Rewrite lab with BoW

classifiers/feature_classifier.py

@@ -4,8 +4,6 @@ from sklearn.feature_extraction import DictVectorizer
 from sklearn.linear_model import LogisticRegression
 from sklearn.pipeline import Pipeline
 
-from cleaning.transformers import LowercaseTransformer
-
 
 class FeatureExtractor(BaseEstimator, TransformerMixin):
     def __init__(self, extract_fn):
@@ -24,10 +22,9 @@ class FeatureClassifier(BaseEstimator, ClassifierMixin):
 
     def fit(self, X, y):
         self._pipeline = Pipeline([
-            ("lowercase", LowercaseTransformer()),
             ("features", FeatureExtractor(self.extract_features)),
-            ("vec", DictVectorizer()),
-            ("clf", LogisticRegression(C=self.C, max_iter=1000)),
+            ("vectorizer", DictVectorizer()),
+            ("classifier", LogisticRegression(C=self.C, max_iter=1000)),
         ])
         y_binary = (np.array(y) == "spam").astype(int)
         self._pipeline.fit(X, y_binary)
@@ -39,15 +36,15 @@ class FeatureClassifier(BaseEstimator, ClassifierMixin):
 
     def extract_features(self, message):
         return {
-            "contains_free": int("free" in message),
+            "contains_free": int("free" in message.lower()),
             "num_exclamations": message.count("!"),
             "length": len(message),
         }
 
     def feature_weights(self, top_n=10):
-        vec = self._pipeline.named_steps["vec"]
-        clf = self._pipeline.named_steps["clf"]
-        names = vec.get_feature_names_out()
-        weights = clf.coef_[0]
+        vectorizer = self._pipeline.named_steps["vectorizer"]
+        classifier = self._pipeline.named_steps["classifier"]
+        names = vectorizer.get_feature_names_out()
+        weights = classifier.coef_[0]
         pairs = sorted(zip(names, weights), key=lambda x: abs(x[1]), reverse=True)
         return pairs[:top_n]