def test_integration_nonperfect_linear():
X, y = data_gen(nrows=100, Non_perfect=True)
X_train, X_test, y_train, y_test = train_test_split(X, y)
scores = cross_validation(lm(), X=X_train, y=y_train, shuffle=False)
summary = summary_cv(scores)
assert summary['mean'] < 1 and summary['median'] < 1 and summary[
'sd'] > 0, 'Non-perfect linear relation test does not give correct summary'
def test_integration_nonperfect_linear():
X, y = data_gen(nrows=100, Non_perfect=True)
X_train, X_test, y_train, y_test = train_test_split(X, y)
scores = cross_validation(lm(), X=X_train, y=y_train, shuffle=False)
summary = summary_cv(scores)
assert summary['mean'] < 1 and summary['median'] < 1 and summary[
'sd'] > 0, 'Non-perfect linear relation test does not give correct summary'
def test_X_y_perfect_linear_random_state_None():
X, y = data_gen(nrows=100, Non_perfect=False)
function_scores = cross_validation(lm(),
X=X,
y=y,
shuffle=True,
random_state=None)
assert np.mean(function_scores
) == 1, "shuffle=True, randome state should have no effect"
def test_shuffle_as_boolean():
with pytest.raises(TypeError('`shuffle` must be True or False')):
cross_validation(lm, X=X, y=y, shuffle='1')
with pytest.raises(TypeError('`shuffle` must be True or False')):
cross_validation(lm, X=X, y=y, shuffle=1)
with pytest.raises(TypeError('`shuffle` must be True or False')):
cross_validation(lm, X=X, y=y, shuffle=1.0)
def test_X_y_Nrows():
X, y = data_gen(nrows=2)
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y, k=2)
def test_y_one_column():
X, y = data_gen()
y = X
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y)
def test_X_y_perfect_linear():
X, y = data_gen(nrows=100, Non_perfect=False)
function_scores = cross_validation(lm(), X=X, y=y, shuffle=False)
assert np.mean(function_scores) == 1, "Testing perfect linear case should have perfect socres (score=1)"
def test_k_range_k_not_one():
X, y = data_gen(nrows=5)
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y, k=1)
def test_random_state_range():
X, y = data_gen()
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y, random_state=-10)
def test_y_one_column():
with pytest.raises(TypeError('`y` is more than one feature')):
cross_validation(lm, X=X, y=y_2)
def test_X_as_dataframe():
X, y = data_gen()
with pytest.raises(TypeError):
cross_validation(lm(), X="X", y=y)
def test_shuffle_as_boolean_not_numeric():
X, y = data_gen()
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y, shuffle=1.0)
def test_random_state_as_number():
X, y = data_gen()
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y, random_state='10')
def test_compare_sklearn_mod_not_0():
X, y = data_gen(nrows=100)
function_scores = cross_validation(lm(), X=X, y=y, shuffle=False)
sklearn_scores = cross_val_score(lm(), X=X, y=y, cv=3)
assert max(function_scores -
sklearn_scores) < 0.000001, "results doesn't match sklearn"
def test_k_as_number():
X, y = data_gen()
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y, k='3')
def test_X_y_not_perfect_linear():
X, y = data_gen(nrows=100, Non_perfect=True)
function_scores = cross_validation(lm(), X=X, y=y, shuffle=False)
assert np.mean(function_scores) > 0 and np.mean(
function_scores) < 1, "results doesn't match sklearn"
def test_X_y_match():
X, y = data_gen()
y = y[0:90]
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y)
def test_X_y_perfect_linear():
X, y = data_gen(nrows=100, Non_perfect=False)
function_scores = cross_validation(lm(), X=X, y=y, shuffle=False)
assert np.mean(
function_scores
) == 1, "Testing perfect linear case should have perfect socres (score=1)"
def test_model_linear_regression():
X, y = data_gen()
with pytest.raises(TypeError):
cross_validation("LINEAR MODEL", X=X, y=y, random_state=10)
def test_model_linear_regression():
X, y = data_gen()
with pytest.raises(TypeError):
cross_validation("LINEAR MODEL", X=X, y=y, random_state=10)
def test_k_range_k_not_larger_than_nrows():
X, y = data_gen(nrows=5)
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y, k=40)
def test_X_as_dataframe():
with pytest.raises(TypeError('`X` must be a dataframe')):
cross_validation(lm, X=X_matrix, y=y)
def test_X_y_Nrows():
with pytest.raises(
TypeError('sample size is less than 3, too small for CV')):
cross_validation(lm, X=X.iloc[0:2, :], y=y.iloc[0:2, :])
def test_y_as_dataframe():
with pytest.raises(TypeError('`y` must be a dataframe')):
cross_validation(lm, X=X, y=y_list)
def test_random_state_range():
X, y = data_gen()
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y, random_state=-10)
def test_k_as_number():
with pytest.raises(TypeError('`k` must be an integer')):
cross_validation(lm, X=X, y=y, k='3')
def test_k_range_k_not_larger_than_nrows():
X, y = data_gen(nrows=5)
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y, k=40)
def test_X_y_not_perfect_linear():
X, y = data_gen(nrows=100, Non_perfect=True)
function_scores = cross_validation(lm(), X=X, y=y, shuffle=False)
assert np.mean(function_scores) > 0 and np.mean(function_scores) < 1, "results doesn't match sklearn"
def test_X_y_match():
X, y = data_gen()
y = y[0:90]
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y)
def test_y_as_dataframe():
X, y = data_gen()
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y="y")
def test_X_y_Nrows():
X, y = data_gen(nrows=2)
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y, k=2)
def test_shuffle_as_boolean_not_numeric():
X, y = data_gen()
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y, shuffle=1.0)
def test_X_y_perfect_linear_random_state_None():
X, y = data_gen(nrows=100, Non_perfect=False)
function_scores = cross_validation(lm(), X=X, y=y, shuffle=True, random_state=None)
assert np.mean(function_scores) == 1, "shuffle=True, randome state should have no effect"
def test_y_one_column():
X, y = data_gen()
y = X
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y)
def test_compare_sklearn_mod_not_0():
X, y = data_gen(nrows=100)
function_scores = cross_validation(lm(), X=X, y=y, shuffle=False)
sklearn_scores = cross_val_score(lm(), X=X, y=y, cv=3)
assert max(function_scores - sklearn_scores) < 0.000001, "results doesn't match sklearn"
def test_random_state_as_number():
with pytest.raises(TypeError('`random_state` must be a number or None')):
cross_validation(lm, X=X, y=y, random_state='10')
def test_k_as_number():
X, y = data_gen()
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y, k='3')
def test_k_range():
with pytest.raises(TypeError('`k` must be an integer 2 or greater')):
cross_validation(lm, X=X, y=y, k=1)
with pytest.raises(TypeError('`k` must be greater than # obs in X and y')):
cross_validation(lm, X=X, y=y, k=40)
def test_random_state_as_number():
X, y = data_gen()
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y, random_state='10')
def test_random_state_range():
with pytest.raises(TypeError('`random_state` must be nonnegative')):
cross_validation(lm, X=X, y=y, random_state=-10)
def test_X_y_match():
with pytest.raises(TypeError("dim of `X` doesn't equal dim of `y`")):
cross_validation(lm, X=X_longer, y=y)
def test_k_range_k_not_one():
X, y = data_gen(nrows=5)
with pytest.raises(TypeError):
cross_validation(lm(), X=X, y=y, k=1)
