def r_convert_pandas_dataframe(df: pd.DataFrame) -> RDataFrame:
"""
Pandas dataframe to R dataframe conversion.
See:
http://chris.friedline.net/2015-12-15-rutgers/lessons/python2/03-data-types-and-format.html
TODO/FIXME: Error when a dataframe column has NA elements.
"""
pd_names = [str(header) for header in list(df)]
pd_types = [str(dtype) for dtype in df.dtypes]
elements = {}
for column_name, column_type in zip(pd_names, pd_types):
if column_type == 'int64':
elements[column_name] = RIntVector(df[column_name])
elif column_type == 'float64':
elements[column_name] = RFloatVector(df[column_name])
elif column_type == 'object':
elements[column_name] = RFactorVector(df[column_name])
elif column_type == 'datetime64' or column_type == 'timedelta[ns]':
raise NotImplementedError(
'Date values are not currently implemented')
else:
msg = ' '.join(
['Given column_type is not recognized', column_type])
raise TypeError(msg)
return RDataFrame(elements)
def _extract_mapping(self, cimpl_obj, cis_sites):
# Convert CIS sites to frame format.
cis_frame = CisSite.to_frame(cis_sites)
# Convert to R representation for cimpl.
chr_with_prefix = add_prefix(cis_frame['chromosome'], prefix='chr')
r_base = importr('base')
cis_frame_r = RDataFrame({
'id':
r_base.I(StrVector(cis_frame['id'])),
'chromosome':
r_base.I(StrVector(chr_with_prefix)),
'scale':
StrVector(cis_frame['scale']),
'start':
IntVector(cis_frame['start']),
'end':
IntVector(cis_frame['end'])
})
cis_frame_r.rownames = StrVector(cis_frame['id'])
# Retrieve cis matrix from cimpl.
cis_matrix_r = self._cimpl.getCISMatrix(cimpl_obj, cis_frame_r)
cis_matrix = dataframe_to_pandas(cis_matrix_r)
# Extract scale information from cis matrix.
scale_cols = [c for c in cis_matrix.columns if c.startswith('X')]
cis_matrix_scales = cis_matrix[['id'] + scale_cols]
# Melt matrix into long format.
mapping = pd.melt(cis_matrix_scales, id_vars=['id'])
mapping = mapping[['id', 'value']]
mapping = mapping.rename(columns={
'id': 'insertion_id',
'value': 'cis_id'
})
# Split cis_id column into individual entries (for entries
# with multiple ids). Then drop any empty rows, as these
# entries are empty cells in the matrix.
mapping = mapping.ix[mapping['cis_id'] != '']
mapping = expand_column(mapping, col='cis_id', delimiter='|')
mapping_dict = {
ins_id: set(grp['cis_id'])
for ins_id, grp in mapping.groupby('insertion_id')
}
return mapping_dict
def _python_params_to_r_objects(self, r_package=None):
"""Converts python objects to the appropriate R objects."""
# get a ref to base R namespace
Rbase = r_package
# convert the pandas.DataFrame to an R dataframe
r_df_ = RDataFrame(self.df)
# convert the model params to strings in R
r_model_params_ = {
"path_feature":
Rbase.toString(self.path_feature),
"conversion_feature":
Rbase.toString(self.conversion_feature),
"conversion_value_feature":
Rbase.toString(self.conversion_value_feature)
if self.conversion_value_feature is not None else NULL,
"null_path_feature":
Rbase.toString(self.null_path_feature)
if self.null_path_feature is not None else NULL,
"separator":
Rbase.toString(self.separator),
"order":
Rbase.as_double(self.order),
"n_simulations":
Rbase.as_double(self.n_simulations)
if self.n_simulations is not None else NULL,
"max_step":
Rbase.as_double(self.max_step)
if self.max_step is not None else NULL,
"return_transition_probs":
Rbase.as_logical(self.return_transition_probs)
if self.return_transition_probs is not None else NULL,
"random_state":
Rbase.as_double(self.random_state)
if self.random_state != None else NULL
}
return r_df_, r_model_params_
def py2ro_pandasdataframe(obj):
ri_dataf = conversion.py2ri(obj)
# cast down to an R list (goes through a different code path
# in the DataFrame constructor, avoiding `str(k)`)
ri_list = rinterface.SexpVector(ri_dataf)
return RDataFrame(ri_list)
