def generate_input(self):
if self._regression:
(
dtypes_meta,
num_rows,
num_cols,
seed,
) = self.get_next_regression_params()
else:
dtypes_list = list(
cudf.utils.dtypes.ALL_TYPES
- {"category", "datetime64[ns]"}
- cudf.utils.dtypes.TIMEDELTA_TYPES
)
dtypes_meta, num_rows, num_cols = _generate_rand_meta(
self, dtypes_list
)
self._current_params["dtypes_meta"] = dtypes_meta
seed = random.randint(0, 2 ** 32 - 1)
self._current_params["seed"] = seed
self._current_params["num_rows"] = num_rows
self._current_params["num_cols"] = num_cols
logging.info(
f"Generating DataFrame with rows: {num_rows} "
f"and columns: {num_cols}"
)
table = dg.rand_dataframe(dtypes_meta, num_rows, seed)
df = pyarrow_to_pandas(table)
logging.info(f"Shape of DataFrame generated: {table.shape}")
file = io.BytesIO()
df.to_parquet(file)
file.seek(0)
return file.read()
def generate_input(self):
if self._regression:
(
dtypes_meta,
num_rows,
num_cols,
seed,
) = self.get_next_regression_params()
else:
seed = random.randint(0, 2 ** 32 - 1)
random.seed(seed)
dtypes_list = list(
cudf.utils.dtypes.ALL_TYPES
- {"category", "timedelta64[ns]", "datetime64[ns]"}
)
dtypes_meta, num_rows, num_cols = _generate_rand_meta(
self, dtypes_list
)
self._current_params["dtypes_meta"] = dtypes_meta
self._current_params["seed"] = seed
self._current_params["num_rows"] = num_rows
self._current_params["num_columns"] = num_cols
logging.info(
f"Generating DataFrame with rows: {num_rows} "
f"and columns: {num_cols}"
)
df = cudf.DataFrame.from_arrow(
dg.rand_dataframe(dtypes_meta, num_rows, seed)
)
logging.info(f"Shape of DataFrame generated: {df.shape}")
return df
def generate_input(self):
if self._regression:
(
dtypes_meta,
num_rows,
num_cols,
seed,
) = self.get_next_regression_params()
else:
seed = random.randint(0, 2**32 - 1)
random.seed(seed)
dtypes_list = list(cudf.utils.dtypes.ALL_TYPES)
dtypes_meta, num_rows, num_cols = _generate_rand_meta(
self, dtypes_list)
self._current_params["dtypes_meta"] = dtypes_meta
self._current_params["file_name"] = self._file_name
self._current_params["seed"] = seed
self._current_params["num_rows"] = num_rows
self._current_params["num_columns"] = num_cols
logging.info(f"Generating DataFrame with rows: {num_rows} "
f"and columns: {num_cols}")
table = dg.rand_dataframe(dtypes_meta, num_rows, seed)
df = pyarrow_to_pandas(table)
logging.info(f"Shape of DataFrame generated: {df.shape}")
return df.to_json()