def _unsupported_function_rolling(method_name, deprecated=False, reason=""):
return unsupported_function(
class_name="pandas.core.window.Rolling",
method_name=method_name,
deprecated=deprecated,
reason=reason,
)
def _unsupported_function(method_name, deprecated=False, reason=""):
return unsupported_function(
class_name="pd.groupby.GroupBy",
method_name=method_name,
deprecated=deprecated,
reason=reason,
)
def _unsupported_function(method_name, deprecated=False, reason="", cls="Index"):
return unsupported_function(
class_name="pd.{}".format(cls),
method_name=method_name,
deprecated=deprecated,
reason=reason,
)
def _unsupported_function(method_name, deprecated=False, reason=""):
return unsupported_function(
class_name="pd.resample.Resampler",
method_name=method_name,
deprecated=deprecated,
reason=reason,
)
def _unsupported_function_exponential_moving(method_name,
deprecated=False,
reason=""):
return unsupported_function(
class_name="pandas.core.window.ExponentialMovingWindow",
method_name=method_name,
deprecated=deprecated,
reason=reason,
)
def box(self, **kwds):
"""
Make a box plot of the Series columns.
Parameters
----------
**kwds : optional
Additional keyword arguments are documented in
:meth:`pyspark.pandas.Series.plot`.
precision: scalar, default = 0.01
This argument is used by pandas-on-Spark to compute approximate statistics
for building a boxplot. Use *smaller* values to get more precise
statistics (matplotlib-only).
Returns
-------
:class:`plotly.graph_objs.Figure`
Return an custom object when ``backend!=plotly``.
Return an ndarray when ``subplots=True`` (matplotlib-only).
Notes
-----
There are behavior differences between pandas-on-Spark and pandas.
* pandas-on-Spark computes approximate statistics - expect differences between
pandas and pandas-on-Spark boxplots, especially regarding 1st and 3rd quartiles.
* The `whis` argument is only supported as a single number.
* pandas-on-Spark doesn't support the following argument(s) (matplotlib-only).
* `bootstrap` argument is not supported
* `autorange` argument is not supported
Examples
--------
Draw a box plot from a DataFrame with four columns of randomly
generated data.
For Series:
.. plotly::
>>> data = np.random.randn(25, 4)
>>> df = ps.DataFrame(data, columns=list('ABCD'))
>>> df['A'].plot.box() # doctest: +SKIP
This is an unsupported function for DataFrame type
"""
from pyspark.pandas import DataFrame, Series
if isinstance(self.data, Series):
return self(kind="box", **kwds)
elif isinstance(self.data, DataFrame):
return unsupported_function(class_name="pd.DataFrame",
method_name="box")()
def _unsupported_function(method_name, deprecated=False, reason=""):
return unsupported_function(class_name="pd.DataFrame",
method_name=method_name,
deprecated=deprecated,
reason=reason)
def hexbin(self, **kwds):
return unsupported_function(class_name="pd.DataFrame",
method_name="hexbin")()