dataiter 0.9999__tar.gz → 1.1__tar.gz

{dataiter-0.9999 → dataiter-1.1}/PKG-INFO

@@ -1,10 +1,10 @@
 Metadata-Version: 2.1
 Name: dataiter
-Version: 0.9999
+Version: 1.1
 Summary: Simple, light-weight data frames for Python
 Project-URL: Homepage, https://github.com/otsaloma/dataiter
 Author-email: Osmo Salomaa <otsaloma@iki.fi>
-License-Expression: MIT
+License: MIT
 License-File: AUTHORS.md
 License-File: COPYING
 Requires-Python: >=3.9.0

{dataiter-0.9999 → dataiter-1.1}/dataiter/__init__.py

@@ -25,7 +25,7 @@ import numpy as np
 
 from dataiter import util
 
-__version__ = "0.9999"
+__version__ = "1.1"
 
 DEFAULT_PEEK_ELEMENTS = 10
 DEFAULT_PEEK_ITEMS = 3

{dataiter-0.9999 → dataiter-1.1}/dataiter/data_frame.py

@@ -776,6 +776,69 @@ class DataFrame(dict):
     def _parse_rows_from_integer(self, rows):
         return Vector.fast(rows, int)
 
+    def pivot_longer(self, *, ids=None, names=None, values=None):
+        """
+        Pivot data from wide to long format.
+
+        `ids` should be the name or a list of names of identifier columns. All
+        other columns are considered variable columns and will be pivoted.
+        `names` and `values` are names of columns into which the variable names
+        and values are put in the result.
+
+        >>> wide = di.read_csv("data/listings.csv")
+        >>> wide
+        >>> wide.pivot_longer(ids="id", names="name", values="value")
+        """
+        ids = util.sequencify(ids)
+        if not all(x in self for x in ids):
+            raise ValueError(f"Bad {ids=}")
+        long = self.__class__()
+        for name in (x for x in self if x not in ids):
+            part = self.select(*ids)
+            part[names] = name
+            # Maybe we could avoid using object here,
+            # but it gets complicated.
+            part[values] = self[name].as_object()
+            long = long.rbind(part)
+        return long.sort(**dict.fromkeys(ids, 1))
+
+    def pivot_wider(self, *, ids=None, names=None, values=None, rename=None):
+        """
+        Pivot data from long to wide format.
+
+        `ids` should be the name or a list of names of identifier columns by
+        which the result will be unique. If `ids` is not given, it defaults to
+        all columns except `names` and `values`. `names` should be the name of
+        the column that contains the names of variables, which become new
+        columns. `values` should be the name of the column that contains the
+        corresponding values. `rename` is an optional function that you can use
+        to e.g. lowercase the new column names or add a prefix or suffix.
+
+        >>> long = di.read_csv("data/downloads.csv")
+        >>> long = long.sort(date=1)
+        >>> long
+        >>> long.pivot_wider(ids="date", names="category", values="downloads", rename=str.lower)
+        """
+        if names not in self:
+            raise ValueError(f"Bad {names=}")
+        if values not in self:
+            raise ValueError(f"Bad {values=}")
+        if not ids:
+            ids = [x for x in self if x not in [names, values]]
+        ids = util.sequencify(ids)
+        if not all(x in self for x in ids):
+            raise ValueError(f"Bad {ids=}")
+        long = self.copy()
+        wide = self.select(*ids).unique(*ids)
+        if rename:
+            long[names] = long[names].map(rename)
+        for name in long[names].unique().sort():
+            part = long.filter(long[names] == name)
+            part = part.select(*ids, values)
+            part = part.rename(**{name: values})
+            wide = wide.left_join(part, *ids)
+        return wide
+
     def pop(self, key, *args, **kwargs):
         """"""
         value = super().pop(key, *args, **kwargs)

{dataiter-0.9999 → dataiter-1.1}/dataiter/dtypes.py

@@ -20,6 +20,8 @@
 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 # THE SOFTWARE.
 
+import warnings
+
 from numpy.dtypes import StringDType
 
 #: Instance of NumPy variable-width StringDType used
@@ -30,3 +32,7 @@ string = StringDType(na_object="")
 # input, a distinction between NA and blank cannot usually be made.
 # TODO: Consider changing this to something like ':NA:'.
 # https://numpy.org/doc/stable/user/basics.strings.html#missing-data-support
+
+# Ignore pointless warnings about using StringDType in numpy.savez.
+_pattern = "Custom dtypes are saved as python objects using the pickle protocol"
+warnings.filterwarnings("ignore", message=_pattern, category=UserWarning)

{dataiter-0.9999 → dataiter-1.1}/dataiter/regex.py

@@ -129,7 +129,7 @@ def sub(pattern, repl, string, count=0, flags=0):
     out, na = _prep(string, dtypes.string, dtypes.string.na_object)
     for i in np.flatnonzero(~na):
         out[i] = re.sub(pattern, repl, string[i], count=count, flags=flags)
-    return Vector.fast(out, dtypes.string)
+    return Vector.fast(out, str)
 
 def subn(pattern, repl, string, count=0, flags=0):
     """

{dataiter-0.9999 → dataiter-1.1}/dataiter/test/test_data_frame.py

@@ -31,9 +31,8 @@ from dataiter import test
 from pathlib import Path
 from unittest.mock import patch
 
-# This UserWarning seems unavoidable when using StringDtype, which unlike
-# other dtypes must be instantiated and that custom instance used.
-IGNORE_NPZ_PICKLE_WARNING = "ignore:Custom dtypes are saved as python objects using the pickle protocol."
+# See dataiter/dtypes.py for the equivalent non-test ignore.
+IGNORE_NPZ_PICKLE_WARNING = "ignore:Custom dtypes are saved as python objects using the pickle protocol"
 
 class TestDataFrameColumn:
 
@@ -376,6 +375,32 @@ class TestDataFrame:
         data = test.data_frame("vehicles.csv")
         assert data.nrow == 33442
 
+    def test_pivot_longer(self):
+        wide = test.data_frame("listings.csv")
+        wide = wide.sort(id=1).head(10)
+        long = wide.pivot_longer(ids="id",
+                                 names="name",
+                                 values="value")
+
+        assert long.nrow == 50
+        assert long.ncol == 3
+        assert all(np.isin(long.name, wide.colnames))
+
+    def test_pivot_wider(self):
+        long = test.data_frame("downloads.csv")
+        long = long.sort(date=1).tail(100)
+        wide = long.pivot_wider(ids="date",
+                                names="category",
+                                values="downloads",
+                                rename=lambda x: f"dl_{x.lower()}")
+
+        assert wide.nrow == 20
+        assert wide.ncol == 6
+        total_downloads = sum(
+            sum(wide[x]) for x in wide.colnames
+            if x.startswith("dl_"))
+        assert total_downloads == sum(long.downloads)
+
     def test_pop(self):
         data = test.data_frame("vehicles.csv")
         data.pop("fuel")

{dataiter-0.9999 → dataiter-1.1}/pyproject.toml

@@ -1,5 +1,5 @@
 [build-system]
-requires = ["hatchling==1.21.1"]
+requires = ["build==1.2.2.post1", "hatchling==1.21.1"]
 build-backend = "hatchling.build"
 
 [project]
@@ -7,7 +7,7 @@ name = "dataiter"
 dynamic = ["version"]
 description = "Simple, light-weight data frames for Python"
 readme = "README.md"
-license = "MIT"
+license = { text = "MIT" }
 requires-python = ">=3.9.0"
 authors = [{ name = "Osmo Salomaa", email = "otsaloma@iki.fi" }]
 dependencies = ["attd>=0.3", "numpy>=2.0,<3.0", "pyarrow>=2.0", "wcwidth>=0.1"]