init commit

lab4/generate_spam_data.py

@@ -0,0 +1,64 @@
+import csv
+import random
+
+random.seed(42)
+
+SPAM_TEMPLATES = [
+    "CONGRATULATIONS! You've WON a {prize}! Click {link} now to claim!!!",
+    "URGENT: Your account will be suspended. Verify at {link} immediately",
+    "Make ${amount} a week working from home, no experience needed! {link}",
+    "FREE {prize} for the first 100 people! Limited time offer {link}",
+    "Dear winner, you have been selected to receive {amount} dollars. Reply now",
+    "Lowest prices on {product}! Buy now and save 90%! {link}",
+    "Your {product} order could not be delivered, click {link} to reschedule",
+    "Hot singles in your area want to meet you! {link}",
+    "Act now! This {product} offer expires in 24 hours {link}",
+    "You have 1 unread message regarding your {amount} refund, claim at {link}",
+]
+
+HAM_TEMPLATES = [
+    "Hey, are we still on for lunch tomorrow at noon?",
+    "Please find attached the {product} report you requested.",
+    "Can you review the pull request I sent over this morning?",
+    "Reminder: team meeting moved to 3pm today.",
+    "Thanks for your help with the {product} demo yesterday.",
+    "The invoice for {amount} has been processed, receipt attached.",
+    "Let's catch up sometime this week, been a while.",
+    "I'll be out of office next Monday, please contact the team lead.",
+    "Great presentation earlier, learned a lot about {product}.",
+    "Attached is the agenda for tomorrow's {product} planning session.",
+]
+
+PRIZES = ["iPhone", "vacation package", "gift card", "laptop", "cash prize"]
+PRODUCTS = ["software", "quarterly", "marketing", "onboarding", "budget"]
+LINKS = ["http://bit.ly/xyz123", "http://claim-now.co/win", "http://free-gift.biz"]
+AMOUNTS = ["500", "1000", "2500", "10000"]
+
+
+def fill(template):
+    return template.format(
+        prize=random.choice(PRIZES),
+        link=random.choice(LINKS),
+        amount=random.choice(AMOUNTS),
+        product=random.choice(PRODUCTS),
+    )
+
+
+def generate(n_per_class=300):
+    rows = []
+    for _ in range(n_per_class):
+        rows.append((fill(random.choice(SPAM_TEMPLATES)), 1,
+                     round(min(1.0, max(0.0, random.gauss(0.85, 0.1))), 3)))
+        rows.append((fill(random.choice(HAM_TEMPLATES)), 0,
+                     round(min(1.0, max(0.0, random.gauss(0.08, 0.07))), 3)))
+    random.shuffle(rows)
+    return rows
+
+
+if __name__ == "__main__":
+    rows = generate(n_per_class=300)
+    with open("data.csv", "w", newline="", encoding="utf-8") as f:
+        writer = csv.writer(f)
+        writer.writerow(["text", "label", "spam_score"])
+        writer.writerows(rows)
+    print(f"Wrote {len(rows)} rows to data.csv")

lab4/test_model.py

@@ -0,0 +1,15 @@
+import joblib
+
+vectorizer = joblib.load("vectorizer.joblib")
+clf = joblib.load("classifier.joblib")
+
+print("Type text to classify. Ctrl+C or empty line to quit.\n")
+while True:
+    text = input("> ").strip()
+    if not text:
+        break
+    X = vectorizer.transform([text])
+    pred = clf.predict(X)[0]
+    verdict = "SPAM" if pred == 1 else "HAM"
+    print(f"[{verdict}] {text}\n")
+

lab4/train_spam_model.py

@@ -0,0 +1,75 @@
+import joblib
+import csv
+
+import numpy as np
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.linear_model import LogisticRegression, Ridge
+from sklearn.metrics import (
+    accuracy_score,
+    classification_report,
+    mean_absolute_error,
+    r2_score,
+)
+from sklearn.model_selection import train_test_split
+
+
+def load_data(path="data.csv"):
+    texts, labels, scores = [], [], []
+    with open(path, newline="", encoding="utf-8") as f:
+        for row in csv.DictReader(f):
+            texts.append(row["text"])
+            labels.append(int(row["label"]))
+            scores.append(float(row["spam_score"]))
+    return texts, np.array(labels), np.array(scores)
+
+
+def main():
+    texts, labels, scores = load_data()
+
+    X_train_txt, X_test_txt, y_train, y_test, s_train, s_test = train_test_split(
+        texts, labels, scores, test_size=0.25, random_state=42, stratify=labels
+    )
+
+    vectorizer = TfidfVectorizer(lowercase=True, ngram_range=(1, 2), max_features=2000)
+    X_train = vectorizer.fit_transform(X_train_txt)
+    X_test = vectorizer.transform(X_test_txt)
+
+    # Classification Model (Spam/Ham)
+    clf = LogisticRegression(max_iter=1000)
+    clf.fit(X_train, y_train)
+    y_pred = clf.predict(X_test)
+
+    print("Classification: Spam vs Ham")
+    print(f"Accuracy: {accuracy_score(y_test, y_pred):.3f}")
+    print(classification_report(y_test, y_pred, target_names=["ham", "spam"]))
+
+    # Regression model
+    reg = Ridge(alpha=1.0)
+    reg.fit(X_train, s_train)
+    s_pred = reg.predict(X_test)
+    s_pred = np.clip(s_pred, 0, 1)
+
+    print("Regression: Spam Score (0-1)")
+    print(f"MAE: {mean_absolute_error(s_test, s_pred):.3f}")
+    print(f"R^2: {r2_score(s_test, s_pred):.3f}")
+
+    # Demo model
+    print("\nTest Samples")
+    samples = [
+        "Congratulations! You've won a free vacation, click here now!",
+        "Hey, can you send me the meeting notes from earlier?",
+    ]
+    X_demo = vectorizer.transform(samples)
+    preds = clf.predict(X_demo)
+    scores_demo = np.clip(reg.predict(X_demo), 0, 1)
+    for text, label, score in zip(samples, preds, scores_demo):
+        verdict = "SPAM" if label == 1 else "HAM"
+        print(f"[{verdict}] score={score:.2f} :: {text}")
+
+
+if __name__ == "__main__":
+    # persist our model
+    joblib.dump(vectorizer, "vectorizer.joblib")
+    joblib.dump(clf, "classifier.joblib")
+    print("\nSaved model artifacts.")
+    main()