add application and requirements

app.py

@@ -0,0 +1,75 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+from fugashi import Tagger
+import re
+import random
+import matplotlib.pyplot as plt
+import japanize_matplotlib
+import seaborn as sns
+from gensim.corpora.dictionary import Dictionary
+from gensim import  models
+from gensim.models.word2vec import Word2Vec
+from gensim import similarities
+
+sns.set(font='IPAexGothic')
+
+# モデルなどの読み込み
+pattern = r"[^\u3040-\u30ff\u3400-\u4dbf\u4e00-\u9fff\uf900-\ufaff\u20000-\u2ffff\sa-zA-Z]"  # 記号を取り除くための正規表現
+df = pd.read_csv("./raw_corpus.csv")  # コーパス
+dictionary = Dictionary.load("./livedoor.dict")  # 辞書
+lda = models.ldamodel.LdaModel.load("./lda.model")  # トピックモデル
+index = similarities.MatrixSimilarity.load("./lda.index")  # トピックモデルによるコーパスのindex
+word_dist = lda.get_topics()  # トピックモデルの単語分布（K, V）
+w2v = Word2Vec.load('./word2vec.gensim.model')  # 白やぎword2vec https://github.com/shiroyagicorp/japanese-word2vec-model-builder
+
+# トピックモデルの情報（トピックごとの単語分布）のDataFrame化
+num_words = 30
+topic_list = []
+word_list = []
+weight_list = []
+for n, values in lda.show_topics(num_topics=5, num_words=num_words, formatted=False): 
+    for word, weight in values: 
+        topic_list.append(n)
+        word_list.append(word)
+        weight_list.append(round(float(weight) * 100, 2))
+
+topic_df = pd.DataFrame()
+topic_df["topic"] = topic_list
+topic_df["word"] = word_list
+topic_df["weight"] = weight_list
+
+
+st.sidebar.markdown("Set Parameter")
+
+#word_list = ["任天堂", "バイオハザード", "ポケモン"]
+#atom = st.sidebar.radio("元になる単語", word_list)
+#negative = st.sidebar.radio("ー引く単語", word_list)
+#positive = st.sidebar.radio("＋足す単語", word_list)
+
+
+
+st.header("word2vecによるアナロジー")
+st.subheader("単語の演算")
+st.caption("演算対象の単語")
+col1, col2, col3 = st.columns(3)
+
+with col1:
+    #atom = st.text_input("元になる単語", atom)
+    atom = st.text_input("元になる単語")
+
+with col2:
+    #negative = st.text_input("ー引く単語", negative)
+    negative = st.text_input("ー引く単語")
+
+with col3:
+    #positive = st.text_input("＋足す単語", positive)
+    positive = st.text_input("＋足す単語")
+
+button = st.button("演算する")
+
+if button:
+    st.text(f"{atom} - {negative} + {positive}") 
+    x = w2v.wv.most_similar(positive=[atom, positive], negative=negative)
+    #st.text(f"{x}")
+    st.dataframe(x)

requirements.txt

@@ -0,0 +1,190 @@
+accelerate==0.15.0
+aiohttp==3.8.3
+aiosignal==1.3.1
+altair==4.2.0
+anyio==3.6.2
+appnope==0.1.3
+argon2-cffi==21.3.0
+argon2-cffi-bindings==21.2.0
+arrow==1.2.3
+asttokens==2.2.1
+async-timeout==4.0.2
+attrs==22.2.0
+backcall==0.2.0
+beautifulsoup4==4.11.1
+bleach==5.0.1
+blinker==1.5
+cachetools==5.3.0
+certifi==2022.12.7
+cffi==1.15.1
+charset-normalizer==2.1.1
+click==8.1.3
+comm==0.1.2
+contourpy==1.0.6
+cycler==0.11.0
+datasets==2.8.0
+debugpy==1.6.4
+decorator==5.1.1
+defusedxml==0.7.1
+dill==0.3.6
+entrypoints==0.4
+evaluate==0.4.0
+executing==1.2.0
+fastapi==0.89.0
+fastjsonschema==2.16.2
+ffmpy==0.3.0
+filelock==3.9.0
+fonttools==4.38.0
+fqdn==1.5.1
+frozenlist==1.3.3
+fsspec==2022.11.0
+fst-pso==1.8.1
+fugashi==1.2.1
+FuzzyTM==2.0.5
+gensim==4.3.0
+gitdb==4.0.10
+GitPython==3.1.30
+gradio==3.16.1
+h11==0.14.0
+httpcore==0.16.3
+httpx==0.23.3
+huggingface-hub==0.11.1
+idna==3.4
+importlib-metadata==5.2.0
+ipadic==1.0.0
+ipykernel==6.19.4
+ipython==8.7.0
+ipython-genutils==0.2.0
+ipywidgets==8.0.4
+isoduration==20.11.0
+japanize-matplotlib==1.1.3
+jedi==0.18.2
+Jinja2==3.1.2
+joblib==1.2.0
+jsonpointer==2.3
+jsonschema==4.17.3
+jupyter==1.0.0
+jupyter-console==6.4.4
+jupyter-events==0.5.0
+jupyter_client==7.4.8
+jupyter_core==5.1.1
+jupyter_server==2.0.6
+jupyter_server_terminals==0.4.3
+jupyterlab-pygments==0.2.2
+jupyterlab-widgets==3.0.5
+kiwisolver==1.4.4
+linkify-it-py==1.0.3
+markdown-it-py==2.1.0
+MarkupSafe==2.1.1
+matplotlib==3.6.2
+matplotlib-inline==0.1.6
+mdit-py-plugins==0.3.3
+mdurl==0.1.2
+miniful==0.0.6
+mistune==2.0.4
+multidict==6.0.4
+multiprocess==0.70.14
+nbclassic==0.4.8
+nbclient==0.7.2
+nbconvert==7.2.7
+nbformat==5.7.1
+nest-asyncio==1.5.6
+notebook==6.5.2
+notebook_shim==0.2.2
+numpy==1.24.1
+orjson==3.8.4
+packaging==22.0
+pandas==1.5.2
+pandocfilters==1.5.0
+parso==0.8.3
+pexpect==4.8.0
+pickleshare==0.7.5
+Pillow==9.3.0
+plac==1.3.5
+platformdirs==2.6.2
+polars==0.15.17
+portalocker==2.6.0
+prometheus-client==0.15.0
+prompt-toolkit==3.0.36
+protobuf==3.20.1
+psutil==5.9.4
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pyarrow==10.0.1
+pycparser==2.21
+pycryptodome==3.16.0
+pydantic==1.10.4
+pydeck==0.8.0
+pydub==0.25.1
+pyFUME==0.2.25
+Pygments==2.13.0
+Pympler==1.0.1
+pyparsing==3.0.9
+pyrsistent==0.19.3
+python-dateutil==2.8.2
+python-json-logger==2.0.4
+python-multipart==0.0.5
+pytz==2022.7
+pytz-deprecation-shim==0.1.0.post0
+PyYAML==6.0
+pyzmq==24.0.1
+qtconsole==5.4.0
+QtPy==2.3.0
+regex==2022.10.31
+requests==2.28.1
+responses==0.18.0
+rfc3339-validator==0.1.4
+rfc3986==1.5.0
+rfc3986-validator==0.1.1
+rich==13.2.0
+scikit-learn==1.2.0
+scipy==1.10.0
+seaborn==0.12.2
+semver==2.13.0
+Send2Trash==1.8.0
+sentencepiece==0.1.97
+simpful==2.9.0
+six==1.16.0
+smart-open==6.3.0
+smmap==5.0.0
+sniffio==1.3.0
+soupsieve==2.3.2.post1
+stack-data==0.6.2
+starlette==0.22.0
+streamlit==1.17.0
+terminado==0.17.1
+threadpoolctl==3.1.0
+tinycss2==1.2.1
+tokenizers==0.13.2
+toml==0.10.2
+toolz==0.12.0
+torch==1.13.1
+torchaudio==0.13.1
+torchdata==0.5.1
+torchtext==0.14.1
+torchvision==0.14.1
+tornado==6.2
+tqdm==4.64.1
+traitlets==5.8.0
+transformers==4.25.1
+typing_extensions==4.4.0
+tzdata==2022.7
+tzlocal==4.2
+uc-micro-py==1.0.1
+unidic==1.1.0
+unidic-lite==1.0.8
+uri-template==1.2.0
+urllib3==1.26.13
+uvicorn==0.20.0
+validators==0.20.0
+wasabi==0.10.1
+wcwidth==0.2.5
+webcolors==1.12
+webencodings==0.5.1
+websocket-client==1.4.2
+websockets==10.4
+widgetsnbextension==4.0.5
+wordcloud==1.8.2.2
+xxhash==3.2.0
+yarl==1.8.2
+zipp==3.11.0