add data/code

app.py

@@ -0,0 +1,27 @@
+import gradio as gr
+from datasets import load_dataset
+import os
+
+dataset_names = os.listdir("./samples")
+dataset_names = [name.split("_")[0] for name in dataset_names]
+
+datasets = {}
+for name in dataset_names:
+    print(f"./samples/{name}_sample/00000.jsonl")
+    datasets[name] = load_dataset("json", data_files=f"samples/{name}_sample/00000.jsonl.gz", split="train")
+
+def get_sample(source, sample_id):
+    return f"``````\n{datasets[source][sample_id]['text']}\n``````"
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Text Data Inspection 👀")
+    with gr.Row():
+        data_source = gr.Dropdown(dataset_names, label="Data source:", value=dataset_names[0])
+        sample = gr.Number(0, 900, 0 , step=1, label="Sample ID:")
+    with gr.Row():
+        md = gr.Markdown(get_sample(dataset_names[0], 0))
+
+    sample.change(get_sample, inputs=[data_source, sample], outputs=[md])
+    data_source.change(get_sample, inputs=[data_source, sample], outputs=[md])
+
+demo.launch()

samples/arxiv_sample/00000.jsonl.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0814f72be9ba2eb21223002d6c45f18e6bc1efbe27ab2aec75da95a6c2480fa8
+size 16105196

samples/owm_sample/00000.jsonl.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce8ce10619131942840adb4ca76680834e86bd84fc8441f99a031892419c3f2c
+size 3005231

samples/stack_sample/00000.jsonl.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74b4d26a428598a5ed19732ffb175a9babd13b5bd4485fc16a58fdce318ede02
+size 7484894

samples/stackoverflow_sample/00000.jsonl.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cfeac647e3bfd0fbe3c3b6a89e2ad6f68be8a98b0902c849918acfa3b47874d
+size 1320690

samples/wiki_sample/00000.jsonl.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59c7a2e36f246447630f6ac394d436758ab678518845bfc7ecdd48cfdc7c0912
+size 2999516