Functions used to create pytorch `DataSet`s and `DataLoader`s.
convert_date
(dates
)
Converts pandas date format to torch Tensors (floats)
get_moments
(df
)
Gets the mean and variance of all columns.
create_tensors
(df
, moments
, predict
=False
)
converts a pandas dataframe to pytorch tensors
TimeSeries
(x
, y
) :: Dataset
Load raw x,y data
DataFrame
(df
, moments
=None
) :: Dataset
Take a data frame with columns ds | y | other_cols and convert to pytorch tensors.
Functions to create Fastai DataBunch
es.
create_db
(df
, train_p
=0.8
, bs
=96
, moments
=None
)
Take dataframe and convert to Fastai databunch