FelixChop

lda_model[corpus[0]] # corpus[0] means the first document.

FelixChop

for i,topic in lda_model.show_topics(formatted=True, num_topics=num_topics, num_words=10):
    print(str(i)+": "+ topic)
    print()

FelixChop

from gensim import corpora, models

# list_of_list_of_tokens = [["a","b","c"], ["d","e","f"]]
# ["a","b","c"] are the tokens of document 1, ["d","e","f"] are the tokens of document 2...
dictionary_LDA = corpora.Dictionary(list_of_list_of_tokens)
dictionary_LDA.filter_extremes(no_below=3)
corpus = [dictionary_LDA.doc2bow(list_of_tokens) for list_of_tokens in list_of_list_of_tokens]

num_topics = 20
%time lda_model = models.LdaModel(corpus, num_topics=num_topics, \

FelixChop

from gensim import corpora, models

# list_of_list_of_tokens = [["a","b","c"], ["d","e","f"]]
# ["a","b","c"] are the tokens of document 1, ["d","e","f"] are the tokens of document 2...
dictionary_LDA = corpora.Dictionary(list_of_list_of_tokens)
dictionary_LDA.filter_extremes(no_below=3)
corpus = [dictionary_LDA.doc2bow(list_of_tokens) for list_of_tokens in list_of_list_of_tokens]

num_topics = 20
%time lda_model = models.LdaModel(corpus, num_topics=num_topics, \

FelixChop

from gensim import corpora, models

dictionary_LDA = corpora.Dictionary(list_of_list_of_tokens)
dictionary_LDA.filter_extremes(no_below=3)
corpus = [dictionary_LDA.doc2bow(list_of_tokens) for list_of_tokens in list_of_list_of_tokens]

num_topics = 20
%time lda_model = models.LdaModel(corpus, num_topics=num_topics, \
                                  id2word=dictionary_LDA, \
                                  passes=4, alpha=[0.01]*num_topics, \

FelixChop

FelixChop

dictionary = {}

for i,row in data.iterrows():
  dictionary[row['column_1']] = row['column_2']

FelixChop

data.groupby('column_1')['column_2'].apply(sum).reset_index()

FelixChop

data.merge(other_data, on=['column_1', 'column_2', 'column_3'])

FelixChop

pd.plotting.scatter_matrix(data, figsize=(12,8))