fix tests, coverage

Author: cosmicBboy

pandera/engines/pandas_engine.py

@@ -198,7 +198,7 @@ class BOOL(DataType, dtypes.Bool):
     """Semantic representation of a :class:`pandas.BooleanDtype`."""
 
     type = pd.BooleanDtype()
-    _bool_like = frozenset({1, 0, 1.0, 0.0, True, False})
+    _bool_like = frozenset({True, False})
 
     def coerce_value(self, value: Any) -> Any:
         """Coerce an value to specified datatime type."""
@@ -440,7 +440,7 @@ def coerce(self, data_container: PandasObject) -> PandasObject:
 
     def coerce_value(self, value: Any) -> Any:
         """Coerce an value to a particular type."""
-        if value not in self.type.categories:  # pylint: disable=no-member
+        if value not in self.categories:  # type: ignore
             raise TypeError(
                 f"value {value} cannot be coerced to type {self.type}"
             )

tests/core/test_pandas_engine.py

@@ -1,7 +1,9 @@
 """Test numpy engine."""
 
+import hypothesis.strategies as st
 import pandas as pd
 import pytest
+from hypothesis import given
 
 from pandera.engines import pandas_engine
 from pandera.errors import ParserError
@@ -42,3 +44,65 @@ def test_pandas_data_type_coerce(data_type):
         data_type().try_coerce(pd.Series(["1", "2", "a"]))
     except ParserError as exc:
         assert exc.failure_cases.shape[0] > 0
+
+
+CATEGORIES = ["A", "B", "C"]
+
+
+@given(st.lists(st.sampled_from(CATEGORIES), min_size=5))
+def test_pandas_category_dtype(data):
+    """Test pandas_engine.Category correctly coerces valid categorical data."""
+    data = pd.Series(data)
+    dtype = pandas_engine.Category(CATEGORIES)
+    coerced_data = dtype.coerce(data)
+    assert dtype.check(coerced_data.dtype)
+
+    for _, value in data.iteritems():
+        coerced_value = dtype.coerce_value(value)
+        assert coerced_value in CATEGORIES
+
+
+@given(st.lists(st.sampled_from(["X", "Y", "Z"]), min_size=5))
+def test_pandas_category_dtype_error(data):
+    """Test pandas_engine.Category raises TypeErrors on invalid data."""
+    data = pd.Series(data)
+    dtype = pandas_engine.Category(CATEGORIES)
+
+    with pytest.raises(TypeError):
+        dtype.coerce(data)
+
+    for _, value in data.iteritems():
+        with pytest.raises(TypeError):
+            dtype.coerce_value(value)
+
+
+@given(st.lists(st.sampled_from([1, 0, 1.0, 0.0, True, False]), min_size=5))
+def test_pandas_boolean_native_type(data):
+    """Test native pandas bool type correctly coerces valid bool-like data."""
+    data = pd.Series(data)
+    dtype = pandas_engine.Engine.dtype("boolean")
+
+    # the BooleanDtype can't handle Series of non-boolean, mixed dtypes
+    if data.dtype == "object":
+        with pytest.raises(TypeError):
+            dtype.coerce(data)
+    else:
+        coerced_data = dtype.coerce(data)
+        assert dtype.check(coerced_data.dtype)
+
+    for _, value in data.iteritems():
+        dtype.coerce_value(value)
+
+
+@given(st.lists(st.sampled_from(["A", "True", "False", 5, -1]), min_size=5))
+def test_pandas_boolean_native_type_error(data):
+    """Test native pandas bool type raises TypeErrors on non-bool-like data."""
+    data = pd.Series(data)
+    dtype = pandas_engine.Engine.dtype("boolean")
+
+    with pytest.raises(TypeError):
+        dtype.coerce(data)
+
+    for _, value in data.iteritems():
+        with pytest.raises(TypeError):
+            dtype.coerce_value(value)