def read_data(self, file_name, col_from, col_to):
RawData = DataFrame(excel.read_excel("../Data/" + file_name + '.xlsx'))
NumericData = RawData.rx(True, IntVector(range(col_from, col_to + 1)))
MetaData = RawData.rx(True, col_from - 1)[0]
RawData._set_rownames(IntVector(range(1, len(MetaData) + 1)))
self.file_name = file_name
self.raw_data = RawData
#print(self.raw_data)
self.numeric_data = NumericData
self.metadata = r_base.factor(MetaData)
self.metadata_list = list(MetaData)
self.metabolite_list = list(self.raw_data.names)[1:]
self.make_metabolite_dict()
def r_c50(rdf: RDataFrame, target: str, predictors: List[str]) -> RListVector:
"""
Wrapper function around the C5.0 classifier.
Note: The target column must be a factor vector.
TODO: Training control and other parameters.
"""
predictor_slice = rdf.rx(r_c(*predictors))
target_slice = rdf.rx2(r_c(target))
return C50.C5_0(predictor_slice, target_slice)
def r_dataframe_subset_one_element(rdf: RDataFrame, n: int) -> RDataFrame:
"""
Creates a dataframe with one column from the given dataframe and index.
See:
https://github.com/topepo/caret/issues/672
https://stackoverflow.com/questions/40505994/how-to-apply-preprocessing-in-carets-train-to-only-some-variables
https://stackoverflow.com/questions/31497479/how-to-select-columns-from-r-dataframe-in-rpy2-in-python
"""
return r('data.frame')(rdf.rx(RIntVector([
n,
])))
def r_formula(rdf: RDataFrame, target: str, predictors: List[str]) -> RFormula:
"""
Creates an R modelling formula associated with the given dataframe.
The produced string formula is 'predictor ~ var1 + var2 + etc...'
"""
lhs_items = [target, '~']
rhs_items = []
for predictor in predictors:
rhs_items.append(predictor)
rhs_items.append('+')
rhs_items = rhs_items[:-1] # remove the last '+'
all_items = lhs_items + rhs_items
formula_string = ' '.join(all_items)
formula = RFormula(formula_string)
for predictor in predictors:
formula.environment[predictor] = rdf.rx(predictor)
return formula
