Add pydocstyle for tests

tasks.py

@@ -73,6 +73,7 @@ def lint(c):
     c.run('flake8 rdt')
     c.run('pydocstyle rdt')
     c.run('flake8 tests --ignore=D')
+    c.run('pydocstyle tests')
     c.run('isort -c --recursive rdt tests')
     c.run('pylint rdt tests/performance --rcfile=setup.cfg')
 

tests/__init__.py

@@ -1,3 +1,6 @@
+"""RDT test module."""
+
+
 def safe_compare_dataframes(first, second):
     """Compare two dataframes even if they have NaN values.
 
@@ -8,7 +11,6 @@ def safe_compare_dataframes(first, second):
     Returns:
         bool
     """
-
     if first.isnull().all().all():
         return first.equals(second)
 

tests/datasets/base.py

@@ -16,6 +16,7 @@ def generate(num_rows):
         Args:
             num_rows (int):
                 Number of rows to generate.
+
         Returns:
             numpy.ndarray of size ``num_rows``
         """

tests/datasets/boolean.py

@@ -36,6 +36,7 @@ class RandomBooleanNaNsGenerator(BooleanGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         percent_null = np.random.randint(MIN_PERCENT, MAX_PERCENT_NULL)
         percent_true = (100 - percent_null) / 2
         percent_false = 100 - percent_true - percent_null
@@ -52,6 +53,7 @@ class RandomSkewedBooleanGenerator(BooleanGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         percent_true = np.random.randint(MIN_PERCENT, 100 - MIN_PERCENT)
 
         return np.random.choice(
@@ -66,6 +68,7 @@ class RandomSkewedBooleanNaNsGenerator(BooleanGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         percent_null = np.random.randint(MIN_PERCENT, MAX_PERCENT_NULL)
         percent_true = np.random.randint(MIN_PERCENT, 100 - percent_null - MIN_PERCENT)
         percent_false = 100 - percent_null - percent_true
@@ -78,10 +81,11 @@ def generate(num_rows):
 
 
 class ConstantBooleanGenerator(BooleanGenerator):
-    """Generator that creates a constant array with either True or False"""
+    """Generator that creates a constant array with either True or False."""
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         constant = np.random.choice([True, False])
         return np.full(num_rows, constant)
 
@@ -91,6 +95,7 @@ class ConstantBooleanNaNsGenerator(BooleanGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         constant = np.random.choice([True, False])
         percent_null = np.random.randint(MIN_PERCENT, MAX_PERCENT_NULL)
 

tests/datasets/categorical.py

@@ -18,6 +18,7 @@ class RandomIntegerGenerator(CategoricalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         categories = [1, 2, 3, 4, 5]
         return np.random.choice(a=categories, size=num_rows)
 
@@ -27,6 +28,7 @@ class RandomIntegerNaNsGenerator(CategoricalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         return add_nans(RandomIntegerGenerator.generate(num_rows).astype(np.float))
 
 
@@ -35,6 +37,7 @@ class RandomStringGenerator(CategoricalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         categories = ['Alice', 'Bob', 'Charlie', 'Dave', 'Eve']
         return np.random.choice(a=categories, size=num_rows)
 
@@ -44,6 +47,7 @@ class RandomStringNaNsGenerator(CategoricalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         return add_nans(RandomStringGenerator.generate(num_rows).astype('O'))
 
 
@@ -55,6 +59,7 @@ class RandomMixedGenerator(CategoricalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         cat_size = 5
         categories = np.hstack([
             cat.astype('O') for cat in [
@@ -77,6 +82,7 @@ class RandomMixedNaNsGenerator(CategoricalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         array = RandomMixedGenerator.generate(num_rows)
 
         length = len(array)
@@ -93,6 +99,7 @@ class SingleIntegerGenerator(CategoricalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         constant = np.random.randint(0, 100)
         return np.full(num_rows, constant)
 
@@ -102,6 +109,7 @@ class SingleIntegerNaNsGenerator(CategoricalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         return add_nans(SingleIntegerGenerator.generate(num_rows).astype(np.float))
 
 
@@ -110,6 +118,7 @@ class SingleStringGenerator(CategoricalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         constant = 'A'
         return np.full(num_rows, constant)
 
@@ -119,6 +128,7 @@ class SingleStringNaNsGenerator(CategoricalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         return add_nans(SingleStringGenerator.generate(num_rows).astype('O'))
 
 
@@ -127,6 +137,7 @@ class UniqueIntegerGenerator(CategoricalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         return np.arange(num_rows)
 
 
@@ -135,6 +146,7 @@ class UniqueIntegerNaNsGenerator(CategoricalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         return add_nans(UniqueIntegerGenerator.generate(num_rows))
 
 
@@ -143,6 +155,7 @@ class UniqueStringGenerator(CategoricalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         return np.arange(num_rows).astype(str)
 
 
@@ -151,4 +164,5 @@ class UniqueStringNaNsGenerator(CategoricalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         return add_nans(UniqueStringGenerator.generate(num_rows).astype('O'))

tests/datasets/datetime.py

@@ -9,69 +9,75 @@
 
 
 class DatetimeGenerator(BaseDatasetGenerator):
-    """Base class for generators that generate datatime data"""
+    """Base class for generators that generate datatime data."""
 
     DATA_TYPE = 'datetime'
 
 
 class RandomGapDatetimeGenerator(DatetimeGenerator):
-    """Generator that creates dates with random gaps between them"""
+    """Generator that creates dates with random gaps between them."""
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         today = datetime.datetime.today()
         delta = datetime.timedelta(days=1)
         dates = [(np.random.random() * delta + today) for i in range(num_rows)]
         return np.array(dates, dtype='datetime64')
 
 
 class RandomGapSecondsDatetimeGenerator(DatetimeGenerator):
-    """Generator that creates dates with random gaps of seconds between them"""
+    """Generator that creates dates with random gaps of seconds between them."""
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         today = datetime.datetime.today()
         delta = datetime.timedelta(seconds=1)
         dates = [(np.random.random() * delta + today) for i in range(num_rows)]
         return np.array(dates, dtype='datetime64')
 
 
 class RandomGapDatetimeNaNsGenerator(DatetimeGenerator):
-    """Generator that creates dates with random gaps and NaNs"""
+    """Generator that creates dates with random gaps and NaNs."""
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         dates = RandomGapDatetimeGenerator.generate(num_rows)
         return add_nans(dates.astype('O'))
 
 
 class EqualGapHoursDatetimeGenerator(DatetimeGenerator):
-    """Generator that creates dates with hour gaps between them"""
+    """Generator that creates dates with hour gaps between them."""
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         today = datetime.datetime.today()
         delta = datetime.timedelta
         dates = [delta(hours=i) + today for i in range(num_rows)]
         return np.array(dates, dtype='datetime64')
 
 
 class EqualGapDaysDatetimeGenerator(DatetimeGenerator):
-    """Generator that creates dates with 1 day gaps between them"""
+    """Generator that creates dates with 1 day gaps between them."""
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         today = datetime.datetime.today()
         delta = datetime.timedelta
         dates = [delta(i) + today for i in range(num_rows)]
         return np.array(dates, dtype='datetime64')
 
 
 class EqualGapWeeksDatetimeGenerator(DatetimeGenerator):
-    """Generator that creates dates with 1 week gaps between them"""
+    """Generator that creates dates with 1 week gaps between them."""
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         today = datetime.datetime.today()
         delta = datetime.timedelta
         dates = [delta(weeks=i) + today for i in range(num_rows)]

tests/datasets/numerical.py

@@ -17,6 +17,7 @@ class RandomIntegerGenerator(NumericalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         ii32 = np.iinfo(np.int32)
         return np.random.randint(ii32.min, ii32.max, num_rows)
 
@@ -26,6 +27,7 @@ class RandomIntegerNaNsGenerator(NumericalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         return add_nans(RandomIntegerGenerator.generate(num_rows).astype(np.float))
 
 
@@ -34,6 +36,7 @@ class ConstantIntegerGenerator(NumericalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         ii32 = np.iinfo(np.int32)
         constant = np.random.randint(ii32.min, ii32.max)
         return np.full(num_rows, constant)
@@ -44,6 +47,7 @@ class ConstantIntegerNaNsGenerator(NumericalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         return add_nans(ConstantIntegerGenerator.generate(num_rows).astype(np.float))
 
 
@@ -52,6 +56,7 @@ class AlmostConstantIntegerGenerator(NumericalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         ii32 = np.iinfo(np.int32)
         values = np.random.randint(ii32.min, ii32.max, size=2)
         additional_values = np.full(num_rows - 2, values[1])
@@ -65,6 +70,7 @@ class AlmostConstantIntegerNaNsGenerator(NumericalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         ii32 = np.iinfo(np.int32)
         values = np.random.randint(ii32.min, ii32.max, size=2)
         additional_values = np.full(num_rows - 2, values[1]).astype(np.float)
@@ -78,6 +84,7 @@ class NormalGenerator(NumericalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         return np.random.normal(size=num_rows)
 
 
@@ -86,6 +93,7 @@ class NormalNaNsGenerator(NumericalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         return add_nans(NormalGenerator.generate(num_rows))
 
 
@@ -94,6 +102,7 @@ class BigNormalGenerator(NumericalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         return np.random.normal(scale=1e10, size=num_rows)
 
 
@@ -102,4 +111,5 @@ class BigNormalNaNsGenerator(NumericalGenerator):
 
     @staticmethod
     def generate(num_rows):
+        """Generate a ``num_rows`` number of rows."""
         return add_nans(BigNormalGenerator.generate(num_rows))

tests/integration/__init__.py

@@ -0,0 +1 @@
+"""RDT integration testing package."""

tests/integration/transformers/__init__.py

@@ -0,0 +1 @@
+"""RDT transformers integration testing package."""

tests/performance/tests/__init__.py

@@ -0,0 +1 @@
+"""RDT performance testing package."""

tests/unit/__init__.py

@@ -0,0 +1 @@
+"""RDT unit testing package."""

tests/unit/transformers/__init__.py

@@ -0,0 +1 @@
+"""RDT transformers unit testing package."""