def transforms_available(self):
"""
Returns a list of all transformations available
"""
txfm = tx.transforms(self.x, self.D, {})
TXFM_FCN_DICT = txfm.transforms_available()
return TXFM_FCN_DICT
def transform(self, source_name, txfm_fcn, txfm_name, **kwargs):
"""
This runs transform (txfm_fcn) on the data matrix defined by
source_name with parameters that are variable for each transform.
For example, oe.data.transform('parent', 'zscore','zscore_parent', axis=0) will run the
zscore in a vector-wise manner across the matrix (column-wise) and the new data
dictionary access to the transformed data is oe.data['zscore_parent']
Successful completion results in
the addition of a new entry in the data dictionary with a key according
to txfm_name.
Parameters
----------
source_name: string
the name of the source data, for example 'parent', or 'log2'
txfm_fcn: string
the name of the transform function. See transforms.py or run oe.data.transforms_available() for list
txfm_name: string
the name you want to use in the data object dictionary oe.data.D['name'] to access transformed data
Other Parameters
----------------
**Keep_NaN: boolean
Set to True in order to prevent transformations from being added that produce NaNs.
Default Keep_NaN=True this will add transformed data even if NaNs are produced. Set to 0 to prevent addition of data transforms containing NaNs.
**Keep_Inf: boolean
Set to True in order to prevent transformations from being added that produce infinite values
Default: Keep_Inf = True (this will add transformed data even if infinite values are produced. Set to 0 to prevent addition of data transforms conta
Warnings
--------
NaNs or infinite values are produced
Raises
------
ValueError
if the transform function does not exist OR if the data source does not exist by source_name
Examples
--------
>>> import pandas as pd
>>> import openensembles as oe
>>> df = pd.read_csv(file)
>>> d = oe.data(df, df.columns
>>> d.transform('parent', 'zscore', 'zscore')
>>> d.transform('zscore', 'PCA', 'pca', n_components=3)
"""
#CHECK that the source exists
if source_name not in self.D:
raise ValueError(
"ERROR: the source you requested for transformation does not exist by that name %s"
% (source_name))
TXFM_FCN_DICT = self.transforms_available()
Keep_NaN_txfm = 1 #default value is to keep a transform, even if NaN values are created
Keep_Inf_txfm = 1 #default value is to keep a transform, even if NaN values are created
paramDict = {}
if not kwargs:
var_params = []
else:
var_params = kwargs
if 'Keep_NaN' in kwargs:
Keep_NaN_txfm = kwargs['Keep_NaN']
if 'Keep_Inf' in kwargs:
Keep_Inf_txfm = kwargs['Keep_Inf']
######BEGIN TXFM BLOCK ######
if txfm_fcn not in TXFM_FCN_DICT:
raise ValueError(
"The transform function you requested does not exist, currently the following are supported %s"
% (list(TXFM_FCN_DICT.keys())))
txfm = tx.transforms(self.x[source_name], self.D[source_name], kwargs)
func = getattr(txfm, txfm_fcn)
outputs = func()
#### FINAL staging, X, D and var_params have been set in transform block, now add each
#check and print a warning if NaN values were created in the transformation
boolCheck = np.isnan(txfm.data_out)
numNaNs = sum(sum(boolCheck))
if numNaNs.any():
warnings.warn(
"WARNING: transformation %s resulted in %d NaN values" %
(txfm_fcn, numNaNs), UserWarning)
if not Keep_NaN_txfm:
print(
"Transformation %s resulted in %d NaN values, and you requested not to keep a transformation with NaNs"
% (txfm_fcn, numNaNs))
return
infCheck = np.isinf(txfm.data_out)
numInf = sum(sum(infCheck))
if numInf.any() > 0:
warnings.warn(
"WARNING: transformation %s resulted in %d Inf values" %
(txfm_fcn, numInf), UserWarning)
if not Keep_Inf_txfm:
#print("Transformation %s resulted in %d Inf values, and you requested not to keep a transformation with infinite values"%(txfm_fcn, numInf))
return
self.x[txfm_name] = txfm.x_out
self.params[txfm_name] = txfm.var_params
self.D[txfm_name] = txfm.data_out
return outputs
