Update README.md

README.md

@@ -0,0 +1,22 @@
+# Assuming training and testing data are using the same names as we did in the skeleton code provided by the TA
+
+X_train = dataset_train['title']
+y_train = dataset_train['labels']
+
+X_test = dataset_test['title']
+y_test = dataset_test['labels']
+
+from sklearn.feature_extraction.text import TfidfVectorizer
+tfidf = TfidfVectorizer(max_features=5000, ngram_range=(1, 2), stop_words='english')
+X_train_tfidf = tfidf.fit_transform(X_train)
+X_test_tfidf = tfidf.transform(X_test)
+
+
+from sklearn.svm import SVC
+svm_model = SVC(kernel='linear', random_state=42)
+svm_model.fit(X_train_tfidf, y_train)
+y_pred = svm_model.predict(X_test_tfidf)
+accuracy = accuracy_score(y_test, y_pred)
+print(f"Random Forest Accuracy: {accuracy:.4f}")
+print(classification_report(y_test, y_pred))
+