def test_feature_hasher_dicts():
h = FeatureHasher(n_features=16)
assert_equal("dict", h.input_type)
raw_X = [{"dada": 42, "tzara": 37}, {"gaga": 17}]
X1 = FeatureHasher(n_features=16).transform(raw_X)
gen = (d.iteritems() for d in raw_X)
X2 = FeatureHasher(n_features=16, input_type="pair").transform(gen)
assert_array_equal(X1.toarray(), X2.toarray())
def test_feature_hasher_dicts():
feature_hasher = FeatureHasher(n_features=16)
assert "dict" == feature_hasher.input_type
raw_X = [{"foo": "bar", "dada": 42, "tzara": 37}, {"foo": "baz", "gaga": "string1"}]
X1 = FeatureHasher(n_features=16).transform(raw_X)
gen = (iter(d.items()) for d in raw_X)
X2 = FeatureHasher(n_features=16, input_type="pair").transform(gen)
assert_array_equal(X1.toarray(), X2.toarray())
def test_feature_hasher_dicts():
h = FeatureHasher(n_features=16)
assert_equal("dict", h.input_type)
raw_X = [{"dada": 42, "tzara": 37}, {"gaga": 17}]
X1 = FeatureHasher(n_features=16).transform(raw_X)
gen = (iter(d.items()) for d in raw_X)
X2 = FeatureHasher(n_features=16, input_type="pair").transform(gen)
assert_array_equal(X1.toarray(), X2.toarray())
def ordinal_encode(df):
df = df.copy()
oe = FeatureHasher(n_features=2)
print(df.state.values.reshape(-1, 1))
oe.transform(df.state.values.reshape(-1, 1))
df[['state1', 'state2']] = oe.toarray()
return train_test_split(df.drop('churn', axis=1), df.churn, random_state=1234)
def feature_hashing(features, size_f):
h = FeatureHasher(n_features=size_f)
f = h.transform(features)
print h.toarray()
