diff --git a/pandas/tests/frame/methods/test_set_index.py b/pandas/tests/frame/methods/test_set_index.py index 98113b6c41821..d958c80fbcdef 100644 --- a/pandas/tests/frame/methods/test_set_index.py +++ b/pandas/tests/frame/methods/test_set_index.py @@ -155,7 +155,11 @@ 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"] diff --git a/pandas/tests/frame/test_arithmetic.py b/pandas/tests/frame/test_arithmetic.py index 8083795a69413..7fd795dc84cca 100644 --- a/pandas/tests/frame/test_arithmetic.py +++ b/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 diff --git a/pandas/tests/indexing/test_chaining_and_caching.py b/pandas/tests/indexing/test_chaining_and_caching.py index bf0975a803dce..73ac9a3bb1a44 100644 --- a/pandas/tests/indexing/test_chaining_and_caching.py +++ b/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 diff --git a/pandas/tests/io/excel/test_writers.py b/pandas/tests/io/excel/test_writers.py index 507d7ed4bf9d0..9aeac58de50bb 100644 --- a/pandas/tests/io/excel/test_writers.py +++ b/pandas/tests/io/excel/test_writers.py @@ -1234,7 +1234,11 @@ 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) @@ -1242,7 +1246,11 @@ def test_path_path_lib(self, engine, 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) diff --git a/pandas/tests/io/formats/test_to_csv.py b/pandas/tests/io/formats/test_to_csv.py index 613f609320f31..33b9fe9b665f3 100644 --- a/pandas/tests/io/formats/test_to_csv.py +++ b/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) diff --git a/pandas/tests/io/parser/common/test_file_buffer_url.py b/pandas/tests/io/parser/common/test_file_buffer_url.py index c374795019ff4..a7a8d031da215 100644 --- a/pandas/tests/io/parser/common/test_file_buffer_url.py +++ b/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( @@ -66,7 +70,11 @@ 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) @@ -74,7 +82,11 @@ def test_path_path_lib(all_parsers): @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) ) diff --git a/pandas/tests/io/pytables/test_append.py b/pandas/tests/io/pytables/test_append.py index 89a0162af1c54..9eb9ffa53dd22 100644 --- a/pandas/tests/io/pytables/test_append.py +++ b/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" diff --git a/pandas/tests/io/pytables/test_errors.py b/pandas/tests/io/pytables/test_errors.py index adf42cc7e8d39..d956e4f5775eb 100644 --- a/pandas/tests/io/pytables/test_errors.py +++ b/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) diff --git a/pandas/tests/io/pytables/test_file_handling.py b/pandas/tests/io/pytables/test_file_handling.py index cb44512d4506c..2920f0b07b31e 100644 --- a/pandas/tests/io/pytables/test_file_handling.py +++ b/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) diff --git a/pandas/tests/io/pytables/test_keys.py b/pandas/tests/io/pytables/test_keys.py index fd7df29595090..c0f2c34ff37ed 100644 --- a/pandas/tests/io/pytables/test_keys.py +++ b/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"} diff --git a/pandas/tests/io/pytables/test_put.py b/pandas/tests/io/pytables/test_put.py index 59a05dc9ea546..8a6e3c9006439 100644 --- a/pandas/tests/io/pytables/test_put.py +++ b/pandas/tests/io/pytables/test_put.py @@ -47,7 +47,11 @@ def test_format_kwarg_in_constructor(tmp_path, setup_path): def test_api_default_format(tmp_path, setup_path): # default_format option 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), + ) with pd.option_context("io.hdf.default_format", "fixed"): _maybe_remove(store, "df") @@ -68,7 +72,11 @@ def test_api_default_format(tmp_path, setup_path): assert store.get_storer("df").is_table 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), + ) with pd.option_context("io.hdf.default_format", "fixed"): df.to_hdf(path, key="df") diff --git a/pandas/tests/io/pytables/test_round_trip.py b/pandas/tests/io/pytables/test_round_trip.py index e05e1e96eb11f..693f10172a99e 100644 --- a/pandas/tests/io/pytables/test_round_trip.py +++ b/pandas/tests/io/pytables/test_round_trip.py @@ -39,7 +39,11 @@ def roundtrip(key, obj, **kwargs): o = Series(range(10), dtype="float64", index=[f"i_{i}" for i in range(10)]) tm.assert_series_equal(o, roundtrip("string_series", o)) - o = tm.makeDataFrame() + o = 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), + ) tm.assert_frame_equal(o, roundtrip("frame", o)) # table @@ -136,7 +140,11 @@ def test_api_2(tmp_path, setup_path): def test_api_invalid(tmp_path, setup_path): path = tmp_path / setup_path # Invalid. - 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), + ) msg = "Can only append to Tables" @@ -347,7 +355,11 @@ def test_timeseries_preepoch(setup_path, request): "compression", [False, pytest.param(True, marks=td.skip_if_windows)] ) def test_frame(compression, 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), + ) # put in some random NAs df.iloc[0, 0] = np.nan @@ -424,7 +436,11 @@ def test_store_hierarchical(setup_path, multiindex_dataframe_random_data): ) def test_store_mixed(compression, setup_path): def _make_one(): - 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["bool1"] = df["A"] > 0 diff --git a/pandas/tests/io/pytables/test_select.py b/pandas/tests/io/pytables/test_select.py index e387b1b607f63..3eaa1e86dbf6d 100644 --- a/pandas/tests/io/pytables/test_select.py +++ b/pandas/tests/io/pytables/test_select.py @@ -266,7 +266,11 @@ def test_select_dtypes(setup_path): # test selection with comparison against numpy scalar # GH 11283 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), + ) expected = df[df["A"] > 0] diff --git a/pandas/tests/io/pytables/test_store.py b/pandas/tests/io/pytables/test_store.py index 7e8365a8f9ffa..98257f1765d53 100644 --- a/pandas/tests/io/pytables/test_store.py +++ b/pandas/tests/io/pytables/test_store.py @@ -45,7 +45,11 @@ def test_context(setup_path): pass with tm.ensure_clean(setup_path) as path: with HDFStore(path) as tbl: - tbl["a"] = tm.makeDataFrame() + tbl["a"] = 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(tbl) == 1 assert type(tbl["a"]) == DataFrame @@ -107,9 +111,17 @@ def test_repr(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), + ) - 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["bool1"] = df["A"] > 0 @@ -136,7 +148,11 @@ def test_repr(setup_path): # storers 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) s = store.get_storer("df") @@ -147,8 +163,16 @@ def test_repr(setup_path): def test_contains(setup_path): with ensure_clean_store(setup_path) as store: store["a"] = tm.makeTimeSeries() - store["b"] = tm.makeDataFrame() - store["foo/bar"] = tm.makeDataFrame() + store["b"] = 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["foo/bar"] = 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 "a" in store assert "b" in store assert "c" not in store @@ -161,14 +185,22 @@ def test_contains(setup_path): with tm.assert_produces_warning( tables.NaturalNameWarning, check_stacklevel=False ): - store["node())"] = tm.makeDataFrame() + store["node())"] = 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 "node())" in store def test_versioning(setup_path): with ensure_clean_store(setup_path) as store: store["a"] = tm.makeTimeSeries() - store["b"] = tm.makeDataFrame() + store["b"] = 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 = tm.makeTimeDataFrame() _maybe_remove(store, "df1") store.append("df1", df[:10]) @@ -432,7 +464,11 @@ def test_mi_data_columns(setup_path): def test_table_mixed_dtypes(setup_path): # 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["bool1"] = df["A"] > 0 @@ -482,7 +518,11 @@ def test_calendar_roundtrip_issue(setup_path): def test_remove(setup_path): with ensure_clean_store(setup_path) as store: ts = tm.makeTimeSeries() - 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["a"] = ts store["b"] = df _maybe_remove(store, "a") @@ -542,7 +582,11 @@ def test_same_name_scoping(setup_path): def test_store_index_name(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.index.name = "foo" with ensure_clean_store(setup_path) as store: @@ -581,7 +625,11 @@ def test_store_index_name_numpy_str(tmp_path, table_format, setup_path, unit, tz def test_store_series_name(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), + ) series = df["A"] with ensure_clean_store(setup_path) as store: @@ -783,7 +831,11 @@ def test_start_stop_fixed(setup_path): tm.assert_series_equal(result, expected) # sparse; not implemented - 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.iloc[3:5, 1:3] = np.nan df.iloc[8:10, -2] = np.nan @@ -806,7 +858,11 @@ def test_select_filter_corner(setup_path): def test_path_pathlib(): - 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( lambda p: df.to_hdf(p, key="df"), lambda p: read_hdf(p, "df") @@ -832,7 +888,11 @@ def test_contiguous_mixed_data_table(start, stop, setup_path): def test_path_pathlib_hdfstore(): - 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), + ) def writer(path): with HDFStore(path) as store: @@ -847,7 +907,11 @@ def reader(path): def test_pickle_path_localpath(): - 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( lambda p: df.to_hdf(p, key="df"), lambda p: read_hdf(p, "df") ) @@ -855,7 +919,11 @@ def test_pickle_path_localpath(): def test_path_localpath_hdfstore(): - 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), + ) def writer(path): with HDFStore(path) as store: @@ -871,7 +939,11 @@ def reader(path): @pytest.mark.parametrize("propindexes", [True, False]) def test_copy(propindexes): - 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 HDFStore(path) as st: diff --git a/pandas/tests/io/test_common.py b/pandas/tests/io/test_common.py index 26035d1af7f90..718f967f2f3d8 100644 --- a/pandas/tests/io/test_common.py +++ b/pandas/tests/io/test_common.py @@ -15,6 +15,7 @@ import pickle import tempfile +import numpy as np import pytest from pandas.compat import is_platform_windows @@ -442,7 +443,11 @@ def test_next(self, mmap_file): def test_unknown_engine(self): with tm.ensure_clean() as path: - df = tm.makeDataFrame() + df = pd.DataFrame( + 1.1 * np.arange(120).reshape((30, 4)), + columns=pd.Index(list("ABCD"), dtype=object), + index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + ) df.to_csv(path) with pytest.raises(ValueError, match="Unknown engine"): pd.read_csv(path, engine="pyt") @@ -454,7 +459,11 @@ def test_binary_mode(self): GH 35058 """ with tm.ensure_clean() as path: - df = tm.makeDataFrame() + df = pd.DataFrame( + 1.1 * np.arange(120).reshape((30, 4)), + columns=pd.Index(list("ABCD"), dtype=object), + index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + ) df.to_csv(path, mode="w+b") tm.assert_frame_equal(df, pd.read_csv(path, index_col=0)) @@ -468,7 +477,11 @@ def test_warning_missing_utf_bom(self, encoding, compression_): GH 35681 """ - df = tm.makeDataFrame() + df = pd.DataFrame( + 1.1 * np.arange(120).reshape((30, 4)), + columns=pd.Index(list("ABCD"), dtype=object), + index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + ) with tm.ensure_clean() as path: with tm.assert_produces_warning(UnicodeWarning): df.to_csv(path, compression=compression_, encoding=encoding) @@ -498,7 +511,11 @@ def test_is_fsspec_url(): @pytest.mark.parametrize("format", ["csv", "json"]) def test_codecs_encoding(encoding, format): # GH39247 - expected = tm.makeDataFrame() + expected = pd.DataFrame( + 1.1 * np.arange(120).reshape((30, 4)), + columns=pd.Index(list("ABCD"), dtype=object), + index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + ) with tm.ensure_clean() as path: with codecs.open(path, mode="w", encoding=encoding) as handle: getattr(expected, f"to_{format}")(handle) @@ -512,7 +529,11 @@ def test_codecs_encoding(encoding, format): def test_codecs_get_writer_reader(): # GH39247 - expected = tm.makeDataFrame() + expected = pd.DataFrame( + 1.1 * np.arange(120).reshape((30, 4)), + columns=pd.Index(list("ABCD"), dtype=object), + index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + ) with tm.ensure_clean() as path: with open(path, "wb") as handle: with codecs.getwriter("utf-8")(handle) as encoded: @@ -534,7 +555,11 @@ def test_explicit_encoding(io_class, mode, msg): # GH39247; this test makes sure that if a user provides mode="*t" or "*b", # it is used. In the case of this test it leads to an error as intentionally the # wrong mode is requested - expected = tm.makeDataFrame() + expected = pd.DataFrame( + 1.1 * np.arange(120).reshape((30, 4)), + columns=pd.Index(list("ABCD"), dtype=object), + index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + ) with io_class() as buffer: with pytest.raises(TypeError, match=msg): expected.to_csv(buffer, mode=f"w{mode}") diff --git a/pandas/tests/io/test_compression.py b/pandas/tests/io/test_compression.py index af83ec4a55fa5..3a58dda9e8dc4 100644 --- a/pandas/tests/io/test_compression.py +++ b/pandas/tests/io/test_compression.py @@ -9,6 +9,7 @@ import time import zipfile +import numpy as np import pytest from pandas.compat import is_platform_windows @@ -142,7 +143,11 @@ def test_compression_binary(compression_only): GH22555 """ - df = tm.makeDataFrame() + df = pd.DataFrame( + 1.1 * np.arange(120).reshape((30, 4)), + columns=pd.Index(list("ABCD"), dtype=object), + index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + ) # with a file with tm.ensure_clean() as path: @@ -170,7 +175,11 @@ def test_gzip_reproducibility_file_name(): GH 28103 """ - df = tm.makeDataFrame() + df = pd.DataFrame( + 1.1 * np.arange(120).reshape((30, 4)), + columns=pd.Index(list("ABCD"), dtype=object), + index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + ) compression_options = {"method": "gzip", "mtime": 1} # test for filename @@ -189,7 +198,11 @@ def test_gzip_reproducibility_file_object(): GH 28103 """ - df = tm.makeDataFrame() + df = pd.DataFrame( + 1.1 * np.arange(120).reshape((30, 4)), + columns=pd.Index(list("ABCD"), dtype=object), + index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + ) compression_options = {"method": "gzip", "mtime": 1} # test for file object diff --git a/pandas/tests/io/test_feather.py b/pandas/tests/io/test_feather.py index 5ec8705251d95..572abbf7c48f7 100644 --- a/pandas/tests/io/test_feather.py +++ b/pandas/tests/io/test_feather.py @@ -132,17 +132,29 @@ def test_rw_use_threads(self): self.check_round_trip(df, use_threads=False) def test_path_pathlib(self): - df = tm.makeDataFrame().reset_index() + df = pd.DataFrame( + 1.1 * np.arange(120).reshape((30, 4)), + columns=pd.Index(list("ABCD"), dtype=object), + index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + ).reset_index() result = tm.round_trip_pathlib(df.to_feather, read_feather) tm.assert_frame_equal(df, result) def test_path_localpath(self): - df = tm.makeDataFrame().reset_index() + df = pd.DataFrame( + 1.1 * np.arange(120).reshape((30, 4)), + columns=pd.Index(list("ABCD"), dtype=object), + index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + ).reset_index() result = tm.round_trip_localpath(df.to_feather, read_feather) tm.assert_frame_equal(df, result) def test_passthrough_keywords(self): - df = tm.makeDataFrame().reset_index() + df = pd.DataFrame( + 1.1 * np.arange(120).reshape((30, 4)), + columns=pd.Index(list("ABCD"), dtype=object), + index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + ).reset_index() self.check_round_trip(df, write_kwargs={"version": 1}) @pytest.mark.network diff --git a/pandas/tests/io/test_gcs.py b/pandas/tests/io/test_gcs.py index 6e55cde12f2f9..0ce6a8bf82cd8 100644 --- a/pandas/tests/io/test_gcs.py +++ b/pandas/tests/io/test_gcs.py @@ -9,6 +9,7 @@ from pandas import ( DataFrame, + Index, date_range, read_csv, read_excel, @@ -145,7 +146,11 @@ def test_to_csv_compression_encoding_gcs( GH 35677 (to_csv, compression), GH 26124 (to_csv, encoding), and GH 32392 (read_csv, encoding) """ - 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), + ) # reference of compressed and encoded file compression = {"method": compression_only} diff --git a/pandas/tests/io/test_pickle.py b/pandas/tests/io/test_pickle.py index 780b25fd0f346..e1fac21094139 100644 --- a/pandas/tests/io/test_pickle.py +++ b/pandas/tests/io/test_pickle.py @@ -41,6 +41,7 @@ import pandas as pd from pandas import ( + DataFrame, Index, Series, period_range, @@ -220,13 +221,21 @@ def test_round_trip_current(typ, expected, pickle_writer, writer): def test_pickle_path_pathlib(): - 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_pickle, pd.read_pickle) tm.assert_frame_equal(df, result) def test_pickle_path_localpath(): - 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_pickle, pd.read_pickle) tm.assert_frame_equal(df, result) @@ -280,7 +289,11 @@ def test_write_explicit(self, compression, get_random_path): path2 = base + ".raw" with tm.ensure_clean(path1) as p1, tm.ensure_clean(path2) as p2: - 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), + ) # write to compressed file df.to_pickle(p1, compression=compression) @@ -299,7 +312,11 @@ def test_write_explicit(self, compression, get_random_path): def test_write_explicit_bad(self, compression, get_random_path): with pytest.raises(ValueError, match="Unrecognized compression type"): with tm.ensure_clean(get_random_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), + ) df.to_pickle(path, compression=compression) def test_write_infer(self, compression_ext, get_random_path): @@ -309,7 +326,11 @@ def test_write_infer(self, compression_ext, get_random_path): compression = self._extension_to_compression.get(compression_ext.lower()) with tm.ensure_clean(path1) as p1, tm.ensure_clean(path2) as p2: - 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), + ) # write to compressed file by inferred compression method df.to_pickle(p1) @@ -330,7 +351,11 @@ def test_read_explicit(self, compression, get_random_path): path2 = base + ".compressed" with tm.ensure_clean(path1) as p1, tm.ensure_clean(path2) as p2: - 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), + ) # write to uncompressed file df.to_pickle(p1, compression=None) @@ -349,7 +374,11 @@ def test_read_infer(self, compression_ext, get_random_path): compression = self._extension_to_compression.get(compression_ext.lower()) with tm.ensure_clean(path1) as p1, tm.ensure_clean(path2) as p2: - 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), + ) # write to uncompressed file df.to_pickle(p1, compression=None) @@ -371,7 +400,11 @@ class TestProtocol: @pytest.mark.parametrize("protocol", [-1, 0, 1, 2]) def test_read(self, protocol, get_random_path): with tm.ensure_clean(get_random_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), + ) df.to_pickle(path, protocol=protocol) df2 = pd.read_pickle(path) tm.assert_frame_equal(df, df2) @@ -404,7 +437,11 @@ def test_unicode_decode_error(datapath, pickle_file, excols): def test_pickle_buffer_roundtrip(): with tm.ensure_clean() 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), + ) with open(path, "wb") as fh: df.to_pickle(fh) with open(path, "rb") as fh: @@ -450,7 +487,11 @@ def close(self): def mock_urlopen_read(*args, **kwargs): return MockReadResponse(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), + ) python_pickler(df, path) monkeypatch.setattr("urllib.request.urlopen", mock_urlopen_read) result = pd.read_pickle(mockurl) @@ -461,7 +502,11 @@ def test_pickle_fsspec_roundtrip(): pytest.importorskip("fsspec") with tm.ensure_clean(): mockurl = "memory://mockfile" - 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_pickle(mockurl) result = pd.read_pickle(mockurl) tm.assert_frame_equal(df, result) @@ -487,7 +532,11 @@ def test_pickle_binary_object_compression(compression): GH 26237, GH 29054, and GH 29570 """ - 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), + ) # reference for compression with tm.ensure_clean() as path: @@ -567,7 +616,7 @@ def test_pickle_preserves_block_ndim(): @pytest.mark.parametrize("protocol", [pickle.DEFAULT_PROTOCOL, pickle.HIGHEST_PROTOCOL]) def test_pickle_big_dataframe_compression(protocol, compression): # GH#39002 - df = pd.DataFrame(range(100000)) + df = DataFrame(range(100000)) result = tm.round_trip_pathlib( partial(df.to_pickle, protocol=protocol, compression=compression), partial(pd.read_pickle, compression=compression), @@ -587,13 +636,13 @@ def test_pickle_frame_v124_unpickle_130(datapath): with open(path, "rb") as fd: df = pickle.load(fd) - expected = pd.DataFrame(index=[], columns=[]) + expected = DataFrame(index=[], columns=[]) tm.assert_frame_equal(df, expected) def test_pickle_pos_args_deprecation(): # GH-54229 - df = pd.DataFrame({"a": [1, 2, 3]}) + df = DataFrame({"a": [1, 2, 3]}) msg = ( r"Starting with pandas version 3.0 all arguments of to_pickle except for the " r"argument 'path' will be keyword-only." diff --git a/pandas/tests/io/test_stata.py b/pandas/tests/io/test_stata.py index 82e6c2964b8c5..19d81d50f5774 100644 --- a/pandas/tests/io/test_stata.py +++ b/pandas/tests/io/test_stata.py @@ -1549,14 +1549,22 @@ def test_inf(self, infval): df.to_stata(path) def test_path_pathlib(self): - df = tm.makeDataFrame() + df = DataFrame( + 1.1 * np.arange(120).reshape((30, 4)), + columns=pd.Index(list("ABCD"), dtype=object), + index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + ) df.index.name = "index" reader = lambda x: read_stata(x).set_index("index") result = tm.round_trip_pathlib(df.to_stata, reader) tm.assert_frame_equal(df, result) def test_pickle_path_localpath(self): - df = tm.makeDataFrame() + df = DataFrame( + 1.1 * np.arange(120).reshape((30, 4)), + columns=pd.Index(list("ABCD"), dtype=object), + index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + ) df.index.name = "index" reader = lambda x: read_stata(x).set_index("index") result = tm.round_trip_localpath(df.to_stata, reader) @@ -1577,7 +1585,11 @@ def test_value_labels_iterator(self, write_index): def test_set_index(self): # GH 17328 - df = tm.makeDataFrame() + df = DataFrame( + 1.1 * np.arange(120).reshape((30, 4)), + columns=pd.Index(list("ABCD"), dtype=object), + index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + ) df.index.name = "index" with tm.ensure_clean() as path: df.to_stata(path) @@ -1714,7 +1726,11 @@ def test_invalid_date_conversion(self): def test_nonfile_writing(self, version): # GH 21041 bio = io.BytesIO() - df = tm.makeDataFrame() + df = DataFrame( + 1.1 * np.arange(120).reshape((30, 4)), + columns=pd.Index(list("ABCD"), dtype=object), + index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + ) df.index.name = "index" with tm.ensure_clean() as path: df.to_stata(bio, version=version) @@ -1726,7 +1742,11 @@ def test_nonfile_writing(self, version): def test_gzip_writing(self): # writing version 117 requires seek and cannot be used with gzip - df = tm.makeDataFrame() + df = DataFrame( + 1.1 * np.arange(120).reshape((30, 4)), + columns=pd.Index(list("ABCD"), dtype=object), + index=pd.Index([f"i-{i}" for i in range(30)], dtype=object), + ) df.index.name = "index" with tm.ensure_clean() as path: with gzip.GzipFile(path, "wb") as gz: diff --git a/pandas/tests/plotting/test_datetimelike.py b/pandas/tests/plotting/test_datetimelike.py index bfb9a5a9a1647..3195b7637ee3c 100644 --- a/pandas/tests/plotting/test_datetimelike.py +++ b/pandas/tests/plotting/test_datetimelike.py @@ -1314,7 +1314,11 @@ def test_secondary_legend_multi_col(self): def test_secondary_legend_nonts(self): # non-ts - 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), + ) fig = mpl.pyplot.figure() ax = fig.add_subplot(211) ax = df.plot(secondary_y=["A", "B"], ax=ax) @@ -1331,7 +1335,11 @@ def test_secondary_legend_nonts(self): def test_secondary_legend_nonts_multi_col(self): # non-ts - 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), + ) fig = mpl.pyplot.figure() ax = fig.add_subplot(211) ax = df.plot(secondary_y=["C", "D"], ax=ax) diff --git a/pandas/tests/series/methods/test_reset_index.py b/pandas/tests/series/methods/test_reset_index.py index 9e6b4ce0df1d6..634b8699a89e6 100644 --- a/pandas/tests/series/methods/test_reset_index.py +++ b/pandas/tests/series/methods/test_reset_index.py @@ -33,7 +33,11 @@ def test_reset_index_dti_round_trip(self): assert df.reset_index()["Date"].iloc[0] == stamp def test_reset_index(self): - df = tm.makeDataFrame()[:5] + 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), + )[:5] ser = df.stack(future_stack=True) ser.index.names = ["hash", "category"]