Shea commited on
Commit
e5cef20
1 Parent(s): a9871b8
Files changed (2) hide show
  1. app.py +21 -2
  2. requirements.txt +1 -1
app.py CHANGED
@@ -2,7 +2,26 @@ import gradio as gr
2
  import numpy as np
3
  import pandas as pd
4
  from sklearn.metrics.pairwise import cosine_similarity
5
- from datasets import load_dataset
6
 
7
- dataset = load_dataset("sheacon/song_lyrics")
 
8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  import numpy as np
3
  import pandas as pd
4
  from sklearn.metrics.pairwise import cosine_similarity
 
5
 
6
+ import os
7
+ import requests
8
 
9
+ url = 'https://huggingface.co/datasets/sheacon/song_lyrics/resolve/main/v2ga_w_embeddings.parquet'
10
+ response = requests.get(url, stream=True)
11
+
12
+ filename = os.path.join(os.getcwd(), url.split('/')[-1])
13
+ with open(filename, 'wb') as file:
14
+ for chunk in response.iter_content(chunk_size=8192):
15
+ if chunk:
16
+ file.write(chunk)
17
+
18
+ print(f"File '{filename}' has been downloaded to the present working directory.")
19
+
20
+
21
+ pwd = os.getcwd()
22
+ print("Present Working Directory:", pwd)
23
+
24
+ contents = os.listdir(pwd)
25
+ print("Contents of the Directory:")
26
+ for item in contents:
27
+ print(item)
requirements.txt CHANGED
@@ -1,4 +1,4 @@
1
  gradio
2
  pandas
3
  scikit-learn
4
- datasets
 
1
  gradio
2
  pandas
3
  scikit-learn
4
+ requests