finished app domain conversion #120

utilities/ml.py

@@ -52,7 +52,7 @@ class Dataset(ABC):
         self.add_rows([row])
 
     def block_indices(self, prefix) -> List[int]:
-        """Find the start and end indexes in column labels that has the prefix"""
+        """Find the indexes in column labels that has the prefix"""
         indices: List[int] = []
         for i, feature in enumerate(self.columns):
             if feature.startswith(prefix):
@@ -128,6 +128,29 @@ class Dataset(ABC):
     def iter_rows(self, named=False):
         return self.df.iter_rows(named=named)
 
+    def filter(self, *predicates, **constraints):
+        return self.__class__(data=self.df.filter(*predicates, **constraints))
+
+    def select(self, *exprs, **named_exprs):
+        return self.__class__(data=self.df.select(*exprs, **named_exprs))
+
+    def with_columns(self, *exprs, **name_exprs):
+        return self.__class__(data=self.df.with_columns(*exprs, **name_exprs))
+
+    def sort(self, by, *more_by, descending=False, nulls_last=False, multithreaded=True, maintain_order=False):
+        return self.__class__(data=self.df.sort(by, *more_by, descending=descending, nulls_last=nulls_last,
+                                                multithreaded=multithreaded, maintain_order=maintain_order))
+
+    def item(self, row=None, column=None):
+        return self.df.item(row, column)
+
+    def fill_nan(self, value):
+        return self.__class__(data=self.df.fill_nan(value))
+
+    @property
+    def height(self):
+        return self.df.height
+
 
 class RuleBasedDataset(Dataset):
     def __init__(self, num_labels=None, columns=None, data=None):