TST: Consolidate tests that raise in groupby (#50404)

Author: rhshadrach

pandas/tests/groupby/test_function.py

@@ -166,8 +166,6 @@ def test_averages(self, df, method):
             ],
         )
 
-        with pytest.raises(TypeError, match="[Cc]ould not convert"):
-            getattr(gb, method)()
         result = getattr(gb, method)(numeric_only=True)
         tm.assert_frame_equal(result.reindex_like(expected), expected)
 
@@ -317,21 +315,6 @@ def gni(self, df):
         gni = df.groupby("A", as_index=False)
         return gni
 
-    # TODO: non-unique columns, as_index=False
-    def test_idxmax_nuisance_raises(self, gb):
-        # GH#5610, GH#41480
-        expected = DataFrame([[0.0], [np.nan]], columns=["B"], index=[1, 3])
-        expected.index.name = "A"
-        with pytest.raises(TypeError, match="not allowed for this dtype"):
-            gb.idxmax()
-
-    def test_idxmin_nuisance_raises(self, gb):
-        # GH#5610, GH#41480
-        expected = DataFrame([[0.0], [np.nan]], columns=["B"], index=[1, 3])
-        expected.index.name = "A"
-        with pytest.raises(TypeError, match="not allowed for this dtype"):
-            gb.idxmin()
-
     def test_describe(self, df, gb, gni):
         # describe
         expected_index = Index([1, 3], name="A")

pandas/tests/groupby/test_groupby.py

@@ -433,19 +433,12 @@ def test_frame_groupby_columns(tsframe):
 def test_frame_set_name_single(df):
     grouped = df.groupby("A")
 
-    msg = "The default value of numeric_only"
-    with pytest.raises(TypeError, match="Could not convert"):
-        grouped.mean()
     result = grouped.mean(numeric_only=True)
     assert result.index.name == "A"
 
-    with pytest.raises(TypeError, match="Could not convert"):
-        df.groupby("A", as_index=False).mean()
     result = df.groupby("A", as_index=False).mean(numeric_only=True)
     assert result.index.name != "A"
 
-    with pytest.raises(TypeError, match="Could not convert"):
-        grouped.agg(np.mean)
     result = grouped[["C", "D"]].agg(np.mean)
     assert result.index.name == "A"
 

pandas/tests/groupby/test_grouping.py

@@ -55,11 +55,7 @@ def test_column_select_via_attr(self, df):
         tm.assert_series_equal(result, expected)
 
         df["mean"] = 1.5
-        with pytest.raises(TypeError, match="Could not convert"):
-            df.groupby("A").mean()
         result = df.groupby("A").mean(numeric_only=True)
-        with pytest.raises(TypeError, match="Could not convert"):
-            df.groupby("A").agg(np.mean)
         expected = df.groupby("A")[["C", "D", "mean"]].agg(np.mean)
         tm.assert_frame_equal(result, expected)
 
@@ -289,8 +285,6 @@ def test_grouper_column_and_index(self):
         result = df_multi.groupby(["B", pd.Grouper(level="inner")]).mean(
             numeric_only=True
         )
-        with pytest.raises(TypeError, match="Could not convert"):
-            df_multi.reset_index().groupby(["B", "inner"]).mean()
         expected = (
             df_multi.reset_index().groupby(["B", "inner"]).mean(numeric_only=True)
         )
@@ -300,8 +294,6 @@ def test_grouper_column_and_index(self):
         result = df_multi.groupby([pd.Grouper(level="inner"), "B"]).mean(
             numeric_only=True
         )
-        with pytest.raises(TypeError, match="Could not convert"):
-            df_multi.reset_index().groupby(["inner", "B"]).mean()
         expected = (
             df_multi.reset_index().groupby(["inner", "B"]).mean(numeric_only=True)
         )
@@ -310,26 +302,18 @@ def test_grouper_column_and_index(self):
         # Grouping a single-index frame by a column and the index should
         # be equivalent to resetting the index and grouping by two columns
         df_single = df_multi.reset_index("outer")
-        with pytest.raises(TypeError, match="Could not convert"):
-            df_single.groupby(["B", pd.Grouper(level="inner")]).mean()
         result = df_single.groupby(["B", pd.Grouper(level="inner")]).mean(
             numeric_only=True
         )
-        with pytest.raises(TypeError, match="Could not convert"):
-            df_single.reset_index().groupby(["B", "inner"]).mean()
         expected = (
             df_single.reset_index().groupby(["B", "inner"]).mean(numeric_only=True)
         )
         tm.assert_frame_equal(result, expected)
 
         # Test the reverse grouping order
-        with pytest.raises(TypeError, match="Could not convert"):
-            df_single.groupby([pd.Grouper(level="inner"), "B"]).mean()
         result = df_single.groupby([pd.Grouper(level="inner"), "B"]).mean(
             numeric_only=True
         )
-        with pytest.raises(TypeError, match="Could not convert"):
-            df_single.reset_index().groupby(["inner", "B"]).mean()
         expected = (
             df_single.reset_index().groupby(["inner", "B"]).mean(numeric_only=True)
         )
@@ -406,11 +390,7 @@ def test_empty_groups(self, df):
     def test_groupby_grouper(self, df):
         grouped = df.groupby("A")
 
-        with pytest.raises(TypeError, match="Could not convert"):
-            df.groupby(grouped.grouper).mean()
         result = df.groupby(grouped.grouper).mean(numeric_only=True)
-        with pytest.raises(TypeError, match="Could not convert"):
-            grouped.mean()
         expected = grouped.mean(numeric_only=True)
         tm.assert_frame_equal(result, expected)
 

pandas/tests/groupby/test_min_max.py

@@ -47,16 +47,12 @@ def test_max_min_object_multiple_columns(using_array_manager):
 
     gb = df.groupby("A")
 
-    with pytest.raises(TypeError, match="not supported between instances"):
-        gb.max(numeric_only=False)
     result = gb[["C"]].max()
     # "max" is valid for column "C" but not for "B"
     ei = Index([1, 2, 3], name="A")
     expected = DataFrame({"C": ["b", "d", "e"]}, index=ei)
     tm.assert_frame_equal(result, expected)
 
-    with pytest.raises(TypeError, match="not supported between instances"):
-        gb.max(numeric_only=False)
     result = gb[["C"]].min()
     # "min" is valid for column "C" but not for "B"
     ei = Index([1, 2, 3], name="A")

pandas/tests/groupby/test_raises.py

@@ -0,0 +1,178 @@
+# Only tests that raise an error and have no better location should go here.
+# Tests for specific groupby methods should go in their respective
+# test file.
+
+import datetime
+
+import pytest
+
+from pandas import DataFrame
+from pandas.tests.groupby import get_groupby_method_args
+
+
+@pytest.mark.parametrize("how", ["method", "agg", "transform"])
+def test_groupby_raises_string(how, groupby_func, as_index, sort):
+    df = DataFrame(
+        {
+            "a": [1, 1, 1, 2, 2],
+            "b": range(5),
+            "c": list("xyzwt"),
+        }
+    )
+    args = get_groupby_method_args(groupby_func, df)
+    gb = df.groupby("a", as_index=as_index, sort=sort)
+
+    klass, msg = {
+        "all": (None, ""),
+        "any": (None, ""),
+        "bfill": (None, ""),
+        "corrwith": (TypeError, "Could not convert"),
+        "count": (None, ""),
+        "cumcount": (None, ""),
+        "cummax": (NotImplementedError, "function is not implemented for this dtype"),
+        "cummin": (NotImplementedError, "function is not implemented for this dtype"),
+        "cumprod": (NotImplementedError, "function is not implemented for this dtype"),
+        "cumsum": (NotImplementedError, "function is not implemented for this dtype"),
+        "diff": (TypeError, "unsupported operand type"),
+        "ffill": (None, ""),
+        "fillna": (None, ""),
+        "first": (None, ""),
+        "idxmax": (TypeError, "'argmax' not allowed for this dtype"),
+        "idxmin": (TypeError, "'argmin' not allowed for this dtype"),
+        "last": (None, ""),
+        "max": (None, ""),
+        "mean": (TypeError, "Could not convert xyz to numeric"),
+        "median": (TypeError, "could not convert string to float"),
+        "min": (None, ""),
+        "ngroup": (None, ""),
+        "nunique": (None, ""),
+        "pct_change": (TypeError, "unsupported operand type"),
+        "prod": (TypeError, "can't multiply sequence by non-int of type 'str'"),
+        "quantile": (TypeError, "cannot be performed against 'object' dtypes!"),
+        "rank": (None, ""),
+        "sem": (ValueError, "could not convert string to float"),
+        "shift": (None, ""),
+        "size": (None, ""),
+        "skew": (TypeError, "could not convert string to float"),
+        "std": (ValueError, "could not convert string to float"),
+        "sum": (None, ""),
+        "var": (TypeError, "could not convert string to float"),
+    }[groupby_func]
+
+    if klass is None:
+        if how == "method":
+            getattr(gb, groupby_func)(*args)
+        elif how == "agg":
+            gb.agg(groupby_func, *args)
+        else:
+            gb.transform(groupby_func, *args)
+    else:
+        with pytest.raises(klass, match=msg):
+            if how == "method":
+                getattr(gb, groupby_func)(*args)
+            elif how == "agg":
+                gb.agg(groupby_func, *args)
+            else:
+                gb.transform(groupby_func, *args)
+
+
+@pytest.mark.parametrize("how", ["agg", "transform"])
+def test_groupby_raises_string_udf(how):
+    df = DataFrame(
+        {
+            "a": [1, 1, 1, 2, 2],
+            "b": range(5),
+            "c": list("xyzwt"),
+        }
+    )
+    gb = df.groupby("a")
+
+    def func(x):
+        raise TypeError("Test error message")
+
+    with pytest.raises(TypeError, match="Test error message"):
+        getattr(gb, how)(func)
+
+
+@pytest.mark.parametrize("how", ["method", "agg", "transform"])
+def test_groupby_raises_datetime(how, groupby_func, as_index, sort):
+    df = DataFrame(
+        {
+            "a": [1, 1, 1, 2, 2],
+            "b": range(5),
+            "c": datetime.datetime(2005, 1, 1, 10, 30, 23, 540000),
+        }
+    )
+    args = get_groupby_method_args(groupby_func, df)
+    gb = df.groupby("a", as_index=as_index, sort=sort)
+
+    klass, msg = {
+        "all": (None, ""),
+        "any": (None, ""),
+        "bfill": (None, ""),
+        "corrwith": (TypeError, "cannot perform __mul__ with this index type"),
+        "count": (None, ""),
+        "cumcount": (None, ""),
+        "cummax": (None, ""),
+        "cummin": (None, ""),
+        "cumprod": (TypeError, "datetime64 type does not support cumprod operations"),
+        "cumsum": (TypeError, "datetime64 type does not support cumsum operations"),
+        "diff": (None, ""),
+        "ffill": (None, ""),
+        "fillna": (None, ""),
+        "first": (None, ""),
+        "idxmax": (None, ""),
+        "idxmin": (None, ""),
+        "last": (None, ""),
+        "max": (None, ""),
+        "mean": (None, ""),
+        "median": (None, ""),
+        "min": (None, ""),
+        "ngroup": (None, ""),
+        "nunique": (None, ""),
+        "pct_change": (TypeError, "cannot perform __truediv__ with this index type"),
+        "prod": (TypeError, "datetime64 type does not support prod"),
+        "quantile": (None, ""),
+        "rank": (None, ""),
+        "sem": (TypeError, "Cannot cast DatetimeArray to dtype float64"),
+        "shift": (None, ""),
+        "size": (None, ""),
+        "skew": (TypeError, r"dtype datetime64\[ns\] does not support reduction"),
+        "std": (TypeError, "Cannot cast DatetimeArray to dtype float64"),
+        "sum": (TypeError, "datetime64 type does not support sum operations"),
+        "var": (None, ""),
+    }[groupby_func]
+
+    if klass is None:
+        if how == "method":
+            getattr(gb, groupby_func)(*args)
+        elif how == "agg":
+            gb.agg(groupby_func, *args)
+        else:
+            gb.transform(groupby_func, *args)
+    else:
+        with pytest.raises(klass, match=msg):
+            if how == "method":
+                getattr(gb, groupby_func)(*args)
+            elif how == "agg":
+                gb.agg(groupby_func, *args)
+            else:
+                gb.transform(groupby_func, *args)
+
+
+@pytest.mark.parametrize("how", ["agg", "transform"])
+def test_groupby_raises_datetime_udf(how):
+    df = DataFrame(
+        {
+            "a": [1, 1, 1, 2, 2],
+            "b": range(5),
+            "c": datetime.datetime(2005, 1, 1, 10, 30, 23, 540000),
+        }
+    )
+    gb = df.groupby("a")
+
+    def func(x):
+        raise TypeError("Test error message")
+
+    with pytest.raises(TypeError, match="Test error message"):
+        getattr(gb, how)(func)

pandas/tests/groupby/transform/test_transform.py

@@ -426,11 +426,7 @@ def test_transform_nuisance_raises(df):
 
 
 def test_transform_function_aliases(df):
-    with pytest.raises(TypeError, match="Could not convert"):
-        df.groupby("A").transform("mean")
     result = df.groupby("A").transform("mean", numeric_only=True)
-    with pytest.raises(TypeError, match="Could not convert"):
-        df.groupby("A").transform(np.mean)
     expected = df.groupby("A")[["C", "D"]].transform(np.mean)
     tm.assert_frame_equal(result, expected)
 
@@ -508,8 +504,6 @@ def test_groupby_transform_with_int():
         }
     )
     with np.errstate(all="ignore"):
-        with pytest.raises(TypeError, match="Could not convert"):
-            df.groupby("A").transform(lambda x: (x - x.mean()) / x.std())
         result = df.groupby("A")[["B", "C"]].transform(
             lambda x: (x - x.mean()) / x.std()
         )
@@ -554,8 +548,6 @@ def test_groupby_transform_with_int():
     tm.assert_frame_equal(result, expected)
 
     # int doesn't get downcasted
-    with pytest.raises(TypeError, match="unsupported operand type"):
-        df.groupby("A").transform(lambda x: x * 2 / 2)
     result = df.groupby("A")[["B", "C"]].transform(lambda x: x * 2 / 2)
     expected = DataFrame({"B": 1.0, "C": [2.0, 3.0, 4.0, 10.0, 5.0, -1.0]})
     tm.assert_frame_equal(result, expected)
@@ -748,14 +740,8 @@ def test_cython_transform_frame(op, args, targop):
 
             expected = expected.sort_index(axis=1)
 
-            if op != "shift":
-                with pytest.raises(TypeError, match="datetime64 type does not support"):
-                    gb.transform(op, *args).sort_index(axis=1)
             result = gb[expected.columns].transform(op, *args).sort_index(axis=1)
             tm.assert_frame_equal(result, expected)
-            if op != "shift":
-                with pytest.raises(TypeError, match="datetime64 type does not support"):
-                    getattr(gb, op)(*args).sort_index(axis=1)
             result = getattr(gb[expected.columns], op)(*args).sort_index(axis=1)
             tm.assert_frame_equal(result, expected)
             # individual columns