diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..55cab133643a2a73e083373d2106533678d0edd5 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -8,6 +8,7 @@
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.lz4 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
@@ -33,3 +34,25 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
+# Audio files - uncompressed
+*.pcm filter=lfs diff=lfs merge=lfs -text
+*.sam filter=lfs diff=lfs merge=lfs -text
+*.raw filter=lfs diff=lfs merge=lfs -text
+# Audio files - compressed
+*.aac filter=lfs diff=lfs merge=lfs -text
+*.flac filter=lfs diff=lfs merge=lfs -text
+*.mp3 filter=lfs diff=lfs merge=lfs -text
+*.ogg filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+# Image files - uncompressed
+*.bmp filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.tiff filter=lfs diff=lfs merge=lfs -text
+# Image files - compressed
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.webp filter=lfs diff=lfs merge=lfs -text
+# Video files - compressed
+*.mp4 filter=lfs diff=lfs merge=lfs -text
+*.webm filter=lfs diff=lfs merge=lfs -text
diff --git a/.github/workflows/update_space.yml b/.github/workflows/update_space.yml
new file mode 100644
index 0000000000000000000000000000000000000000..67dbc84e4e59320a7c98b94460eb976e5cd2984f
--- /dev/null
+++ b/.github/workflows/update_space.yml
@@ -0,0 +1,28 @@
+name: Run Python script
+
+on:
+ push:
+ branches:
+ - main
+
+jobs:
+ build:
+ runs-on: ubuntu-latest
+
+ steps:
+ - name: Checkout
+ uses: actions/checkout@v2
+
+ - name: Set up Python
+ uses: actions/setup-python@v2
+ with:
+ python-version: '3.9'
+
+ - name: Install Gradio
+ run: python -m pip install gradio
+
+ - name: Log in to Hugging Face
+ run: python -c 'import huggingface_hub; huggingface_hub.login(token="${{ secrets.hf_token }}")'
+
+ - name: Deploy to Spaces
+ run: gradio deploy
diff --git a/README.md b/README.md
index e4d372802859cc798d43f5e7e2114bdb838f2d3a..b00dba207f6cdf61a2ab35090f783f55cf99806d 100644
--- a/README.md
+++ b/README.md
@@ -1,12 +1,6 @@
---
-title: Npb Data Viz Demo
-emoji: 🐨
-colorFrom: red
-colorTo: indigo
+title: npb_data_viz_demo
+app_file: demo.py
sdk: gradio
sdk_version: 4.44.0
-app_file: app.py
-pinned: false
---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/__pycache__/translate.cpython-310.pyc b/__pycache__/translate.cpython-310.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..c257adbc7c5107398dbc2c8f28c1ee9c956f3caf
Binary files /dev/null and b/__pycache__/translate.cpython-310.pyc differ
diff --git a/demo.py b/demo.py
new file mode 100644
index 0000000000000000000000000000000000000000..f3ec2668195b4b8c071942c235ee199bfbeee99e
--- /dev/null
+++ b/demo.py
@@ -0,0 +1,88 @@
+
+import pandas as pd
+import numpy as np
+from tqdm.auto import tqdm
+import plotly.express as px
+import gradio as gr
+from gradio_client import Client
+
+import os
+import re
+
+from translate import translate_pa_outcome, translate_pitch_outcome, jp_pitch_to_en_pitch, jp_pitch_to_pitch_code, translate_pitch_outcome
+
+# load game data
+game_df = pd.read_csv('game.csv').drop_duplicates()
+assert len(game_df) == len(game_df['game_pk'].unique())
+
+# load pa data
+pa_df = []
+for game_pk in tqdm(game_df['game_pk']):
+ pa_df.append(pd.read_csv(os.path.join('pa', f'{game_pk}.csv'), dtype={'pa_pk': str}))
+pa_df = pd.concat(pa_df, axis='rows')
+
+# load pitch data
+pitch_df = []
+for game_pk in tqdm(game_df['game_pk']):
+ pitch_df.append(pd.read_csv(os.path.join('pitch', f'{game_pk}.csv'), dtype={'pa_pk': str}))
+pitch_df = pd.concat(pitch_df, axis='rows')
+pitch_df
+
+# load player data
+player_df = pd.read_csv('player.csv')
+player_df
+
+# translate pa data
+pa_df['_des'] = pa_df['des'].str.strip()
+pa_df['des'] = pa_df['des'].str.strip()
+pa_df['des_more'] = pa_df['des_more'].str.strip()
+pa_df.loc[pa_df['des'].isna(), 'des'] = pa_df[pa_df['des'].isna()]['des_more']
+pa_df.loc[:, 'des'] = pa_df['des'].apply(lambda item: item.split()[0] if (len(item.split()) > 1 and re.search(r'＋\d+点', item)) else item)
+non_home_plate_outcome = (pa_df['des'].isin(['ボール', '見逃し', '空振り'])) | (pa_df['des'].str.endswith('塁けん制'))
+pa_df.loc[non_home_plate_outcome, 'des'] = pa_df.loc[non_home_plate_outcome, 'des_more']
+pa_df['des'] = pa_df['des'].apply(translate_pa_outcome)
+
+# translate pitch data
+pitch_df = pitch_df[~pitch_df['pitch_name'].isna()]
+pitch_df.loc[:, 'jp_pitch_name'] = pitch_df['pitch_name']
+pitch_df.loc[:, 'pitch_name'] = pitch_df['jp_pitch_name'].apply(lambda pitch_name: jp_pitch_to_en_pitch[pitch_name])
+pitch_df.loc[:, 'pitch_type'] = pitch_df['jp_pitch_name'].apply(lambda pitch_name: jp_pitch_to_pitch_code[pitch_name])
+pitch_df.loc[:, 'description'] = pitch_df['description'].apply(lambda item: item.split()[0] if len(item.split()) > 1 else item)
+pitch_df.loc[:, 'description'] = pitch_df['description'].apply(translate_pitch_outcome)
+
+# translate player data
+client = Client("Ramos-Ramos/npb_name_translator")
+en_names = client.predict(
+ jp_names='\n'.join(player_df.name.tolist()),
+ api_name="/predict"
+)
+player_df['jp_name'] = player_df['name']
+player_df['name'] = [name if name != 'nan' else np.nan for name in en_names.splitlines()]
+
+# merge pitch and pa data
+df = pd.merge(pitch_df, pa_df, 'inner', on=['game_pk', 'pa_pk'])
+df = pd.merge(df, player_df.rename(columns={'player_id': 'pitcher'}), 'inner', on='pitcher')
+df['whiff'] = df['description'].isin(['SS', 'K'])
+df['swing'] = ~df['description'].isin(['B', 'BB', 'LS', 'inv_K', 'bunt_K', 'HBP', 'SH', 'SH E', 'SH FC', 'obstruction', 'illegal_pitch', 'defensive_interference'])
+
+# gradio function(s)
+def get_usage(player):
+ _df = df.set_index('name').loc[player, 'pitch_name'].value_counts()
+ fig = px.pie(df.set_index('name').loc[player, 'pitch_name'], names='pitch_name')
+ fig.update_traces(texttemplate='%{percent:.1%}', hovertemplate=f'{player}
' + 'threw a %{label}
%{percent:.1%} of the time
(%{value}