54 lines
1.7 KiB
Python
54 lines
1.7 KiB
Python
import numpy as np
|
|
from sklearn.base import BaseEstimator, ClassifierMixin, TransformerMixin
|
|
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):
|
|
self.extract_fn = extract_fn
|
|
|
|
def fit(self, X, y=None):
|
|
return self
|
|
|
|
def transform(self, X):
|
|
return [self.extract_fn(msg) for msg in X]
|
|
|
|
|
|
class FeatureClassifier(BaseEstimator, ClassifierMixin):
|
|
def __init__(self, C=1.0):
|
|
self.C = C
|
|
|
|
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)),
|
|
])
|
|
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 extract_features(self, message):
|
|
return {
|
|
"contains_free": int("free" in message),
|
|
"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]
|
|
pairs = sorted(zip(names, weights), key=lambda x: abs(x[1]), reverse=True)
|
|
return pairs[:top_n]
|