Create app.py

app.py

@@ -0,0 +1,66 @@
+from datasets import load_dataset
+from transformers import pipeline
+import gradio as gr
+
+# Load Jigsaw dataset (streaming for large size)
+dataset = load_dataset("Koushim/processed-jigsaw-toxic-comments", split="train", streaming=True)
+
+# Fetch sample comments with low, medium, high toxicity
+low, medium, high = [], [], []
+for example in dataset:
+    score = example['toxicity']
+    text = example['text']
+    if score < 0.3 and len(low) < 3:
+        low.append((text, score))
+    elif 0.3 <= score < 0.7 and len(medium) < 3:
+        medium.append((text, score))
+    elif score >= 0.7 and len(high) < 3:
+        high.append((text, score))
+    if len(low) == 3 and len(medium) == 3 and len(high) == 3:
+        break
+
+examples_html = f"""
+### 🔷 Examples of Toxicity Levels
+
+**🟢 Low Toxicity**
+- {low[0][0]} (score: {low[0][1]:.2f})
+- {low[1][0]} (score: {low[1][1]:.2f})
+- {low[2][0]} (score: {low[2][1]:.2f})
+
+**🟡 Medium Toxicity**
+- {medium[0][0]} (score: {medium[0][1]:.2f})
+- {medium[1][0]} (score: {medium[1][1]:.2f})
+- {medium[2][0]} (score: {medium[2][1]:.2f})
+
+**🔴 High Toxicity**
+- {high[0][0]} (score: {high[0][1]:.2f})
+- {high[1][0]} (score: {high[1][1]:.2f})
+- {high[2][0]} (score: {high[2][1]:.2f})
+"""
+
+# Load a toxicity/offensive detection pipeline
+classifier = pipeline(
+    "text-classification", 
+    model="cardiffnlp/twitter-roberta-base-offensive",
+    top_k=None
+)
+
+def predict_toxicity(text):
+    preds = classifier(text)
+    result_str = ""
+    for pred in preds:
+        result_str += f"**{pred['label']}**: {pred['score']:.2f}\n"
+    return result_str.strip()
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("# 🧹 Hate Speech & Toxicity Monitor")
+    gr.Markdown("This tool shows examples of toxic comments and lets you check your own text for toxicity using a Hugging Face model.")
+    gr.Markdown(examples_html)
+
+    inp = gr.Textbox(label="🔷 Enter your comment")
+    out = gr.Markdown(label="Toxicity Scores")
+    btn = gr.Button("Check Toxicity")
+    btn.click(fn=predict_toxicity, inputs=inp, outputs=out)
+
+demo.launch()