dukit 0.2.7__tar.gz → 0.3.1__tar.gz

{dukit-0.2.7 → dukit-0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dukit
-Version: 0.2.7
+Version: 0.3.1
 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

dukit-0.3.1/pyproject.toml

@@ -0,0 +1,48 @@
+[project]
+name = "dukit"
+version = "0.3.1"
+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-0.2.7/pyproject.toml → dukit-0.3.1/pyproject.toml.orig

@@ -1,6 +1,6 @@
 [project]
 name = "dukit"
-version = "0.2.7"
+version = "0.3.1"
 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-0.2.7 → dukit-0.3.1}/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-0.2.7 → dukit-0.3.1}/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)
@@ -1577,8 +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.'
@@ -1602,7 +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-0.2.7 → dukit-0.3.1}/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
 

{dukit-0.2.7 → dukit-0.3.1}/src/dukit/pandas.py

@@ -442,7 +442,7 @@ def compose(
 
     col_new = df[cols].apply(lambda row: template.format(*row), axis='columns')
     df.insert(pos, col, col_new)
-    df.drop(columns=cols, inplace=True)
+    df = df.drop(columns=cols)
 
     return df
 
@@ -550,7 +550,7 @@ def stack(
     _stack_check_uid_unique1(df, uid, verbosity)
 
     uid_old = ensure_unique_string(uid, df.columns)
-    df.set_index(uid, inplace=True)
+    df = df.set_index(uid)
     df.index.name = uid_old
     cols_keep = list_(cols_keep)
     cols_stack = [col for col in df.columns if col not in cols_keep]
@@ -577,32 +577,30 @@ def stack(
     _stack_check_successfull_match(not_matched, verbosity)
 
     for subid_val in subdfs.keys():
-        subdf = subdfs[subid_val]
         if dropna:
-            subdf.dropna(
-                inplace=True,
-                how='all',
-                )
+            subdfs[subid_val] = subdfs[subid_val].dropna(how='all')
         uid_vals = [
             uid_template.format(uid=uid_old, subid=subid_val)
-            for uid_old in subdf.index
+            for uid_old in subdfs[subid_val].index
             ]
-        subdf.insert(0, uid, uid_vals)
+        subdfs[subid_val].insert(0, uid, uid_vals)
 
+    df_keep = df[cols_keep].reset_index()
     df_new = pd.concat(list(subdfs.values()), axis='index')
+    df_new = df_new.reset_index()
     df_new = pd.merge(
-        df[cols_keep].reset_index(),
-        df_new.reset_index(),
+        df_keep,
+        df_new,
         on=uid_old,
         how='right',
         )
-    df_new.drop(columns=[uid_old], inplace=True)
+    df_new = df_new.drop(columns=[uid_old])
 
     _stack_check_missed_values(df_new, uid, cols_keep, non_na_vals, verbosity)
 
     if sort:
-        df_new.sort_values(by=uid, inplace=True)
-    df_new.reset_index(drop=True, inplace=True)
+        df_new = df_new.sort_values(by=uid)
+    df_new = df_new.reset_index(drop=True)
  
     _stack_check_uid_unique2(uid, verbosity, df_new)
 
@@ -678,9 +676,9 @@ def unstack(
     _unstack_check_successfull_extraction(df, uid, ids, expected_cols, verbosity)
 
 
-    ids.set_index('uid', inplace=True)
+    ids = ids.set_index('uid')
     df[uid] = ids.index
-    df.set_index(uid, inplace=True)
+    df = df.set_index(uid)
     subid_col = ids['subid']
     subid_vals = subid_col.unique()
     cols_keep = list_(cols_keep)
@@ -720,9 +718,9 @@ def unstack(
             how='left'
             )
 
-    _unstack_check_missed_values(uid, cols_keep, verbosity, non_na_vals, df_new)
+    _unstack_check_missed_values(df_new, uid, cols_keep, non_na_vals, verbosity)
 
-    df_new.reset_index(inplace=True)
+    df_new = df_new.reset_index()
 
     return df_new
 
@@ -762,22 +760,22 @@ def _unstack_check_successfull_extraction(df, uid, ids, expected_cols, verbosity
             log(msg, 'dk.pandas.unstack', verbosity)
 
 
-def _unstack_check_missed_values(uid, cols_keep, verbosity, non_na_vals1, df_new):
+def _unstack_check_missed_values(df_new, uid, cols_keep, non_na_vals, verbosity):
     cols_stacked = [
         col for col
         in df_new.columns
         if col not in cols_keep + [uid]
         ]
-    non_na_vals2 = int(
+    non_na_vals_new = int(
         df_new[cols_stacked]
         .notna()
         .sum()
         .sum()
         )
-    if non_na_vals1 != non_na_vals2:
+    if non_na_vals != non_na_vals_new:
         msg = (
             'WARNING: Non-NA value mismatch: '
-            f'before={non_na_vals1}, after={non_na_vals2}'
+            f'before={non_na_vals}, after={non_na_vals_new}'
             )
         log(msg, 'dk.pandas.unstack', verbosity)
 
@@ -809,8 +807,8 @@ def transpose(
     df = df.T
     df.columns = cols_new
     df.insert(0, header, cols_old)
-    df.drop(header, axis=0, inplace=True)
-    df.reset_index(drop=True, inplace=True)
+    df = df.drop(header, axis=0)
+    df = df.reset_index(drop=True)
 
     return df
 
@@ -857,10 +855,10 @@ def date_delta(
 
     for col in df_dates.columns:
         if df_dates[col].isna().all():
-            df_dates.drop(columns=col, inplace=True)
+            df_dates = df_dates.drop(columns=col)
         else:
             cols_dates.append(col)
-            df.drop(columns=col, inplace=True)
+            df = df.drop(columns=col)
 
     df = pd.concat([df, df_dates], axis=1)[cols_all]
 
@@ -942,7 +940,7 @@ def date_table(
                 msg = f'WARNING: no dates found in reference col "{reference_col}"'
                 log(msg, 'dk.date_delta', verbosity)
             else:
-                df.drop(columns=col, inplace=True)
+                df = df.drop(columns=col)
 
     reference = df[reference_col].apply(date_).apply(_fix_nas)
 
@@ -1088,7 +1086,7 @@ def split_col(
     pos = df.columns.get_loc(col)
     splits = df[col].str.partition(sep)
 
-    df.drop(columns=[col], inplace=True)
+    df = df.drop(columns=[col])
     if new1 is None:
         new1 = col
     elif new1 in df.columns:
@@ -1123,7 +1121,7 @@ def collapse(
     df = df.map(lambda x: _to_lines(x, template_item))
     df.columns = [template_col.format(colname=col) for col in df.columns]
     df.insert(0, on, df.index)
-    df.reset_index(drop=True, inplace=True)
+    df = df.reset_index(drop=True)
     return df
 
 
@@ -1253,7 +1251,7 @@ def flatten(
 
     df = df[cols_new]
     df.insert(0, on, df.index)
-    df.reset_index(drop=True, inplace=True)
+    df = df.reset_index(drop=True)
 
     return df
 
@@ -1311,7 +1309,7 @@ def stagger(
             col_new.name = template.format(counter=i + 1, colname=col)
             df_new = pd.concat([df_new, col_new], axis=1)
 
-    df_new.reset_index(drop=True, inplace=True)
+    df_new = df_new.reset_index(drop=True)
 
     return df_new
 

{dukit-0.2.7 → dukit-0.3.1}/src/dukit/qlang/symbols.py

@@ -2879,7 +2879,7 @@ class GetIsNA(Symbol):
         if 'strict' in self.flags:
             mask = series.isna()
         else:
-            mask = series.apply(lambda x: na_(x, errors='X')) != 'X'
+            mask = series.apply(lambda x: na_(x, errors='X')).isna()
         return mask
 
 
@@ -5111,7 +5111,7 @@ class SetToYN(Symbol):
             args: list,
             q: Query,
             ) -> pd.Series:
-        series_new = series[mask].apply(yn_).convert_dtypes()
+        series_new = series[mask].apply(yn_).astype('string')
         if mask.all():
             series = series_new
         else: