File size: 6,696 Bytes
a366dd4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 | import numpy as np
import pytest
from pandas.compat.numpy import np_version_gt2
from pandas import (
DataFrame,
Series,
date_range,
)
import pandas._testing as tm
from pandas.tests.copy_view.util import get_array
# -----------------------------------------------------------------------------
# Copy/view behaviour for accessing underlying array of Series/DataFrame
@pytest.mark.parametrize(
"method",
[
lambda ser: ser.values,
lambda ser: np.asarray(ser),
lambda ser: np.array(ser, copy=False),
],
ids=["values", "asarray", "array"],
)
def test_series_values(using_copy_on_write, method):
ser = Series([1, 2, 3], name="name")
ser_orig = ser.copy()
arr = method(ser)
if using_copy_on_write:
# .values still gives a view but is read-only
assert np.shares_memory(arr, get_array(ser, "name"))
assert arr.flags.writeable is False
# mutating series through arr therefore doesn't work
with pytest.raises(ValueError, match="read-only"):
arr[0] = 0
tm.assert_series_equal(ser, ser_orig)
# mutating the series itself still works
ser.iloc[0] = 0
assert ser.values[0] == 0
else:
assert arr.flags.writeable is True
arr[0] = 0
assert ser.iloc[0] == 0
@pytest.mark.parametrize(
"method",
[
lambda df: df.values,
lambda df: np.asarray(df),
lambda ser: np.array(ser, copy=False),
],
ids=["values", "asarray", "array"],
)
def test_dataframe_values(using_copy_on_write, using_array_manager, method):
df = DataFrame({"a": [1, 2, 3], "b": [4, 5, 6]})
df_orig = df.copy()
arr = method(df)
if using_copy_on_write:
# .values still gives a view but is read-only
assert np.shares_memory(arr, get_array(df, "a"))
assert arr.flags.writeable is False
# mutating series through arr therefore doesn't work
with pytest.raises(ValueError, match="read-only"):
arr[0, 0] = 0
tm.assert_frame_equal(df, df_orig)
# mutating the series itself still works
df.iloc[0, 0] = 0
assert df.values[0, 0] == 0
else:
assert arr.flags.writeable is True
arr[0, 0] = 0
if not using_array_manager:
assert df.iloc[0, 0] == 0
else:
tm.assert_frame_equal(df, df_orig)
def test_series_to_numpy(using_copy_on_write):
ser = Series([1, 2, 3], name="name")
ser_orig = ser.copy()
# default: copy=False, no dtype or NAs
arr = ser.to_numpy()
if using_copy_on_write:
# to_numpy still gives a view but is read-only
assert np.shares_memory(arr, get_array(ser, "name"))
assert arr.flags.writeable is False
# mutating series through arr therefore doesn't work
with pytest.raises(ValueError, match="read-only"):
arr[0] = 0
tm.assert_series_equal(ser, ser_orig)
# mutating the series itself still works
ser.iloc[0] = 0
assert ser.values[0] == 0
else:
assert arr.flags.writeable is True
arr[0] = 0
assert ser.iloc[0] == 0
# specify copy=True gives a writeable array
ser = Series([1, 2, 3], name="name")
arr = ser.to_numpy(copy=True)
assert not np.shares_memory(arr, get_array(ser, "name"))
assert arr.flags.writeable is True
# specifying a dtype that already causes a copy also gives a writeable array
ser = Series([1, 2, 3], name="name")
arr = ser.to_numpy(dtype="float64")
assert not np.shares_memory(arr, get_array(ser, "name"))
assert arr.flags.writeable is True
@pytest.mark.parametrize("order", ["F", "C"])
def test_ravel_read_only(using_copy_on_write, order):
ser = Series([1, 2, 3])
with tm.assert_produces_warning(FutureWarning, match="is deprecated"):
arr = ser.ravel(order=order)
if using_copy_on_write:
assert arr.flags.writeable is False
assert np.shares_memory(get_array(ser), arr)
def test_series_array_ea_dtypes(using_copy_on_write):
ser = Series([1, 2, 3], dtype="Int64")
arr = np.asarray(ser, dtype="int64")
assert np.shares_memory(arr, get_array(ser))
if using_copy_on_write:
assert arr.flags.writeable is False
else:
assert arr.flags.writeable is True
arr = np.asarray(ser)
assert np.shares_memory(arr, get_array(ser))
if using_copy_on_write:
assert arr.flags.writeable is False
else:
assert arr.flags.writeable is True
def test_dataframe_array_ea_dtypes(using_copy_on_write):
df = DataFrame({"a": [1, 2, 3]}, dtype="Int64")
arr = np.asarray(df, dtype="int64")
assert np.shares_memory(arr, get_array(df, "a"))
if using_copy_on_write:
assert arr.flags.writeable is False
else:
assert arr.flags.writeable is True
arr = np.asarray(df)
assert np.shares_memory(arr, get_array(df, "a"))
if using_copy_on_write:
assert arr.flags.writeable is False
else:
assert arr.flags.writeable is True
def test_dataframe_array_string_dtype(using_copy_on_write, using_array_manager):
df = DataFrame({"a": ["a", "b"]}, dtype="string")
arr = np.asarray(df)
if not using_array_manager:
assert np.shares_memory(arr, get_array(df, "a"))
if using_copy_on_write:
assert arr.flags.writeable is False
else:
assert arr.flags.writeable is True
def test_dataframe_multiple_numpy_dtypes():
df = DataFrame({"a": [1, 2, 3], "b": 1.5})
arr = np.asarray(df)
assert not np.shares_memory(arr, get_array(df, "a"))
assert arr.flags.writeable is True
if np_version_gt2:
# copy=False semantics are only supported in NumPy>=2.
msg = "Starting with NumPy 2.0, the behavior of the 'copy' keyword has changed"
with pytest.raises(FutureWarning, match=msg):
arr = np.array(df, copy=False)
arr = np.array(df, copy=True)
assert arr.flags.writeable is True
def test_dataframe_single_block_copy_true():
# the copy=False/None cases are tested above in test_dataframe_values
df = DataFrame({"a": [1, 2, 3], "b": [4, 5, 6]})
arr = np.array(df, copy=True)
assert not np.shares_memory(arr, get_array(df, "a"))
assert arr.flags.writeable is True
def test_values_is_ea(using_copy_on_write):
df = DataFrame({"a": date_range("2012-01-01", periods=3)})
arr = np.asarray(df)
if using_copy_on_write:
assert arr.flags.writeable is False
else:
assert arr.flags.writeable is True
def test_empty_dataframe():
df = DataFrame()
arr = np.asarray(df)
assert arr.flags.writeable is True
|