REF: implement test_astype (#33734)

Author: jbrockmendel

pandas/tests/frame/methods/test_astype.py

@@ -0,0 +1,66 @@
+import numpy as np
+import pytest
+
+from pandas import Categorical, CategoricalDtype, CategoricalIndex, Index, IntervalIndex
+import pandas._testing as tm
+
+
+class TestAstype:
+    def test_astype(self):
+        ci = CategoricalIndex(list("aabbca"), categories=list("cab"), ordered=False)
+
+        result = ci.astype(object)
+        tm.assert_index_equal(result, Index(np.array(ci)))
+
+        # this IS equal, but not the same class
+        assert result.equals(ci)
+        assert isinstance(result, Index)
+        assert not isinstance(result, CategoricalIndex)
+
+        # interval
+        ii = IntervalIndex.from_arrays(left=[-0.001, 2.0], right=[2, 4], closed="right")
+
+        ci = CategoricalIndex(
+            Categorical.from_codes([0, 1, -1], categories=ii, ordered=True)
+        )
+
+        result = ci.astype("interval")
+        expected = ii.take([0, 1, -1])
+        tm.assert_index_equal(result, expected)
+
+        result = IntervalIndex(result.values)
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize("name", [None, "foo"])
+    @pytest.mark.parametrize("dtype_ordered", [True, False])
+    @pytest.mark.parametrize("index_ordered", [True, False])
+    def test_astype_category(self, name, dtype_ordered, index_ordered):
+        # GH#18630
+        index = CategoricalIndex(
+            list("aabbca"), categories=list("cab"), ordered=index_ordered
+        )
+        if name:
+            index = index.rename(name)
+
+        # standard categories
+        dtype = CategoricalDtype(ordered=dtype_ordered)
+        result = index.astype(dtype)
+        expected = CategoricalIndex(
+            index.tolist(),
+            name=name,
+            categories=index.categories,
+            ordered=dtype_ordered,
+        )
+        tm.assert_index_equal(result, expected)
+
+        # non-standard categories
+        dtype = CategoricalDtype(index.unique().tolist()[:-1], dtype_ordered)
+        result = index.astype(dtype)
+        expected = CategoricalIndex(index.tolist(), name=name, dtype=dtype)
+        tm.assert_index_equal(result, expected)
+
+        if dtype_ordered is False:
+            # dtype='category' can't specify ordered, so only test once
+            result = index.astype("category")
+            expected = index
+            tm.assert_index_equal(result, expected)

pandas/tests/frame/test_dtypes.py

@@ -3,10 +3,8 @@
 
 from pandas._libs import index as libindex
 
-from pandas.core.dtypes.dtypes import CategoricalDtype
-
 import pandas as pd
-from pandas import Categorical, IntervalIndex
+from pandas import Categorical
 import pandas._testing as tm
 from pandas.core.indexes.api import CategoricalIndex, Index
 
@@ -196,63 +194,6 @@ def test_delete(self):
             # Either depending on NumPy version
             ci.delete(10)
 
-    def test_astype(self):
-
-        ci = self.create_index()
-        result = ci.astype(object)
-        tm.assert_index_equal(result, Index(np.array(ci)))
-
-        # this IS equal, but not the same class
-        assert result.equals(ci)
-        assert isinstance(result, Index)
-        assert not isinstance(result, CategoricalIndex)
-
-        # interval
-        ii = IntervalIndex.from_arrays(left=[-0.001, 2.0], right=[2, 4], closed="right")
-
-        ci = CategoricalIndex(
-            Categorical.from_codes([0, 1, -1], categories=ii, ordered=True)
-        )
-
-        result = ci.astype("interval")
-        expected = ii.take([0, 1, -1])
-        tm.assert_index_equal(result, expected)
-
-        result = IntervalIndex(result.values)
-        tm.assert_index_equal(result, expected)
-
-    @pytest.mark.parametrize("name", [None, "foo"])
-    @pytest.mark.parametrize("dtype_ordered", [True, False])
-    @pytest.mark.parametrize("index_ordered", [True, False])
-    def test_astype_category(self, name, dtype_ordered, index_ordered):
-        # GH 18630
-        index = self.create_index(ordered=index_ordered)
-        if name:
-            index = index.rename(name)
-
-        # standard categories
-        dtype = CategoricalDtype(ordered=dtype_ordered)
-        result = index.astype(dtype)
-        expected = CategoricalIndex(
-            index.tolist(),
-            name=name,
-            categories=index.categories,
-            ordered=dtype_ordered,
-        )
-        tm.assert_index_equal(result, expected)
-
-        # non-standard categories
-        dtype = CategoricalDtype(index.unique().tolist()[:-1], dtype_ordered)
-        result = index.astype(dtype)
-        expected = CategoricalIndex(index.tolist(), name=name, dtype=dtype)
-        tm.assert_index_equal(result, expected)
-
-        if dtype_ordered is False:
-            # dtype='category' can't specify ordered, so only test once
-            result = index.astype("category")
-            expected = index
-            tm.assert_index_equal(result, expected)
-
     @pytest.mark.parametrize(
         "data, non_lexsorted_data",
         [[[1, 2, 3], [9, 0, 1, 2, 3]], [list("abc"), list("fabcd")]],

pandas/tests/indexes/categorical/test_astype.py

@@ -12,7 +12,6 @@
     Int64Index,
     NaT,
     PeriodIndex,
-    Series,
     Timestamp,
     date_range,
 )
@@ -65,38 +64,22 @@ def test_astype_with_tz(self):
         )
         tm.assert_index_equal(result, expected)
 
-        # BUG#10442 : testing astype(str) is correct for Series/DatetimeIndex
-        result = pd.Series(pd.date_range("2012-01-01", periods=3)).astype(str)
-        expected = pd.Series(["2012-01-01", "2012-01-02", "2012-01-03"], dtype=object)
-        tm.assert_series_equal(result, expected)
-
-        result = Series(pd.date_range("2012-01-01", periods=3, tz="US/Eastern")).astype(
-            str
-        )
-        expected = Series(
-            [
-                "2012-01-01 00:00:00-05:00",
-                "2012-01-02 00:00:00-05:00",
-                "2012-01-03 00:00:00-05:00",
-            ],
-            dtype=object,
-        )
-        tm.assert_series_equal(result, expected)
-
+    def test_astype_tzaware_to_tzaware(self):
         # GH 18951: tz-aware to tz-aware
         idx = date_range("20170101", periods=4, tz="US/Pacific")
         result = idx.astype("datetime64[ns, US/Eastern]")
         expected = date_range("20170101 03:00:00", periods=4, tz="US/Eastern")
         tm.assert_index_equal(result, expected)
         assert result.freq == expected.freq
 
+    def test_astype_tznaive_to_tzaware(self):
         # GH 18951: tz-naive to tz-aware
         idx = date_range("20170101", periods=4)
         result = idx.astype("datetime64[ns, US/Eastern]")
         expected = date_range("20170101", periods=4, tz="US/Eastern")
         tm.assert_index_equal(result, expected)
 
-    def test_astype_str_compat(self):
+    def test_astype_str_nat(self):
         # GH 13149, GH 13209
         # verify that we are returning NaT as a string (and not unicode)
 
@@ -107,18 +90,19 @@ def test_astype_str_compat(self):
 
     def test_astype_str(self):
         # test astype string - #10442
-        result = date_range("2012-01-01", periods=4, name="test_name").astype(str)
+        dti = date_range("2012-01-01", periods=4, name="test_name")
+        result = dti.astype(str)
         expected = Index(
             ["2012-01-01", "2012-01-02", "2012-01-03", "2012-01-04"],
             name="test_name",
             dtype=object,
         )
         tm.assert_index_equal(result, expected)
 
+    def test_astype_str_tz_and_name(self):
         # test astype string with tz and name
-        result = date_range(
-            "2012-01-01", periods=3, name="test_name", tz="US/Eastern"
-        ).astype(str)
+        dti = date_range("2012-01-01", periods=3, name="test_name", tz="US/Eastern")
+        result = dti.astype(str)
         expected = Index(
             [
                 "2012-01-01 00:00:00-05:00",
@@ -130,21 +114,23 @@ def test_astype_str(self):
         )
         tm.assert_index_equal(result, expected)
 
+    def test_astype_str_freq_and_name(self):
         # test astype string with freqH and name
-        result = date_range("1/1/2011", periods=3, freq="H", name="test_name").astype(
-            str
-        )
+        dti = date_range("1/1/2011", periods=3, freq="H", name="test_name")
+        result = dti.astype(str)
         expected = Index(
             ["2011-01-01 00:00:00", "2011-01-01 01:00:00", "2011-01-01 02:00:00"],
             name="test_name",
             dtype=object,
         )
         tm.assert_index_equal(result, expected)
 
+    def test_astype_str_freq_and_tz(self):
         # test astype string with freqH and timezone
-        result = date_range(
+        dti = date_range(
             "3/6/2012 00:00", periods=2, freq="H", tz="Europe/London", name="test_name"
-        ).astype(str)
+        )
+        result = dti.astype(str)
         expected = Index(
             ["2012-03-06 00:00:00+00:00", "2012-03-06 01:00:00+00:00"],
             dtype=object,

pandas/tests/indexes/categorical/test_category.py

@@ -0,0 +1,83 @@
+import re
+
+import numpy as np
+import pytest
+
+from pandas.core.dtypes.common import pandas_dtype
+
+from pandas import Float64Index, Index, Int64Index
+import pandas._testing as tm
+
+
+class TestAstype:
+    def test_astype_float64_to_object(self):
+        float_index = Float64Index([0.0, 2.5, 5.0, 7.5, 10.0])
+        result = float_index.astype(object)
+        assert result.equals(float_index)
+        assert float_index.equals(result)
+        assert isinstance(result, Index) and not isinstance(result, Float64Index)
+
+    def test_astype_float64_mixed_to_object(self):
+        # mixed int-float
+        idx = Float64Index([1.5, 2, 3, 4, 5])
+        idx.name = "foo"
+        result = idx.astype(object)
+        assert result.equals(idx)
+        assert idx.equals(result)
+        assert isinstance(result, Index) and not isinstance(result, Float64Index)
+
+    @pytest.mark.parametrize("dtype", ["int16", "int32", "int64"])
+    def test_astype_float64_to_int_dtype(self, dtype):
+        # GH#12881
+        # a float astype int
+        idx = Float64Index([0, 1, 2])
+        result = idx.astype(dtype)
+        expected = Int64Index([0, 1, 2])
+        tm.assert_index_equal(result, expected)
+
+        idx = Float64Index([0, 1.1, 2])
+        result = idx.astype(dtype)
+        expected = Int64Index([0, 1, 2])
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize("dtype", ["float32", "float64"])
+    def test_astype_float64_to_float_dtype(self, dtype):
+        # GH#12881
+        # a float astype int
+        idx = Float64Index([0, 1, 2])
+        result = idx.astype(dtype)
+        expected = idx
+        tm.assert_index_equal(result, expected)
+
+        idx = Float64Index([0, 1.1, 2])
+        result = idx.astype(dtype)
+        expected = Index(idx.values.astype(dtype))
+        tm.assert_index_equal(result, expected)
+
+    @pytest.mark.parametrize("dtype", ["M8[ns]", "m8[ns]"])
+    def test_cannot_cast_to_datetimelike(self, dtype):
+        idx = Float64Index([0, 1.1, 2])
+
+        msg = (
+            f"Cannot convert Float64Index to dtype {pandas_dtype(dtype)}; "
+            f"integer values are required for conversion"
+        )
+        with pytest.raises(TypeError, match=re.escape(msg)):
+            idx.astype(dtype)
+
+    @pytest.mark.parametrize("dtype", [int, "int16", "int32", "int64"])
+    @pytest.mark.parametrize("non_finite", [np.inf, np.nan])
+    def test_cannot_cast_inf_to_int(self, non_finite, dtype):
+        # GH#13149
+        idx = Float64Index([1, 2, non_finite])
+
+        msg = r"Cannot convert non-finite values \(NA or inf\) to integer"
+        with pytest.raises(ValueError, match=msg):
+            idx.astype(dtype)
+
+    def test_astype_from_object(self):
+        index = Index([1.0, np.nan, 0.2], dtype="object")
+        result = index.astype(float)
+        expected = Float64Index([1.0, np.nan, 0.2])
+        assert result.dtype == expected.dtype
+        tm.assert_index_equal(result, expected)