Spaces:
Build error
Build error
| import numpy as np | |
| import pandas as pd | |
| from gensim.corpora import Dictionary, MmCorpus | |
| from gensim.models import LdaModel, Word2Vec | |
| import matplotlib.pyplot as plt | |
| import streamlit as st | |
| from pyLDAvis import prepared_data_to_html | |
| import pyLDAvis.gensim_models as gensimvis | |
| # 生データ・コーパス・辞書・モデルのロード | |
| df = pd.read_csv("./raw_corpus.csv") | |
| corpus = MmCorpus('./corpus.mm') | |
| dict = Dictionary.load(f'./livedoor_demo.dict') | |
| lda = LdaModel.load('./lda_demo.model') | |
| st.caption("生データ一覧") | |
| st.dataframe(df.iloc[:100]) | |
| st.caption("記事のカテゴリ") | |
| fig, ax = plt.subplots() | |
| count = df[["CATEGORY", "DOCUMENT"]].groupby("CATEGORY").count() | |
| count.plot.pie(y="DOCUMENT", ax=ax, ylabel="", legend=False) | |
| st.pyplot(fig) | |
| # pyLDAvisによるトピックの可視化 | |
| vis = gensimvis.prepare(lda, corpus, dict) | |
| html_string = prepared_data_to_html(vis) | |
| st.components.v1.html(html_string, width=1300, height=800) | |