pyochain 0.5.0__py3-none-any.whl → 0.5.2__py3-none-any.whl

pyochain/_core/_main.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from abc import ABC, abstractmethod
-from collections.abc import Callable, Collection, Iterable, Iterator
+from collections.abc import Callable, Iterable, Iterator, Sequence
 from typing import TYPE_CHECKING, Any, Concatenate, Self
 
 if TYPE_CHECKING:
@@ -53,9 +53,9 @@ class CommonBase[T](ABC, Pipeable):
         from pprint import pprint
 
         if pretty:
-            pprint(self.unwrap(), sort_dicts=False)
+            self.into(pprint, sort_dicts=False)
         else:
-            print(self.unwrap())
+            self.into(print)
         return self
 
     def unwrap(self) -> T:
@@ -90,49 +90,34 @@ class CommonBase[T](ABC, Pipeable):
 class IterWrapper[T](CommonBase[Iterable[T]]):
     _data: Iterable[T]
 
-    def apply[**P, R](
+    def __repr__(self) -> str:
+        return f"{self.__class__.__name__}({self.unwrap().__repr__()})"
+
+    def _eager[**P, U](
         self,
-        func: Callable[Concatenate[Iterable[T], P], Iterator[R]],
+        factory: Callable[Concatenate[Iterable[T], P], Sequence[U]],
         *args: P.args,
         **kwargs: P.kwargs,
-    ) -> Iter[R]:
-        """
-        Apply a function to the underlying iterable and return an Iter of the result.
-        Allow to pass user defined functions that transform the iterable while retaining the Iter wrapper.
-        Args:
-            func: Function to apply to the underlying iterable.
-            *args: Positional arguments to pass to the function.
-            **kwargs: Keyword arguments to pass to the function.
+    ) -> Seq[U]:
+        from .._iter import Seq
 
-        Example:
-        ```python
-        >>> import pyochain as pc
-        >>> def double(data: Iterable[int]) -> Iterator[int]:
-        ...     return (x * 2 for x in data)
-        >>> pc.Iter.from_([1, 2, 3]).apply(double).into(list)
-        [2, 4, 6]
-        """
-        from .._iter import Iter
+        def _(data: Iterable[T]):
+            return Seq(factory(data, *args, **kwargs))
 
-        return Iter(self.into(func, *args, **kwargs))
+        return self.into(_)
 
-    def collect(self, factory: Callable[[Iterable[T]], Collection[T]] = list) -> Seq[T]:
-        """
-        Collect the elements into a sequence.
-        Args:
-            factory: A callable that takes an iterable and returns a collection. Defaults to list.
-
-        Example:
-        ```python
-        >>> import pyochain as pc
-        >>> pc.Iter.from_(range(5)).collect().unwrap()
-        [0, 1, 2, 3, 4]
+    def _lazy[**P, U](
+        self,
+        factory: Callable[Concatenate[Iterable[T], P], Iterator[U]],
+        *args: P.args,
+        **kwargs: P.kwargs,
+    ) -> Iter[U]:
+        from .._iter import Iter
 
-        ```
-        """
-        from .._iter import Seq
+        def _(data: Iterable[T]):
+            return Iter(factory(data, *args, **kwargs))
 
-        return Seq(self.into(factory))
+        return self.into(_)
 
 
 class MappingWrapper[K, V](CommonBase[dict[K, V]]):
@@ -147,6 +132,7 @@ class MappingWrapper[K, V](CommonBase[dict[K, V]]):
         """
         Apply a function to the underlying dict and return a Dict of the result.
         Allow to pass user defined functions that transform the dict while retaining the Dict wrapper.
+
         Args:
             func: Function to apply to the underlying dict.
             *args: Positional arguments to pass to the function.

pyochain/_dict/_exprs.py

@@ -17,6 +17,7 @@ class Expr(Pipeable):
     An Expr encapsulates a sequence of operations to be applied to keys on a python dict.
 
     Each Expr instance maintains:
+
     - A list of tokens representing the keys to access in the dict (the first being the input given to the `key` function),
     - A tuple of operations to apply to the accessed data
     - An alias for the expression (default to the last token).

pyochain/_dict/_filters.py

@@ -112,6 +112,7 @@ class FilterDict[K, V](MappingWrapper[K, V]):
         Filter values that have a given attribute.
 
         This does not enforce type checking at runtime for performance considerations.
+
         Args:
             attr: Attribute name to check for.
             dtype: Optional expected type of the attribute for type hinting.

pyochain/_dict/_groups.py

@@ -143,8 +143,7 @@ class GroupsDict[K, V](MappingWrapper[K, V]):
         ...     agg_func=lambda d: d.iter_keys().count(),
         ... ).unwrap()
         {'A': 2, 'B': 1}
-        >>>
-        >>> # --- Exemple 2: Agrégation plus complexe ---
+        >>> # Second example
         >>> sales_data = {
         ...     "store_1": "Electronics",
         ...     "store_2": "Groceries",

pyochain/_dict/_iter.py

@@ -43,7 +43,7 @@ class IterDict[K, V](MappingWrapper[K, V]):
 
         def _itr(data: Mapping[K, Iterable[U]]) -> dict[K, R]:
             def _(v: Iterable[U]) -> R:
-                return func(Iter.from_(v), *args, **kwargs)
+                return func(Iter(iter(v)), *args, **kwargs)
 
             return cz.dicttoolz.valmap(_, data)
 
@@ -61,7 +61,10 @@ class IterDict[K, V](MappingWrapper[K, V]):
         """
         from .._iter import Iter
 
-        return Iter.from_(self.unwrap().keys())
+        def _keys(data: dict[K, V]) -> Iter[K]:
+            return Iter(iter(data.keys()))
+
+        return self.into(_keys)
 
     def iter_values(self) -> Iter[V]:
         """
@@ -75,7 +78,10 @@ class IterDict[K, V](MappingWrapper[K, V]):
         """
         from .._iter import Iter
 
-        return Iter.from_(self.unwrap().values())
+        def _values(data: dict[K, V]) -> Iter[V]:
+            return Iter(iter(data.values()))
+
+        return self.into(_values)
 
     def iter_items(self) -> Iter[tuple[K, V]]:
         """
@@ -89,4 +95,7 @@ class IterDict[K, V](MappingWrapper[K, V]):
         """
         from .._iter import Iter
 
-        return Iter.from_(self.unwrap().items())
+        def _items(data: dict[K, V]) -> Iter[tuple[K, V]]:
+            return Iter(iter(data.items()))
+
+        return self.into(_items)

pyochain/_dict/_main.py

@@ -300,8 +300,5 @@ class Dict[K, V](
 
         ```
         """
-        return (
-            self.unwrap() == other.unwrap()
-            if isinstance(other, Dict)
-            else self.unwrap() == other
-        )
+        other_data = other.unwrap() if isinstance(other, Dict) else other
+        return self.unwrap() == other_data

pyochain/_dict/_process.py

@@ -5,7 +5,7 @@ from typing import TYPE_CHECKING, Any, Concatenate
 
 import cytoolz as cz
 
-from .._core import MappingWrapper
+from .._core import MappingWrapper, SupportsRichComparison
 
 if TYPE_CHECKING:
     from ._main import Dict
@@ -169,3 +169,24 @@ class ProcessDict[K, V](MappingWrapper[K, V]):
             return dict(sorted(data.items(), reverse=reverse))
 
         return self.apply(_sort)
+
+    def sort_values[U: SupportsRichComparison[Any]](
+        self: ProcessDict[K, U], reverse: bool = False
+    ) -> Dict[K, U]:
+        """
+        Sort the dictionary by its values and return a new Dict.
+
+        Args:
+            reverse: Whether to sort in descending order. Defaults to False.
+        ```python
+        >>> import pyochain as pc
+        >>> pc.Dict({"a": 2, "b": 1}).sort_values().unwrap()
+        {'b': 1, 'a': 2}
+
+        ```
+        """
+
+        def _sort_values(data: dict[K, U]) -> dict[K, U]:
+            return dict(sorted(data.items(), key=lambda item: item[1], reverse=reverse))
+
+        return self.apply(_sort_values)

pyochain/_iter/_aggregations.py

@@ -30,6 +30,7 @@ class BaseAgg[T](IterWrapper[T]):
 
         - one from the left elements of the pairs
         - one from the right elements.
+
         This function is, in some sense, the opposite of zip.
         ```python
         >>> import pyochain as pc

pyochain/_iter/_booleans.py

@@ -21,6 +21,7 @@ class BaseBool[T](IterWrapper[T]):
         If any of them return false, it returns false.
 
         An empty iterator returns true.
+
         Args:
             predicate: Function to evaluate each item. Defaults to checking truthiness.
         Example:
@@ -57,6 +58,7 @@ class BaseBool[T](IterWrapper[T]):
         If they all return false, it returns false.
 
         An empty iterator returns false.
+
         Args:
             predicate: Function to evaluate each item. Defaults to checking truthiness.
         Example:
@@ -200,6 +202,7 @@ class BaseBool[T](IterWrapper[T]):
         - Returning the first element that satisfies the `predicate`.
 
         If all the elements return false, `Iter.find()` returns the default value.
+
         Args:
             default: Value to return if no element satisfies the predicate. Defaults to None.
             predicate: Function to evaluate each item. Defaults to checking truthiness.

pyochain/_iter/{_groups.py → _dicts.py}

@@ -1,20 +1,73 @@
 from __future__ import annotations
 
-from collections.abc import Callable, Iterable, Iterator
-from functools import partial
-from typing import TYPE_CHECKING, Any, overload
+from collections.abc import Callable, Iterable
+from typing import TYPE_CHECKING
 
 import cytoolz as cz
-import more_itertools as mit
 
 from .._core import IterWrapper
 
 if TYPE_CHECKING:
     from .._dict import Dict
-    from ._main import Iter
 
 
-class BaseGroups[T](IterWrapper[T]):
+class BaseDict[T](IterWrapper[T]):
+    def with_keys[K](self, keys: Iterable[K]) -> Dict[K, T]:
+        """
+        Create a Dict by zipping the iterable with keys.
+
+        Args:
+            keys: Iterable of keys to pair with the values.
+        Example:
+        ```python
+        >>> import pyochain as pc
+        >>> keys = ["a", "b", "c"]
+        >>> values = [1, 2, 3]
+        >>> pc.Iter.from_(values).with_keys(keys).unwrap()
+        {'a': 1, 'b': 2, 'c': 3}
+        >>> # This is equivalent to:
+        >>> pc.Iter.from_(keys).zip(values).pipe(
+        ...     lambda x: pc.Dict(x.into(dict)).unwrap()
+        ... )
+        {'a': 1, 'b': 2, 'c': 3}
+
+        ```
+        """
+        from .._dict import Dict
+
+        def _with_keys(data: Iterable[T]) -> Dict[K, T]:
+            return Dict(dict(zip(keys, data)))
+
+        return self.into(_with_keys)
+
+    def with_values[V](self, values: Iterable[V]) -> Dict[T, V]:
+        """
+        Create a Dict by zipping the iterable with values.
+
+        Args:
+            values: Iterable of values to pair with the keys.
+        Example:
+        ```python
+        >>> import pyochain as pc
+        >>> keys = [1, 2, 3]
+        >>> values = ["a", "b", "c"]
+        >>> pc.Iter.from_(keys).with_values(values).unwrap()
+        {1: 'a', 2: 'b', 3: 'c'}
+        >>> # This is equivalent to:
+        >>> pc.Iter.from_(keys).zip(values).pipe(
+        ...     lambda x: pc.Dict(x.into(dict)).unwrap()
+        ... )
+        {1: 'a', 2: 'b', 3: 'c'}
+
+        ```
+        """
+        from .._dict import Dict
+
+        def _with_values(data: Iterable[T]) -> Dict[T, V]:
+            return Dict(dict(zip(data, values)))
+
+        return self.into(_with_values)
+
     def reduce_by[K](
         self, key: Callable[[T], K], binop: Callable[[T, T], T]
     ) -> Dict[K, T]:
@@ -58,7 +111,10 @@ class BaseGroups[T](IterWrapper[T]):
         """
         from .._dict import Dict
 
-        return Dict(self.into(partial(cz.itertoolz.reduceby, key, binop)))
+        def _reduce_by(data: Iterable[T]) -> Dict[K, T]:
+            return Dict(cz.itertoolz.reduceby(key, binop, data))
+
+        return self.into(_reduce_by)
 
     def group_by[K](self, on: Callable[[T], K]) -> Dict[K, list[T]]:
         """
@@ -117,7 +173,10 @@ class BaseGroups[T](IterWrapper[T]):
         """
         from .._dict import Dict
 
-        return Dict(self.into(partial(cz.itertoolz.groupby, on)))
+        def _group_by(data: Iterable[T]) -> Dict[K, list[T]]:
+            return Dict(cz.itertoolz.groupby(on, data))
+
+        return self.into(_group_by)
 
     def frequencies(self) -> Dict[T, int]:
         """
@@ -132,7 +191,10 @@ class BaseGroups[T](IterWrapper[T]):
         """
         from .._dict import Dict
 
-        return Dict(self.into(cz.itertoolz.frequencies))
+        def _frequencies(data: Iterable[T]) -> Dict[T, int]:
+            return Dict(cz.itertoolz.frequencies(data))
+
+        return self.into(_frequencies)
 
     def count_by[K](self, key: Callable[[T], K]) -> Dict[K, int]:
         """
@@ -154,111 +216,7 @@ class BaseGroups[T](IterWrapper[T]):
         """
         from .._dict import Dict
 
-        return Dict(self.into(partial(cz.recipes.countby, key)))
-
-    @overload
-    def group_by_transform(
-        self,
-        keyfunc: None = None,
-        valuefunc: None = None,
-        reducefunc: None = None,
-    ) -> Iter[tuple[T, Iterator[T]]]: ...
-    @overload
-    def group_by_transform[U](
-        self,
-        keyfunc: Callable[[T], U],
-        valuefunc: None,
-        reducefunc: None,
-    ) -> Iter[tuple[U, Iterator[T]]]: ...
-    @overload
-    def group_by_transform[V](
-        self,
-        keyfunc: None,
-        valuefunc: Callable[[T], V],
-        reducefunc: None,
-    ) -> Iter[tuple[T, Iterator[V]]]: ...
-    @overload
-    def group_by_transform[U, V](
-        self,
-        keyfunc: Callable[[T], U],
-        valuefunc: Callable[[T], V],
-        reducefunc: None,
-    ) -> Iter[tuple[U, Iterator[V]]]: ...
-    @overload
-    def group_by_transform[W](
-        self,
-        keyfunc: None,
-        valuefunc: None,
-        reducefunc: Callable[[Iterator[T]], W],
-    ) -> Iter[tuple[T, W]]: ...
-    @overload
-    def group_by_transform[U, W](
-        self,
-        keyfunc: Callable[[T], U],
-        valuefunc: None,
-        reducefunc: Callable[[Iterator[T]], W],
-    ) -> Iter[tuple[U, W]]: ...
-    @overload
-    def group_by_transform[V, W](
-        self,
-        keyfunc: None,
-        valuefunc: Callable[[T], V],
-        reducefunc: Callable[[Iterator[V]], W],
-    ) -> Iter[tuple[T, W]]: ...
-    @overload
-    def group_by_transform[U, V, W](
-        self,
-        keyfunc: Callable[[T], U],
-        valuefunc: Callable[[T], V],
-        reducefunc: Callable[[Iterator[V]], W],
-    ) -> Iter[tuple[U, W]]: ...
-    def group_by_transform[U, V](
-        self,
-        keyfunc: Callable[[T], U] | None = None,
-        valuefunc: Callable[[T], V] | None = None,
-        reducefunc: Any = None,
-    ) -> Iter[tuple[Any, ...]]:
-        """
-        An extension of itertools.groupby that can apply transformations to the grouped data.
-
-        Args:
-            keyfunc: Function to compute the key for grouping. Defaults to None.
-            valuefunc: Function to transform individual items after grouping. Defaults to None.
-            reducefunc: Function to transform each group of items. Defaults to None.
-
-        Example:
-        ```python
-        >>> import pyochain as pc
-        >>> data = pc.Iter.from_("aAAbBBcCC")
-        >>> data.group_by_transform(
-        ...     lambda k: k.upper(), lambda v: v.lower(), lambda g: "".join(g)
-        ... ).into(list)
-        [('A', 'aaa'), ('B', 'bbb'), ('C', 'ccc')]
-
-        ```
-        Each optional argument defaults to an identity function if not specified.
-
-        group_by_transform is useful when grouping elements of an iterable using a separate iterable as the key.
-
-        To do this, zip the iterables and pass a keyfunc that extracts the first element and a valuefunc that extracts the second element:
-
-        Note that the order of items in the iterable is significant.
-
-        Only adjacent items are grouped together, so if you don't want any duplicate groups, you should sort the iterable by the key function.
-
-        Example:
-        ```python
-        >>> from operator import itemgetter
-        >>> data = pc.Iter.from_([0, 0, 1, 1, 1, 2, 2, 2, 3])
-        >>> data.zip("abcdefghi").group_by_transform(itemgetter(0), itemgetter(1)).map(
-        ...     lambda kv: (kv[0], "".join(kv[1]))
-        ... ).into(list)
-        [(0, 'ab'), (1, 'cde'), (2, 'fgh'), (3, 'i')]
-
-        ```
-        """
-
-        def _group_by_transform(data: Iterable[T]) -> Iterator[tuple[Any, ...]]:
-            return mit.groupby_transform(data, keyfunc, valuefunc, reducefunc)
+        def _count_by(data: Iterable[T]) -> Dict[K, int]:
+            return Dict(cz.recipes.countby(key, data))
 
-        return self.apply(_group_by_transform)
+        return self.into(_count_by)

pyochain/_iter/_eager.py

@@ -38,7 +38,7 @@ class BaseEager[T](IterWrapper[T]):
         def _sort(data: Iterable[U]) -> list[U]:
             return sorted(data, reverse=reverse, key=key)
 
-        return self.collect(_sort)
+        return self._eager(_sort)
 
     def tail(self, n: int) -> Seq[T]:
         """
@@ -54,7 +54,7 @@ class BaseEager[T](IterWrapper[T]):
 
         ```
         """
-        return self.collect(partial(cz.itertoolz.tail, n))
+        return self._eager(partial(cz.itertoolz.tail, n))
 
     def top_n(self, n: int, key: Callable[[T], Any] | None = None) -> Seq[T]:
         """
@@ -71,7 +71,7 @@ class BaseEager[T](IterWrapper[T]):
 
         ```
         """
-        return self.collect(partial(cz.itertoolz.topk, n, key=key))
+        return self._eager(partial(cz.itertoolz.topk, n, key=key))
 
     def union(self, *others: Iterable[T]) -> Seq[T]:
         """
@@ -91,10 +91,10 @@ class BaseEager[T](IterWrapper[T]):
         ```
         """
 
-        def _union(data: Iterable[T]) -> set[T]:
-            return set(data).union(*others)
+        def _union(data: Iterable[T]) -> list[T]:
+            return list(set(data).union(*others))
 
-        return self.collect(_union)
+        return self._eager(_union)
 
     def intersection(self, *others: Iterable[T]) -> Seq[T]:
         """
@@ -109,15 +109,15 @@ class BaseEager[T](IterWrapper[T]):
         ```python
         >>> import pyochain as pc
         >>> pc.Iter.from_([1, 2, 2]).intersection([2, 3], [2]).unwrap()
-        {2}
+        [2]
 
         ```
         """
 
-        def _intersection(data: Iterable[T]) -> set[T]:
-            return set(data).intersection(*others)
+        def _intersection(data: Iterable[T]) -> list[T]:
+            return list(set(data).intersection(*others))
 
-        return self.collect(_intersection)
+        return self._eager(_intersection)
 
     def diff_unique(self, *others: Iterable[T]) -> Seq[T]:
         """
@@ -133,15 +133,15 @@ class BaseEager[T](IterWrapper[T]):
         ```python
         >>> import pyochain as pc
         >>> pc.Iter.from_([1, 2, 2]).diff_unique([2, 3]).unwrap()
-        {1}
+        [1]
 
         ```
         """
 
-        def _difference(data: Iterable[T]) -> set[T]:
-            return set(data).difference(*others)
+        def _difference(data: Iterable[T]) -> list[T]:
+            return list(set(data).difference(*others))
 
-        return self.collect(_difference)
+        return self._eager(_difference)
 
     def diff_symmetric(self, *others: Iterable[T]) -> Seq[T]:
         """
@@ -163,10 +163,10 @@ class BaseEager[T](IterWrapper[T]):
         ```
         """
 
-        def _symmetric_difference(data: Iterable[T]) -> set[T]:
-            return set(data).symmetric_difference(*others)
+        def _symmetric_difference(data: Iterable[T]) -> list[T]:
+            return list(set(data).symmetric_difference(*others))
 
-        return self.collect(_symmetric_difference)
+        return self._eager(_symmetric_difference)
 
     def most_common(self, n: int | None = None) -> Seq[tuple[T, int]]:
         """
@@ -176,7 +176,6 @@ class BaseEager[T](IterWrapper[T]):
 
         Args:
             n: Number of most common elements to return. Defaults to None (all elements).
-
         Example:
         ```python
         >>> import pyochain as pc
@@ -187,9 +186,7 @@ class BaseEager[T](IterWrapper[T]):
         """
         from collections import Counter
 
-        from ._main import Seq
-
         def _most_common(data: Iterable[T]) -> list[tuple[T, int]]:
             return Counter(data).most_common(n)
 
-        return Seq(self.into(_most_common))
+        return self._eager(_most_common)