more work on unit tests

Author: davidsebfischer

diffxpy/stats/stats.py

@@ -56,14 +56,13 @@ def mann_whitney_u_test(
     """
     axis = 1
     if np.any(np.ndim(x0) != np.ndim(x1)):
-        raise ValueError('stats.wilcoxon(): number of dimensions is not allowed to differ between x0 and x1!')
+        raise ValueError('number of dimensions is not allowed to differ between x0 and x1')
     # Reshape into 2D array if only one test is performed.
     if np.ndim(x0) == 1:
         x0 = x0.reshape([x0.shape[0], 1])
         x1 = x1.reshape([x1.shape[0], 1])
     if np.any(x0.shape[axis] != x1.shape[axis]):
-        raise ValueError(
-            'stats.wilcoxon(): the first axis (number of tests) is not allowed to differ between x0 and x1!')
+        raise ValueError('the first axis (number of tests) is not allowed to differ between x0 and x1')
 
     pvals = np.asarray([
         scipy.stats.mannwhitneyu(

diffxpy/unit_test/test_data_types.py

@@ -15,44 +15,38 @@ class TestDataTypesSingle(unittest.TestCase):
     def _test_wald(self, data, sample_description, gene_names=None):
         test = de.test.wald(
             data=data,
-            factor_loc_totest="condition",
-            formula_loc="~ 1 + condition",
             sample_description=sample_description,
             gene_names=gene_names,
-            quick_scale=True,
-            training_strategy="DEFAULT",
-            dtype="float64"
+            factor_loc_totest="condition",
+            formula_loc="~ 1 + condition"
         )
         _ = test.summary()
 
     def _test_lrt(self, data, sample_description, gene_names=None):
         test = de.test.lrt(
             data=data,
-            full_formula_loc="~ 1 + condition",
-            reduced_formula_loc="~ 1",
             sample_description=sample_description,
             gene_names=gene_names,
-            quick_scale=True,
-            training_strategy="DEFAULT",
-            dtype="float64"
+            full_formula_loc="~ 1 + condition",
+            reduced_formula_loc="~ 1"
         )
         _ = test.summary()
 
     def _test_t_test(self, data, sample_description, gene_names=None):
         test = de.test.t_test(
             data=data,
-            grouping="condition",
             sample_description=sample_description,
-            gene_names=gene_names
+            gene_names=gene_names,
+            grouping="condition"
         )
         _ = test.summary()
 
     def _test_rank(self, data, sample_description, gene_names=None):
         test = de.test.rank_test(
             data=data,
-            grouping="condition",
             sample_description=sample_description,
-            gene_names=gene_names
+            gene_names=gene_names,
+            grouping="condition"
         )
         _ = test.summary()
 

diffxpy/unit_test/test_extreme_values.py

@@ -3,7 +3,6 @@
 
 import numpy as np
 import pandas as pd
-import scipy.stats as stats
 
 from batchglm.api.models.glm_nb import Simulator
 import diffxpy.api as de
@@ -19,6 +18,8 @@ def test_t_test_zero_variance(self):
         logging.getLogger("batchglm").setLevel(logging.WARNING)
         logging.getLogger("diffxpy").setLevel(logging.WARNING)
 
+        np.random.seed(1)
+        de.pkg_constants.DE_TREAT_ZEROVAR_TT_AS_SIG = True
         sim = Simulator(num_observations=1000, num_features=10)
         sim.generate_sample_description(num_batches=0, num_conditions=0)
         sim.generate()
@@ -30,14 +31,14 @@ def test_t_test_zero_variance(self):
         })
 
         test = de.test.t_test(
-            data=sim.X,
-            grouping="condition",
+            data=sim.input_data,
             sample_description=random_sample_description,
+            grouping="condition",
             is_sig_zerovar=True
         )
 
         assert np.isnan(test.pval[0]) and test.pval[1] == 1, \
-            "rank test did not assign p-value of zero to groups with zero variance and same mean, %f, %f" % \
+            "t test did not assign p-value of zero to groups with zero variance and same mean, %f, %f" % \
             (test.pval[0], test.pval[1])
         return True
 
@@ -49,6 +50,8 @@ def test_rank_test_zero_variance(self):
         logging.getLogger("batchglm").setLevel(logging.WARNING)
         logging.getLogger("diffxpy").setLevel(logging.WARNING)
 
+        np.random.seed(1)
+        de.pkg_constants.DE_TREAT_ZEROVAR_TT_AS_SIG = True
         sim = Simulator(num_observations=1000, num_features=10)
         sim.generate_sample_description(num_batches=0, num_conditions=0)
         sim.generate()
@@ -60,9 +63,9 @@ def test_rank_test_zero_variance(self):
         })
 
         test = de.test.rank_test(
-            data=sim.X,
-            grouping="condition",
+            data=sim.input_data,
             sample_description=random_sample_description,
+            grouping="condition",
             is_sig_zerovar=True
         )