TST: Reduce some test data sizes (pandas-dev#57897)

TST: Reduce some test sizes

Author: mroeschke

pandas/tests/frame/methods/test_cov_corr.py

@@ -355,8 +355,8 @@ def test_corrwith_series(self, datetime_frame):
         tm.assert_series_equal(result, expected)
 
     def test_corrwith_matches_corrcoef(self):
-        df1 = DataFrame(np.arange(10000), columns=["a"])
-        df2 = DataFrame(np.arange(10000) ** 2, columns=["a"])
+        df1 = DataFrame(np.arange(100), columns=["a"])
+        df2 = DataFrame(np.arange(100) ** 2, columns=["a"])
         c1 = df1.corrwith(df2)["a"]
         c2 = np.corrcoef(df1["a"], df2["a"])[0][1]
 

pandas/tests/groupby/transform/test_transform.py

@@ -87,8 +87,8 @@ def demean(arr):
 def test_transform_fast():
     df = DataFrame(
         {
-            "id": np.arange(100000) / 3,
-            "val": np.random.default_rng(2).standard_normal(100000),
+            "id": np.arange(10) / 3,
+            "val": np.random.default_rng(2).standard_normal(10),
         }
     )
 

pandas/tests/indexing/test_chaining_and_caching.py

@@ -17,15 +17,6 @@
 msg = "A value is trying to be set on a copy of a slice from a DataFrame"
 
 
-def random_text(nobs=100):
-    # Construct a DataFrame where each row is a random slice from 'letters'
-    idxs = np.random.default_rng(2).integers(len(ascii_letters), size=(nobs, 2))
-    idxs.sort(axis=1)
-    strings = [ascii_letters[x[0] : x[1]] for x in idxs]
-
-    return DataFrame(strings, columns=["letters"])
-
-
 class TestCaching:
     def test_slice_consolidate_invalidate_item_cache(self):
         # this is chained assignment, but will 'work'
@@ -233,7 +224,11 @@ def test_detect_chained_assignment_is_copy_pickle(self, temp_file):
 
     @pytest.mark.arm_slow
     def test_detect_chained_assignment_str(self):
-        df = random_text(100000)
+        idxs = np.random.default_rng(2).integers(len(ascii_letters), size=(100, 2))
+        idxs.sort(axis=1)
+        strings = [ascii_letters[x[0] : x[1]] for x in idxs]
+
+        df = DataFrame(strings, columns=["letters"])
         indexer = df.letters.apply(lambda x: len(x) > 10)
         df.loc[indexer, "letters"] = df.loc[indexer, "letters"].apply(str.lower)
 

pandas/tests/io/json/test_ujson.py

@@ -1036,11 +1036,7 @@ def test_decode_floating_point(self, sign, float_number):
         )
 
     def test_encode_big_set(self):
-        s = set()
-
-        for x in range(100000):
-            s.add(x)
-
+        s = set(range(100000))
         # Make sure no Exception is raised.
         ujson.ujson_dumps(s)
 

pandas/tests/resample/test_datetime_index.py

@@ -1464,12 +1464,12 @@ def test_resample_nunique_with_date_gap(func, unit):
     tm.assert_series_equal(result, expected)
 
 
-@pytest.mark.parametrize("n", [10000, 100000])
-@pytest.mark.parametrize("k", [10, 100, 1000])
-def test_resample_group_info(n, k, unit):
+def test_resample_group_info(unit):
     # GH10914
 
     # use a fixed seed to always have the same uniques
+    n = 100
+    k = 10
     prng = np.random.default_rng(2)
 
     dr = date_range(start="2015-08-27", periods=n // 10, freq="min").as_unit(unit)