def test_grad_objective_function_infinite_end_time_two_features():
df = pd.DataFrame(
[[0, np.nan, 1, random()], [random(), np.nan, 1,
random()],
[0, random(), 1, random()], [0, random(), 1, random()]],
columns=['click_time', 'conv_time', 'intercept', 'random'])
features = ['intercept', 'random']
end_time = 1000000
y = df[['click_time', 'conv_time']].values
X = csr_matrix(df[features].values)
grad_objective_function = grad_objective_function_factory(
fit_intercept=False)
input_ = prepare_input(y, X, end_time=end_time)
input_['Jacobian'] = np.zeros(4)
y1 = input_['y1']
x0, x1 = input_['x0'], input_['x1']
w_zero = np.zeros(4)
input_['mu'] = 0
assert np.allclose(
grad_objective_function(w_zero, **input_),
np.array([
0, 1 / 2 * x0[:, 1].sum() - 1 / 2 * x1[:, 1].sum(),
(y1[:, 1] - y1[:, 0] - 1).sum(),
((y1[:, 1] - y1[:, 0] - 1) * x1[:, 1]).sum()
]))
def test_objective_function_zero_and_one_weights():
end_time = 10 * random()
df = pd.DataFrame(
[[0, np.nan, 1], [end_time * random(), np.nan, 1],
[0, end_time * random(), 1], [0, end_time * random(), 1]],
columns=['click_time', 'conv_time', 'intercept'])
features = ['intercept']
end_time = 10
y = df[['click_time', 'conv_time']].values
X = csr_matrix(df[features].values)
objective_function = objective_function_factory(fit_intercept=False)
input_ = prepare_input(y, X, end_time=end_time)
input_['Jacobian'] = np.zeros(2)
y0, y1 = input_['y0'], input_['y1']
w_zero = np.zeros(2)
w_one = np.ones(2)
a0_zero = -np.sum(np.log(1 / 2 + 1 / 2 * np.exp(-(end_time - y0[:, 0]))))
a1_zero = y1.shape[0] * np.log(2) + (y1[:, 1] - y1[:, 0]).sum()
a0_one = -np.sum(
np.log(1 - sigmoid(1) + sigmoid(1) * np.exp(-np.exp(1) *
(end_time - y0[:, 0]))))
a1_one = -y1.shape[0] * (np.log(sigmoid(1)) +
1) + np.exp(1) * (y1[:, 1] - y1[:, 0]).sum()
assert np.allclose(objective_function(w_zero, **input_), a0_zero + a1_zero)
assert np.allclose(objective_function(w_one, **input_),
a0_one + a1_one + 1.)
def test_grad_objective_function_infinite_end_time():
df = pd.DataFrame([[0, np.nan, 1], [random(), np.nan, 1],
[0, random(), 1], [0, random(), 1]],
columns=['click_time', 'conv_time', 'intercept'])
end_time = 1000000
y = df[['click_time', 'conv_time']].values
X = csr_matrix(df[['intercept']].values)
grad_objective_function = grad_objective_function_factory(
fit_intercept=False)
input_ = prepare_input(y, X, end_time=end_time)
input_['Jacobian'] = np.zeros(2)
y1 = input_['y1']
w_zero = np.zeros(2)
w_one = np.ones(2)
assert np.allclose(grad_objective_function(w_zero, **input_),
np.array([0, (y1[:, 1] - y1[:, 0]).sum() - 2]))
assert np.allclose(
grad_objective_function(w_one, **input_),
np.array([
df.shape[0] * sigmoid(1) - y1.shape[0],
np.exp(1) * (y1[:, 1] - y1[:, 0]).sum() - 2
]) + w_one)
def test_minimize():
df = pd.DataFrame(
[[0., np.nan, random()], [random(), np.nan, random()],
[0., random(), random()], [0., random(), random()]],
columns=['click_time', 'conv_time', 'random_feature'])
features = ['random_feature']
end_time = 1.
y = df[['click_time', 'conv_time']].as_matrix()
X = csr_matrix(df[features])
input_ = prepare_input(y, X, end_time=end_time)
input_['Jacobian'] = np.array([random(), random(), random(), random()])
clf = ConversionEstimator(end_time=end_time)
clf.fit(X, y)
assert isinstance(clf.coef_, np.ndarray) and isinstance(
clf.lag_coef_, np.ndarray)
assert clf.convergence_info['success']
assert clf.convergence_info['message'] in {
b'CONVERGENCE: NORM_OF_PROJECTED_GRADIENT_<=_PGTOL',
b'CONVERGENCE: REL_REDUCTION_OF_F_<=_FACTR*EPSMCH'
}
def fit(self, X, y):
utils_input = (y, X, self.end_time)
opt_input = prepare_input(*utils_input)
self.convergence_info = self._get_optimization_result(**opt_input)
self._get_optimal_params(self.convergence_info)
return self
def test_objective_function_output_type(test_data_input):
p = test_data_input['X'].shape[1]
objective_function = objective_function_factory(fit_intercept=False)
input_ = prepare_input(**test_data_input)
w = np.zeros(2 * p)
input_['Jacobian'] = np.zeros(2 * p)
assert isinstance(objective_function(w, **input_), float)
def test_minimize_large(test_dummied_matrix):
y, X = test_dummied_matrix
end_time = 1.1 * y[:, 1][~np.isnan(y[:, 1])].max()
input_ = prepare_input(y, X, end_time=end_time)
input_['Jacobian'] = np.array([random() for _ in range(2 * X.shape[1])])
clf = ConversionEstimator(end_time=end_time)
clf.fit(X, y)
assert isinstance(clf.coef_, np.ndarray) and isinstance(
clf.lag_coef_, np.ndarray)
assert clf.convergence_info['success']
assert clf.convergence_info['message'] in {
b'CONVERGENCE: NORM_OF_PROJECTED_GRADIENT_<=_PGTOL',
b'CONVERGENCE: REL_REDUCTION_OF_F_<=_FACTR*EPSMCH'
}
def test_prepare_input():
features = [
'int_feat_1', 'int_feat_2', 'int_feat_3', 'cat_feat_1', 'cat_feat_2',
'cat_feat_3'
]
df = pd.read_csv('convpy/tests/data/test_conv_logs.csv')
enc = OneHotEncoderCOO()
X = enc.transform(df[features].values)
y = df[['click_time', 'conv_time']].values
end_time = 10.
input_ = prepare_input(y, X, end_time)
assert isinstance(input_['y0'], np.ndarray)
assert isinstance(input_['y1'], np.ndarray)
assert isinstance(input_['x0'], csr_matrix)
assert isinstance(input_['x1'], csr_matrix)
assert isinstance(input_['diagonal0'], coo_matrix)
assert isinstance(input_['diagonal1'], coo_matrix)
def get_fitted_estimator_and_encoder():
df = pd.DataFrame(
[[0., np.nan, random()], [random(), np.nan,
random()],
[0., random(), random()], [0., random(), random()]],
columns=['click_time', 'conv_time', 'random_feature'])
features = ['random_feature']
end_time = 1.
y, X = df[['click_time', 'conv_time']].values, df[features].values
X_enc = csr_matrix(X)
input_ = prepare_input(y, X_enc, end_time=end_time)
input_['Jacobian'] = np.array([random(), random(), random(), random()])
estimator = ConversionEstimator(end_time=end_time)
estimator.fit(X_enc, y)
encoder = OneHotEncoderCOO(features=['random_feature'])
encoder.fit(X)
return estimator, encoder
def test_scipy_check_grad(test_dummied_matrix):
y, X = test_dummied_matrix
end_time = 1.1 * y[:, 1][~np.isnan(y[:, 1])].max()
for fit_intercept in [True, False]:
objective_function = objective_function_factory(
fit_intercept=fit_intercept)
grad_objective_function = grad_objective_function_factory(
fit_intercept=fit_intercept)
input_ = prepare_input(y, X, end_time=end_time)
p = input_['x0'].shape[1]
input_['Jacobian'] = np.zeros(2 * p)
input_['mu'] = 0.
for i in range(20):
w0 = (5. - i) * np.ones(2 * p)
L = partial(objective_function, **input_)
DL = partial(grad_objective_function, **input_)
assert isclose(check_grad(L, DL, w0), 0.)
