def predict(self, data):
"""
Returns a prediction on the data.
If the data is a koalas DataFrame, the return is a Koalas Series.
If the data is a pandas Dataframe, the return is the expected output of the underlying
pyfunc object (typically a pandas Series or a numpy array).
"""
if isinstance(data, pd.DataFrame):
return self._model.predict(data)
if isinstance(data, DataFrame):
return_col = self._model_udf(*data._internal.data_spark_columns)
# TODO: the columns should be named according to the mlflow spec
# However, this is only possible with spark >= 3.0
# s = F.struct(*data.columns)
# return_col = self._model_udf(s)
column_labels = [(col, )
for col in data._internal.spark_frame.select(
return_col).columns]
return Series(
data._internal.copy(spark_column=return_col,
column_labels=column_labels),
anchor=data,
)
def align_diff_series(func, this_series, *args, how="full"):
from databricks.koalas.base import IndexOpsMixin
from databricks.koalas.series import Series
cols = [arg for arg in args if isinstance(arg, IndexOpsMixin)]
combined = combine_frames(this_series.to_frame(), *cols, how=how)
scol = func(combined["this"]._internal.column_scols[0],
*combined["that"]._internal.column_scols)
return Series(
combined._internal.copy(
scol=scol, column_labels=this_series._internal.column_labels),
anchor=combined,
)
def align_diff_series(func, this_series, *args, how="full"):
from databricks.koalas.base import IndexOpsMixin
from databricks.koalas.series import Series
cols = [arg for arg in args if isinstance(arg, IndexOpsMixin)]
combined = combine_frames(this_series.to_frame(), *cols, how=how)
that_columns = [combined['that'][arg._internal.column_index[0]]._scol
if isinstance(arg, IndexOpsMixin) else arg for arg in args]
scol = func(combined['this'][this_series._internal.column_index[0]]._scol,
*that_columns)
return Series(combined._internal.copy(scol=scol,
column_index=this_series._internal.column_index),
anchor=combined)
