def test_cosine_similarity():
"""Test for CosineSimilarity."""
X = np.array([[1, 0, 0, 0, 0, 0], [1, 0, 1, 1, 0, 0], [1, 0, 0, 1, 0, 0],
[0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1]])
Xt = CosineSimilarity().fit_transform(X)
assert_array_almost_equal(Xt, [[0.], [2**-0.5], [1.], [0.], [1.]])
Xt = CosineSimilarity().fit_transform(sp.csr_matrix(X))
assert_array_almost_equal(Xt, [[0.], [2**-0.5], [1.], [0.], [1.]])
def fit(self):
"""Fit data using the estimator"""
transformer = FeatureUnion([
(
"author_full_name_similarity",
Pipeline([
(
"pairs",
PairTransformer(
element_transformer=Pipeline([
(
"full_name",
FuncTransformer(func=get_author_full_name),
),
("shaper", Shaper(newshape=(-1, ))),
(
"tf-idf",
TfidfVectorizer(
analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace",
),
),
]),
groupby=group_by_signature,
),
),
("combiner", CosineSimilarity()),
]),
),
(
"author_second_initial_similarity",
Pipeline([
(
"pairs",
PairTransformer(
element_transformer=FuncTransformer(
func=get_second_initial),
groupby=group_by_signature,
),
),
(
"combiner",
StringDistance(
similarity_function="character_equality"),
),
]),
),
(
"author_first_given_name_similarity",
Pipeline([
(
"pairs",
PairTransformer(
element_transformer=FuncTransformer(
func=get_first_given_name),
groupby=group_by_signature,
),
),
("combiner", StringDistance()),
]),
),
(
"author_second_given_name_similarity",
Pipeline([
(
"pairs",
PairTransformer(
element_transformer=FuncTransformer(
func=get_second_given_name),
groupby=group_by_signature,
),
),
("combiner", StringDistance()),
]),
),
(
"author_other_names_similarity",
Pipeline([
(
"pairs",
PairTransformer(
element_transformer=Pipeline([
(
"other_names",
FuncTransformer(
func=get_author_other_names),
),
("shaper", Shaper(newshape=(-1, ))),
(
"tf-idf",
TfidfVectorizer(
analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace",
),
),
]),
groupby=group_by_signature,
),
),
("combiner", CosineSimilarity()),
]),
),
(
"affiliation_similarity",
Pipeline([
(
"pairs",
PairTransformer(
element_transformer=Pipeline([
(
"affiliation",
FuncTransformer(
func=get_normalized_affiliation),
),
("shaper", Shaper(newshape=(-1, ))),
(
"tf-idf",
TfidfVectorizer(
analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace",
),
),
]),
groupby=group_by_signature,
),
),
("combiner", CosineSimilarity()),
]),
),
(
"coauthors_similarity",
Pipeline([
(
"pairs",
PairTransformer(
element_transformer=Pipeline([
(
"coauthors",
FuncTransformer(
func=get_coauthors_neighborhood),
),
("shaper", Shaper(newshape=(-1, ))),
(
"tf-idf",
TfidfVectorizer(
dtype=np.float32,
decode_error="replace",
),
),
]),
groupby=group_by_signature,
),
),
("combiner", CosineSimilarity()),
]),
),
(
"abstract_similarity",
Pipeline([
(
"pairs",
PairTransformer(
element_transformer=Pipeline([
(
"abstract",
FuncTransformer(func=get_abstract),
),
("shaper", Shaper(newshape=(-1, ))),
(
"tf-idf",
TfidfVectorizer(
dtype=np.float32,
decode_error="replace",
),
),
]),
groupby=group_by_signature,
),
),
("combiner", CosineSimilarity()),
]),
),
(
"keywords_similarity",
Pipeline([
(
"pairs",
PairTransformer(
element_transformer=Pipeline([
(
"keywords",
FuncTransformer(func=get_keywords),
),
("shaper", Shaper(newshape=(-1, ))),
(
"tf-idf",
TfidfVectorizer(
dtype=np.float32,
decode_error="replace",
),
),
]),
groupby=group_by_signature,
),
),
("combiner", CosineSimilarity()),
]),
),
(
"collaborations_similarity",
Pipeline([
(
"pairs",
PairTransformer(
element_transformer=Pipeline([
(
"collaborations",
FuncTransformer(func=get_collaborations),
),
("shaper", Shaper(newshape=(-1, ))),
(
"tf-idf",
TfidfVectorizer(
dtype=np.float32,
decode_error="replace",
),
),
]),
groupby=group_by_signature,
),
),
("combiner", CosineSimilarity()),
]),
),
(
"subject_similairty",
Pipeline([
(
"pairs",
PairTransformer(
element_transformer=Pipeline([
(
"keywords",
FuncTransformer(func=get_topics),
),
("shaper", Shaper(newshape=(-1))),
(
"tf-idf",
TfidfVectorizer(
dtype=np.float32,
decode_error="replace",
),
),
]),
groupby=group_by_signature,
),
),
("combiner", CosineSimilarity()),
]),
),
(
"title_similarity",
Pipeline([
(
"pairs",
PairTransformer(
element_transformer=Pipeline([
("title", FuncTransformer(func=get_title)),
("shaper", Shaper(newshape=(-1, ))),
(
"tf-idf",
TfidfVectorizer(
analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace",
),
),
]),
groupby=group_by_signature,
),
),
("combiner", CosineSimilarity()),
]),
),
(
"author_ethnicity",
Pipeline([
(
"pairs",
PairTransformer(
element_transformer=Pipeline([
(
"name",
FuncTransformer(func=get_author_full_name),
),
("shaper", Shaper(newshape=(-1, ))),
(
"classifier",
EstimatorTransformer(
self.ethnicity_estimator.estimator),
),
]),
groupby=group_by_signature,
),
),
("sigmoid", FuncTransformer(func=expit)),
("combiner", ElementMultiplication()),
]),
),
])
classifier = RandomForestClassifier(n_estimators=500, n_jobs=8)
self.distance_estimator = Pipeline([("transformer", transformer),
("classifier", classifier)])
self.distance_estimator.fit(self.X, self.y)
def _build_distance_estimator(X,
y,
verbose=0,
ethnicity_estimator=None,
fast=False):
"""Build a vector reprensation of a pair of signatures."""
if not fast:
transformer = FeatureUnion([
("author_full_name_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("full_name",
FuncTransformer(func=get_author_full_name)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("author_second_initial_similarity",
Pipeline([
("pairs",
PairTransformer(element_transformer=FuncTransformer(
func=get_second_initial),
groupby=group_by_signature)),
("combiner",
StringDistance(similarity_function="character_equality"))
])),
("author_first_given_name_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=FuncTransformer(
func=get_first_given_name),
groupby=group_by_signature)),
("combiner", StringDistance())])),
("author_second_given_name_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=FuncTransformer(
func=get_second_given_name),
groupby=group_by_signature)),
("combiner", StringDistance())])),
("author_other_names_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("other_names",
FuncTransformer(func=get_author_other_names)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("affiliation_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("affiliation",
FuncTransformer(func=get_author_affiliation)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("coauthors_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("coauthors",
FuncTransformer(func=get_coauthors_from_range)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("title_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("title", FuncTransformer(func=get_title)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("journal_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("journal", FuncTransformer(func=get_journal)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("abstract_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("abstract", FuncTransformer(func=get_abstract)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("keywords_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("keywords", FuncTransformer(func=get_keywords)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("collaborations_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("collaborations",
FuncTransformer(func=get_collaborations)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("subject_similairty",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("keywords", FuncTransformer(func=get_topics)),
("shaper", Shaper(newshape=(-1))),
("tf-idf",
TfidfVectorizer(dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("year_diff",
Pipeline([("pairs", FuncTransformer(func=get_year, dtype=np.int)),
("combiner", AbsoluteDifference())]))
])
else:
transformer = FeatureUnion([
("author_full_name_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("full_name",
FuncTransformer(func=get_author_full_name)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("author_other_names_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("other_names",
FuncTransformer(func=get_author_other_names)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("affiliation_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("affiliation",
FuncTransformer(func=get_author_affiliation)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("coauthors_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("coauthors",
FuncTransformer(func=get_coauthors_from_range)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("title_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("title", FuncTransformer(func=get_title)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("year_diff",
Pipeline([("pairs", FuncTransformer(func=get_year, dtype=np.int)),
("combiner", AbsoluteDifference())]))
])
if ethnicity_estimator is not None:
transformer.transformer_list.append(
("author_ethnicity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("name",
FuncTransformer(func=get_author_full_name)),
("shaper", Shaper(newshape=(-1, ))),
("classifier",
EstimatorTransformer(ethnicity_estimator)),
]),
groupby=group_by_signature)),
("sigmoid", FuncTransformer(func=expit)),
("combiner", ElementMultiplication())])))
# Train a classifier on these vectors
classifier = GradientBoostingClassifier(n_estimators=500,
max_depth=9,
max_features=10,
learning_rate=0.125,
verbose=verbose)
# classifier = RandomForestClassifier(n_estimators=500,
# verbose=verbose,
# n_jobs=8)
# Return the whole pipeline
estimator = Pipeline([("transformer", transformer),
("classifier", classifier)]).fit(X, y)
return estimator
def fit(self):
transformer = FeatureUnion([
('author_full_name_similarity',
Pipeline([
('pairs',
PairTransformer(
element_transformer=Pipeline([
('full_name',
FuncTransformer(func=get_author_full_name)),
('shaper', Shaper(newshape=(-1, ))),
('tf-idf',
TfidfVectorizer(
analyzer='char_wb',
ngram_range=(2, 4),
dtype=np.float32,
decode_error='replace',
)),
]),
groupby=group_by_signature,
)),
('combiner', CosineSimilarity()),
])),
('author_second_initial_similarity',
Pipeline([
('pairs',
PairTransformer(
element_transformer=FuncTransformer(
func=get_second_initial),
groupby=group_by_signature,
)),
('combiner',
StringDistance(similarity_function='character_equality')),
])),
('author_first_given_name_similarity',
Pipeline([
('pairs',
PairTransformer(element_transformer=FuncTransformer(
func=get_first_given_name),
groupby=group_by_signature)),
('combiner', StringDistance()),
])),
('author_second_given_name_similarity',
Pipeline([
('pairs',
PairTransformer(
element_transformer=FuncTransformer(
func=get_second_given_name),
groupby=group_by_signature,
)),
('combiner', StringDistance()),
])),
('author_other_names_similarity',
Pipeline([
('pairs',
PairTransformer(
element_transformer=Pipeline([
('other_names',
FuncTransformer(func=get_author_other_names)),
('shaper', Shaper(newshape=(-1, ))),
('tf-idf',
TfidfVectorizer(
analyzer='char_wb',
ngram_range=(2, 4),
dtype=np.float32,
decode_error='replace',
)),
]),
groupby=group_by_signature,
)),
('combiner', CosineSimilarity()),
])),
('affiliation_similarity',
Pipeline([
('pairs',
PairTransformer(
element_transformer=Pipeline([
('affiliation',
FuncTransformer(func=get_author_affiliation)),
('shaper', Shaper(newshape=(-1, ))),
('tf-idf',
TfidfVectorizer(
analyzer='char_wb',
ngram_range=(2, 4),
dtype=np.float32,
decode_error='replace',
)),
]),
groupby=group_by_signature,
)),
('combiner', CosineSimilarity()),
])),
('coauthors_similarity',
Pipeline([
('pairs',
PairTransformer(
element_transformer=Pipeline([
('coauthors',
FuncTransformer(func=get_coauthors_neighborhood)),
('shaper', Shaper(newshape=(-1, ))),
('tf-idf',
TfidfVectorizer(
dtype=np.float32,
decode_error='replace',
)),
]),
groupby=group_by_signature,
)),
('combiner', CosineSimilarity()),
])),
('abstract_similarity',
Pipeline([
('pairs',
PairTransformer(
element_transformer=Pipeline([
('abstract', FuncTransformer(func=get_abstract)),
('shaper', Shaper(newshape=(-1, ))),
('tf-idf',
TfidfVectorizer(
dtype=np.float32,
decode_error='replace',
)),
]),
groupby=group_by_signature,
)),
('combiner', CosineSimilarity()),
])),
('keywords_similarity',
Pipeline([
('pairs',
PairTransformer(
element_transformer=Pipeline([
('keywords', FuncTransformer(func=get_keywords)),
('shaper', Shaper(newshape=(-1, ))),
('tf-idf',
TfidfVectorizer(
dtype=np.float32,
decode_error='replace',
)),
]),
groupby=group_by_signature,
)),
('combiner', CosineSimilarity()),
])),
('collaborations_similarity',
Pipeline([
('pairs',
PairTransformer(
element_transformer=Pipeline([
('collaborations',
FuncTransformer(func=get_collaborations)),
('shaper', Shaper(newshape=(-1, ))),
('tf-idf',
TfidfVectorizer(
dtype=np.float32,
decode_error='replace',
)),
]),
groupby=group_by_signature,
)),
('combiner', CosineSimilarity()),
])),
('subject_similairty',
Pipeline([
('pairs',
PairTransformer(
element_transformer=Pipeline([
('keywords', FuncTransformer(func=get_topics)),
('shaper', Shaper(newshape=(-1))),
('tf-idf',
TfidfVectorizer(
dtype=np.float32,
decode_error='replace',
)),
]),
groupby=group_by_signature,
)),
('combiner', CosineSimilarity()),
])),
('title_similarity',
Pipeline([
('pairs',
PairTransformer(
element_transformer=Pipeline([
('title', FuncTransformer(func=get_title)),
('shaper', Shaper(newshape=(-1, ))),
('tf-idf',
TfidfVectorizer(
analyzer='char_wb',
ngram_range=(2, 4),
dtype=np.float32,
decode_error='replace',
)),
]),
groupby=group_by_signature,
)),
('combiner', CosineSimilarity()),
])),
('author_ethnicity',
Pipeline([
('pairs',
PairTransformer(
element_transformer=Pipeline([
('name', FuncTransformer(func=get_author_full_name)),
('shaper', Shaper(newshape=(-1, ))),
('classifier',
EstimatorTransformer(
self.ethnicity_estimator.estimator)),
]),
groupby=group_by_signature,
)),
('sigmoid', FuncTransformer(func=expit)),
('combiner', ElementMultiplication()),
])),
])
classifier = RandomForestClassifier(n_estimators=500, n_jobs=8)
self.distance_estimator = Pipeline([('transformer', transformer),
('classifier', classifier)])
self.distance_estimator.fit(self.X, self.y)
def _build_distance_estimator(X, y, w2v, PoS, NER, regressor, verbose=1):
"""Build a vector reprensation of a pair of signatures."""
if w2v == 'glove':
PairVecTransformer = PairGloveTransformer
elif w2v == 'spacy':
PairVecTransformer = PairSpacyVecTransformer
elif w2v == 'polyglot':
PairVecTransformer = PairPolyglotVecTransformer
else:
print('error passing w2v argument value')
if PoS == 'polyglot':
get_nouns = polyglot_nouns
get_verbs = polyglot_verbs
get_words = polyglot_words
get_particle = polyglot_particle
get_interjection = polyglot_interjection
get_symbol = polyglot_symbol
get_numbers = polyglot_numbers
get_proper_nouns = polyglot_proper_nouns
get_pronouns = polyglot_pronouns
get_auxiliary_verbs = polyglot_auxiliary_verbs
get_adjectives = polyglot_adjectives
get_adverbs = polyglot_adverbs
get_punctuation = polyglot_punctuation
get_determiner = polyglot_determiner
get_coordinating_conjunction = polyglot_coordinating_conjunction
get_adpositions = polyglot_adpositions
get_others = polyglot_others
get_subordinating_conjunctions = polyglot_subordinating_conjunctions
elif PoS == 'spacy':
get_nouns = spacy_noun
get_verbs = spacy_verb
get_words = spacy_tokens
get_particle = spacy_part
get_interjection = spacy_intj
get_symbol = spacy_sym
get_numbers = spacy_num
get_proper_nouns = spacy_propn
get_pronouns = spacy_pron
get_auxiliary_verbs = spacy_aux
get_adjectives = spacy_adj
get_adverbs = spacy_adv
get_punctuation = spacy_punct
get_determiner = spacy_det
get_coordinating_conjunction = spacy_conj
get_adpositions = spacy_adp
get_others = spacy_x
get_subordinating_conjunctions = spacy_sconj
else:
print('error passing PoS argument value')
transformer = FeatureUnion([
("get_nouns",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=get_nouns),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("get_verbs",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=get_verbs),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("get_words",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=get_words),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("get_particle",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=get_particle),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("get_symbol",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=get_symbol),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("num_diff",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=Pipeline([
("rsn", FuncTransformer(func=replace_spelled_numbers)),
("get_num", FuncTransformer(func=get_numbers)),
("to_num", FuncTransformer(func=to_numeric)),
]),
groupby=None)),
('1st_nm_comb', NumCombiner()),
])),
("get_proper_nouns",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=get_proper_nouns),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("get_pronouns",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=get_pronouns),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("get_auxiliary_verbs",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=get_auxiliary_verbs),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("adjectives_glove",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=get_adjectives),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("adverbs_glove",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=get_adverbs),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("get_punctuation",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=get_punctuation),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("get_determiner",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=get_determiner),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("get_coordinating_conjunction",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=get_coordinating_conjunction),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("get_adpositions",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=get_adpositions),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("get_subordinating_conjunctions",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=get_subordinating_conjunctions),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("spacy_organizations",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=spacy_organizations),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("spacy_persons",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=spacy_persons),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("spacy_locations",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=spacy_locations),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("spacy_groups",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=spacy_groups),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("spacy_geo_locations",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(
dtype=None, func=spacy_geo_locations),
groupby=None)),
('sop', SmallerOtherParing()),
('pgt', PairVecTransformer()),
('rgpc', RefGroupPairCosine()),
('gm', GetMatches()),
('sd', SolveDuplicate()),
('ac', AvgPOSCombiner()),
])),
("sent_tfidf",
Pipeline([
("pairs",
PairTransformer(element_transformer=Pipeline(
[("1st_verb",
FuncTransformer(
func=get_text)), ("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 3),
dtype=np.float32,
decode_error="replace",
stop_words="english"))]))),
("combiner", CosineSimilarity())
])),
("sent_len_diff",
Pipeline(steps=[
('pairtransformer',
PairTransformer(element_transformer=FuncTransformer(dtype=None,
func=len),
groupby=None)),
('abs_diff', AbsoluteDifference()),
])),
])
# Train a classifier on these vectors
if regressor == 'lasso':
classifier = LassoLarsCV(cv=5, max_iter=512, n_jobs=-1)
elif regressor == 'RF':
classifier = RandomForestRegressor(n_jobs=-1,
max_depth=8,
n_estimators=500)
else:
print('Error passing the regressor type')
# Return the whole pipeline
estimator = Pipeline([("transformer", transformer),
("classifier", classifier)]).fit(X, y)
return estimator
def build_distance_estimator(X, y):
# Build a vector reprensation of a pair of signatures
transformer = FeatureUnion([
("author_full_name_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("full_name",
FuncTransformer(func=get_author_full_name)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("author_other_names_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("other_names",
FuncTransformer(func=get_author_other_names)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("author_initials_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("initials",
FuncTransformer(func=get_author_initials)),
("shaper", Shaper(newshape=(-1, ))),
("count",
CountVectorizer(analyzer="char_wb",
ngram_range=(1, 1),
binary=True,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("affiliation_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("affiliation",
FuncTransformer(func=get_author_affiliation)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("coauthors_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("coauthors", FuncTransformer(func=get_coauthors)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("title_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("title", FuncTransformer(func=get_title)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("journal_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("journal", FuncTransformer(func=get_journal)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("abstract_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("abstract", FuncTransformer(func=get_abstract)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("keywords_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("keywords", FuncTransformer(func=get_keywords)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("collaborations_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("collaborations",
FuncTransformer(func=get_collaborations)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
("references_similarity",
Pipeline([("pairs",
PairTransformer(element_transformer=Pipeline([
("references", FuncTransformer(func=get_references)),
("shaper", Shaper(newshape=(-1, ))),
("tf-idf",
TfidfVectorizer(dtype=np.float32,
decode_error="replace")),
]),
groupby=group_by_signature)),
("combiner", CosineSimilarity())])),
(
"year_diff",
Pipeline([
("pairs", FuncTransformer(func=get_year, dtype=np.int)),
("combiner", AbsoluteDifference()
) # FIXME: when one is missing
]))
])
# Train a classifier on these vectors
classifier = GradientBoostingClassifier(n_estimators=500,
max_depth=9,
max_features=10,
learning_rate=0.125,
verbose=3)
# Return the whole pipeline
estimator = Pipeline([("transformer", transformer),
("classifier", classifier)]).fit(X, y)
return estimator
def _build_distance_estimator(X, y, verbose=0, ethnicity_estimator=None):
"""Build a vector reprensation of a pair of signatures."""
transformer = FeatureUnion([
# ("author_full_name_similarity", Pipeline([
# ("pairs", PairTransformer(element_transformer=Pipeline([
# ("full_name", FuncTransformer(func=get_author_full_name)),
# ("shaper", Shaper(newshape=(-1,))),
# ("tf-idf", TfidfVectorizer(analyzer="char_wb",
# ngram_range=(2, 4),
# dtype=np.float32,
# decode_error="replace")),
# ]), groupby=group_by_signature)),
# ("combiner", CosineSimilarity())
# ])),
# ("author_second_initial_similarity", Pipeline([
# ("pairs", PairTransformer(element_transformer=FuncTransformer(
# func=get_second_initial
# ), groupby=group_by_signature)),
# ("combiner", StringDistance(
# similarity_function="character_equality"))
# ])),
# ("mesh_similarity", Pipeline([
# ("pairs", PairTransformer(element_transformer=Pipeline([
# ("mesh_terms", FuncTransformer(func=get_mesh_terms)),
# ("shaper", Shaper(newshape=(-1,))),
# ("tf-idf", TfidfVectorizer(dtype=np.float32,
# decode_error="replace")),
# ]), groupby=group_by_signature)),
# ("combiner", CosineSimilarity())
# ])),
("mesh_word2vec", Pipeline([
("pairs", FuncTransformer(func=get_mesh_word2vec)),
("combiner", MyCosineSimilarity())
])),
("affiliation_similarity", Pipeline([
("pairs", PairTransformer(element_transformer=Pipeline([
("affiliation", FuncTransformer(func=get_author_affiliation)),
("shaper", Shaper(newshape=(-1,))),
("tf-idf", TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace")),
]), groupby=group_by_signature)),
("combiner", CosineSimilarity())
])),
("title_similarity", Pipeline([
("pairs", PairTransformer(element_transformer=Pipeline([
("title", FuncTransformer(func=get_title)),
("shaper", Shaper(newshape=(-1,))),
("tf-idf", TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace")),
]), groupby=group_by_signature)),
("combiner", CosineSimilarity())
])),
("journal_similarity", Pipeline([
("pairs", PairTransformer(element_transformer=Pipeline([
("journal", FuncTransformer(func=get_journal)),
("shaper", Shaper(newshape=(-1,))),
("tf-idf", TfidfVectorizer(analyzer="char_wb",
ngram_range=(2, 4),
dtype=np.float32,
decode_error="replace")),
]), groupby=group_by_signature)),
("combiner", CosineSimilarity())
])),
("abstract_similarity", Pipeline([
("pairs", PairTransformer(element_transformer=Pipeline([
("abstract", FuncTransformer(func=get_abstract)),
("shaper", Shaper(newshape=(-1,))),
("tf-idf", TfidfVectorizer(dtype=np.float32,
decode_error="replace")),
]), groupby=group_by_signature)),
("combiner", CosineSimilarity())
]))
# ("mesh_word2vec", Pipeline([
# ("pairs", FuncTransformer(func=get_year, dtype=np.int)),
# ("combiner", AbsoluteDifference())
# ]))
# ("keywords_similarity", Pipeline([
# ("pairs", PairTransformer(element_transformer=Pipeline([
# ("keywords", FuncTransformer(func=get_keywords)),
# ("shaper", Shaper(newshape=(-1,))),
# ("tf-idf", TfidfVectorizer(dtype=np.float32,
# decode_error="replace")),
# ]), groupby=group_by_signature)),
# ("combiner", CosineSimilarity())
# ])),
# ("year_diff", Pipeline([
# ("pairs", FuncTransformer(func=get_year, dtype=np.int)),
# ("combiner", AbsoluteDifference())
# ]))
])
if ethnicity_estimator is not None:
transformer.transformer_list.append(("author_ethnicity", Pipeline([
("pairs", PairTransformer(element_transformer=Pipeline([
("name", FuncTransformer(func=get_author_full_name)),
("shaper", Shaper(newshape=(-1,))),
("classifier", EstimatorTransformer(ethnicity_estimator)),
]), groupby=group_by_signature)),
("sigmoid", FuncTransformer(func=expit)),
("combiner", ElementMultiplication())
])))
# Train a classifier on these vectors
classifier = GradientBoostingClassifier(n_estimators=2000,
max_depth=9,
max_features=5,
learning_rate=0.125,
verbose=verbose)
# Return the whole pipeline
estimator = Pipeline([("transformer", transformer),
("classifier", classifier)]).fit(X, y)
return estimator
