dukit 0.2.6__tar.gz → 0.3.0__tar.gz

{dukit-0.2.6 → dukit-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dukit
-Version: 0.2.6
+Version: 0.3.0
 Summary: dukit - data utilities kit for exploring, modifying and visualizing small but messy data using pandas
 Keywords: pandas,query,utility,data,diff
 Author: MartinVoelkl94
@@ -10,7 +10,8 @@ Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
 Requires-Dist: ipython>=9.15.0
 Requires-Dist: jinja2>=3.1.6
-Requires-Dist: pandas>=3.0.3
+Requires-Dist: openpyxl>=3.1.5
+Requires-Dist: pandas>=3.1.0
 Requires-Python: >=3.14
 Project-URL: Repository, https://github.com/MartinVoelkl94/dukit
 Description-Content-Type: text/markdown
@@ -89,8 +90,8 @@ these functions offer various ways to deal with non-unique keys/ids.
 primarily used when merging 2 dfs with a one-to-many relationship.
 
 available functions:
-- df.dk.flatten()
-- df.dk.stagger()
+- df.dk.stack()
+- df.dk.unstack()
 - df.dk.embed()
 - df.dk.collapse()
 <br>

{dukit-0.2.6 → dukit-0.3.0}/README.md

@@ -72,8 +72,8 @@ these functions offer various ways to deal with non-unique keys/ids.
 primarily used when merging 2 dfs with a one-to-many relationship.
 
 available functions:
-- df.dk.flatten()
-- df.dk.stagger()
+- df.dk.stack()
+- df.dk.unstack()
 - df.dk.embed()
 - df.dk.collapse()
 <br>

dukit-0.3.0/pyproject.toml

@@ -0,0 +1,48 @@
+[project]
+name = "dukit"
+version = "0.3.0"
+description = "dukit - data utilities kit for exploring, modifying and visualizing small but messy data using pandas"
+readme = "README.md"
+license = "MIT"
+requires-python = ">=3.14"
+classifiers = [
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 3",
+]
+keywords = [
+    "pandas",
+    "query",
+    "utility",
+    "data",
+    "diff",
+]
+dependencies = [
+    "ipython>=9.15.0",
+    "jinja2>=3.1.6",
+    "openpyxl>=3.1.5",
+    "pandas>=3.1.0",
+]
+
+[[project.authors]]
+name = "MartinVoelkl94"
+email = "martinv16248@gmail.com"
+
+[project.urls]
+Repository = "https://github.com/MartinVoelkl94/dukit"
+
+[build-system]
+requires = ["uv_build>=0.10.9,<0.11.0"]
+build-backend = "uv_build"
+
+[dependency-groups]
+dev = [
+    "faker>=40.28.1",
+    "flake8>=7.3.0",
+    "ipykernel>=7.3.0",
+    "ipywidgets>=8.1.8",
+    "pip>=26.1.2",
+    "pylance>=8.0.0",
+    "pytest>=9.2.0",
+    "pytest-cov>=7.1.0",
+    "viztracer>=1.1.1",
+]

dukit-0.2.6/pyproject.toml → dukit-0.3.0/pyproject.toml.orig

@@ -1,6 +1,6 @@
 [project]
 name = "dukit"
-version = "0.2.6"
+version = "0.3.0"
 description = "dukit - data utilities kit for exploring, modifying and visualizing small but messy data using pandas"
 readme = "README.md"
 authors = [{ name = "MartinVoelkl94", email = "martinv16248@gmail.com" }]
@@ -20,7 +20,8 @@ keywords = [
 dependencies = [
     "ipython>=9.15.0",
     "jinja2>=3.1.6",
-    "pandas>=3.0.3",
+    "openpyxl>=3.1.5",
+    "pandas>=3.1.0",
 ]
 
 
@@ -39,10 +40,9 @@ dev = [
     "flake8>=7.3.0",
     "ipykernel>=7.3.0",
     "ipywidgets>=8.1.8",
-    "openpyxl>=3.1.5",
     "pip>=26.1.2",
     "pylance>=8.0.0",
-    "pytest>=9.1.1",
+    "pytest>=9.2.0",
     "pytest-cov>=7.1.0",
     "viztracer>=1.1.1",
 ]

{dukit-0.2.6 → dukit-0.3.0}/src/dukit/__init__.py

@@ -24,20 +24,24 @@ from .excel import (
     save,
     )
 from .pandas import (
-    collapse,
+    compose,
+    decompose,
+    stack,
+    unstack,
+    transpose,
     date_delta,
     date_table,
     deduplicate,
-    embed,
-    flatten,
     get_df,
     get_df_patients,
     get_df_medications,
     get_df_old,
     get_df_new,
-    stagger,
-    transpose,
     split_col,
+    embed,
+    collapse,
+    stagger,
+    flatten,
     )
 from .os import (
     cd,
@@ -89,20 +93,24 @@ __all__ = (
     'format',
     'save',
 
-    'collapse',
+    'compose',
+    'decompose',
+    'stack',
+    'unstack',
+    'transpose',
     'date_delta',
     'date_table',
     'deduplicate',
-    'embed',
-    'flatten',
     'get_df',
     'get_df_patients',
     'get_df_medications',
     'get_df_old',
     'get_df_new',
-    'stagger',
-    'transpose',
     'split_col',
+    'embed',
+    'collapse',
+    'stagger',
+    'flatten',
 
     'cd',
     'cp',

{dukit-0.2.6 → dukit-0.3.0}/src/dukit/_test_utils.py

@@ -63,7 +63,7 @@ def _get_expected_new():
     expected.loc['x2', 'a'] = 1
     expected.loc['z', 'a'] = pd.NA
 
-    expected.reset_index(drop=True, inplace=True)
+    expected = expected.reset_index(drop=True)
 
     return expected.convert_dtypes()
 
@@ -107,7 +107,7 @@ def _get_expected_newplus():
     expected.loc['z', 'a *old'] = 3
 
     expected['b *old'] = expected['b *old'].astype('Int64')
-    expected.reset_index(drop=True, inplace=True)
+    expected = expected.reset_index(drop=True)
 
     return expected.convert_dtypes()
 
@@ -142,7 +142,7 @@ def _get_expected_old():
     expected.loc['y', 'c'] = 2
     expected.loc['z', 'c'] = 3
 
-    expected.reset_index(drop=True, inplace=True)
+    expected = expected.reset_index(drop=True)
 
     return expected.convert_dtypes()
 
@@ -187,7 +187,7 @@ def _get_expected_mix():
     expected.loc['z', 'c'] = 3
     expected.loc['x', 'c'] = 1
 
-    expected.reset_index(drop=True, inplace=True)
+    expected = expected.reset_index(drop=True)
 
     return expected.convert_dtypes()
 
@@ -218,7 +218,7 @@ def _get_expected_style_new():
     expected.loc['x2', 'a'] = f'background-color: {GREEN};'
     expected.loc['z', 'a'] = f'background-color: {RED_LIGHT};'
 
-    expected.reset_index(drop=True, inplace=True)
+    expected = expected.reset_index(drop=True)
 
     return expected.convert_dtypes()
 
@@ -256,7 +256,7 @@ def _get_expected_style_newplus():
     expected.loc['x2', 'a *old'] = f'font-style: italic;background-color: {GREEN};'
     expected.loc['z', 'a *old'] = 'font-style: italic;'
 
-    expected.reset_index(drop=True, inplace=True)
+    expected = expected.reset_index(drop=True)
 
     return expected.convert_dtypes()
 
@@ -286,7 +286,7 @@ def _get_expected_style_old():
     expected.loc['y', 'c'] = f'background-color: {RED};'
     expected.loc['z', 'c'] = f'background-color: {RED};'
 
-    expected.reset_index(drop=True, inplace=True)
+    expected = expected.reset_index(drop=True)
 
     return expected.convert_dtypes()
 
@@ -325,6 +325,6 @@ def _get_expected_style_mix():
     expected.loc['z', 'c'] = f'background-color: {RED};'
 
 
-    expected.reset_index(drop=True, inplace=True)
+    expected = expected.reset_index(drop=True)
 
     return expected.convert_dtypes()

{dukit-0.2.6 → dukit-0.3.0}/src/dukit/diffing.py

@@ -1058,15 +1058,15 @@ def _set_uid(d: Diff, uid: typing.Any) -> Diff:
             )
         d.old.index = d.old[uid]
         d.new.index = d.new[uid]
-        d.old.drop(columns=uid, inplace=True)
-        d.new.drop(columns=uid, inplace=True)
+        d.old = d.old.drop(columns=uid)
+        d.new = d.new.drop(columns=uid)
         d.uid = uid
 
     elif uid in d.old.columns and uid in d.new.columns:
         d.old.index = d.old[uid]
         d.new.index = d.new[uid]
-        d.old.drop(columns=uid, inplace=True)
-        d.new.drop(columns=uid, inplace=True)
+        d.old = d.old.drop(columns=uid)
+        d.new = d.new.drop(columns=uid)
         d.uid = uid
 
     else:
@@ -1295,7 +1295,7 @@ def _create_meta_cols(d: Diff) -> Diff:
 
     df_meta = values.loc[:, col_mapping.keys()].copy()
     df_meta.loc[:, :] = pd.NA
-    df_meta.rename(columns=col_mapping, inplace=True)
+    df_meta = df_meta.rename(columns=col_mapping)
 
     data = {
         colname: ['font-style: italic;'] * len(values.index)
@@ -1498,15 +1498,26 @@ def _add_retained_cols(d: Diff) -> Diff:
 
     idx_shared = d._values.index.intersection(d._cols_retained.index)
     df_retained = d._cols_retained.loc[idx_shared, :]
-    d._values = pd.concat([df_retained, d._values], axis='columns')
+    d._values = pd.merge(
+        df_retained,
+        d._values,
+        left_index=True,
+        right_index=True,
+        how='right',
+        )
 
     df_style = pd.DataFrame(
         data='',
         index=df_retained.index,
         columns=df_retained.columns,
         )
-    d._style = pd.concat([df_style, d._style], axis='columns')
-
+    d._style = pd.merge(
+        df_style,
+        d._style,
+        left_index=True,
+        right_index=True,
+        how='right',
+        )
     return d
 
 
@@ -1566,8 +1577,8 @@ def _reset_index(d: Diff) -> Diff:
 
     index_diff = d._values.index.difference(d._style.index)
     if index_diff.empty:
-        d._values.reset_index(drop=True, inplace=True)
-        d._style.reset_index(drop=True, inplace=True)
+        d._values = d._values.reset_index(drop=True)
+        d._style = d._style.reset_index(drop=True)
     else:
         msg = (
             'ERROR: index of values and style dfs do not match.'
@@ -1591,7 +1602,7 @@ def _apply_style(d: Diff) -> Diff:
             )
         log(msg, context, d.verbosity)
 
-    d._style.fillna('', inplace=True)
+    d._style = d._style.fillna('')
     d.result = (
         d._values
         .style

{dukit-0.2.6 → dukit-0.3.0}/src/dukit/interfaces.py

@@ -9,13 +9,15 @@ from .qlang import (
     qs,
     )
 from .pandas import (
+    compose,
+    decompose,
+    stack,
+    unstack,
+    transpose,
     date_delta,
     date_table,
     collapse,
     embed,
-    flatten,
-    stagger,
-    transpose,
     split_col,
     )
 
@@ -55,6 +57,124 @@ class DukitAccessor():
         return qr(self.df, code, verbosity)
 
 
+    def compose(
+            self,
+            col: str,
+            cols: list[str],
+            template='{0}_{1}',
+            verbosity=3,
+            ):
+        return compose(
+            self.df,
+            col=col,
+            cols=cols,
+            template=template,
+            verbosity=verbosity,
+            )
+
+
+    def stack(
+            self,
+            uid: str,
+            col_pattern: str = r'(?P<col>.+)_(?P<subid>.+)',
+            uid_template: str = '{uid}_{subid}',
+            cols_keep: list[str] | None = None,
+            dropna: bool = True,
+            sort: bool = True,
+            verbosity: int = 3,
+            ) -> pd.DataFrame:
+        df_new = stack(
+            self.df,
+            uid=uid,
+            col_pattern=col_pattern,
+            uid_template=uid_template,
+            cols_keep=cols_keep,
+            dropna=dropna,
+            sort=sort,
+            verbosity=verbosity,
+            )
+        return df_new
+
+
+    def unstack(
+            self,
+            uid: str,
+            uid_pattern: str = r'(?P<uid>.+)_(?P<subid>.+)',
+            col_template: str = '{col}_{subid}',
+            cols_keep: list[str] | None = None,
+            stagger: bool = True,
+            verbosity: int = 3,
+            ) -> pd.DataFrame:
+        df_new = unstack(
+            self.df,
+            uid=uid,
+            uid_pattern=uid_pattern,
+            col_template=col_template,
+            cols_keep=cols_keep,
+            stagger=stagger,
+            verbosity=verbosity
+            )
+        return df_new
+
+
+    def transpose(
+            self,
+            header='uid',
+            ) -> pd.DataFrame:
+        df_new = transpose(
+            self.df,
+            header=header,
+            )
+        return df_new
+
+
+    def save(
+            self,
+            path: str,
+            sheet_name='df',
+            index=False,
+            format_excel=True,
+            freeze_panes='B2',
+            hide_sheets=None,
+            hide_cols=None,
+            col_width_max=70,
+            col_width_padding=2,
+            align_vertical='top',
+            align_horizontal='left',
+            wrap_text=True,
+            **kwargs,
+            ):
+        save(
+            df=self.df,
+            path=path,
+            sheet_name=sheet_name,
+            index=index,
+            format_excel=format_excel,
+            freeze_panes=freeze_panes,
+            hide_sheets=hide_sheets,
+            hide_cols=hide_cols,
+            col_width_max=col_width_max,
+            col_width_padding=col_width_padding,
+            align_vertical=align_vertical,
+            align_horizontal=align_horizontal,
+            wrap_text=wrap_text,
+            **kwargs,
+            )
+        return None
+
+
+    def style(self):
+        code = r"""
+        .replace("\n", "<br>")
+        .wrap(normal)
+        .mono()
+        .align(left)
+        %.align(center)
+        """
+        df_styled = qs(self.df, code)
+        return df_styled
+
+
     def date_delta(
             self,
             reference_date: str | datetime.date | pd.Timestamp = None,
@@ -135,45 +255,6 @@ class DukitAccessor():
         return df_new
 
 
-    def flatten(
-            self,
-            on: str,
-            template='{colname}_#{counter}',
-            ):
-        df_new = flatten(
-            self.df,
-            on=on,
-            template=template,
-            )
-        return df_new
-
-
-    def stagger(
-            self,
-            on: str,
-            template='#{counter}_{colname}',
-            separator_col='#{counter}',
-            ):
-        df_new = stagger(
-            self.df,
-            on=on,
-            template=template,
-            separator_col=separator_col,
-            )
-        return df_new
-
-
-    def transpose(
-            self,
-            header='uid',
-            ) -> pd.DataFrame:
-        df_new = transpose(
-            self.df,
-            header=header,
-            )
-        return df_new
-
-
     def split_col(
             self,
             col: str = 'uid',
@@ -189,50 +270,3 @@ class DukitAccessor():
             new2=new2,
             )
         return df_new
-
-
-    def save(
-            self,
-            path: str,
-            sheet_name='df',
-            index=False,
-            format_excel=True,
-            freeze_panes='B2',
-            hide_sheets=None,
-            hide_cols=None,
-            col_width_max=70,
-            col_width_padding=2,
-            align_vertical='top',
-            align_horizontal='left',
-            wrap_text=True,
-            **kwargs,
-            ):
-        save(
-            df=self.df,
-            path=path,
-            sheet_name=sheet_name,
-            index=index,
-            format_excel=format_excel,
-            freeze_panes=freeze_panes,
-            hide_sheets=hide_sheets,
-            hide_cols=hide_cols,
-            col_width_max=col_width_max,
-            col_width_padding=col_width_padding,
-            align_vertical=align_vertical,
-            align_horizontal=align_horizontal,
-            wrap_text=wrap_text,
-            **kwargs,
-            )
-        return None
-
-
-    def style(self):
-        code = r"""
-        .replace("\n", "<br>")
-        .wrap(normal)
-        .mono()
-        .align(left)
-        %.align(center)
-        """
-        df_styled = qs(self.df, code)
-        return df_styled

{dukit-0.2.6 → dukit-0.3.0}/src/dukit/os.py

@@ -101,7 +101,7 @@ def ls(path='', recursive=False) -> pd.DataFrame:
             )
         )
 
-    files.drop(columns='_path', inplace=True)
+    files = files.drop(columns='_path')
 
     return files