Update app.py

app.py

@@ -3,48 +3,70 @@ 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 = {
+# ---------- CONFIGURATION ---------- #
+DATASET_NAME = "ag_news"
+LABEL_MAPPING = {
     0: "World",
     1: "Sports",
     2: "Business",
-    3: "Sci/Tech"
+    3: "Science/Technology"
 }
-df["label_name"] = df["label"].map(label_map)
+SPLIT = "train[:1000]"  # For demo purposes, only use a subset
+
+# ---------- DATA LOADING ---------- #
+def load_data():
+    dataset = load_dataset(DATASET_NAME, split=SPLIT)
+    df = pd.DataFrame(dataset)
+    df["label_name"] = df["label"].map(LABEL_MAPPING)
+    return df
 
-def preview_data(n_rows):
+df = load_data()
+
+# ---------- APP FUNCTIONALITY ---------- #
+def get_data_preview(n_rows: int = 5) -> pd.DataFrame:
+    """Return the top n rows of the dataset."""
     return df.head(n_rows)
 
-def plot_distribution():
-    counts = df["label_name"].value_counts()
+def get_label_distribution_plot():
+    """Return a bar chart of label distribution."""
+    counts = df["label_name"].value_counts().sort_index()
     fig, ax = plt.subplots()
-    counts.plot(kind="bar", ax=ax, color="skyblue")
+    counts.plot(kind="bar", ax=ax, color="#4C72B0")
     ax.set_title("Label Distribution")
-    ax.set_ylabel("Count")
+    ax.set_ylabel("Number of Samples")
     ax.set_xlabel("Category")
+    ax.grid(axis="y", linestyle="--", alpha=0.7)
+    plt.tight_layout()
     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.")
+# ---------- UI LAYOUT ---------- #
+with gr.Blocks(title="AG News Dataset Explorer") as demo:
+    gr.Markdown("""
+    # 🧠 AG News Dataset Explorer  
+    Explore a cleaned and labeled version of the AG News dataset using Hugging Face `datasets`.
+
+    - View sample records  
+    - Understand label distribution  
+    - Great for data engineers & NLP practitioners  
+    """)
+
+    with gr.Tab("📄 Data Preview"):
+        with gr.Row():
+            n_slider = gr.Slider(1, 20, value=5, label="Number of rows to preview")
+            preview_btn = gr.Button("Show Preview")
+        preview_table = gr.Dataframe(label="Sample Rows")
+        preview_btn.click(get_data_preview, inputs=n_slider, outputs=preview_table)
 
-    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])
+    with gr.Tab("📊 Label Distribution"):
+        dist_btn = gr.Button("Generate Distribution Plot")
+        dist_plot = gr.Plot(label="Label Distribution")
+        dist_btn.click(get_label_distribution_plot, outputs=dist_plot)
 
-    gr.Markdown("## 📊 Class Distribution")
-    dist_btn = gr.Button("Show Distribution Chart")
-    chart_output = gr.Plot()
-    dist_btn.click(plot_distribution, outputs=[chart_output])
+    gr.Markdown("""
+    ---
+    🔗 **Dataset**: [AG News on Hugging Face](https://huggingface.co/datasets/ag_news)  
+    ✨ Built by a data engineering enthusiast using Python, Gradio, and Hugging Face.
+    """)
 
-# Launch app
+# ---------- LAUNCH ---------- #
 demo.launch()