def test_pandas_from_arrow():
arr = pa.array(["a", "b", "c"], pa.string())
expected_series_woutname = pd.Series(fr.FletcherArray(arr))
pdt.assert_series_equal(expected_series_woutname,
fr.pandas_from_arrow(arr))
rb = pa.RecordBatch.from_arrays([arr], ["column"])
expected_df = pd.DataFrame({"column": fr.FletcherArray(arr)})
pdt.assert_frame_equal(expected_df, fr.pandas_from_arrow(rb))
def test_pandas_from_arrow_casting_to_pandas(arr):
table = pa.Table.from_arrays(
[
arr["int"],
arr["int_with_nulls"],
arr["dict"],
arr["string"],
arr["date"],
arr["list"],
arr["large_list"],
],
[
"int", "int_with_nulls", "dict", "string", "date", "list",
"large_list"
],
)
df = fr.pandas_from_arrow(table)
for col in df.columns:
if col in ["int_with_nulls", "list", "large_list"]:
assert isinstance(df[col].values, fr.FletcherArray)
else:
assert isinstance(
df[col].values,
(np.ndarray, pd.core.arrays.categorical.Categorical))
if col in ["list", "large_list"]:
for i in range(len(arr[col])):
assert np.all(df[col][i] == arr[col][i])
else:
npt.assert_array_equal(df[col], arr[col].to_pandas())
def test_read_parquet(tmpdir, continuous):
str_arr = pa.array(["a", None, "c"], pa.string())
int_arr = pa.array([1, None, -2], pa.int32())
bool_arr = pa.array([True, None, False], pa.bool_())
table = pa.Table.from_arrays([str_arr, int_arr, bool_arr],
["str", "int", "bool"])
pq.write_table(table, "df.parquet")
result = fr.read_parquet("df.parquet", continuous=continuous)
expected = fr.pandas_from_arrow(table, continuous=continuous)
tm.assert_frame_equal(result, expected)
def test_pandas_from_arrow():
arr = pa.array(["a", "b", "c"], pa.string())
expected_series_woutname = pd.Series(fr.FletcherChunkedArray(arr))
pdt.assert_series_equal(expected_series_woutname, fr.pandas_from_arrow(arr))
expected_series_woutname = pd.Series(fr.FletcherContinuousArray(arr))
pdt.assert_series_equal(
expected_series_woutname, fr.pandas_from_arrow(arr, continuous=True)
)
rb = pa.RecordBatch.from_arrays([arr], ["column"])
expected_df = pd.DataFrame({"column": fr.FletcherChunkedArray(arr)})
table = pa.Table.from_arrays([arr], ["column"])
pdt.assert_frame_equal(expected_df, fr.pandas_from_arrow(rb))
pdt.assert_frame_equal(expected_df, fr.pandas_from_arrow(table))
expected_df = pd.DataFrame({"column": fr.FletcherContinuousArray(arr)})
table = pa.Table.from_arrays([arr], ["column"])
pdt.assert_frame_equal(expected_df, fr.pandas_from_arrow(rb, continuous=True))
pdt.assert_frame_equal(expected_df, fr.pandas_from_arrow(table, continuous=True))
