Update app.py

app.py

@@ -1,19 +1,17 @@
-import gradio as gr
+import pandas as pd
 import re
-from datasets import load_dataset
+import gradio as gr
+from sklearn.model_selection import train_test_split
 from sklearn.pipeline import make_pipeline
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.linear_model import LogisticRegression
-from sklearn.model_selection import train_test_split
 from sklearn.metrics import accuracy_score
 from collections import Counter
 
-# 1. Load dataset
-dataset = load_dataset("sms_spam", split="train")
-texts = dataset["sms"]
-labels = [1 if label == "spam" else 0 for label in dataset["label"]]
-
-print("Label distribution:", Counter(labels))  # Debug check
+# 1. Load and clean data
+df = pd.read_csv("spam.csv", encoding="latin1")[["v1", "v2"]]
+df.columns = ["label", "text"]
+df["label"] = df["label"].map({"ham": 0, "spam": 1})
 
 # 2. Clean text
 def clean_text(text):
@@ -21,30 +19,26 @@ def clean_text(text):
     text = re.sub(r"\W+", " ", text)
     return text.strip()
 
-texts_cleaned = [clean_text(t) for t in texts]
+df["text"] = df["text"].apply(clean_text)
 
-# 3. Train/test split with stratification
+# 3. Split data
 X_train, X_test, y_train, y_test = train_test_split(
-    texts_cleaned, labels, test_size=0.2, random_state=42, stratify=labels
+    df["text"], df["label"], test_size=0.2, stratify=df["label"], random_state=42
 )
 
-print("Train labels:", Counter(y_train))  # Debug check
-print("Test labels:", Counter(y_test))    # Debug check
-
-# 4. Build model pipeline
+# 4. Build and train model
 model = make_pipeline(
-    TfidfVectorizer(ngram_range=(1, 2), stop_words="english", max_df=0.9),
+    TfidfVectorizer(ngram_range=(1, 2), stop_words="english"),
     LogisticRegression(max_iter=1000, class_weight="balanced")
 )
 
-# 5. Train model
 model.fit(X_train, y_train)
 
-# 6. Evaluate
-y_pred = model.predict(X_test)
-print("Validation Accuracy:", accuracy_score(y_test, y_pred))
+# 5. Evaluate
+accuracy = accuracy_score(y_test, model.predict(X_test))
+print(f"Validation Accuracy: {accuracy:.2%}")
 
-# 7. Predict function
+# 6. Gradio prediction function
 def predict_spam(message):
     cleaned = clean_text(message)
     pred = model.predict([cleaned])[0]
@@ -52,14 +46,11 @@ def predict_spam(message):
     label = "🚫 Spam" if pred == 1 else "📩 Not Spam (Ham)"
     return f"{label} (Confidence: {prob:.2%})"
 
-# 8. Gradio app
-iface = gr.Interface(
+# 7. Gradio UI
+gr.Interface(
     fn=predict_spam,
-    inputs=gr.Textbox(lines=4, label="Enter your SMS message"),
+    inputs=gr.Textbox(lines=4, label="Enter SMS Message"),
     outputs=gr.Text(label="Prediction"),
-    title="📬 SMS Spam Detector (Improved)",
-    description="Detect spam in SMS messages using Logistic Regression with TF-IDF bi-grams. Trained on a balanced dataset from Hugging Face."
-)
-
-if __name__ == "__main__":
-    iface.launch(share=False)
+    title="SMS Spam Detector",
+    description=f"Detects spam in SMS messages. Trained on uploaded CSV (Accuracy: {accuracy:.2%})."
+).launch()