def test_scoring_logreg_tune_correct(data_fixture, request):
train_data, test_data = request.getfixturevalue(data_fixture)
train_data.features = ScalingWithImputation().fit(
train_data.features).apply(train_data.features)
test_data.features = ScalingWithImputation().fit(test_data.features).apply(
test_data.features)
logreg = Model(model_type='logit')
model, _ = logreg.fit(train_data)
test_predicted = logreg.predict(fitted_model=model, data=test_data)
test_roc_auc = roc_auc(y_true=test_data.target, y_score=test_predicted)
logreg_for_tune = Model(model_type='logit')
model_tuned, _ = logreg_for_tune.fine_tune(
data=train_data, iterations=50, max_lead_time=timedelta(minutes=0.1))
test_predicted_tuned = logreg_for_tune.predict(fitted_model=model_tuned,
data=test_data)
test_roc_auc_tuned = roc_auc(y_true=test_data.target,
y_score=test_predicted_tuned)
roc_threshold = 0.6
assert round(test_roc_auc_tuned, 2) >= round(test_roc_auc,
2) > roc_threshold
def test_knn_classification_tune_correct(data_fixture, request):
data = request.getfixturevalue(data_fixture)
data.features = ScalingWithImputation().fit(data.features).apply(
data.features)
train_data, test_data = train_test_data_setup(data=data)
knn = Model(model_type='knn')
model, _ = knn.fit(data=train_data)
test_predicted = knn.predict(fitted_model=model, data=test_data)
roc_on_test = roc_auc(y_true=test_data.target, y_score=test_predicted)
roc_on_test_tuned_list = []
for _ in range(3):
knn_for_tune = Model(model_type='knn')
model, _ = knn_for_tune.fine_tune(data=train_data,
iterations=10,
max_lead_time=timedelta(minutes=1))
test_predicted_tuned = knn_for_tune.predict(fitted_model=model,
data=test_data)
roc_on_test_tuned = roc_auc(y_true=test_data.target,
y_score=test_predicted_tuned)
roc_on_test_tuned_list.append(roc_on_test_tuned)
roc_threshold = 0.6
assert np.array(
roc_on_test_tuned_list).any() >= roc_on_test > roc_threshold
def test_scaling_with_imputation(np_array_regression_with_missing_values):
scaler = ScalingWithImputation()
actual_scaled_data = scaler.fit_apply(
np_array_regression_with_missing_values)
scaler = StandardScaler()
df = pd.DataFrame(np_array_regression_with_missing_values)
data = df.fillna(df.mean()).to_numpy()
expected_scaled_data = scaler.fit_transform(data)
result = []
for i in range(len(actual_scaled_data)):
for j in range(len(actual_scaled_data[0])):
result.append(
math.isclose(actual_scaled_data[i][j],
expected_scaled_data[i][j],
abs_tol=0.00001))
assert all(result)
def test_log_clustering_fit_correct(data_fixture, request):
data = request.getfixturevalue(data_fixture)
data.features = ScalingWithImputation().fit(data.features).apply(
data.features)
train_data, test_data = train_test_data_setup(data=data)
kmeans = Model(model_type='kmeans')
_, train_predicted = kmeans.fit(data=train_data)
assert all(np.unique(train_predicted) == [0, 1])
def test_random_forest_fit_correct(data_fixture, request):
data = request.getfixturevalue(data_fixture)
data.features = ScalingWithImputation().fit(data.features).apply(
data.features)
train_data, test_data = train_test_data_setup(data=data)
random_forest = Model(model_type='rf')
_, train_predicted = random_forest.fit(data=train_data)
roc_on_train = get_roc_auc(train_data, train_predicted)
roc_threshold = 0.95
assert roc_on_train >= roc_threshold
def test_log_regression_fit_correct(classification_dataset):
data = classification_dataset
data.features = ScalingWithImputation().fit(data.features).apply(
data.features)
train_data, test_data = train_test_data_setup(data=data)
log_reg = Model(model_type='logit')
_, train_predicted = log_reg.fit(data=train_data)
roc_on_train = get_roc_auc(train_data, train_predicted)
roc_threshold = 0.95
assert roc_on_train >= roc_threshold
def test_classification_manual_tuning_correct(data_fixture, request):
data = request.getfixturevalue(data_fixture)
data.features = ScalingWithImputation().fit(data.features).apply(
data.features)
train_data, test_data = train_test_data_setup(data=data)
knn = Model(model_type='knn')
model, _ = knn.fit(data=train_data)
test_predicted = knn.predict(fitted_model=model, data=test_data)
knn_for_tune = Model(model_type='knn')
knn_for_tune.params = {'n_neighbors': 1}
model, _ = knn_for_tune.fit(data=train_data)
test_predicted_tuned = knn_for_tune.predict(fitted_model=model,
data=test_data)
assert not np.array_equal(test_predicted, test_predicted_tuned)
def test_rf_class_tune_correct(data_fixture, request):
data = request.getfixturevalue(data_fixture)
data.features = ScalingWithImputation().fit(data.features).apply(
data.features)
train_data, test_data = train_test_data_setup(data=data)
rf = Model(model_type='rf')
model, _ = rf.fit(train_data)
test_predicted = rf.predict(fitted_model=model, data=test_data)
test_roc_auc = roc_auc(y_true=test_data.target, y_score=test_predicted)
model_tuned, _ = rf.fine_tune(data=train_data,
iterations=12,
max_lead_time=timedelta(minutes=0.1))
test_predicted_tuned = rf.predict(fitted_model=model_tuned, data=test_data)
test_roc_auc_tuned = roc_auc(y_true=test_data.target,
y_score=test_predicted_tuned)
roc_threshold = 0.7
assert test_roc_auc_tuned >= test_roc_auc
assert test_roc_auc_tuned > roc_threshold
def test_pca_manual_tuning_correct(data_fixture, request):
data = request.getfixturevalue(data_fixture)
data.features = ScalingWithImputation().fit(data.features).apply(
data.features)
train_data, test_data = train_test_data_setup(data=data)
pca = Model(model_type='pca_data_model')
model, _ = pca.fit(data=train_data)
test_predicted = pca.predict(fitted_model=model, data=test_data)
pca_for_tune = Model(model_type='pca_data_model')
pca_for_tune.params = {
'svd_solver': 'randomized',
'iterated_power': 'auto',
'dim_reduction_expl_thr': 0.7,
'dim_reduction_min_expl': 0.001
}
model, _ = pca_for_tune.fit(data=train_data)
test_predicted_tuned = pca_for_tune.predict(fitted_model=model,
data=test_data)
assert not np.array_equal(test_predicted, test_predicted_tuned)