improving testing

tfm000 · Dec 4, 2023 · b5cf517 · b5cf517
1 parent 39fb6a8
commit b5cf517
Show file tree

Hide file tree

Showing 15 changed files with 179 additions and 264 deletions.
diff --git a/sklarpy/tests/copulas/test_fitted_dists.py b/sklarpy/tests/copulas/test_fitted_dists.py
@@ -13,7 +13,6 @@ def test_fitted_logpdf_pdf_cdf_mc_cdfs(all_mvt_data, copula_params_2d,
                                        all_mdists_2d):
     """Testing the logpdf, pdf, cdf and mc-cdf functions of fitted copula
     models."""
-    print("\nTesting logpdf, pdf, cdf and mc-cdf functions")
     eps: float = 10 ** -5
     num_generate: int = 10
     cdf_num: int = 10
@@ -72,7 +71,6 @@ def test_fitted_copula_logpdf_pdf_cdf_mc_cdfs(all_mvt_uniform_data,
                                               copula_params_2d, all_mdists_2d):
     """Testing the copula-logpdf, copula-pdf, copula-cdf and copula-mc-cdf
     functions of fitted copula models."""
-    print("\nTesting copula logpdf, pdf, cdf and mc-cdf functions")
     eps: float = 10 ** -5
     num_generate: int = 10
     cdf_num: int = 10
@@ -130,7 +128,6 @@ def test_fitted_copula_logpdf_pdf_cdf_mc_cdfs(all_mvt_uniform_data,
 
 def test_fitted_rvs(all_mvt_data, copula_params_2d, all_mdists_2d):
     """Testing the rvs and copula-rvs functions of fitted copula models."""
-    print("\nTesting rvs and copula-rvs")
     eps: float = 10 ** -5
     dataset_name: str = 'mvt_mixed'
     data: np.ndarray = all_mvt_data[dataset_name]
@@ -168,8 +165,6 @@ def test_fitted_rvs(all_mvt_data, copula_params_2d, all_mdists_2d):
 def test_fitted_scalars(all_mvt_data, copula_params_2d, all_mdists_2d):
     """Testing the likelihood, loglikelihood, AIC and BIC functions of
     fitted copula models."""
-    print("\nTesting scalars")
-
     for dataset_name, data in all_mvt_data.items():
         mdists = all_mdists_2d[dataset_name]
         for name in distributions_map['all']:
@@ -215,8 +210,6 @@ def test_fitted_scalars(all_mvt_data, copula_params_2d, all_mdists_2d):
 def test_fitted_integers(all_mvt_data, copula_params_2d, all_mdists_2d):
     """Testing the num_marginal_params, num_copula_params,
     num_scalar_params and num_params functions of fitted copula models."""
-    print("\nTesting integers")
-
     dataset_name: str = 'mvt_mixed'
     data: np.ndarray = all_mvt_data[dataset_name]
     mdists = all_mdists_2d[dataset_name]
@@ -239,8 +232,6 @@ def test_fitted_plots(all_mvt_data, copula_params_2d, copula_params_3d,
     """Testing the marginal_pairplot, pdf_plot, cdf_plot, mc_cdf_plot,
     copula_pdf_plot, copula_cdf_plot and copula_mc_cdf_plot methods of
     fitted copula models."""
-    print("\nTesting plots")
-
     num_generate: int = 10
     mc_num_generate: int = num_generate
     num_points = 2
@@ -287,8 +278,6 @@ def test_fitted_plots(all_mvt_data, copula_params_2d, copula_params_3d,
 
 
 def test_fitted_names(all_mvt_data, copula_params_2d, all_mdists_2d):
-    print("\nTesting name")
-
     dataset_name: str = 'mvt_mixed'
     data: np.ndarray = all_mvt_data[dataset_name]
     mdists = all_mdists_2d[dataset_name]

diff --git a/sklarpy/tests/copulas/test_marginal_fitter.py b/sklarpy/tests/copulas/test_marginal_fitter.py
@@ -9,14 +9,12 @@
 
 def test_init(all_mvt_data):
     """Testing whether MarginalFitter initialises without errors."""
-    print("\nTesting init")
     for data in all_mvt_data.values():
         mfitter = MarginalFitter(data)
 
 
 def test_fit(all_mvt_data):
     """Testing the fit method for MarginalFitter"""
-    print("\nTesting fit")
     for dataset_name, data in all_mvt_data.items():
         # testing fit with default arguments
         mfitter1: MarginalFitter = MarginalFitter(data)
@@ -46,7 +44,6 @@ def test_fit(all_mvt_data):
 
 def test_pdfs_cdfs_ppfs_logpdf(all_mvt_data, all_mvt_uniform_data):
     """Testing the cdfs method for MarginalFitter"""
-    print("\nTesting pdfs, cdfs, ppfs and logpdfs")
     for dataset_name in ('mvt_mixed', 'pd_mvt_mixed'):
         data = all_mvt_data[dataset_name]
         mfitter: MarginalFitter = MarginalFitter(data)

diff --git a/sklarpy/tests/copulas/test_prefit_dists.py b/sklarpy/tests/copulas/test_prefit_dists.py
@@ -15,7 +15,6 @@
 
 def test_correct_type():
     """Testing copula distributions are all SklarPy objects."""
-    print("\nTesting correct type")
     for name in distributions_map['all']:
         copula = eval(name)
         assert issubclass(type(copula), PreFitCopula), \
@@ -24,7 +23,6 @@ def test_correct_type():
 
 def test_fit(all_mvt_data):
     """Testing we can fit copula distributions to data."""
-    print("\nTesting fit")
     for data in all_mvt_data.values():
         mfitter: MarginalFitter = MarginalFitter(data)
         mfitter.fit()
@@ -92,7 +90,6 @@ def test_prefit_logpdf_pdf_cdf_mc_cdfs(all_mvt_data, copula_params_2d,
                                        all_mdists_2d):
     """Testing the logpdf, pdf, cdf and mc-cdf functions of pre-fit copula
     models."""
-    print("\nTesting logpdf, pdf, cdf and mc-cdf functions")
     eps: float = 10 ** -5
     num_generate: int = 10
     cdf_num: int = 10
@@ -153,7 +150,6 @@ def test_prefit_copula_logpdf_pdf_cdf_mc_cdfs(all_mvt_uniform_data,
                                               copula_params_2d, all_mdists_2d):
     """Testing the copula-logpdf, copula-pdf, copula-cdf and copula-mc-cdf
     functions of pre-fit copula models."""
-    print("\nTesting copula logpdf, pdf, cdf and mc-cdf functions")
     eps: float = 10 ** -5
     num_generate: int = 10
     cdf_num: int = 10
@@ -213,8 +209,6 @@ def test_prefit_copula_logpdf_pdf_cdf_mc_cdfs(all_mvt_uniform_data,
 
 def test_prefit_rvs(all_mvt_data, copula_params_2d, all_mdists_2d):
     """Testing the rvs and copula-rvs functions of pre-fit copula models."""
-    print("\nTesting rvs and copula-rvs")
-
     eps: float = 10 ** -5
     dataset_name: str = 'mvt_mixed'
     data: np.ndarray = all_mvt_data[dataset_name]
@@ -252,8 +246,6 @@ def test_prefit_rvs(all_mvt_data, copula_params_2d, all_mdists_2d):
 def test_prefit_scalars(all_mvt_data, copula_params_2d, all_mdists_2d):
     """Testing the likelihood, loglikelihood, AIC and BIC functions of
     pre-fit copula models."""
-    print("\nTesting scalars")
-
     for dataset_name, data in all_mvt_data.items():
         mdists = all_mdists_2d[dataset_name]
         for name in distributions_map['all']:
@@ -294,8 +286,6 @@ def test_prefit_scalars(all_mvt_data, copula_params_2d, all_mdists_2d):
 def test_prefit_integers(all_mvt_data, copula_params_2d, all_mdists_2d):
     """Testing the num_marginal_params, num_copula_params,
     num_scalar_params and num_params functions of pre-fit copula models."""
-    print("\nTesting integers")
-
     dataset_name: str = 'mvt_mixed'
     data: np.ndarray = all_mvt_data[dataset_name]
     mdists = all_mdists_2d[dataset_name]
@@ -318,8 +308,6 @@ def test_prefit_plots(all_mvt_data, copula_params_2d, copula_params_3d,
     """Testing the marginal_pairplot, pdf_plot, cdf_plot, mc_cdf_plot,
     copula_pdf_plot, copula_cdf_plot and copula_mc_cdf_plot methods of
     pre-fit copula models."""
-    print("\nTesting plots")
-
     num_generate: int = 10
     mc_num_generate: int = num_generate
     num_points = 2
@@ -368,7 +356,6 @@ def test_prefit_plots(all_mvt_data, copula_params_2d, copula_params_3d,
 
 
 def test_prefit_names():
-    print("\nTesting name")
     for name in distributions_map['all']:
         copula = eval(name)
         assert isinstance(copula.name, str), f"name of {name} is not a string."
diff --git a/sklarpy/tests/misc/test_correlation.py b/sklarpy/tests/misc/test_correlation.py
@@ -7,7 +7,6 @@
 
 def test_implemented():
     """Testing CorrelationMatrix object has IMPLEMENTED class attribute."""
-    print("\nTesting implemented")
     # checking class attribute exists
     CorrelationMatrix.IMPLEMENTED
 
@@ -30,7 +29,6 @@ def test_implemented():
 def test_corr(continuous_data, discrete_data, mvt_continuous_data,
               mvt_discrete_data):
     """Testing correlation matrices generated by implemented methods."""
-    print("\nTesting corr")
     for method in CorrelationMatrix.IMPLEMENTED:
         for data in (mvt_continuous_data, mvt_discrete_data):
             d: int = data.shape[1]
@@ -78,7 +76,6 @@ def test_corr(continuous_data, discrete_data, mvt_continuous_data,
 def test_cov(continuous_data, discrete_data, mvt_continuous_data,
              mvt_discrete_data):
     """Testing the covariance matrix generated by implemented methods."""
-    print("\nTesting cov")
     for method in CorrelationMatrix.IMPLEMENTED:
         for data in (mvt_continuous_data, mvt_discrete_data):
             d: int = data.shape[1]

diff --git a/sklarpy/tests/misc/test_debye.py b/sklarpy/tests/misc/test_debye.py
@@ -4,7 +4,6 @@
 
 def test_debye():
     """Testing debye function."""
-    print("\nTesting debye")
     n_values = range(0, 10)
     x_values: list = [0, 1.5, -0.5, 4.3]
 

diff --git a/sklarpy/tests/misc/test_gradient.py b/sklarpy/tests/misc/test_gradient.py
@@ -8,7 +8,6 @@
 
 def test_gradient_1d():
     """Testing gradient_1d function."""
-    print("\nTesting gradient-1d")
     funcs: list = [XCubed, Exp, Log]
     x_values = [0, 1.5, -0.5, 4.3, 9.7, 11, -8]
     datatypes = [np.asarray, list, pd.DataFrame, pd.Series, set]

diff --git a/sklarpy/tests/misc/test_modified_bessel.py b/sklarpy/tests/misc/test_modified_bessel.py
@@ -8,7 +8,6 @@
 
 def test_kv():
     """Testing the Modified Bessel function of the 2nd kind."""
-    print("\nTesting kv")
     v_values = [0, 0.1, 4.3, 9.7]
     z_values = [0, *np.random.uniform(0, 200, 100)]
 

diff --git a/sklarpy/tests/multivariate/test_fitted_dists.py b/sklarpy/tests/multivariate/test_fitted_dists.py
@@ -10,68 +10,67 @@
 from sklarpy.utils._params import Params
 
 
-# def test_fitted_logpdf_pdf_cdf_mc_cdf(
-#         mvt_continuous_data, mvt_discrete_data, pd_mvt_continuous_data,
-#         pd_mvt_discrete_data, mv_dists_to_test, params_2d):
-#     """Testing the logpdf, pdf, cdf and mc-cdf functions of fitted multivariate
-#      distributions"""
-#     print('\nTesting logpdf, pdf, cdf and mc-cdf functions')
-#     eps: float = 10 ** -5
-#     num_generate: int = 10
-#
-#     for name in mv_dists_to_test:
-#         _, fitted, _ = get_dist(name, params_2d, mvt_continuous_data)
-#         for func_str in ('logpdf', 'pdf', 'mc_cdf'): #, 'cdf'):
-#             func: Callable = eval(f'fitted.{func_str}')
-#             cdf_num: int = 10
-#             datasets = (mvt_continuous_data[:cdf_num, :],
-#                         mvt_discrete_data[:cdf_num, :],
-#                         pd_mvt_continuous_data.iloc[:cdf_num, :],
-#                         pd_mvt_discrete_data.iloc[:cdf_num, :]) \
-#                 if func_str == 'cdf' else (mvt_continuous_data,
-#                                            mvt_discrete_data,
-#                                            pd_mvt_continuous_data,
-#                                            pd_mvt_discrete_data)
-#
-#             for data in datasets:
-#                 output = func(x=data, match_datatype=True,
-#                               num_generate=num_generate)
-#
-#                 np_output = np.asarray(output)
-#                 n, d = np.asarray(data).shape
-#
-#                 # checking same datatype
-#                 assert isinstance(output, type(data)), \
-#                     f"{func_str} values for {name} do not match the " \
-#                     f"datatype: {type(data)}."
-#
-#                 # checking the correct size
-#                 assert np_output.size == n, \
-#                     f"{func_str} values for {name} are not the correct size."
-#
-#                 # checking for nan-values
-#                 assert np.isnan(np_output).sum() == 0, \
-#                     f'nans present in {name} {func_str} values.'
-#
-#                 # function specific tests
-#                 if func_str == 'pdf':
-#                     assert np.all(np_output >= -eps), \
-#                         f"pdf values in {name} are negative."
-#                 elif func_str in ('cdf', 'mc_cdf'):
-#                     assert np.all((-eps <= np_output) & (output <= 1 + eps)), \
-#                         f"{func_str} values in {name} outside [0, 1]."
-#
-#             # checking error if wrong dimension
-#             new_dataset: np.ndarray = np.zeros((n, d + 1))
-#             with pytest.raises(
-#                     ValueError, match="Dimensions implied by parameters do "
-#                                       "not match those of the dataset."):
-#                 func(x=new_dataset, num_generate=num_generate)
+@pytest.mark.test_local_only
+def test_fitted_logpdf_pdf_cdf_mc_cdf(
+        mvt_continuous_data, mvt_discrete_data, pd_mvt_continuous_data,
+        pd_mvt_discrete_data, mv_dists_to_test, params_2d):
+    """Testing the logpdf, pdf, cdf and mc-cdf functions of fitted multivariate
+     distributions"""
+    eps: float = 10 ** -5
+    num_generate: int = 10
+
+    for name in mv_dists_to_test:
+        _, fitted, _ = get_dist(name, params_2d, mvt_continuous_data)
+        for func_str in ('logpdf', 'pdf', 'mc_cdf'): #, 'cdf'):
+            func: Callable = eval(f'fitted.{func_str}')
+            cdf_num: int = 10
+            datasets = (mvt_continuous_data[:cdf_num, :],
+                        mvt_discrete_data[:cdf_num, :],
+                        pd_mvt_continuous_data.iloc[:cdf_num, :],
+                        pd_mvt_discrete_data.iloc[:cdf_num, :]) \
+                if func_str == 'cdf' else (mvt_continuous_data,
+                                           mvt_discrete_data,
+                                           pd_mvt_continuous_data,
+                                           pd_mvt_discrete_data)
+
+            for data in datasets:
+                output = func(x=data, match_datatype=True,
+                              num_generate=num_generate)
+
+                np_output = np.asarray(output)
+                n, d = np.asarray(data).shape
+
+                # checking same datatype
+                assert isinstance(output, type(data)), \
+                    f"{func_str} values for {name} do not match the " \
+                    f"datatype: {type(data)}."
+
+                # checking the correct size
+                assert np_output.size == n, \
+                    f"{func_str} values for {name} are not the correct size."
+
+                # checking for nan-values
+                assert np.isnan(np_output).sum() == 0, \
+                    f'nans present in {name} {func_str} values.'
+
+                # function specific tests
+                if func_str == 'pdf':
+                    assert np.all(np_output >= -eps), \
+                        f"pdf values in {name} are negative."
+                elif func_str in ('cdf', 'mc_cdf'):
+                    assert np.all((-eps <= np_output) & (output <= 1 + eps)), \
+                        f"{func_str} values in {name} outside [0, 1]."
+
+            # checking error if wrong dimension
+            new_dataset: np.ndarray = np.zeros((n, d + 1))
+            with pytest.raises(
+                    ValueError, match="Dimensions implied by parameters do "
+                                      "not match those of the dataset."):
+                func(x=new_dataset, num_generate=num_generate)
 
 
 def test_fitted_rvs(mv_dists_to_test, params_2d, mvt_continuous_data):
     """Testing the rvs functions of fitted multivariate distributions."""
-    print('\nTesting rvs')
     for name in mv_dists_to_test:
         _, fitted, _ = get_dist(name, params_2d, mvt_continuous_data)
         for size in (1, 2, 5, 101):
@@ -93,7 +92,6 @@ def test_fitted_scalars(mvt_continuous_data, mvt_discrete_data,
                         mv_dists_to_test, params_2d):
     """Testing the likelihood, loglikelihood, AIC and BIC functions of
     multivariate fitted distributions."""
-    print('\nTesting scalars')
     for name in mv_dists_to_test:
         _, fitted, _ = get_dist(name, params_2d, mvt_continuous_data)
         for func_str in ('likelihood', 'loglikelihood', 'aic', 'bic'):
@@ -131,7 +129,6 @@ def test_fitted_scalars(mvt_continuous_data, mvt_discrete_data,
 def test_fitted_plots(params_2d, params_3d, mvt_continuous_data):
     """Testing the marginal_pairplot, pdf_plot, cdf_plot and mc_cdf_plot
     methods of fitted multivariate distributions."""
-    print('\nTesting plots')
     mvt_continuous_data_3d: np.ndarray = scipy.stats.multivariate_normal.rvs(
         size=(mvt_continuous_data.shape[0], 3))
     kwargs: dict = {'num_points': 2, 'num_generate': 10, 'mc_num_generate': 10,
@@ -162,7 +159,6 @@ def test_fitted_plots(params_2d, params_3d, mvt_continuous_data):
 
 def test_fitted_params(mv_dists_to_test, params_2d, mvt_continuous_data):
     """Testing the params attribute of fitted multivariate distributions."""
-    print('\nTesting params')
     for name in mv_dists_to_test:
         _, fitted, _ = get_dist(name, params_2d, mvt_continuous_data)
 
@@ -178,7 +174,6 @@ def test_fitted_params(mv_dists_to_test, params_2d, mvt_continuous_data):
 def test_fitted_integers(mv_dists_to_test, params_2d, mvt_continuous_data):
     """Testing the num_params, num_scalar_params, num_variables and
     fitted_num_data_points of fitted multivariate distributions."""
-    print('\nTesting integers')
     for name in mv_dists_to_test:
         _, fitted, params = get_dist(name, params_2d, mvt_continuous_data)
 
@@ -199,7 +194,6 @@ def test_fitted_integers(mv_dists_to_test, params_2d, mvt_continuous_data):
 
 def test_fitted_converged(mv_dists_to_test, params_2d, mvt_continuous_data):
     """Testing converged attributes of fitted multivariate distributions."""
-    print('\nTesting converged')
     for name in mv_dists_to_test:
         _, fitted, _ = get_dist(name, params_2d, mvt_continuous_data)
 
@@ -214,7 +208,6 @@ def test_fitted_converged(mv_dists_to_test, params_2d, mvt_continuous_data):
 
 def test_fitted_summaries(mv_dists_to_test, params_2d, mvt_continuous_data):
     """Testing the summaries of fitted multivariate distributions."""
-    print('\nTesting summaries')
     for name in mv_dists_to_test:
         _, fitted, _ = get_dist(name, params_2d, mvt_continuous_data)