Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -1,12 +1,50 @@
|
|
1 |
-
import
|
2 |
from datasets import load_dataset
|
3 |
import pandas as pd
|
|
|
4 |
|
5 |
-
|
6 |
dataset = load_dataset("ag_news", split="train[:1000]")
|
7 |
|
|
|
8 |
df = pd.DataFrame(dataset)
|
9 |
-
st.write("Sample data:", df.head())
|
10 |
|
11 |
-
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
from datasets import load_dataset
|
3 |
import pandas as pd
|
4 |
+
import matplotlib.pyplot as plt
|
5 |
|
6 |
+
# Load a dataset (you can change this to any HF dataset)
|
7 |
dataset = load_dataset("ag_news", split="train[:1000]")
|
8 |
|
9 |
+
# Convert to DataFrame
|
10 |
df = pd.DataFrame(dataset)
|
|
|
11 |
|
12 |
+
# Label map for better readability
|
13 |
+
label_map = {
|
14 |
+
0: "World",
|
15 |
+
1: "Sports",
|
16 |
+
2: "Business",
|
17 |
+
3: "Sci/Tech"
|
18 |
+
}
|
19 |
+
df["label_name"] = df["label"].map(label_map)
|
20 |
+
|
21 |
+
def preview_data(n_rows):
|
22 |
+
return df.head(n_rows)
|
23 |
+
|
24 |
+
def plot_distribution():
|
25 |
+
counts = df["label_name"].value_counts()
|
26 |
+
fig, ax = plt.subplots()
|
27 |
+
counts.plot(kind="bar", ax=ax, color="skyblue")
|
28 |
+
ax.set_title("Label Distribution")
|
29 |
+
ax.set_ylabel("Count")
|
30 |
+
ax.set_xlabel("Category")
|
31 |
+
return fig
|
32 |
+
|
33 |
+
with gr.Blocks() as demo:
|
34 |
+
gr.Markdown("# 🧠 AG News Dataset Explorer")
|
35 |
+
gr.Markdown("Explore the AG News dataset from Hugging Face. Useful for data engineers and NLP practitioners.")
|
36 |
+
|
37 |
+
with gr.Row():
|
38 |
+
num_slider = gr.Slider(1, 20, value=5, label="Number of Rows")
|
39 |
+
data_output = gr.Dataframe()
|
40 |
+
|
41 |
+
show_data_btn = gr.Button("Show Data")
|
42 |
+
show_data_btn.click(preview_data, inputs=[num_slider], outputs=[data_output])
|
43 |
+
|
44 |
+
gr.Markdown("## 📊 Class Distribution")
|
45 |
+
dist_btn = gr.Button("Show Distribution Chart")
|
46 |
+
chart_output = gr.Plot()
|
47 |
+
dist_btn.click(plot_distribution, outputs=[chart_output])
|
48 |
+
|
49 |
+
# Launch app
|
50 |
+
demo.launch()
|