def __init__(self, **kwargs):
"""
set _node_transformer, _edge_transformer, tdifNodeTextVectorizer
"""
FeatureDefinition.__init__(self)
nbTypes = self._getTypeNumber(kwargs)
print("BETTER FEATURES")
block_transformer = FeatureUnion( [ #CAREFUL IF YOU CHANGE THIS - see cleanTransformers method!!!!
("xywh", Pipeline([
('selector', NodeTransformerXYWH_v2()),
#v1 ('xywh', StandardScaler(copy=False, with_mean=True, with_std=True)) #use in-place scaling
('xywh', QuantileTransformer(n_quantiles=self.n_QUANTILES, copy=False)) #use in-place scaling
])
)
, ("neighbors", Pipeline([
('selector', NodeTransformerNeighbors()),
#v1 ('neighbors', StandardScaler(copy=False, with_mean=True, with_std=True)) #use in-place scaling
('neighbors', QuantileTransformer(n_quantiles=self.n_QUANTILES, copy=False)) #use in-place scaling
])
)
, ("1hot", Pipeline([
('1hot', Node1HotFeatures()) #does the 1-hot encoding directly
])
)
])
grid_line_transformer = GridLine_NodeTransformer_v2()
self._node_transformer = TransformerListByType([block_transformer, grid_line_transformer])
edge_BB_transformer = FeatureUnion( [ #CAREFUL IF YOU CHANGE THIS - see cleanTransformers method!!!!
("1hot", Pipeline([
('1hot', Edge1HotFeatures(PageNumberSimpleSequenciality()))
])
)
, ("boolean", Pipeline([
('boolean', EdgeBooleanFeatures_v2())
])
)
, ("numerical", Pipeline([
('selector', EdgeNumericalSelector()),
#v1 ('numerical', StandardScaler(copy=False, with_mean=True, with_std=True)) #use in-place scaling
('numerical', QuantileTransformer(n_quantiles=self.n_QUANTILES, copy=False)) #use in-place scaling
])
)
] )
edge_BL_transformer = Block2GridLine_EdgeTransformer()
edge_LL_transformer = GridLine2GridLine_EdgeTransformer()
self._edge_transformer = TransformerListByType([edge_BB_transformer,
edge_BL_transformer,
edge_BL_transformer, # useless but required
edge_LL_transformer
])
self.tfidfNodeTextVectorizer = None #tdifNodeTextVectorizer
def __init__(self):
FeatureDefinition.__init__(self)
# self.n_tfidf_node, self.t_ngrams_node, self.b_tfidf_node_lc = n_tfidf_node, t_ngrams_node, b_tfidf_node_lc
# self.n_tfidf_edge, self.t_ngrams_edge, self.b_tfidf_edge_lc = n_tfidf_edge, t_ngrams_edge, b_tfidf_edge_lc
# tdifNodeTextVectorizer = TfidfVectorizer(lowercase=self.b_tfidf_node_lc, max_features=self.n_tfidf_node
# , analyzer = 'char', ngram_range=self.t_ngrams_node #(2,6)
# , dtype=np.float64)
node_transformer = FeatureUnion(
[ #CAREFUL IF YOU CHANGE THIS - see cleanTransformers method!!!!
(
"xywh",
Pipeline([
('selector', NodeTransformerXYWH_v2()),
('xywh',
StandardScaler(copy=False,
with_mean=True,
with_std=True)) #use in-place scaling
])),
("neighbors", NodeTransformerNeighbors_v2()),
("1hot", Node1HotFeatures()) #does the 1-hot encoding directly
])
lEdgeFeature = [ #CAREFUL IF YOU CHANGE THIS - see cleanTransformers method!!!!
("1hot", Edge1HotFeatures(PageNumberSimpleSequenciality())),
('boolean', EdgeBooleanFeatures_v2()),
(
"numerical",
Pipeline([
('selector', EdgeNumericalSelector()),
('numerical',
StandardScaler(copy=False, with_mean=True,
with_std=True)) #use in-place scaling
]))
]
edge_transformer = FeatureUnion(lEdgeFeature)
#return _node_transformer, _edge_transformer, tdifNodeTextVectorizer
self._node_transformer = node_transformer
self._edge_transformer = edge_transformer
self.tfidfNodeTextVectorizer = None #tdifNodeTextVectorizer
def __init__(self):
FeatureDefinition.__init__(self)
node_transformer = FeatureUnion(
[ #CAREFUL IF YOU CHANGE THIS - see cleanTransformers method!!!!
(
"xywh",
Pipeline([
('selector', NodeTransformerXYWH_v2()),
('xywh',
StandardScaler(copy=False,
with_mean=True,
with_std=True)) #use in-place scaling
])),
("neighbors", NodeTransformerNeighbors_v2()),
("1hot", Node1HotFeatures()) #does the 1-hot encoding directly
])
lEdgeFeature = [ #CAREFUL IF YOU CHANGE THIS - see cleanTransformers method!!!!
("1hot", Edge1HotFeatures(PageNumberSimpleSequenciality())),
('boolean', EdgeBooleanFeatures_v2()),
(
"numerical",
Pipeline([
('selector', EdgeNumericalSelector()),
('numerical',
StandardScaler(copy=False, with_mean=True,
with_std=True)) #use in-place scaling
]))
]
edge_transformer = FeatureUnion(lEdgeFeature)
#return _node_transformer, _edge_transformer, tdifNodeTextVectorizer
self._node_transformer = node_transformer
self._edge_transformer = edge_transformer
self.tfidfNodeTextVectorizer = None #tdifNodeTextVectorizer
