From 7525e14b31dc93c926b9e2154b1c83daf460af68 Mon Sep 17 00:00:00 2001
From: Mathieu Blondel <mathieu@mblondel.org>
Date: Thu, 21 Oct 2010 12:44:45 +0900
Subject: [PATCH] Remove Sparse prefix from class names.
---
scikits/learn/datasets/mlcomp.py | 3 ++-
.../feature_extraction/sparse/__init__.py | 4 ++--
.../learn/feature_extraction/sparse/text.py | 14 +++++++-------
.../feature_extraction/tests/test_text.py | 19 ++++++++++++-------
4 files changed, 23 insertions(+), 17 deletions(-)
diff --git a/scikits/learn/datasets/mlcomp.py b/scikits/learn/datasets/mlcomp.py
index fa14da4015..6bdc20fa99 100644
--- a/scikits/learn/datasets/mlcomp.py
+++ b/scikits/learn/datasets/mlcomp.py
@@ -6,7 +6,8 @@ import os
import numpy as np
from scikits.learn.datasets.base import load_text_files
from scikits.learn.feature_extraction.text import HashingVectorizer
-from scikits.learn.feature_extraction.sparse.text import SparseHashingVectorizer
+from scikits.learn.feature_extraction.sparse.text import HashingVectorizer as \
+ SparseCountVectorizer
def _load_document_classification(dataset_path, metadata, set_=None):
diff --git a/scikits/learn/feature_extraction/sparse/__init__.py b/scikits/learn/feature_extraction/sparse/__init__.py
index 890ce8f7f1..fa0f61b5bd 100644
--- a/scikits/learn/feature_extraction/sparse/__init__.py
+++ b/scikits/learn/feature_extraction/sparse/__init__.py
@@ -1,3 +1,3 @@
-from .text import SparseCountVectorizer, SparseTfidfTransformer, \
- SparseVectorizer, SparseHashingVectorizer
+from .text import CountVectorizer, TfidfTransformer, Vectorizer, \
+ HashingVectorizer
diff --git a/scikits/learn/feature_extraction/sparse/text.py b/scikits/learn/feature_extraction/sparse/text.py
index 1ba7dd7174..290f4d9f4b 100644
--- a/scikits/learn/feature_extraction/sparse/text.py
+++ b/scikits/learn/feature_extraction/sparse/text.py
@@ -11,12 +11,12 @@ import scipy.sparse as sp
from ..text import BaseCountVectorizer, BaseTfidfTransformer, BaseVectorizer, \
DEFAULT_ANALYZER
-class SparseCountVectorizer(BaseCountVectorizer):
+class CountVectorizer(BaseCountVectorizer):
def _init_matrix(self, shape):
return sp.dok_matrix(shape, dtype=self.dtype)
-class SparseTfidfTransformer(BaseTfidfTransformer):
+class TfidfTransformer(BaseTfidfTransformer):
def fit(self, X, y=None):
"""
@@ -73,11 +73,11 @@ class SparseTfidfTransformer(BaseTfidfTransformer):
return X
-class SparseVectorizer(BaseVectorizer):
+class Vectorizer(BaseVectorizer):
"""
Convert a collection of raw documents to a sparse matrix.
- Equivalent to SparseCountVectorizer followed by SparseTfidfTransformer.
+ Equivalent to CountVectorizer followed by TfidfTransformer.
"""
def __init__(self,
@@ -85,10 +85,10 @@ class SparseVectorizer(BaseVectorizer):
use_tf=True,
use_idf=True,
normalize=False):
- self.tc = SparseCountVectorizer(analyzer, dtype=np.float64)
- self.tfidf = SparseTfidfTransformer(use_tf, use_idf, normalize)
+ self.tc = CountVectorizer(analyzer, dtype=np.float64)
+ self.tfidf = TfidfTransformer(use_tf, use_idf, normalize)
-class SparseHashingVectorizer(object):
+class HashingVectorizer(object):
"""Compute term freq vectors using hashed term space in a sparse matrix
The logic is the same as HashingVectorizer but it is possible to use much
diff --git a/scikits/learn/feature_extraction/tests/test_text.py b/scikits/learn/feature_extraction/tests/test_text.py
index f741ce6a48..2ce2e325b1 100644
--- a/scikits/learn/feature_extraction/tests/test_text.py
+++ b/scikits/learn/feature_extraction/tests/test_text.py
@@ -1,14 +1,19 @@
from scikits.learn.feature_extraction.text import CharNGramAnalyzer
+from scikits.learn.feature_extraction.text import WordNGramAnalyzer
+from scikits.learn.feature_extraction.text import strip_accents
+
from scikits.learn.feature_extraction.text import CountVectorizer
-from scikits.learn.feature_extraction.text import HashingVectorizer
from scikits.learn.feature_extraction.text import TfidfTransformer
from scikits.learn.feature_extraction.text import Vectorizer
-from scikits.learn.feature_extraction.sparse.text import SparseCountVectorizer
-from scikits.learn.feature_extraction.sparse.text import SparseHashingVectorizer
-from scikits.learn.feature_extraction.sparse.text import SparseTfidfTransformer
-from scikits.learn.feature_extraction.sparse.text import SparseVectorizer
-from scikits.learn.feature_extraction.text import WordNGramAnalyzer
-from scikits.learn.feature_extraction.text import strip_accents
+from scikits.learn.feature_extraction.text import HashingVectorizer
+
+import scikits.learn.feature_extraction.sparse.text as st
+
+SparseCountVectorizer = st.CountVectorizer
+SparseTfidfTransformer = st.TfidfTransformer
+SparseVectorizer = st.Vectorizer
+SparseHashingVectorizer = st.HashingVectorizer
+
from scikits.learn.grid_search import GridSearchCV
from scikits.learn.pipeline import Pipeline
from scikits.learn.svm import LinearSVC as DenseLinearSVC
--
GitLab