def test_model_tfidf_transform(self):
corpus = numpy.array([
'This is the first document.',
'This document is the second document.',
'And this is the third one.',
'Is this the first document?',
"Troisième document en français",
]).reshape((5, 1))
data = CountVectorizer(ngram_range=(1, 1)).fit_transform(
corpus.ravel()).todense()
data = data.astype(numpy.float32)
for sublinear_tf in (False, True):
if sublinear_tf:
# scikit-learn applies a log on a matrix
# but only on strictly positive coefficients
break
for norm in (None, 'l1', 'l2'):
for smooth_idf in (False, True):
for use_idf in (False, True):
model = TfidfTransformer(norm=norm,
use_idf=use_idf,
smooth_idf=smooth_idf,
sublinear_tf=sublinear_tf)
model.fit(data)
dt = data.copy()
model_onnx = convert_sklearn(
model, 'TfidfTransformer',
[('input', FloatTensorType([1, data.shape[1]]))])
self.assertTrue(model_onnx is not None)
suffix = norm.upper() if norm else ''
suffix += 'Sub' if sublinear_tf else ''
suffix += 'Idf' if use_idf else ''
suffix += 'Smooth' if smooth_idf else ''
dump_data_and_model(
data,
model,
model_onnx,
basename="SklearnTfidfTransform" + suffix,
# Operator mul is not implemented in onnxruntime
allow_failure=
"StrictVersion(onnx.__version__) < StrictVersion('1.2')"
)
class EasyNLP(EasyClassi):
""" class EasyNLP
Building the Natural language processing class library.
This class has as father the classification class and as grandfather the
main generic MayML class.
"""
def __init__(self):
""" __init__(self)
Constructor.
"""
super(EasyNLP, self).__init__()
def downloadSTOPWords(self):
""" downloadSTOPWords
Get all the words that should be removed from text
"""
nltk.download("stopwords")
def cleanTXT(self, fieldToReview="Review"):
""" cleanTXT
Clean all text instances from the dataset with :
- special characters
- words not needed
- stem: verbe tenses not needed, plurals...
"""
self.corpus = []
for iText in self.myDS[fieldToReview]:
review = re.sub("[^a-zA-Z]", " ", iText)
review = review.lower()
review = review.split()
ps = PorterStemmer()
review = [
ps.stem(word) for word in review
if not word in set(stopwords.words("english"))
]
review = " ".join(review)
self.corpus.append(review)
def createBagOfWords(self, maximumFtrs=None):
""" createBagOfWords
Create model with bag of words matrix.
maximumFtrs: Maximum number of words collected.
"""
if (maximumFtrs == None):
self.bowMatrix = CountVectorizer()
else:
self.bowMatrix = CountVectorizer(max_features=maximumFtrs)
self.bowMatrix = self.bowMatrix.fit_transform(self.corpus).toarray()
def split_X_y(self, yColumn=-1):
"""split_X_y (self,yColumn=-1)
Process and get X and y:
X will be taken from the bag of words matrix.
y will be taken from the original source of data.
If y column index is not defined, or set to -1, so
by default we determine that y is at the last column.
"""
# Getting features X and y
self.X = self.bowMatrix.copy()
self.y = self.myDS.iloc[:, yColumn].values
