word2Vec_AverageVectors.csv", index=False, quoting=3)
print "Wrote Word2Vec_AverageVectors.csv"
def main():
data_dir = 'C:\\Users\\John\\Documents\\Kaggle\\Word2Vec\\'
model = Word2Vec.load(data_dir + '300features_40minwords_10context')
# Run k-means on the word vectors and print a few clusters
# Start time
start = time.time()
# Set "k" (num_clusters) to be 1/5th of the vocabulary size, or an
# average of 5 words per cluster
word_vectors = model.syn0
num_clusters = word_vectors.shape[0] / 5
# Initialize a k-means object and use it to extract centroids
print 'Running K means'
kmeans_clustering = KMeans(n_clusters=num_clusters)
idx = kmeans_clustering.fit_predict(word_vectors)
# Get the end time and print how long the process took
end = time.time()
elapsed = end - start
print 'Time taken for K Means clustering: ', elapsed, 'seconds.'
# Create a Word / Index dictionary, mapping each vocabulary word to
# a cluster number
word_centroid_map = dict(zip(model.index2word, idx))
# Print the first ten clusters
for cluster in xrange(0, 10):
# Print the cluster number
print '\nCluster %d' % cluster
# Find all of the words for that cluster number, and print them out
words = []
for i in xrange(0, len(word_centroid_map.values())):
if word_centroid_map.values()[i] == cluster:
words.append(word_centroid_map.keys()[i])
print words
# Create clean_train_reviews and clean_test_reviews as we did before
# Read data from files
train = pd.read_csv(data_dir + 'labeledTrainData.tsv', header=0, delimiter='\t', quoting=3)
test = pd.read_csv(data_dir + 'testData.tsv', header=0, delimiter='\t', quoting=3)
print 'Cleaning training reviews'
clean_train_reviews = []
for review in train['review']:
clean_train_reviews.append(KaggleUtility.review_to_wordlist(review, remove_stopwords=True))
print 'Cleaning test reviews'
clean_test_reviews = []
for review in test['review']:
clean_test_reviews.append(KaggleUtility.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
for review in clean_train_reviews:
train_centroids[counter] = create_bag_of_centroids(review, word_centroid_map)
counter += 1
# Repeat for test reviews
test_centroids = np.zeros((test['review'].size, num_clusters), dtype='float32')
counter = 0
for review in clean_test_reviews:
test_centroids[counter] = create_bag_of_centroids(review, word_centroid_map)
counter += 1
# Fit a random forest and extract predictions
forest = RandomForestClassifier(n_estimators=100)
# Fitting the forest may take a few minutes
print 'Fitting a random forest to labeled training data...'
forest = forest.fit(train_centroids, train['sentiment'])
result = forest.predict(test_centroids)
# Write the test results
output = pd.DataFrame(data={'id': test['id'], 'sentiment': result})
output.to_csv(data_dir + 'BagOfCentroids.csv', index=False, quoting=3)
print 'Wrote BagOfCentroids.csv'
def get_clean_reviews(reviews):
clean_reviews = []
for review in reviews["review"]:
clean_reviews.append(KaggleUtility.review_to_wordlist(review, remove_stopwords=True))
return clean_reviews
def main():
data_dir = 'C:\\Users\\John\\Documents\\Kaggle\\Word2Vec\\'
train = pd.read_csv(data_dir + 'labeledTrainData.tsv', header=0, delimiter='\t', quoting=3)
test = pd.read_csv(data_dir + 'testData.tsv', header=0, delimiter='\t', quoting=3)
print 'The first review is:'
print train['review'][0]
raw_input('Press Enter to continue...')
# print 'Downloading text data sets...'
# nltk.download()
# 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 xrange(0, len(train['review'])):
clean_train_reviews.append(' '.join(KaggleUtility.review_to_wordlist(train['review'][i], True)))
# 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 input to fit_transform should be a list of
# strings
train_data_features = vectorizer.fit_transform(clean_train_reviews)
# Numpy arrays are easy to work with, so convert the result to an array
train_data_features = train_data_features.toarray()
# Train a random forest using the bag of words
print 'Training the random forest (this may take a while)...'
# Initialize a Random Forest classifier with 100 trees
forest = RandomForestClassifier(n_estimators=100)
# Fit the forest to the training set, using the bag of words as
# features and the sentiment labels as the response variable
# This may take a few minutes to run
forest = forest.fit(train_data_features, train['sentiment'])
# Create an empty list and append the clean reviews one by one
clean_test_reviews = []
print 'Cleaning and parsing the test set movie reviews...\n'
for i in xrange(0, len(test['review'])):
clean_test_reviews.append(' '.join(KaggleUtility.review_to_wordlist(test['review'][i], True)))
# Get a bag of words for the test set, and convert to a numpy array
test_data_features = vectorizer.transform(clean_test_reviews)
test_data_features = test_data_features.toarray()
# Use the random forest to make sentiment label predictions
print 'Predicting test labels...\n'
result = forest.predict(test_data_features)
# Copy the results to a pandas dataframe with an "id" column and
# a "sentiment" column
output = pd.DataFrame(data={'id': test['id'], 'sentiment': result})
# Use pandas to write the comma-separated output file
output.to_csv(data_dir + 'Bag_of_Words_model.csv', index=False, quoting=3)
print 'Wrote results to Bag_of_Words_model.csv'
