Rewrite lab with BoW

classifiers/bag_of_words.py

@@ -0,0 +1,46 @@
+from collections import Counter
+
+import numpy as np
+from sklearn.base import BaseEstimator, ClassifierMixin
+from sklearn.feature_extraction import DictVectorizer
+from sklearn.linear_model import LogisticRegression
+from sklearn.pipeline import Pipeline
+
+from classifiers.feature_classifier import FeatureExtractor
+from cleaning.transformers import LowercaseTransformer, PunctuationRemover
+
+
+class BagOfWordsClassifier(BaseEstimator, ClassifierMixin):
+    def __init__(self):
+        self.cleaning = Pipeline([
+            ("lowercase", LowercaseTransformer()),
+            ("punctuation", PunctuationRemover()),
+        ])
+
+    def fit(self, X, y):
+        X_clean = self.cleaning.fit_transform(X)
+        self._pipeline = Pipeline([
+            ("features", FeatureExtractor(self.extract_features)),
+            ("vectorizer", DictVectorizer()),
+            ("classifier", LogisticRegression(max_iter=1000)),
+        ])
+        y_binary = (np.array(y) == "spam").astype(int)
+        self._pipeline.fit(X_clean, y_binary)
+        return self
+
+    def predict(self, X):
+        X_clean = self.cleaning.transform(X)
+        y_binary = self._pipeline.predict(X_clean)
+        return np.where(y_binary == 1, "spam", "ham")
+
+    def extract_features(self, message):
+        return dict(Counter(message.split()))
+
+    def feature_weights(self, top_n=10):
+        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: x[1])
+        half = top_n // 2
+        return pairs[-half:][::-1] + pairs[:half]

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]

classifiers/manual_cleaning.py

@@ -1,20 +0,0 @@
-import numpy as np
-from sklearn.pipeline import Pipeline
-
-from classifiers.manual import ManualClassifier
-from cleaning.transformers import LowercaseTransformer
-
-
-class ManualCleaningClassifier(ManualClassifier):
-    def __init__(self):
-        self.cleaning = Pipeline([
-            ("lowercase", LowercaseTransformer()),
-        ])
-
-    def fit(self, X, y):
-        self.cleaning.fit(X)
-        return self
-
-    def predict(self, X):
-        X_clean = self.cleaning.transform(X)
-        return np.array([self.predict_one(msg) for msg in X_clean])