def main():
"""
main function to make prediction
use random forest
:return:
"""
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)
modelName = "/path/Word2VectforNLPTraining"
model = Word2Vec.load(modelName)
print("Processing training data...")
cleaned_training_data = processData.clean_data(train)
trainingDataFV = getAvgFeatureVecs(cleaned_training_data,model)
print("Processing test data...")
cleaned_test_data = processData.clean_data(test)
testDataFV = getAvgFeatureVecs(cleaned_test_data,model)
n_estimators = 100
result = randomForestClassifier.rfClassifer(n_estimators, trainingDataFV, train["sentiment"],testDataFV)
output = pd.DataFrame(data={"id": test["id"], "sentiment": result})
output.to_csv("Word2Vec_AvgVecPredict.csv", index=False, quoting=3)
def main():
modelName = "Word2VectforNLPTraining"
model = Word2Vec.load(modelName)
# model.init_sims(replace=True)
word_vectors = model.syn0
# print(word_vectors[0])
num_clusters = int(word_vectors.shape[0] / 5)
# print("number of clusters: {}".format(num_clusters))
# input("Press enter to continue:")
print("Clustering...")
startTime = time.time()
cluster_index = kMeans.kmeans(num_clusters, word_vectors)
endTime = time.time()
print("Time taken for clustering: {} seconds".format(endTime - startTime))
# create a word/index dictionary, mapping each vocabulary word to a cluster number
# zip(): make an iterator that aggregates elements from each of the iterables
index_word_map = dict(zip(model.index2word, cluster_index))
def create_bag_of_centroids(reviewData):
"""
assign each word in the review to a centroid
this returns a numpy array with the dimension as num_clusters
each will be served as one feature for classification
:param reviewData:
:return:
"""
featureVector = np.zeros(num_clusters, dtype=np.float)
for word in reviewData:
if word in index_word_map:
index = index_word_map[word]
featureVector[index] += 1
return featureVector
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)
trainingDataFV = np.zeros((train["review"].size, num_clusters), dtype=np.float)
testDataFV = np.zeros((test["review"].size, num_clusters), dtype=np.float)
print("Processing training data...")
counter = 0
cleaned_training_data = processData.clean_data(train)
for review in cleaned_training_data:
trainingDataFV[counter] = create_bag_of_centroids(review)
counter += 1
print("Processing test data...")
counter = 0
cleaned_test_data = processData.clean_data(test)
for review in cleaned_test_data:
testDataFV[counter] = create_bag_of_centroids(review)
counter += 1
n_estimators = 100
result = randomForestClassifier.rfClassifer(n_estimators, trainingDataFV, train["sentiment"],testDataFV)
output = pd.DataFrame(data={"id": test["id"], "sentiment": result})
output.to_csv("Doc2Vec_Clustering.csv", index=False, quoting=3)
