dppd 0.26__tar.gz → 0.30__tar.gz

{dppd-0.26 → dppd-0.30}/LICENSE.txt

@@ -1,6 +1,6 @@
 The MIT License (MIT)
 
-Copyright (c) 2018 Florian Finkernagel
+Copyright (c) 2025 Florian Finkernagel
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

{dppd-0.26/src/dppd.egg-info → dppd-0.30}/PKG-INFO

@@ -1,20 +1,28 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: dppd
-Version: 0.26
+Version: 0.30
 Summary: A pythonic dplyr clone
-Home-page: https://github.com/TyberiusPrime/dppd
-Author: Florian Finkernagel
-Author-email: finkernagel@imt.uni-marburg.de
-License: mit
-Platform: any
-Classifier: Development Status :: 4 - Beta
-Classifier: Programming Language :: Python
-Requires-Python: >=3.6
+Author-email: Florian Finkernagel <finkernagel@imt.uni-marburg.de>
+License-Expression: MIT
+Project-URL: Documentation, https://dppd.readthedocs.io/en/latest/
+Project-URL: Repository, https://github.com/TyberiusPrime/dppd
+Requires-Python: >=3.9
 Description-Content-Type: text/markdown
-Provides-Extra: testing
-Provides-Extra: doc
 License-File: LICENSE.txt
 License-File: AUTHORS.rst
+Requires-Dist: natsort
+Requires-Dist: numpy
+Requires-Dist: pandas>=2
+Requires-Dist: wrapt
+Provides-Extra: dev
+Requires-Dist: build; extra == "dev"
+Requires-Dist: numpydoc; extra == "dev"
+Requires-Dist: plotnine; extra == "dev"
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: sphinx; extra == "dev"
+Requires-Dist: sphinx-bootstrap-theme; extra == "dev"
+Dynamic: license-file
 
 # dppd
 

dppd-0.30/pyproject.toml

@@ -0,0 +1,57 @@
+[project]
+name = "dppd"
+version = "0.30"
+description = "A pythonic dplyr clone"
+readme = "README.md"
+requires-python = ">=3.9"
+authors = [
+	{name = "Florian Finkernagel", email = "finkernagel@imt.uni-marburg.de"}
+]
+license="MIT"
+dependencies = [
+    "natsort",
+    "numpy",
+	"pandas>=2",
+    "wrapt",
+]
+
+[project.urls]
+Documentation = "https://dppd.readthedocs.io/en/latest/"
+Repository = "https://github.com/TyberiusPrime/dppd"
+
+[build-system]
+requires = ["setuptools >= 61.0"]
+build-backend = "setuptools.build_meta"
+
+[project.optional-dependencies]
+	dev = [
+	"build",
+    "numpydoc",
+	"plotnine",
+    "pytest",
+    "pytest-cov",
+    "sphinx",
+    "sphinx-bootstrap-theme",
+]
+
+[tool.pytest.ini_options]
+# Options for py.test:
+# Specify command line options as you would do when invoking py.test directly.
+# e.g. --cov-report html (or xml) for html/xml output or --junitxml junit.xml
+# in order to write a coverage file that can be read by Jenkins.
+addopts = """
+    --cov dppd --cov-report term-missing
+    --verbose
+"""
+norecursedirs = [
+    "dist",
+    "build",
+    ".tox",
+]
+testpaths = "tests"
+filterwarnings = [
+    "ignore:::statsmodels.base.wrapper:100",
+    "ignore:::patsy.constraint:13",
+    "ignore:::matplotlib.backends.backend_wx:",
+]
+

dppd-0.30/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

{dppd-0.26 → dppd-0.30}/src/dppd/__init__.py

@@ -4,6 +4,6 @@ from .base import dppd, register_verb, register_type_methods_as_verbs
 from . import single_verbs  # noqa:F401
 from . import non_df_verbs  # noqa:F401
 
-__version__ = "0.26"
+__version__ = "0.30"
 
 __all_ = [dppd, register_verb, register_type_methods_as_verbs, __version__]

{dppd-0.26 → dppd-0.30}/src/dppd/single_verbs.py

@@ -23,14 +23,20 @@ register_type_methods_as_verbs(SeriesGroupBy, [])
 
 
 def group_variables(grp):
-    return grp.grouper.names
+    if hasattr(grp, "_grouper"):
+        return grp._grouper.names
+    else:
+        return grp.grouper.names
 
 
 def group_extract_params(grp):
-    if grp.axis != 0:
+    if hasattr(grp, "axis") and grp.axis != 0:
         raise ValueError(f"Verbs assume that groupby is on axis=0, was {grp.axis}")
     res = {"by": group_variables(grp)}
-    for k in ["squeeze", "axis", "level", "as_index", "sort", "group_keys", "observed"]:
+    attrs = ["squeeze", "level", "as_index", "sort", "group_keys", "observed"]
+    if pd.__version__ < "2.1.":
+        attrs.append("axis")
+    for k in attrs:
         if hasattr(grp, k):
             res[k] = getattr(grp, k)
         else:  # pragma: no cover
@@ -56,7 +62,10 @@ def _print(obj):
 @register_verb(name="debug", types=None)
 def _debug(obj, k=5):
     d = obj.iloc[np.r_[0:k, -k:0]]
-    print(d)
+    try:
+        display(d)  # noqa: F821 - Jupyter only, needs to import.
+    except NameError:
+        print(d)
     return obj
 
 
@@ -354,9 +363,12 @@ def mutate_DataFrameGroupBy(grp, **kwargs):
                 try:
                     r = v[group_key]
                 except KeyError:
-                    raise KeyError(
-                        f"Grouped mutate results did not contain data for {group_key}"
-                    )
+                    try:
+                        r = v[group_key,]
+                    except KeyError:
+                        raise KeyError(
+                            f"Grouped mutate results did not contain data for {group_key}. Keys where {v.keys()}"
+                        )
                 r = pd.Series(r, index=sub_index)
                 parts.append(r)
             parts = pd.concat(parts)
@@ -451,7 +463,10 @@ def filter_by(obj, filter_arg):
         for idx, sub_df in df.groupby(groups):
             # if not idx in filter_arg and not isinstance(tuple(idx)):
             # idx = (idx,)
-            keep = filter_arg[idx]
+            try:
+                keep = filter_arg[idx]
+            except KeyError:
+                keep = filter_arg[idx[0]]
             parts.append(sub_df[keep])
         result = pd.concat(parts, axis=0)
     elif isinstance(filter_arg, str):
@@ -543,7 +558,7 @@ def summarize(obj, *args):
         result = result[groups + [x for x in result.columns if x not in groups]]
         # restore category to categories
         for g in groups:
-            if pd.api.types.is_categorical_dtype(df[g]):
+            if isinstance(df.dtypes[g], pd.CategoricalDtype):
                 result = result.assign(
                     **{
                         g: pd.Categorical(
@@ -603,7 +618,7 @@ def do(obj, func, *args, **kwargs):
         result = result[groups + [x for x in result.columns if x not in groups]]
         # restore category to categories
         for g in groups:
-            if pd.api.types.is_categorical_dtype(df[g]):
+            if isinstance(df.dtypes[g], pd.CategoricalDtype):
                 result = result.assign(
                     **{
                         g: pd.Categorical(
@@ -767,7 +782,10 @@ def seperate(df, column, new_names, sep=".", remove=False):
 
 @register_verb("print", types=DataFrameGroupBy)
 def print_DataFrameGroupBy(grps):
-    print("groups: %s" % (grps.grouper.names))
+    if hasattr(grps, "_grouper"):
+        print("groups: %s" % (grps._grouper.names))
+    else:
+        print("groups: %s" % (grps.grouper.names))
     print(grps._selected_obj)
     return grps
 
@@ -809,7 +827,7 @@ def arrange_DataFrameGroupBy(grp, column_spec, kind="quicksort", na_position="la
     columns = grp_params["by"].copy()
     ascending = [True] * len(columns)
     columns += [x[0] for x in cols_plus_inversed]
-    ascending += [~x[1] for x in cols_plus_inversed]
+    ascending += [not x[1] for x in cols_plus_inversed]
     df_out = df.sort_values(
         columns, ascending=ascending, kind=kind, na_position=na_position
     )
@@ -939,7 +957,7 @@ def to_frame_dict(d, **kwargs):
 
 
 @register_verb("norm_0_to_1", types=pd.DataFrame)
-def norm_0_to_1(df, axis=1):
+def norm_0_to_1(df, axis=1, keep_nan=False):
     """Normalize a (numeric) data frame so that
     it goes from 0 to 1 in each row (axis=1) or column (axis=0)
     Usefully for PCA, correlation, etc. because then
@@ -951,7 +969,11 @@ def norm_0_to_1(df, axis=1):
         a1 = 0
         a2 = 1
     df_normed = df.sub(df.min(axis=a1), axis=a2)
-    df_normed = df.div(df.max(axis=a1), axis=a2)
+    assert df_normed.min().min() == 0.0
+    df_normed = df_normed.div(df_normed.max(axis=a1), axis=a2)
+    assert df_normed.max().max() == 1.0
+    if not keep_nan:
+        df_normed = df_normed[~pd.isnull(df_normed).any(axis=1)]
     return df_normed
 
 
@@ -1000,7 +1022,12 @@ def pca_dataframe(df, whiten=False, random_state=None, n_components=2):
 
     p = PCA(n_components=n_components, whiten=whiten, random_state=random_state)
     df_fit = pd.DataFrame(p.fit_transform(df))
-    df_fit.columns = ["1st", "2nd"]
+    cols = ["1st", "2nd"]
+    if n_components > 2:
+        cols.append("3rd")
+    for ii in range(3, n_components):
+        cols.append(f"{ii+1}th")
+    df_fit.columns = cols
     df_fit.index = df.index
     df_fit.index.name = "sample"
     df_fit = df_fit.reset_index()
@@ -1012,7 +1039,6 @@ def pca_dataframe(df, whiten=False, random_state=None, n_components=2):
 
 @register_verb("insert", types=pd.DataFrame, ignore_redefine=True)
 def insert_return_self(df, loc, column, value, **kwargs):
-    """DataFrame.insert, but return self.
-    """
+    """DataFrame.insert, but return self."""
     df.insert(loc, column, value, **kwargs)
     return df

{dppd-0.26 → dppd-0.30/src/dppd.egg-info}/PKG-INFO

@@ -1,20 +1,28 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: dppd
-Version: 0.26
+Version: 0.30
 Summary: A pythonic dplyr clone
-Home-page: https://github.com/TyberiusPrime/dppd
-Author: Florian Finkernagel
-Author-email: finkernagel@imt.uni-marburg.de
-License: mit
-Platform: any
-Classifier: Development Status :: 4 - Beta
-Classifier: Programming Language :: Python
-Requires-Python: >=3.6
+Author-email: Florian Finkernagel <finkernagel@imt.uni-marburg.de>
+License-Expression: MIT
+Project-URL: Documentation, https://dppd.readthedocs.io/en/latest/
+Project-URL: Repository, https://github.com/TyberiusPrime/dppd
+Requires-Python: >=3.9
 Description-Content-Type: text/markdown
-Provides-Extra: testing
-Provides-Extra: doc
 License-File: LICENSE.txt
 License-File: AUTHORS.rst
+Requires-Dist: natsort
+Requires-Dist: numpy
+Requires-Dist: pandas>=2
+Requires-Dist: wrapt
+Provides-Extra: dev
+Requires-Dist: build; extra == "dev"
+Requires-Dist: numpydoc; extra == "dev"
+Requires-Dist: plotnine; extra == "dev"
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Requires-Dist: sphinx; extra == "dev"
+Requires-Dist: sphinx-bootstrap-theme; extra == "dev"
+Dynamic: license-file
 
 # dppd
 

{dppd-0.26 → dppd-0.30}/src/dppd.egg-info/SOURCES.txt

@@ -1,8 +1,7 @@
 AUTHORS.rst
 LICENSE.txt
 README.md
-setup.cfg
-setup.py
+pyproject.toml
 src/dppd/__init__.py
 src/dppd/base.py
 src/dppd/column_spec.py
@@ -11,6 +10,10 @@ src/dppd/single_verbs.py
 src/dppd.egg-info/PKG-INFO
 src/dppd.egg-info/SOURCES.txt
 src/dppd.egg-info/dependency_links.txt
-src/dppd.egg-info/not-zip-safe
 src/dppd.egg-info/requires.txt
-src/dppd.egg-info/top_level.txt
+src/dppd.egg-info/top_level.txt
+tests/test_base.py
+tests/test_pandas_forwards.py
+tests/test_reshaping.py
+tests/test_select.py
+tests/test_single_verbs.py

{dppd-0.26 → dppd-0.30}/src/dppd.egg-info/requires.txt

@@ -1,17 +1,13 @@
-pandas>=0.22
-numpy
 natsort
+numpy
+pandas>=2
 wrapt
 
-[doc]
-sphinx
-sphinx-bootstrap-theme
+[dev]
+build
 numpydoc
-pandas
-
-[testing]
+plotnine
 pytest
 pytest-cov
-plotnine
-pandas<2.0
-flake8
+sphinx
+sphinx-bootstrap-theme