Spaces:
Running
Running
seawolf2357
commited on
Commit
β’
c1c1dea
1
Parent(s):
6eaab32
Update app.py
Browse files
app.py
CHANGED
@@ -7,9 +7,6 @@ import subprocess
|
|
7 |
from datasets import load_dataset
|
8 |
import pandas as pd
|
9 |
from fuzzywuzzy import process
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
# νμ¬ μμ
λλ ν 리 μΆλ ₯
|
14 |
print("Current Working Directory:", os.getcwd())
|
15 |
|
@@ -30,12 +27,17 @@ else:
|
|
30 |
def load_optimized_dataset(data_files):
|
31 |
data_frames = [pd.read_csv(file) for file in data_files]
|
32 |
full_data = pd.concat(data_frames, ignore_index=True)
|
|
|
33 |
# νμΈμ μν λ°μ΄ν° μν μΆλ ₯
|
34 |
-
|
|
|
|
|
|
|
35 |
# μ¬κ±΄λͺ
μ ν€λ‘ νκ³ μ¬κ±΄λ²νΈμ μ λ¬Έμ μ μ₯νλ λμ
λ리 μμ±
|
36 |
name_to_number = full_data.groupby('μ¬κ±΄λͺ
')['μ¬κ±΄λ²νΈ'].apply(list).to_dict()
|
37 |
summary_to_number = full_data.groupby('νμμ¬ν')['μ¬κ±΄λ²νΈ'].apply(list).to_dict()
|
38 |
number_to_fulltext = full_data.set_index('μ¬κ±΄λ²νΈ')['μ λ¬Έ'].to_dict()
|
|
|
39 |
return name_to_number, summary_to_number, number_to_fulltext
|
40 |
|
41 |
name_to_number, summary_to_number, number_to_fulltext = load_optimized_dataset(data_files)
|
@@ -147,4 +149,4 @@ async def generate_response(message):
|
|
147 |
|
148 |
if __name__ == "__main__":
|
149 |
discord_client = MyClient(intents=intents)
|
150 |
-
discord_client.run(os.getenv('DISCORD_TOKEN'))
|
|
|
7 |
from datasets import load_dataset
|
8 |
import pandas as pd
|
9 |
from fuzzywuzzy import process
|
|
|
|
|
|
|
10 |
# νμ¬ μμ
λλ ν 리 μΆλ ₯
|
11 |
print("Current Working Directory:", os.getcwd())
|
12 |
|
|
|
27 |
def load_optimized_dataset(data_files):
|
28 |
data_frames = [pd.read_csv(file) for file in data_files]
|
29 |
full_data = pd.concat(data_frames, ignore_index=True)
|
30 |
+
|
31 |
# νμΈμ μν λ°μ΄ν° μν μΆλ ₯
|
32 |
+
print(full_data[['μ¬κ±΄λͺ
', 'μ¬κ±΄λ²νΈ', 'νμμ¬ν']].head()) # 'νμμ¬ν' νλμ λ°μ΄ν° μν μΆλ ₯
|
33 |
+
logging.debug(f"Columns in dataset: {full_data.columns}")
|
34 |
+
logging.debug(f"Sample data from 'νμμ¬ν': {full_data['νμμ¬ν'].dropna().head()}")
|
35 |
+
|
36 |
# μ¬κ±΄λͺ
μ ν€λ‘ νκ³ μ¬κ±΄λ²νΈμ μ λ¬Έμ μ μ₯νλ λμ
λ리 μμ±
|
37 |
name_to_number = full_data.groupby('μ¬κ±΄λͺ
')['μ¬κ±΄λ²νΈ'].apply(list).to_dict()
|
38 |
summary_to_number = full_data.groupby('νμμ¬ν')['μ¬κ±΄λ²νΈ'].apply(list).to_dict()
|
39 |
number_to_fulltext = full_data.set_index('μ¬κ±΄λ²νΈ')['μ λ¬Έ'].to_dict()
|
40 |
+
|
41 |
return name_to_number, summary_to_number, number_to_fulltext
|
42 |
|
43 |
name_to_number, summary_to_number, number_to_fulltext = load_optimized_dataset(data_files)
|
|
|
149 |
|
150 |
if __name__ == "__main__":
|
151 |
discord_client = MyClient(intents=intents)
|
152 |
+
discord_client.run(os.getenv('DISCORD_TOKEN'))
|