def _fit(self, dataset: Dataset) -> Preprocessor:
if self.strategy == "mean":
aggregates = [Mean(col) for col in self.columns]
self.stats_ = dataset.aggregate(*aggregates)
elif self.strategy == "most_frequent":
self.stats_ = _get_most_frequent_values(dataset, *self.columns)
return self
def get_max_a(ds: Dataset):
# Calculate max value for column A.
max_a = ds.aggregate(Max("A"))
return max_a
def get_max(ds: Dataset):
return ds.aggregate(Max("value"))
def _fit(self, dataset: Dataset) -> Preprocessor:
aggregates = [Agg(col) for Agg in [Min, Max] for col in self.columns]
self.stats_ = dataset.aggregate(*aggregates)
return self
def _fit(self, dataset: Dataset) -> Preprocessor:
mean_aggregates = [Mean(col) for col in self.columns]
std_aggregates = [Std(col, ddof=self.ddof) for col in self.columns]
self.stats_ = dataset.aggregate(*mean_aggregates, *std_aggregates)
return self
