def test_table_grouped_tail_real_data(self):
with temporary_directory() as workdir:
for table_path in (SRC / "test" / "data").glob("*.csv"):
table = read_table(table_path, schema=SCHEMA)
test_output = workdir / f"latest_{table_path.name}"
pandas_output = workdir / f"latest_pandas_{table_path.name}"
# Create the latest slice of the given table
table_grouped_tail(table_path, test_output, ["key"])
# Create a latest slice using pandas grouping
table = table.groupby("key").aggregate(
agg_last_not_null).reset_index()
export_csv(table, path=pandas_output, schema=SCHEMA)
# Converting to a CSV in memory sometimes produces out-of-order values
with open_file_like(test_output) as fd1, open_file_like(
pandas_output) as fd2:
test_result_lines = list(sorted(fd1))
pandas_result_lines = list(sorted(fd2))
self.assertEqual(len(test_result_lines),
len(pandas_result_lines))
for line1, line2 in zip(test_result_lines,
pandas_result_lines):
self.assertEqual(line1, line2)
def test_table_grouped_tail_synthetic(self):
test_csv = _make_test_csv_file(
"""
col1,col2,col3
a,1,foo
a,2,bar
b,1,foo
b,2,baz
c,1,foo
c,2,
"""
)
expected = _make_test_csv_file(
"""
col1,col2,col3
a,2,bar
b,2,baz
c,2,foo
"""
)
with temporary_file() as output_file:
table_grouped_tail(test_csv, output_path=output_file, group_by=["col1"])
_compare_tables_equal(self, output_file, expected)
def _subset_latest(output_folder: Path, csv_file: Path) -> Path:
output_file = output_folder / csv_file.name
# Degenerate case: table has no "date" column
columns = get_table_columns(csv_file)
if "date" not in columns:
shutil.copyfile(csv_file, output_file)
else:
table_grouped_tail(csv_file, output_file, ["key"])
return output_file