ricardo-lsantos commited on
Commit
91c9027
1 Parent(s): b8ec3df

First version

Browse files
Files changed (4) hide show
  1. .gitignore +2 -0
  2. README.md +7 -0
  3. app.py +16 -0
  4. requirements.txt +7 -0
.gitignore ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ .env
2
+ .venv
README.md CHANGED
@@ -9,4 +9,11 @@ app_file: app.py
9
  pinned: false
10
  ---
11
 
 
 
 
 
 
 
12
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
9
  pinned: false
10
  ---
11
 
12
+ # Dataset Explorer
13
+
14
+ This is my version of a dataset explorer using streamlit and python.
15
+
16
+ Set your dataset, language, split and view your data. You can export to csv, also.
17
+
18
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
19
+
app.py ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import streamlit as st
2
+ from datasets import load_dataset, Audio
3
+
4
+ def app():
5
+ st.title('Home')
6
+ st.write('Welcome to the home page')
7
+ ds_ckpt = st.text_input('Enter the dataset checkpoint', 'PolyAI/minds14')
8
+ ds_lang = st.text_input('Enter the dataset language', 'en-US')
9
+ ds_split = st.text_input('Enter the dataset split', 'train')
10
+ # Load the dataset
11
+ dataset = load_dataset(ds_ckpt, ds_lang, split=ds_split)
12
+ # Display the dataset
13
+ st.dataframe(dataset.to_pandas())
14
+
15
+ if __name__ == '__main__':
16
+ app()
requirements.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ streamlit
2
+ pandas
3
+ numpy
4
+ torch
5
+ datasets
6
+ datasets[audio]
7
+ datasets[vision]