How to do LDA in python (for Morten)

watch.py

import numpy as np
import pandas as pd
import lda
import lda.datasets
from sklearn.feature_extraction.text import CountVectorizer


def load_questions():
    sheet = pd.read_excel('android_watch.xlsx')
    Qs = sheet['Question']
    return sheet, list(Qs)


def featurize(questions, stop_words = None):
    cv = CountVectorizer(stop_words = stop_words)
    X = cv.fit_transform(questions)
    return X, list(cv.vocabulary_)

def find_topics(features):
     model = lda.LDA(n_topics=20, n_iter=500, random_state=1)
     model.fit(features)
     return model

def report():
    s,q = load_questions()
    feats, vocab = featurize(q)
    model = find_topics(feats)
    # list topics
    n_top_words = 8
    topic_word = model.topic_word_
    for i, topic_dist in enumerate(topic_word):
        topic_words = np.array(vocab)[np.argsort(topic_dist)][:-n_top_words:-1]
        print('Topic {}: {}'.format(i, ' '.join(topic_words)))
    # list primary topic for each q
    doc_topic = model.doc_topic_
    for i in range(10):
        print("{} (top topic: {})".format(q[i], doc_topic[i].argmax()))

Koden scoret fra https://ariddell.org/lda.html (og ikke helt sikker på om alt er som det skal være)