Cluster labels

Cluster labels.py

from sklearn.feature_extraction.text import TfidfVectorizer
vectorizer = TfidfVectorizer(stop_words='english')
tfidf = vectorizer.fit_transform(df.questionText.values)
totals = 0
for cluster in df.cluster.value_counts()[0:10].index:
  stg = " ".join(df.loc[df.cluster==cluster].questionText.values)
  response = vectorizer.transform([stg])
  count = df.cluster.value_counts().loc[cluster]
  totals += count

  feature_array = np.array(vectorizer.get_feature_names())
  tfidf_sorting = np.argsort(response.toarray()).flatten()[::-1]

  n = 10
  print("Cluster Label: {}, Items in Cluster: {}".format(cluster,count))
  print(feature_array[tfidf_sorting][:n])