mwc/lab_classification_features
Template
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Simplify cleaning transformers and shorten module names

Browse Source 
Move cleaning transformers into classifiers/cleaning.py (dropping the
separate cleaning package) and implement them as plain classes rather
than BaseEstimator/TransformerMixin subclasses, since Pipeline only
needs fit/transform via duck typing. Also rename feature_classifier.py
and bag_of_words.py to features.py and bow.py for brevity.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Chris Proctor
2026-06-08 10:02:41 -04:00
parent 5f6f171369
commit bbe8054910
6 changed files with 6 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
classifiers/bag_of_words.py → classifiers/bow.py
View File

@@ -5,7 +5,7 @@ from sklearn.feature_extraction import DictVectorizer
from sklearn.linear_model import LogisticRegression from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline from sklearn.pipeline import Pipeline
from cleaning.transformers import LowercaseTransformer, PunctuationRemover from classifiers.cleaning import LowercaseTransformer, PunctuationRemover
class FeatureExtractor: class FeatureExtractor:

10
cleaning/transformers.py → classifiers/cleaning.py
View File

@@ -1,7 +1,6 @@
import re import re
import numpy as np import numpy as np
from sklearn.base import BaseEstimator, TransformerMixin
STOPWORDS = { STOPWORDS = {
@@ -14,18 +13,16 @@ STOPWORDS = {
} }
class LowercaseTransformer(BaseEstimator, TransformerMixin): class LowercaseTransformer:
def fit(self, X, y=None): def fit(self, X, y=None):
self.fitted_ = True
return self return self
def transform(self, X): def transform(self, X):
return np.array([msg.lower() for msg in X]) return np.array([msg.lower() for msg in X])
class StopwordRemover(BaseEstimator, TransformerMixin): class StopwordRemover:
def fit(self, X, y=None): def fit(self, X, y=None):
self.fitted_ = True
return self return self
def transform(self, X): def transform(self, X):
@@ -36,9 +33,8 @@ class StopwordRemover(BaseEstimator, TransformerMixin):
return " ".join(w for w in words if w.lower() not in STOPWORDS) return " ".join(w for w in words if w.lower() not in STOPWORDS)
class PunctuationRemover(BaseEstimator, TransformerMixin): class PunctuationRemover:
def fit(self, X, y=None): def fit(self, X, y=None):
self.fitted_ = True
return self return self
def transform(self, X): def transform(self, X):

0
classifiers/feature_classifier.py → classifiers/features.py
View File

0
cleaning/__init__.py
View File

2
cli/main.py
View File

@@ -3,7 +3,7 @@
Usage: Usage:
spam -e spam -e
spam classifiers.manual.ManualClassifier spam classifiers.manual.ManualClassifier
spam classifiers.feature_classifier.FeatureClassifier spam classifiers.features.FeatureClassifier
spam classifiers.manual.ManualClassifier -t 0.2 spam classifiers.manual.ManualClassifier -t 0.2
spam classifiers.manual.ManualClassifier -a spam classifiers.manual.ManualClassifier -a
spam classifiers.manual.ManualClassifier -a 5 spam classifiers.manual.ManualClassifier -a 5

2
pyproject.toml
View File

@@ -16,4 +16,4 @@ requires = ["hatchling"]
build-backend = "hatchling.build" build-backend = "hatchling.build"
[tool.hatch.build.targets.wheel] [tool.hatch.build.targets.wheel]
packages = ["cli", "classifiers", "cleaning"] packages = ["cli", "classifiers"]