def test_one_hot_encoder_sparse():
"""Test OneHotEncoder's fit and transform."""
X = [[3, 2, 1], [0, 1, 1]]
enc = OneHotEncoder()
# discover max values automatically
X_trans = enc.fit_transform(X).toarray()
assert_equal(X_trans.shape, (2, 5))
assert_array_equal(enc.active_features_,
np.where([1, 0, 0, 1, 0, 1, 1, 0, 1])[0])
assert_array_equal(enc.feature_indices_, [0, 4, 7, 9])
# check outcome
assert_array_equal(X_trans,
[[0., 1., 0., 1., 1.],
[1., 0., 1., 0., 1.]])
# max value given as 3
enc = OneHotEncoder(n_values=4)
X_trans = enc.fit_transform(X)
assert_equal(X_trans.shape, (2, 4 * 3))
assert_array_equal(enc.feature_indices_, [0, 4, 8, 12])
# max value given per feature
enc = OneHotEncoder(n_values=[3, 2, 2])
X = [[1, 0, 1], [0, 1, 1]]
X_trans = enc.fit_transform(X)
assert_equal(X_trans.shape, (2, 3 + 2 + 2))
assert_array_equal(enc.n_values_, [3, 2, 2])
# check that testing with larger feature works:
X = np.array([[2, 0, 1], [0, 1, 1]])
enc.transform(X)
# test that an error is raised when out of bounds:
X_too_large = [[0, 2, 1], [0, 1, 1]]
assert_raises(ValueError, enc.transform, X_too_large)
assert_raises(ValueError, OneHotEncoder(n_values=2).fit_transform, X)
# test that error is raised when wrong number of features
assert_raises(ValueError, enc.transform, X[:, :-1])
# test that error is raised when wrong number of features in fit
# with prespecified n_values
assert_raises(ValueError, enc.fit, X[:, :-1])
# test exception on wrong init param
assert_raises(TypeError, OneHotEncoder(n_values=np.int).fit, X)
enc = OneHotEncoder()
# test negative input to fit
assert_raises(ValueError, enc.fit, [[0], [-1]])
# test negative input to transform
enc.fit([[0], [1]])
assert_raises(ValueError, enc.transform, [[0], [-1]])
def test_one_hot_encoder_sparse():
"""Test OneHotEncoder's fit and transform."""
X = [[3, 2, 1], [0, 1, 1]]
enc = OneHotEncoder()
# discover max values automatically
X_trans = enc.fit_transform(X).toarray()
assert_equal(X_trans.shape, (2, 5))
assert_array_equal(enc.active_features_,
np.where([1, 0, 0, 1, 0, 1, 1, 0, 1])[0])
assert_array_equal(enc.feature_indices_, [0, 4, 7, 9])
# check outcome
assert_array_equal(X_trans,
[[0., 1., 0., 1., 1.],
[1., 0., 1., 0., 1.]])
# max value given as 3
enc = OneHotEncoder(n_values=4)
X_trans = enc.fit_transform(X)
assert_equal(X_trans.shape, (2, 4 * 3))
assert_array_equal(enc.feature_indices_, [0, 4, 8, 12])
# max value given per feature
enc = OneHotEncoder(n_values=[3, 2, 2])
X = [[1, 0, 1], [0, 1, 1]]
X_trans = enc.fit_transform(X)
assert_equal(X_trans.shape, (2, 3 + 2 + 2))
assert_array_equal(enc.n_values_, [3, 2, 2])
# check that testing with larger feature works:
X = np.array([[2, 0, 1], [0, 1, 1]])
enc.transform(X)
# test that an error is raised when out of bounds:
X_too_large = [[0, 2, 1], [0, 1, 1]]
assert_raises(ValueError, enc.transform, X_too_large)
assert_raises(ValueError, OneHotEncoder(n_values=2).fit_transform, X)
# test that error is raised when wrong number of features
assert_raises(ValueError, enc.transform, X[:, :-1])
# test that error is raised when wrong number of features in fit
# with prespecified n_values
assert_raises(ValueError, enc.fit, X[:, :-1])
# test exception on wrong init param
assert_raises(TypeError, OneHotEncoder(n_values=np.int).fit, X)
enc = OneHotEncoder()
# test negative input to fit
assert_raises(ValueError, enc.fit, [[0], [-1]])
# test negative input to transform
enc.fit([[0], [1]])
assert_raises(ValueError, enc.transform, [[0], [-1]])
def load_UCI_Credit_Card_data(infile=None, balanced=True, seed=5):
X = []
y = []
sids = []
with open(infile, "r") as fi:
fi.readline()
reader = csv.reader(fi)
for row in reader:
sids.append(row[0])
X.append(row[1:-1])
y0 = int(row[-1])
if y0 == 0:
y0 = -1
y.append(y0)
y = np.array(y)
if balanced:
X, y = balance_X_y(X, y, seed)
X = np.array(X, dtype=np.float32)
y = np.array(y, dtype=np.float32)
encoder = OneHotEncoder(categorical_features=[1, 2, 3])
encoder.fit(X)
X = encoder.transform(X).toarray()
X, y = shuffle_X_y(X, y, seed)
scale_model = StandardScaler()
X = scale_model.fit_transform(X)
return X, np.expand_dims(y, axis=1)
def train(self, X, Y, class_number=-1):
class_count = max(np.unique(Y).size, class_number)
feature_count = X.shape[1]
self.__hpelm = ELM(feature_count, class_count, 'wc')
self.__hpelm.add_neurons(feature_count, "sigm")
Y_arr = Y.reshape(-1, 1)
enc = OneHotEncoder()
enc.fit(Y_arr)
Y_OHE = enc.transform(Y_arr).toarray()
out_fd = sys.stdout
sys.stdout = open(os.devnull, 'w')
self.__hpelm.train(X, Y_OHE)
sys.stdout = out_fd
def buildModel(self, X_train_d, X_train_c, X_test_d, X_test_c, y_train, y_test):
'''
开始构建模型
Args:
X_train_d: 离散特征训练数据
X_train_c: 连续特征训练数据
X_test_d: 离散特征测试数据
X_test_c: 连续特征测试数据
y_train: 训练数据标记 {-1, 1}
y_test: 测试数据标记 {-1, 1}
Returns:
gbc_enc: GBDT OneHotEncoder
gbc: GBDT模型
comb_model: 训练得到的组合模型
threshold: 正负样例阈值, Pred_Prob >= threshold 为正样例; Pred_Prob < threshold 为负样例
comb_model_auc: 模型AUC
precision: 模型精度
recall: 模型召回率
'''
if self._random_state is not None:
gbc = GradientBoostingClassifier(n_estimators=self._n_estimators, learning_rate=self._gbdt_learning_rate, max_depth=self._max_depth, random_state=self._random_state).fit(X_train_c, y_train)
else:
gbc = GradientBoostingClassifier(n_estimators=self._n_estimators, learning_rate=self._gbdt_learning_rate, max_depth=self._max_depth).fit(X_train_c, y_train)
X_train_leaves = gbc.apply(X_train_c)[:,:,0]
X_test_leaves = gbc.apply(X_test_c)[:,:,0]
(X_train_rows, cols) = X_train_leaves.shape
gbc_enc = OneHotEncoder().fit(np.concatenate([X_train_leaves,X_test_leaves], axis = 0))
X_trans = gbc_enc.transform(np.concatenate([X_train_leaves,X_test_leaves], axis = 0))
X_train_ext = hstack([X_trans[:X_train_rows,:], X_train_d])
X_test_ext = hstack([X_trans[X_train_rows:,:], X_test_d])
log.debug("Combine features done.")
comb_model = LogisticRegression().fit(X_train_ext, y_train)
log.debug("Training done.")
comb_model_pred = comb_model.predict_proba(X_test_ext)[:,1]
precision, recall, thresholds = precision_recall_curve(y_test, comb_model_pred)
ap = average_precision_score(y_test, comb_model_pred)
recall_meet = recall >= self._recall_rate
recall_meet_min = len([item for item in recall_meet if item == True])
threshold = thresholds[recall_meet_min-1]
log.debug("threshold: %f - precision: %f - recall: %f", threshold, precision[recall_meet_min-1], recall[recall_meet_min-1])
comb_model_auc = roc_auc_score(y_test, comb_model_pred)
log.debug("AUC score is: %f", comb_model_auc)
return gbc_enc, gbc, comb_model, threshold, comb_model_auc, precision[recall_meet_min-1], recall[recall_meet_min-1]
def test_one_hot_encoder_unknown_transform():
X = np.array([[0, 2, 1], [1, 0, 3], [1, 0, 2]])
y = np.array([[4, 1, 1]])
# Test that one hot encoder raises error for unknown features
# present during transform.
oh = OneHotEncoder(handle_unknown='error')
oh.fit(X)
assert_raises(ValueError, oh.transform, y)
# Test the ignore option, ignores unknown features.
oh = OneHotEncoder(handle_unknown='ignore')
oh.fit(X)
assert_array_equal(
oh.transform(y).toarray(), np.array([[0., 0., 0., 0., 1., 0., 0.]]))
# Raise error if handle_unknown is neither ignore or error.
oh = OneHotEncoder(handle_unknown='42')
oh.fit(X)
assert_raises(ValueError, oh.transform, y)
def test_one_hot_encoder_unknown_transform():
X = np.array([[0, 2, 1], [1, 0, 3], [1, 0, 2]])
y = np.array([[4, 1, 1]])
# Test that one hot encoder raises error for unknown features
# present during transform.
oh = OneHotEncoder(handle_unknown='error')
oh.fit(X)
assert_raises(ValueError, oh.transform, y)
# Test the ignore option, ignores unknown features.
oh = OneHotEncoder(handle_unknown='ignore')
oh.fit(X)
assert_array_equal(
oh.transform(y).toarray(),
np.array([[ 0., 0., 0., 0., 1., 0., 0.]])
)
# Raise error if handle_unknown is neither ignore or error.
oh = OneHotEncoder(handle_unknown='42')
oh.fit(X)
assert_raises(ValueError, oh.transform, y)
def _run_one_hot(X, X2, cat):
enc = OneHotEncoder(categorical_features=cat)
Xtr = enc.fit_transform(X)
X2tr = enc.transform(X2)
return Xtr, X2tr
def _run_one_hot(X, X2, cat):
enc = OneHotEncoder(categorical_features=cat)
Xtr = enc.fit_transform(X)
X2tr = enc.transform(X2)
return Xtr, X2tr
