def main_cluster(rootpath, folderpath, vectorizer, numclusters):
"""Get main function for getCluster."""
folderPath = os.path.join(folderpath, 'final')
vectorizer = vectorizer
numClusters = numclusters
preprocessor = Utility.PreprocessData(rootpath)
gc = Clustering.GetCluster(vectorizer, rootpath)
# get the kmeans model
print("Getting the k-means model...")
startTime = time.time()
km = gc.getKmeans(folderPath, numClusters)
print("---------- K-means: {} seconds ----------".format(time.time() -
startTime))
# get the doc2Label
print("Getting doc to label...")
gc.getDoc2Label(folderPath, km)
# get Label2Doc
print("Getting label to doc...")
gc.getLabel2Doc(folderPath, km)
# get tweets.pkl for each clusters
print("Storing tweets for clusters...")
preprocessor.storeTweets4Clusters(folderPath)
def getCluster(self, vectorizer, numclusters):
"""Get main function for getCluster.
Parameters
----------
vectorizer : str
the vectorizer used in addressing word2vec
options: 'mean', 'tfidf'
numclusters : int
the number of clusters
Returns
-------
None
"""
folderPath = os.path.join(self.folderpath, 'final')
vectorizer = vectorizer
numClusters = numclusters
preprocessor = Utility.PreprocessData(self.rootpath)
gc = Clustering.GetCluster(vectorizer, self.rootpath)
# get the kmeans model
print("Getting the k-means model...")
startTime = time.time()
km = gc.getKmeans(folderPath, numClusters)
print("---------- K-means: {} seconds ----------".format(time.time() -
startTime))
# get the doc2Label
print("Getting doc to label...")
gc.getDoc2Label(folderPath, km)
# get Label2Doc
print("Getting label to doc...")
gc.getLabel2Doc(folderPath, km)
# get tweets.pkl for each clusters
print("Storing tweets for clusters...")
preprocessor.storeTweets4Clusters(folderPath)
