Update app.py
Browse files
app.py
CHANGED
@@ -992,87 +992,6 @@ def refresh_data():
|
|
992 |
|
993 |
|
994 |
|
995 |
-
|
996 |
-
# λ¨Όμ target_datasets λμ
λ리λ₯Ό μΆκ°ν©λλ€
|
997 |
-
target_datasets = {
|
998 |
-
"aiqtech/kolaw": "https://huggingface.co/datasets/aiqtech/kolaw",
|
999 |
-
# μΆκ° λ°μ΄ν°μ
μ μ¬κΈ°μ κ³μ μΆκ°ν μ μμ΅λλ€
|
1000 |
-
}
|
1001 |
-
|
1002 |
-
def get_datasets_data(progress=gr.Progress()):
|
1003 |
-
"""λ°μ΄ν°μ
λ°μ΄ν° κ°μ Έμ€κΈ°"""
|
1004 |
-
def calculate_rank(dataset_id, all_global_datasets, korea_datasets):
|
1005 |
-
# κΈλ‘λ² μμ νμΈ
|
1006 |
-
global_rank = next((idx for idx, d in enumerate(all_global_datasets, 1)
|
1007 |
-
if d.get('id', '').strip() == dataset_id.strip()), None)
|
1008 |
-
|
1009 |
-
# Korea λ°μ΄ν°μ
μΈ κ²½μ°
|
1010 |
-
is_korea = any(d.get('id', '').strip() == dataset_id.strip() for d in korea_datasets)
|
1011 |
-
|
1012 |
-
if is_korea:
|
1013 |
-
# Korea λ°μ΄ν°μ
μ€μμμ μμ νμΈ
|
1014 |
-
korea_rank = next((idx for idx, d in enumerate(korea_datasets, 1)
|
1015 |
-
if d.get('id', '').strip() == dataset_id.strip()), None)
|
1016 |
-
|
1017 |
-
if korea_rank:
|
1018 |
-
return min(global_rank or 3001, korea_rank + 1000), True
|
1019 |
-
|
1020 |
-
return global_rank if global_rank else 'Not in top 3000', is_korea
|
1021 |
-
|
1022 |
-
try:
|
1023 |
-
progress(0, desc="Fetching datasets...")
|
1024 |
-
|
1025 |
-
if not HF_TOKEN:
|
1026 |
-
fig = create_error_plot()
|
1027 |
-
error_html = """
|
1028 |
-
<div style='padding: 20px; background: #fee; border-radius: 10px; margin: 10px 0;'>
|
1029 |
-
<h3 style='color: #c00;'>β οΈ API μΈμ¦μ΄ νμν©λλ€</h3>
|
1030 |
-
<p>HuggingFace API ν ν°μ΄ μ€μ λμ§ μμμ΅λλ€.</p>
|
1031 |
-
</div>
|
1032 |
-
"""
|
1033 |
-
empty_df = pd.DataFrame(columns=['Global Rank', 'Dataset ID', 'Title', 'Downloads', 'Likes', 'Korea Search', 'URL'])
|
1034 |
-
return fig, error_html, empty_df
|
1035 |
-
|
1036 |
-
# μΌλ° λ°μ΄ν°μ
κ³Ό Korea κ΄λ ¨ λ°μ΄ν°μ
κ°μ Έμ€κΈ°
|
1037 |
-
params = {
|
1038 |
-
'limit': 3000,
|
1039 |
-
'full': 'true'
|
1040 |
-
}
|
1041 |
-
|
1042 |
-
all_datasets_response = requests.get(
|
1043 |
-
"https://huggingface.co/api/datasets",
|
1044 |
-
headers={'Authorization': f'Bearer {HF_TOKEN}'},
|
1045 |
-
params=params
|
1046 |
-
)
|
1047 |
-
|
1048 |
-
korea_params = {
|
1049 |
-
'search': 'korea',
|
1050 |
-
'limit': 3000,
|
1051 |
-
'full': 'true'
|
1052 |
-
}
|
1053 |
-
|
1054 |
-
korea_datasets_response = requests.get(
|
1055 |
-
"https://huggingface.co/api/datasets",
|
1056 |
-
headers={'Authorization': f'Bearer {HF_TOKEN}'},
|
1057 |
-
params=korea_params
|
1058 |
-
)
|
1059 |
-
|
1060 |
-
all_global_datasets = all_datasets_response.json()
|
1061 |
-
korea_datasets = korea_datasets_response.json()
|
1062 |
-
|
1063 |
-
# μκ°νλ₯Ό μν Figure μμ±
|
1064 |
-
fig = go.Figure()
|
1065 |
-
|
1066 |
-
# μμ μ 보 μμ§
|
1067 |
-
filtered_datasets = []
|
1068 |
-
for dataset_id in target_datasets.keys():
|
1069 |
-
try:
|
1070 |
-
normalized_id = dataset_id.strip('/')
|
1071 |
-
dataset_url_api = f"https://huggingface.co/api/datasets/{normalized_id}"
|
1072 |
-
response# λ¨Όμ target_datasets λμ
λ리λ₯Ό μΆκ°ν©λλ€
|
1073 |
-
|
1074 |
-
|
1075 |
-
|
1076 |
target_datasets = {
|
1077 |
"aiqtech/kolaw": "https://huggingface.co/datasets/aiqtech/kolaw",
|
1078 |
"heegyu/korquad-v1-v2": "https://huggingface.co/datasets/heegyu/korquad-v1-v2",
|
@@ -1089,8 +1008,6 @@ target_datasets = {
|
|
1089 |
}
|
1090 |
|
1091 |
def get_datasets_data(progress=gr.Progress()):
|
1092 |
-
try:
|
1093 |
-
|
1094 |
def calculate_rank(dataset_id, all_global_datasets, korea_datasets):
|
1095 |
# κΈλ‘λ² μμ νμΈ
|
1096 |
global_rank = next((idx for idx, d in enumerate(all_global_datasets, 1)
|
@@ -1100,7 +1017,6 @@ def get_datasets_data(progress=gr.Progress()):
|
|
1100 |
is_korea = any(d.get('id', '').strip() == dataset_id.strip() for d in korea_datasets)
|
1101 |
|
1102 |
if is_korea:
|
1103 |
-
# Korea λ°μ΄ν°μ
μ€μμμ μμ νμΈ
|
1104 |
korea_rank = next((idx for idx, d in enumerate(korea_datasets, 1)
|
1105 |
if d.get('id', '').strip() == dataset_id.strip()), None)
|
1106 |
|
@@ -1283,7 +1199,9 @@ def get_datasets_data(progress=gr.Progress()):
|
|
1283 |
|
1284 |
progress(1.0, desc="Complete!")
|
1285 |
|
|
|
1286 |
return fig, html_content, df
|
|
|
1287 |
except Exception as e:
|
1288 |
print(f"Error in get_datasets_data: {str(e)}")
|
1289 |
error_fig = create_error_plot()
|
@@ -1296,7 +1214,7 @@ def get_datasets_data(progress=gr.Progress()):
|
|
1296 |
empty_df = pd.DataFrame(columns=['Global Rank', 'Dataset ID', 'Title', 'Downloads', 'Likes', 'Korea Search', 'URL'])
|
1297 |
return error_fig, error_html, empty_df
|
1298 |
|
1299 |
-
|
1300 |
with gr.Blocks(theme=gr.themes.Soft()) as demo:
|
1301 |
gr.Markdown("""
|
1302 |
# π€ νκΉ
νμ΄μ€ 'νκ΅(μΈμ΄) 리λ보λ'
|
@@ -1345,13 +1263,12 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
|
|
1345 |
datasets_results = get_datasets_data()
|
1346 |
|
1347 |
trending_plot.value, trending_info.value, trending_df.value = spaces_results
|
1348 |
-
models_plot.value,
|
1349 |
-
|
1350 |
-
|
1351 |
|
1352 |
# Gradio μ± μ€ν
|
1353 |
demo.launch(
|
1354 |
server_name="0.0.0.0",
|
1355 |
server_port=7860,
|
1356 |
share=False
|
1357 |
-
)
|
|
|
992 |
|
993 |
|
994 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
995 |
target_datasets = {
|
996 |
"aiqtech/kolaw": "https://huggingface.co/datasets/aiqtech/kolaw",
|
997 |
"heegyu/korquad-v1-v2": "https://huggingface.co/datasets/heegyu/korquad-v1-v2",
|
|
|
1008 |
}
|
1009 |
|
1010 |
def get_datasets_data(progress=gr.Progress()):
|
|
|
|
|
1011 |
def calculate_rank(dataset_id, all_global_datasets, korea_datasets):
|
1012 |
# κΈλ‘λ² μμ νμΈ
|
1013 |
global_rank = next((idx for idx, d in enumerate(all_global_datasets, 1)
|
|
|
1017 |
is_korea = any(d.get('id', '').strip() == dataset_id.strip() for d in korea_datasets)
|
1018 |
|
1019 |
if is_korea:
|
|
|
1020 |
korea_rank = next((idx for idx, d in enumerate(korea_datasets, 1)
|
1021 |
if d.get('id', '').strip() == dataset_id.strip()), None)
|
1022 |
|
|
|
1199 |
|
1200 |
progress(1.0, desc="Complete!")
|
1201 |
|
1202 |
+
|
1203 |
return fig, html_content, df
|
1204 |
+
|
1205 |
except Exception as e:
|
1206 |
print(f"Error in get_datasets_data: {str(e)}")
|
1207 |
error_fig = create_error_plot()
|
|
|
1214 |
empty_df = pd.DataFrame(columns=['Global Rank', 'Dataset ID', 'Title', 'Downloads', 'Likes', 'Korea Search', 'URL'])
|
1215 |
return error_fig, error_html, empty_df
|
1216 |
|
1217 |
+
|
1218 |
with gr.Blocks(theme=gr.themes.Soft()) as demo:
|
1219 |
gr.Markdown("""
|
1220 |
# π€ νκΉ
νμ΄μ€ 'νκ΅(μΈμ΄) 리λ보λ'
|
|
|
1263 |
datasets_results = get_datasets_data()
|
1264 |
|
1265 |
trending_plot.value, trending_info.value, trending_df.value = spaces_results
|
1266 |
+
models_plot.value, models_info.value, models_df.value = models_results
|
1267 |
+
datasets_plot.value, datasets_info.value, datasets_df.value = datasets_results
|
|
|
1268 |
|
1269 |
# Gradio μ± μ€ν
|
1270 |
demo.launch(
|
1271 |
server_name="0.0.0.0",
|
1272 |
server_port=7860,
|
1273 |
share=False
|
1274 |
+
)
|