Rename classifiers/ package to models/

Aligns module naming with the upcoming classification_neural lab,
which will use the same models/ package convention.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

models/bow.py

@@ -0,0 +1,46 @@
+from collections import Counter
+
+import numpy as np
+from sklearn.feature_extraction import DictVectorizer
+from sklearn.linear_model import LogisticRegression
+from sklearn.pipeline import Pipeline
+
+from models.cleaning import LowercaseTransformer, PunctuationRemover
+
+
+class FeatureExtractor:
+    def fit(self, X, y=None):
+        return self
+
+    def transform(self, X):
+        return [self.extract_features(msg) for msg in X]
+
+    def extract_features(self, message):
+        return dict(Counter(message.split()))
+
+
+class BagOfWordsClassifier:
+    def fit(self, X, y):
+        self._pipeline = Pipeline([
+            ("lowercase", LowercaseTransformer()),
+            ("punctuation", PunctuationRemover()),
+            ("features", FeatureExtractor()),
+            ("vectorizer", DictVectorizer()),
+            ("classifier", LogisticRegression(max_iter=1000)),
+        ])
+        y_binary = (np.array(y) == "spam").astype(int)
+        self._pipeline.fit(X, y_binary)
+        return self
+
+    def predict(self, X):
+        y_binary = self._pipeline.predict(X)
+        return np.where(y_binary == 1, "spam", "ham")
+
+    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]

models/cleaning.py

@@ -0,0 +1,41 @@
+import re
+
+import numpy as np
+
+
+STOPWORDS = {
+    "a", "an", "the", "is", "it", "in", "on", "at", "to", "for",
+    "of", "and", "or", "but", "not", "with", "as", "by", "from",
+    "this", "that", "was", "are", "be", "been", "have", "has",
+    "had", "do", "did", "will", "would", "could", "should",
+    "i", "me", "my", "you", "your", "he", "she", "we", "they",
+    "his", "her", "our", "their", "its", "what", "which",
+}
+
+
+class LowercaseTransformer:
+    def fit(self, X, y=None):
+        return self
+
+    def transform(self, X):
+        return np.array([msg.lower() for msg in X])
+
+
+class StopwordRemover:
+    def fit(self, X, y=None):
+        return self
+
+    def transform(self, X):
+        return np.array([self._remove(msg) for msg in X])
+
+    def _remove(self, message):
+        words = message.split()
+        return " ".join(w for w in words if w.lower() not in STOPWORDS)
+
+
+class PunctuationRemover:
+    def fit(self, X, y=None):
+        return self
+
+    def transform(self, X):
+        return np.array([re.sub(r"[^\w\s]", " ", msg) for msg in X])

models/features.py

@@ -0,0 +1,43 @@
+import numpy as np
+from sklearn.feature_extraction import DictVectorizer
+from sklearn.linear_model import LogisticRegression
+from sklearn.pipeline import Pipeline
+
+
+class FeatureExtractor:
+    def fit(self, X, y=None):
+        return self
+
+    def transform(self, X):
+        return [self.extract_features(msg) for msg in X]
+
+    def extract_features(self, message):
+        return {
+            "contains_free": int("free" in message.lower()),
+            "num_exclamations": message.count("!"),
+            "length": len(message),
+        }
+
+
+class FeatureClassifier:
+    def fit(self, X, y):
+        self._pipeline = Pipeline([
+            ("features", FeatureExtractor()),
+            ("vectorizer", DictVectorizer()),
+            ("classifier", LogisticRegression(max_iter=1000)),
+        ])
+        y_binary = (np.array(y) == "spam").astype(int)
+        self._pipeline.fit(X, y_binary)
+        return self
+
+    def predict(self, X):
+        y_binary = self._pipeline.predict(X)
+        return np.where(y_binary == 1, "spam", "ham")
+
+    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: abs(x[1]), reverse=True)
+        return pairs[:top_n]

models/manual.py

@@ -0,0 +1,12 @@
+import numpy as np
+
+
+class ManualClassifier:
+    def fit(self, X, y):
+        return self
+
+    def predict(self, X):
+        return np.array([self.predict_one(msg) for msg in X])
+
+    def predict_one(self, message):
+        return "ham"