TST/CLN: Remove makeDataFrame (#56210)

* TST/CLN: Remove makeDataFrame

* Simplify some frames

Author: mroeschke

pandas/tests/frame/methods/test_set_index.py

@@ -156,7 +156,11 @@ def test_set_index(self, float_string_frame):
             df.set_index(idx[::2])
 
     def test_set_index_names(self):
-        df = tm.makeDataFrame()
+        df = DataFrame(
+            np.ones((10, 4)),
+            columns=Index(list("ABCD"), dtype=object),
+            index=Index([f"i-{i}" for i in range(10)], dtype=object),
+        )
         df.index.name = "name"
 
         assert df.set_index(df.index).index.names == ["name"]

pandas/tests/frame/test_arithmetic.py

@@ -1566,7 +1566,10 @@ def test_strings_to_numbers_comparisons_raises(self, compare_operators_no_eq_ne)
             f(df, 0)
 
     def test_comparison_protected_from_errstate(self):
-        missing_df = tm.makeDataFrame()
+        missing_df = DataFrame(
+            np.ones((10, 4), dtype=np.float64),
+            columns=Index(list("ABCD"), dtype=object),
+        )
         missing_df.loc[missing_df.index[0], "A"] = np.nan
         with np.errstate(invalid="ignore"):
             expected = missing_df.values < 0

pandas/tests/indexing/test_chaining_and_caching.py

@@ -12,6 +12,7 @@
 import pandas as pd
 from pandas import (
     DataFrame,
+    Index,
     Series,
     Timestamp,
     date_range,
@@ -627,7 +628,10 @@ def test_chained_getitem_with_lists(self):
     def test_cache_updating(self):
         # GH 4939, make sure to update the cache on setitem
 
-        df = tm.makeDataFrame()
+        df = DataFrame(
+            np.zeros((10, 4)),
+            columns=Index(list("ABCD"), dtype=object),
+        )
         df["A"]  # cache series
         df.loc["Hello Friend"] = df.iloc[0]
         assert "Hello Friend" in df["A"].index

pandas/tests/io/excel/test_writers.py

@@ -1234,15 +1234,23 @@ def test_freeze_panes(self, path):
         tm.assert_frame_equal(result, expected)
 
     def test_path_path_lib(self, engine, ext):
-        df = tm.makeDataFrame()
+        df = DataFrame(
+            1.1 * np.arange(120).reshape((30, 4)),
+            columns=Index(list("ABCD"), dtype=object),
+            index=Index([f"i-{i}" for i in range(30)], dtype=object),
+        )
         writer = partial(df.to_excel, engine=engine)
 
         reader = partial(pd.read_excel, index_col=0)
         result = tm.round_trip_pathlib(writer, reader, path=f"foo{ext}")
         tm.assert_frame_equal(result, df)
 
     def test_path_local_path(self, engine, ext):
-        df = tm.makeDataFrame()
+        df = DataFrame(
+            1.1 * np.arange(120).reshape((30, 4)),
+            columns=Index(list("ABCD"), dtype=object),
+            index=Index([f"i-{i}" for i in range(30)], dtype=object),
+        )
         writer = partial(df.to_excel, engine=engine)
 
         reader = partial(pd.read_excel, index_col=0)

pandas/tests/io/formats/test_to_csv.py

@@ -10,6 +10,7 @@
 import pandas as pd
 from pandas import (
     DataFrame,
+    Index,
     compat,
 )
 import pandas._testing as tm
@@ -665,7 +666,7 @@ def test_na_rep_truncated(self):
     def test_to_csv_errors(self, errors):
         # GH 22610
         data = ["\ud800foo"]
-        ser = pd.Series(data, index=pd.Index(data))
+        ser = pd.Series(data, index=Index(data))
         with tm.ensure_clean("test.csv") as path:
             ser.to_csv(path, errors=errors)
         # No use in reading back the data as it is not the same anymore
@@ -679,7 +680,11 @@ def test_to_csv_binary_handle(self, mode):
 
         GH 35058 and GH 19827
         """
-        df = tm.makeDataFrame()
+        df = DataFrame(
+            1.1 * np.arange(120).reshape((30, 4)),
+            columns=Index(list("ABCD"), dtype=object),
+            index=Index([f"i-{i}" for i in range(30)], dtype=object),
+        )
         with tm.ensure_clean() as path:
             with open(path, mode="w+b") as handle:
                 df.to_csv(handle, mode=mode)
@@ -713,7 +718,11 @@ def test_to_csv_encoding_binary_handle(self, mode):
 
 def test_to_csv_iterative_compression_name(compression):
     # GH 38714
-    df = tm.makeDataFrame()
+    df = DataFrame(
+        1.1 * np.arange(120).reshape((30, 4)),
+        columns=Index(list("ABCD"), dtype=object),
+        index=Index([f"i-{i}" for i in range(30)], dtype=object),
+    )
     with tm.ensure_clean() as path:
         df.to_csv(path, compression=compression, chunksize=1)
         tm.assert_frame_equal(
@@ -723,7 +732,11 @@ def test_to_csv_iterative_compression_name(compression):
 
 def test_to_csv_iterative_compression_buffer(compression):
     # GH 38714
-    df = tm.makeDataFrame()
+    df = DataFrame(
+        1.1 * np.arange(120).reshape((30, 4)),
+        columns=Index(list("ABCD"), dtype=object),
+        index=Index([f"i-{i}" for i in range(30)], dtype=object),
+    )
     with io.BytesIO() as buffer:
         df.to_csv(buffer, compression=compression, chunksize=1)
         buffer.seek(0)

pandas/tests/io/parser/common/test_file_buffer_url.py

@@ -11,6 +11,7 @@
 from urllib.error import URLError
 import uuid
 
+import numpy as np
 import pytest
 
 from pandas.errors import (
@@ -19,7 +20,10 @@
 )
 import pandas.util._test_decorators as td
 
-from pandas import DataFrame
+from pandas import (
+    DataFrame,
+    Index,
+)
 import pandas._testing as tm
 
 pytestmark = pytest.mark.filterwarnings(
@@ -66,15 +70,23 @@ def test_local_file(all_parsers, csv_dir_path):
 @xfail_pyarrow  # AssertionError: DataFrame.index are different
 def test_path_path_lib(all_parsers):
     parser = all_parsers
-    df = tm.makeDataFrame()
+    df = DataFrame(
+        1.1 * np.arange(120).reshape((30, 4)),
+        columns=Index(list("ABCD"), dtype=object),
+        index=Index([f"i-{i}" for i in range(30)], dtype=object),
+    )
     result = tm.round_trip_pathlib(df.to_csv, lambda p: parser.read_csv(p, index_col=0))
     tm.assert_frame_equal(df, result)
 
 
 @xfail_pyarrow  # AssertionError: DataFrame.index are different
 def test_path_local_path(all_parsers):
     parser = all_parsers
-    df = tm.makeDataFrame()
+    df = DataFrame(
+        1.1 * np.arange(120).reshape((30, 4)),
+        columns=Index(list("ABCD"), dtype=object),
+        index=Index([f"i-{i}" for i in range(30)], dtype=object),
+    )
     result = tm.round_trip_localpath(
         df.to_csv, lambda p: parser.read_csv(p, index_col=0)
     )

pandas/tests/io/pytables/test_append.py

@@ -11,6 +11,7 @@
 import pandas as pd
 from pandas import (
     DataFrame,
+    Index,
     Series,
     _testing as tm,
     concat,
@@ -401,7 +402,7 @@ def check_col(key, name, size):
             {
                 "A": [0.0, 1.0, 2.0, 3.0, 4.0],
                 "B": [0.0, 1.0, 0.0, 1.0, 0.0],
-                "C": pd.Index(["foo1", "foo2", "foo3", "foo4", "foo5"], dtype=object),
+                "C": Index(["foo1", "foo2", "foo3", "foo4", "foo5"], dtype=object),
                 "D": date_range("20130101", periods=5),
             }
         ).set_index("C")
@@ -658,7 +659,11 @@ def test_append_hierarchical(tmp_path, setup_path, multiindex_dataframe_random_d
 
 def test_append_misc(setup_path):
     with ensure_clean_store(setup_path) as store:
-        df = tm.makeDataFrame()
+        df = DataFrame(
+            1.1 * np.arange(120).reshape((30, 4)),
+            columns=Index(list("ABCD"), dtype=object),
+            index=Index([f"i-{i}" for i in range(30)], dtype=object),
+        )
         store.append("df", df, chunksize=1)
         result = store.select("df")
         tm.assert_frame_equal(result, df)
@@ -671,7 +676,11 @@ def test_append_misc(setup_path):
 @pytest.mark.parametrize("chunksize", [10, 200, 1000])
 def test_append_misc_chunksize(setup_path, chunksize):
     # more chunksize in append tests
-    df = tm.makeDataFrame()
+    df = DataFrame(
+        1.1 * np.arange(120).reshape((30, 4)),
+        columns=Index(list("ABCD"), dtype=object),
+        index=Index([f"i-{i}" for i in range(30)], dtype=object),
+    )
     df["string"] = "foo"
     df["float322"] = 1.0
     df["float322"] = df["float322"].astype("float32")
@@ -715,7 +724,11 @@ def test_append_raise(setup_path):
         # test append with invalid input to get good error messages
 
         # list in column
-        df = tm.makeDataFrame()
+        df = DataFrame(
+            1.1 * np.arange(120).reshape((30, 4)),
+            columns=Index(list("ABCD"), dtype=object),
+            index=Index([f"i-{i}" for i in range(30)], dtype=object),
+        )
         df["invalid"] = [["a"]] * len(df)
         assert df.dtypes["invalid"] == np.object_
         msg = re.escape(
@@ -732,7 +745,11 @@ def test_append_raise(setup_path):
             store.append("df", df)
 
         # datetime with embedded nans as object
-        df = tm.makeDataFrame()
+        df = DataFrame(
+            1.1 * np.arange(120).reshape((30, 4)),
+            columns=Index(list("ABCD"), dtype=object),
+            index=Index([f"i-{i}" for i in range(30)], dtype=object),
+        )
         s = Series(datetime.datetime(2001, 1, 2), index=df.index)
         s = s.astype(object)
         s[0:5] = np.nan
@@ -756,7 +773,11 @@ def test_append_raise(setup_path):
             store.append("df", Series(np.arange(10)))
 
         # appending an incompatible table
-        df = tm.makeDataFrame()
+        df = DataFrame(
+            1.1 * np.arange(120).reshape((30, 4)),
+            columns=Index(list("ABCD"), dtype=object),
+            index=Index([f"i-{i}" for i in range(30)], dtype=object),
+        )
         store.append("df", df)
 
         df["foo"] = "foo"

pandas/tests/io/pytables/test_errors.py

@@ -9,6 +9,7 @@
     CategoricalIndex,
     DataFrame,
     HDFStore,
+    Index,
     MultiIndex,
     _testing as tm,
     date_range,
@@ -25,7 +26,11 @@
 
 
 def test_pass_spec_to_storer(setup_path):
-    df = tm.makeDataFrame()
+    df = DataFrame(
+        1.1 * np.arange(120).reshape((30, 4)),
+        columns=Index(list("ABCD"), dtype=object),
+        index=Index([f"i-{i}" for i in range(30)], dtype=object),
+    )
 
     with ensure_clean_store(setup_path) as store:
         store.put("df", df)
@@ -60,14 +65,22 @@ def test_unimplemented_dtypes_table_columns(setup_path):
 
         # currently not supported dtypes ####
         for n, f in dtypes:
-            df = tm.makeDataFrame()
+            df = DataFrame(
+                1.1 * np.arange(120).reshape((30, 4)),
+                columns=Index(list("ABCD"), dtype=object),
+                index=Index([f"i-{i}" for i in range(30)], dtype=object),
+            )
             df[n] = f
             msg = re.escape(f"[{n}] is not implemented as a table column")
             with pytest.raises(TypeError, match=msg):
                 store.append(f"df1_{n}", df)
 
     # frame
-    df = tm.makeDataFrame()
+    df = DataFrame(
+        1.1 * np.arange(120).reshape((30, 4)),
+        columns=Index(list("ABCD"), dtype=object),
+        index=Index([f"i-{i}" for i in range(30)], dtype=object),
+    )
     df["obj1"] = "foo"
     df["obj2"] = "bar"
     df["datetime1"] = datetime.date(2001, 1, 2)

pandas/tests/io/pytables/test_file_handling.py

@@ -17,6 +17,7 @@
 from pandas import (
     DataFrame,
     HDFStore,
+    Index,
     Series,
     _testing as tm,
     read_hdf,
@@ -145,7 +146,11 @@ def test_reopen_handle(tmp_path, setup_path):
 
 def test_open_args(setup_path):
     with tm.ensure_clean(setup_path) as path:
-        df = tm.makeDataFrame()
+        df = DataFrame(
+            1.1 * np.arange(120).reshape((30, 4)),
+            columns=Index(list("ABCD"), dtype=object),
+            index=Index([f"i-{i}" for i in range(30)], dtype=object),
+        )
 
         # create an in memory store
         store = HDFStore(
@@ -172,7 +177,11 @@ def test_flush(setup_path):
 
 def test_complibs_default_settings(tmp_path, setup_path):
     # GH15943
-    df = tm.makeDataFrame()
+    df = DataFrame(
+        1.1 * np.arange(120).reshape((30, 4)),
+        columns=Index(list("ABCD"), dtype=object),
+        index=Index([f"i-{i}" for i in range(30)], dtype=object),
+    )
 
     # Set complevel and check if complib is automatically set to
     # default value
@@ -211,7 +220,11 @@ def test_complibs_default_settings(tmp_path, setup_path):
 
 def test_complibs_default_settings_override(tmp_path, setup_path):
     # Check if file-defaults can be overridden on a per table basis
-    df = tm.makeDataFrame()
+    df = DataFrame(
+        1.1 * np.arange(120).reshape((30, 4)),
+        columns=Index(list("ABCD"), dtype=object),
+        index=Index([f"i-{i}" for i in range(30)], dtype=object),
+    )
     tmpfile = tmp_path / setup_path
     store = HDFStore(tmpfile)
     store.append("dfc", df, complevel=9, complib="blosc")
@@ -325,7 +338,11 @@ def test_multiple_open_close(tmp_path, setup_path):
 
     path = tmp_path / setup_path
 
-    df = tm.makeDataFrame()
+    df = DataFrame(
+        1.1 * np.arange(120).reshape((30, 4)),
+        columns=Index(list("ABCD"), dtype=object),
+        index=Index([f"i-{i}" for i in range(30)], dtype=object),
+    )
     df.to_hdf(path, key="df", mode="w", format="table")
 
     # single
@@ -402,7 +419,11 @@ def test_multiple_open_close(tmp_path, setup_path):
     # ops on a closed store
     path = tmp_path / setup_path
 
-    df = tm.makeDataFrame()
+    df = DataFrame(
+        1.1 * np.arange(120).reshape((30, 4)),
+        columns=Index(list("ABCD"), dtype=object),
+        index=Index([f"i-{i}" for i in range(30)], dtype=object),
+    )
     df.to_hdf(path, key="df", mode="w", format="table")
 
     store = HDFStore(path)

pandas/tests/io/pytables/test_keys.py

@@ -1,8 +1,10 @@
+import numpy as np
 import pytest
 
 from pandas import (
     DataFrame,
     HDFStore,
+    Index,
     Series,
     _testing as tm,
 )
@@ -20,7 +22,11 @@ def test_keys(setup_path):
         store["b"] = Series(
             range(10), dtype="float64", index=[f"i_{i}" for i in range(10)]
         )
-        store["c"] = tm.makeDataFrame()
+        store["c"] = DataFrame(
+            1.1 * np.arange(120).reshape((30, 4)),
+            columns=Index(list("ABCD"), dtype=object),
+            index=Index([f"i-{i}" for i in range(30)], dtype=object),
+        )
 
         assert len(store) == 3
         expected = {"/a", "/b", "/c"}