def setup(self, self_type, value_type, shape, limit, inplace):
pd = IMPL[ASV_USE_IMPL]
columns = [f"col{x}" for x in range(shape[1])]
if self_type == "DataFrame":
self.dataset = pd.DataFrame(np.nan,
index=pd.RangeIndex(shape[0]),
columns=columns)
elif self_type == "Series":
self.dataset = pd.Series(np.nan, index=pd.RangeIndex(shape[0]))
else:
assert False
if value_type == "scalar":
self.value = 18.19
elif value_type == "dict":
self.value = {k: k * 1.23 for k in range(shape[0])}
elif value_type == "Series":
self.value = pd.Series([k * 1.23 for k in range(shape[0])],
index=pd.RangeIndex(shape[0]))
elif value_type == "DataFrame":
if self_type == "Series":
raise NotImplementedError
self.value = pd.DataFrame(
{
k: [i + j * 1.23 for j in range(shape[0])]
for i, k in enumerate(columns)
},
index=pd.RangeIndex(shape[0]),
columns=columns,
)
else:
assert False
self.limit = int(limit * shape[0]) if limit else None
def setup(self, value_type, shape, limit):
pd = IMPL[ASV_USE_IMPL]
self.df = gen_nan_data(ASV_USE_IMPL, *shape)
columns = self.df.columns
if value_type == "scalar":
self.value = 18.19
elif value_type == "dict":
self.value = {k: i * 1.23 for i, k in enumerate(columns)}
elif value_type == "Series":
self.value = pd.Series([i * 1.23 for i in range(len(columns))],
index=columns)
elif value_type == "DataFrame":
self.value = pd.DataFrame(
{
k: [i + j * 1.23 for j in range(shape[0])]
for i, k in enumerate(columns)
},
index=pd.RangeIndex(shape[0]),
columns=columns,
)
else:
assert False
limit = int(limit * shape[0]) if limit else None
self.kw = {"value": self.value, "limit": limit}
def setup(self, shape, limit, inplace):
pd = IMPL[ASV_USE_IMPL]
columns = [f"col{x}" for x in range(shape[1])]
self.df = pd.DataFrame(np.nan,
index=pd.RangeIndex(shape[0]),
columns=columns)
self.limit = int(limit * shape[0]) if limit else None
def gen_nan_data(impl: str, nrows: int, ncols: int) -> dict:
"""
Generate nan data with caching.
The generated data are saved in the dictionary and on a subsequent call,
if the keys match, saved data will be returned. Therefore, we need
to carefully monitor the changing of saved data and make its copy if needed.
Parameters
----------
impl : str
Implementation used to create the DataFrame or Series;
supported implemetations: {"modin", "pandas"}.
nrows : int
Number of rows.
ncols : int
Number of columns.
Returns
-------
modin.pandas.DataFrame or pandas.DataFrame or modin.pandas.Series or pandas.Series
DataFrame or Series with shape (nrows, ncols) or (nrows,), respectively.
"""
cache_key = (impl, nrows, ncols)
if cache_key in data_cache:
return data_cache[cache_key]
logging.info("Generating nan data {} rows and {} columns".format(
nrows, ncols))
if ncols > 1:
columns = [f"col{x}" for x in range(ncols)]
data = IMPL[impl].DataFrame(np.nan,
index=pd.RangeIndex(nrows),
columns=columns)
elif ncols == 1:
data = IMPL[impl].Series(np.nan, index=pd.RangeIndex(nrows))
else:
assert False, "Number of columns (ncols) should be >= 1"
data_cache[cache_key] = data
return data
def setup(self, value_type, shape, limit):
pd = IMPL[ASV_USE_IMPL]
self.series = gen_nan_data(ASV_USE_IMPL, *shape)
if value_type == "scalar":
self.value = 18.19
elif value_type == "dict":
self.value = {k: k * 1.23 for k in range(shape[0])}
elif value_type == "Series":
self.value = pd.Series([k * 1.23 for k in range(shape[0])],
index=pd.RangeIndex(shape[0]))
else:
assert False
limit = int(limit * shape[0]) if limit else None
self.kw = {"value": self.value, "limit": limit}
