Spaces:
Running
Running
File size: 1,425 Bytes
940863d 01cde28 940863d 01cde28 940863d 01cde28 940863d 01cde28 940863d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 |
import gradio as gr
from datasets import load_dataset
import pandas as pd
import matplotlib.pyplot as plt
# Load a dataset (you can change this to any HF dataset)
dataset = load_dataset("ag_news", split="train[:1000]")
# Convert to DataFrame
df = pd.DataFrame(dataset)
# Label map for better readability
label_map = {
0: "World",
1: "Sports",
2: "Business",
3: "Sci/Tech"
}
df["label_name"] = df["label"].map(label_map)
def preview_data(n_rows):
return df.head(n_rows)
def plot_distribution():
counts = df["label_name"].value_counts()
fig, ax = plt.subplots()
counts.plot(kind="bar", ax=ax, color="skyblue")
ax.set_title("Label Distribution")
ax.set_ylabel("Count")
ax.set_xlabel("Category")
return fig
with gr.Blocks() as demo:
gr.Markdown("# 🧠 AG News Dataset Explorer")
gr.Markdown("Explore the AG News dataset from Hugging Face. Useful for data engineers and NLP practitioners.")
with gr.Row():
num_slider = gr.Slider(1, 20, value=5, label="Number of Rows")
data_output = gr.Dataframe()
show_data_btn = gr.Button("Show Data")
show_data_btn.click(preview_data, inputs=[num_slider], outputs=[data_output])
gr.Markdown("## 📊 Class Distribution")
dist_btn = gr.Button("Show Distribution Chart")
chart_output = gr.Plot()
dist_btn.click(plot_distribution, outputs=[chart_output])
# Launch app
demo.launch()
|