ENH: Add K-Celebs

gramener · Oct 1, 2024 · 749ac3a · 749ac3a
1 parent 5831a85
commit 749ac3a
Show file tree

Hide file tree

Showing 99 changed files with 27 additions and 0 deletions.
diff --git a/config.json b/config.json
@@ -29,6 +29,12 @@
       "body": "The explorer is designed to celebrate the diversity and talent of Indian cinema, making it a go-to resource for fans and researchers alike.",
       "folder": "indian-actors",
       "source": ""
+    },
+    {
+      "title": "Korean Actors",
+      "body": "This explores 100 most popular celebrities associated with Korea from the TMDb. See who's happy, sad, casual, formal, and more.",
+      "folder": "kcelebs",
+      "source": "https://huggingface.co/datasets/ashraq/tmdb-celeb-10k"
     }
   ]
 }
diff --git a/kcelebs/Ahn Hyo-Seop.jpg b/kcelebs/Ahn Hyo-Seop.jpg
diff --git a/kcelebs/Ahn So-hee.jpg b/kcelebs/Ahn So-hee.jpg
diff --git a/kcelebs/Ali Liebert.jpg b/kcelebs/Ali Liebert.jpg
diff --git a/kcelebs/Angeli Khang.jpg b/kcelebs/Angeli Khang.jpg
diff --git a/kcelebs/Bae Doona.jpg b/kcelebs/Bae Doona.jpg
diff --git a/kcelebs/Byeon Woo-seok.jpg b/kcelebs/Byeon Woo-seok.jpg
diff --git a/kcelebs/Cha Eun-woo.jpg b/kcelebs/Cha Eun-woo.jpg
diff --git a/kcelebs/Chae Soo-bin.jpg b/kcelebs/Chae Soo-bin.jpg
diff --git a/kcelebs/Cho Yeo-jeong.jpg b/kcelebs/Cho Yeo-jeong.jpg
diff --git a/kcelebs/Choi Woo-shik.jpg b/kcelebs/Choi Woo-shik.jpg
diff --git a/kcelebs/Dalpalan.jpg b/kcelebs/Dalpalan.jpg
diff --git a/kcelebs/Fan Bingbing.jpg b/kcelebs/Fan Bingbing.jpg
diff --git a/kcelebs/Go Kyung-pyo.jpg b/kcelebs/Go Kyung-pyo.jpg
diff --git a/kcelebs/Han Hyo-joo.jpg b/kcelebs/Han Hyo-joo.jpg
diff --git a/kcelebs/Han Seo-ah.jpg b/kcelebs/Han Seo-ah.jpg
diff --git a/kcelebs/Han So-hee.jpg b/kcelebs/Han So-hee.jpg
diff --git a/kcelebs/Heo Sung-tae.jpg b/kcelebs/Heo Sung-tae.jpg
diff --git a/kcelebs/IU.jpg b/kcelebs/IU.jpg
diff --git a/kcelebs/Jang Gwang.jpg b/kcelebs/Jang Gwang.jpg
diff --git a/kcelebs/Jennie Kim.jpg b/kcelebs/Jennie Kim.jpg
diff --git a/kcelebs/Jeon Bae-soo.jpg b/kcelebs/Jeon Bae-soo.jpg
diff --git a/kcelebs/Jeong Yoo-jin.jpg b/kcelebs/Jeong Yoo-jin.jpg
diff --git a/kcelebs/Ji Chang-wook.jpg b/kcelebs/Ji Chang-wook.jpg
diff --git a/kcelebs/Ji Eun-seo.jpg b/kcelebs/Ji Eun-seo.jpg
diff --git a/kcelebs/Jun Ji-hyun.jpg b/kcelebs/Jun Ji-hyun.jpg
diff --git a/kcelebs/Jung So-min.jpg b/kcelebs/Jung So-min.jpg
diff --git a/kcelebs/Jung Suk-won.jpg b/kcelebs/Jung Suk-won.jpg
diff --git a/kcelebs/Jung Woo-sung.jpg b/kcelebs/Jung Woo-sung.jpg
diff --git a/kcelebs/Kang Eun-hye.jpg b/kcelebs/Kang Eun-hye.jpg
diff --git a/kcelebs/Kang Ha-neul.jpg b/kcelebs/Kang Ha-neul.jpg
diff --git a/kcelebs/Kang Tae-oh.jpg b/kcelebs/Kang Tae-oh.jpg
diff --git a/kcelebs/Kim Bum.jpg b/kcelebs/Kim Bum.jpg
diff --git a/kcelebs/Kim Do-hee.jpg b/kcelebs/Kim Do-hee.jpg
diff --git a/kcelebs/Kim Go-eun.jpg b/kcelebs/Kim Go-eun.jpg
diff --git a/kcelebs/Kim Hee-jeong.jpg b/kcelebs/Kim Hee-jeong.jpg
diff --git a/kcelebs/Kim Jae-young.jpg b/kcelebs/Kim Jae-young.jpg
diff --git a/kcelebs/Kim Min-gue.jpg b/kcelebs/Kim Min-gue.jpg
diff --git a/kcelebs/Kim Min-ki.jpg b/kcelebs/Kim Min-ki.jpg
diff --git a/kcelebs/Kim Roi-ha.jpg b/kcelebs/Kim Roi-ha.jpg
diff --git a/kcelebs/Kim Se-jeong.jpg b/kcelebs/Kim Se-jeong.jpg
diff --git a/kcelebs/Kim Si-a.jpg b/kcelebs/Kim Si-a.jpg
diff --git a/kcelebs/Kim So-hyun.jpg b/kcelebs/Kim So-hyun.jpg
diff --git a/kcelebs/Kim Soo-ji.jpg b/kcelebs/Kim Soo-ji.jpg
diff --git a/kcelebs/Kim Tae-hyung.jpg b/kcelebs/Kim Tae-hyung.jpg
diff --git a/kcelebs/Kim Tae-ri.jpg b/kcelebs/Kim Tae-ri.jpg
diff --git a/kcelebs/Kim Yoo-yeon.jpg b/kcelebs/Kim Yoo-yeon.jpg
diff --git a/kcelebs/Kim You-jung.jpg b/kcelebs/Kim You-jung.jpg
diff --git a/kcelebs/Kim Young-kwang.jpg b/kcelebs/Kim Young-kwang.jpg
diff --git a/kcelebs/Kwak Dong-yeon.jpg b/kcelebs/Kwak Dong-yeon.jpg
diff --git a/kcelebs/Lee Byung-hun.jpg b/kcelebs/Lee Byung-hun.jpg
diff --git a/kcelebs/Lee Eun-mi.jpg b/kcelebs/Lee Eun-mi.jpg
diff --git a/kcelebs/Lee Jong-suk.jpg b/kcelebs/Lee Jong-suk.jpg
diff --git a/kcelebs/Lee Joo-young.jpg b/kcelebs/Lee Joo-young.jpg
diff --git a/kcelebs/Lee Joon-gi.jpg b/kcelebs/Lee Joon-gi.jpg
diff --git a/kcelebs/Lee Min-ho.jpg b/kcelebs/Lee Min-ho.jpg
diff --git a/kcelebs/Lee Si-woo.jpg b/kcelebs/Lee Si-woo.jpg
diff --git a/kcelebs/Lim Ji-yeon.jpg b/kcelebs/Lim Ji-yeon.jpg
diff --git a/kcelebs/Ma Dong-seok.jpg b/kcelebs/Ma Dong-seok.jpg
diff --git a/kcelebs/Min Do-yoon.jpg b/kcelebs/Min Do-yoon.jpg
diff --git a/kcelebs/Nancy Jewel McDonie.jpg b/kcelebs/Nancy Jewel McDonie.jpg
diff --git a/kcelebs/Oh Jung-se.jpg b/kcelebs/Oh Jung-se.jpg
diff --git a/kcelebs/Oh Yeon-seo.jpg b/kcelebs/Oh Yeon-seo.jpg
diff --git a/kcelebs/Park Byung-eun.jpg b/kcelebs/Park Byung-eun.jpg
diff --git a/kcelebs/Park Cho-hyeon.jpg b/kcelebs/Park Cho-hyeon.jpg
diff --git a/kcelebs/Park Eun-bin.jpg b/kcelebs/Park Eun-bin.jpg
diff --git a/kcelebs/Park Gyu-young.jpg b/kcelebs/Park Gyu-young.jpg
diff --git a/kcelebs/Park Hee-soon.jpg b/kcelebs/Park Hee-soon.jpg
diff --git a/kcelebs/Park Hyun-jung.jpg b/kcelebs/Park Hyun-jung.jpg
diff --git a/kcelebs/Park So-jin.jpg b/kcelebs/Park So-jin.jpg
diff --git a/kcelebs/README.md b/kcelebs/README.md
@@ -0,0 +1,20 @@
+# Celebs with Korean origins
+
+Source: <https://huggingface.co/datasets/ashraq/tmdb-celeb-10k/>
+
+Extraction script:
+
+```python
+import pandas as pd
+
+data = pd.read_parquet("celebs.parquet")
+# Find all rows where 'biography' or 'place_of_birth' contains 'korea' - case insensitive
+korea_data = data[data['biography'].str.contains('korea', case=False, na=False) | data['place_of_birth'].str.contains('korea', case=False, na=False)]
+
+# For the first 100 rows by .popularity, save .image["bytes"] to the .name + ".jpg"
+for index, row in korea_data.sort_values(by='popularity', ascending=False)[:100].iterrows():
+    with open(row['name'] + ".jpg", "wb") as f:
+        f.write(row['image']['bytes'])
+```
+
+After this, we manually deleted a few non-Korean celebrities like "Steve Buscemi", "James Earl Jones", "Wesley Snipes", and a name in Korean.
diff --git a/kcelebs/Randall Park.jpg b/kcelebs/Randall Park.jpg
diff --git a/kcelebs/Rika.jpg b/kcelebs/Rika.jpg
diff --git a/kcelebs/Rowoon.jpg b/kcelebs/Rowoon.jpg
diff --git a/kcelebs/Sae Bom.jpg b/kcelebs/Sae Bom.jpg
diff --git a/kcelebs/Seo In-guk.jpg b/kcelebs/Seo In-guk.jpg
diff --git a/kcelebs/Seo Won.jpg b/kcelebs/Seo Won.jpg
diff --git a/kcelebs/Seung Ha.jpg b/kcelebs/Seung Ha.jpg
diff --git a/kcelebs/Shin Hyun-bin.jpg b/kcelebs/Shin Hyun-bin.jpg
diff --git a/kcelebs/Shin Se-kyung.jpg b/kcelebs/Shin Se-kyung.jpg
diff --git a/kcelebs/Shin Yu-ju.jpg b/kcelebs/Shin Yu-ju.jpg
diff --git a/kcelebs/Son Ye-jin.jpg b/kcelebs/Son Ye-jin.jpg
diff --git a/kcelebs/Song Hye-kyo.jpg b/kcelebs/Song Hye-kyo.jpg
diff --git a/kcelebs/Song Ji-hyo.jpg b/kcelebs/Song Ji-hyo.jpg
diff --git a/kcelebs/Song Joong-ki.jpg b/kcelebs/Song Joong-ki.jpg
diff --git a/kcelebs/Song Kang-ho.jpg b/kcelebs/Song Kang-ho.jpg
diff --git a/kcelebs/Song Kang.jpg b/kcelebs/Song Kang.jpg
diff --git a/kcelebs/Steven Yeun.jpg b/kcelebs/Steven Yeun.jpg
diff --git a/kcelebs/Wang Yibo.jpg b/kcelebs/Wang Yibo.jpg
diff --git a/kcelebs/Will Yun Lee.jpg b/kcelebs/Will Yun Lee.jpg
diff --git a/kcelebs/Yeom Hye-ran.jpg b/kcelebs/Yeom Hye-ran.jpg
diff --git a/kcelebs/Yoo In-young.jpg b/kcelebs/Yoo In-young.jpg
diff --git a/kcelebs/Yoo Jung.jpg b/kcelebs/Yoo Jung.jpg
diff --git a/kcelebs/Yoon Byung-hee.jpg b/kcelebs/Yoon Byung-hee.jpg
diff --git a/kcelebs/Yoon Se-na.jpg b/kcelebs/Yoon Se-na.jpg
diff --git a/kcelebs/Yoon Yoo-sun.jpg b/kcelebs/Yoon Yoo-sun.jpg
diff --git a/kcelebs/Yoon Yool.jpg b/kcelebs/Yoon Yool.jpg
diff --git a/kcelebs/Yoona.jpg b/kcelebs/Yoona.jpg
diff --git a/kcelebs/similarity.json b/kcelebs/similarity.json