def score_with_sample_weight(estimator, X, y=None, sample_weight=None):
if sklearn_version() < '0.19':
if isinstance(estimator, Pipeline) and sample_weight is not None:
estimator = _PipelinePatched(estimator.steps)
if sample_weight is None:
return estimator.score(X, y)
return estimator.score(X, y, sample_weight=sample_weight)
def test_invertable_hashing_vectorizer(always_signed, binary, alternate_sign):
n_features = 8
n_words = 4 * n_features
kwargs = dict(n_features=n_features, binary=binary)
if sklearn_version() < '0.19':
kwargs['non_negative'] = not alternate_sign
else:
kwargs['alternate_sign'] = alternate_sign
vec = HashingVectorizer(**kwargs)
words = ['word_{}'.format(i) for i in range(n_words)]
corpus = [w for i, word in enumerate(words, 1) for w in repeat(word, i)]
split = len(corpus) // 2
doc1, doc2 = ' '.join(corpus[:split]), ' '.join(corpus[split:])
ivec = InvertableHashingVectorizer(vec)
ivec.fit([doc1, doc2])
check_feature_names(vec, ivec, always_signed, corpus, alternate_sign)
ivec = InvertableHashingVectorizer(vec)
ivec.partial_fit([doc1])
ivec.partial_fit([doc2])
check_feature_names(vec, ivec, always_signed, corpus, alternate_sign)
ivec = InvertableHashingVectorizer(vec)
for w in corpus:
ivec.partial_fit([w])
check_feature_names(vec, ivec, always_signed, corpus, alternate_sign)
def _default_clf(self):
kwargs = dict(loss='log',
penalty='elasticnet',
alpha=1e-3,
random_state=self.rng_)
if sklearn_version() >= '0.19':
kwargs['tol'] = 1e-3
return SGDClassifier(**kwargs)
import inspect
import json
from pprint import pprint
from hypothesis.strategies import integers
from hypothesis.extra.numpy import arrays
import numpy as np
from eli5.base import Explanation
from eli5.formatters import format_as_text, format_as_html, format_as_dict
from eli5.formatters.html import html_escape
from eli5.formatters.text import format_signed
from eli5.sklearn.utils import sklearn_version
SGD_KWARGS = {'random_state': 42}
if sklearn_version() >= '0.19':
SGD_KWARGS['tol'] = 1e-3
def rnd_len_arrays(dtype, min_len=0, max_len=3, elements=None):
""" Generate numpy arrays of random length """
lengths = integers(min_value=min_len, max_value=max_len)
return lengths.flatmap(lambda n: arrays(dtype, n, elements=elements))
def format_as_all(res, clf, **kwargs):
""" Format explanation as text and html, check JSON-encoding,
print text explanation, save html, return text and html.
"""
expl_dict = format_as_dict(res)
pprint(expl_dict)