sklearn 实现LDA主题建模

import pandas as pd
import numpy as np
import mglearn

from sklearn.decomposition import LatentDirichletAllocation
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
#from sklearn.feature_extraction.text import ENGLISH_STOP_WORDS

abstract = pd.read_csv('final_data.csv')

#train_text = abstract.loc[0:999,]
#train_text = train_text[(['TI', 'JI', 'PY', 'C1', 'AB', 'AU'])]
input_data = abstract['AB']


#vect = CountVectorizer(max_features=10000, max_df=0.8, min_df=10,
#                       stop_words&#