showstats 0.0.1__tar.gz

showstats-0.0.1/.github/workflows/lint.yaml

@@ -0,0 +1,27 @@
+name: Lint
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.11.9"
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install ruff
+
+      - name: Run Ruff
+        run: ruff check .

showstats-0.0.1/.github/workflows/pytest.yaml

@@ -0,0 +1,25 @@
+name: Python Tests
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11.9"
+          cache: "pip" # caching pip dependencies
+      - run: |
+          pip install -r dev-requirements.txt
+          pip install pytest
+
+      - name: Run tests
+        run: pytest -v -m "not integration"

showstats-0.0.1/.gitignore

@@ -0,0 +1,185 @@
+# Data
+/data/*
+!/data/*/
+/data/*/*
+!/data/*/.gitkeep
+!/data/README.md
+
+# Mac OS-specific storage files
+.DS_Store
+
+# vim
+*.swp
+*.swo
+
+## https://github.com/github/gitignore/blob/4488915eec0b3a45b5c63ead28f286819c0917de/Python.gitignore
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# MkDocs documentation
+docs/site/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+
+# Figures
+references/figures/*
+!references/figures/.gitkeep
+.vscode/settings.json
+
+src/experiments.py
+.python-version

showstats-0.0.1/.pre-commit-config.yaml

@@ -0,0 +1,19 @@
+repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.5.0
+    hooks:
+      - id: ruff
+        types_or: [python, pyi, jupyter]
+        args: [--fix]
+      - id: ruff-format
+        types_or: [python, pyi, jupyter]
+
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0 # Updated to the latest version you mentioned
+    hooks:
+      - id: check-added-large-files
+        args: ["--maxkb=2000"]
+      - id: trailing-whitespace
+        exclude: ".*(.csv|.txt)$"
+      - id: end-of-file-fixer
+        exclude: ".*(.csv|.txt)$"

showstats-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Matthias Kaeding
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

showstats-0.0.1/Makefile

@@ -0,0 +1,72 @@
+# Targets
+
+## Install Python Dependencies
+.PHONY: reqs
+reqs:
+	uv pip install -r dev-requirements.txt
+
+## Delete all compiled Python files
+.PHONY: clean
+clean:
+	find . -type f -name "*.py[co]" -delete
+	find . -type d -name "__pycache__" -delete
+
+## Fix code using ruff
+.PHONY: fix
+fix:
+	ruff check --select I --fix
+	ruff check --fix
+	ruff format
+
+## Run pytests
+.PHONY: test
+test:
+	pytest
+
+test2: reqs test
+
+
+## Make README 
+.PHONY: README.md
+README.md: README.qmd src/showstats/showstats.py
+	quarto render README.qmd
+
+## Run nox
+.PHONY: nox
+nox: 
+	nox
+
+## Build package
+.PHONY: build
+build: 
+	python3 -m build
+
+## Upload to pypi
+.PHONY: upload-pypi
+upload-pypi: 
+	python3 -m twine upload --repository pypi dist/*
+
+## Upload to test-pypi
+.PHONY: upload-testpypi
+	python3 -m twine upload --repository testpypi dist/*
+
+
+## Test install
+.PHONY: test-inst
+test-inst:
+	uv pip install -i https://test.pypi.org/simple/ showstats
+
+# Self Documenting Commands #
+.DEFAULT_GOAL := help
+
+define PRINT_HELP_PYSCRIPT
+import re, sys; \
+lines = '\n'.join([line for line in sys.stdin]); \
+matches = re.findall(r'\n## (.*)\n[\s\S]+?\n([a-zA-Z_-]+):', lines); \
+print('Available rules:\n'); \
+print('\n'.join(['{:25}{}'.format(*reversed(match)) for match in matches]))
+endef
+export PRINT_HELP_PYSCRIPT
+
+help:
+	@python -c "$$PRINT_HELP_PYSCRIPT" < $(MAKEFILE_LIST)

showstats-0.0.1/PKG-INFO

@@ -0,0 +1,60 @@
+Metadata-Version: 2.3
+Name: showstats
+Version: 0.0.1
+Summary: Vertical summary statistics for data frames
+Project-URL: Homepage, https://github.com/matthiaskaeding/showstats
+Project-URL: Issues, https://github.com/matthiaskaeding/showstats/issues
+Author: Matthias Kaeding
+License-File: LICENSE
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Requires-Python: >=3.8
+Requires-Dist: polars>=0.20.21
+Provides-Extra: pandas
+Requires-Dist: pandas>=1.5.3; extra == 'pandas'
+Requires-Dist: pyarrow>=10.0.0; extra == 'pandas'
+Description-Content-Type: text/markdown
+
+# showstats: quick and compact summary statistics
+
+
+**showstats** produces summary statistic tables with vertical
+orientation.
+
+``` python
+from showstats import show_stats
+
+show_stats(df)
+```
+
+    | Var; N = 100  | Missing      | Mean         | Median       | Std.  | Min          | Max          |
+    |---------------|--------------|--------------|--------------|-------|--------------|--------------|
+    | int_col       | 0 (0.0%)     | 49.5         | 49.5         | 29.01 | 0.0          | 99.0         |
+    | int_with_miss | 20 (20.0%)   | 57.0         | 59.5         | 27.6  | 0.0          | 99.0         |
+    | ing           |              |              |              |       |              |              |
+    | float_col     | 0 (0.0%)     | 0.5          | 0.5          | 0.29  | 0.0          | 0.99         |
+    | float_col_wit | 0 (0.0%)     | 2.0          | 2.06         | 0.94  | -0.79        | 4.44         |
+    | h_mean_2      |              |              |              |       |              |              |
+    | float_col_wit | 0 (0.0%)     | -0.11        | 0.02         | 2.0   | -6.01        | 5.06         |
+    | h_std_2       |              |              |              |       |              |              |
+    | float_col_wit | 0 (0.0%)     | 9.79         | 9.85         | 0.94  | 7.0          | 12.22        |
+    | h_min_7       |              |              |              |       |              |              |
+    | float_col_wit | 0 (0.0%)     | 14.56        | 14.62        | 0.94  | 11.78        | 17.0         |
+    | h_max_17      |              |              |              |       |              |              |
+    | bool_col      | 0 (0.0%)     | 0.5          | 0.5          | 0.5   | 0.0          | 1.0          |
+    | datetime_col  | 0 (0.0%)     | 2022-01-01   | 2022-01-01   |       | 2022-01-01   | 2022-01-01   |
+    |               |              | 00:00:49     | 00:00:49     |       | 00:00:00     | 00:01:39     |
+    | datetime_col_ | 0 (0.0%)     | 1995-01-01   | 1995-01-01   |       | 1995-01-01   | 1995-01-01   |
+    | 2             |              | 00:00:49     | 00:00:49     |       | 00:00:00     | 00:01:39     |
+    | date_col      | 0 (0.0%)     |              |              |       | 2022-01-01   | 2022-04-10   |
+    | date_col_2    | 0 (0.0%)     |              |              |       | 1500-01-01   | 1500-04-10   |
+    | str_col       | 0 (0.0%)     |              |              |       | ABC          | foo          |
+    | enum_col      | 0 (0.0%)     |              |              |       | low          | high         |
+    | categorical_c | 0 (0.0%)     |              |              |       | low          | medium       |
+    | ol            |              |              |              |       |              |              |
+    | null_col      | 100 (100.0%) |              |              |       |              |              |
+
+Primarily built for polars data frames. **showstats** converts other
+inputs, for compatibility with pandas.DataFrames install as
+`pip install showstats[pandas]`

showstats-0.0.1/README.md

@@ -0,0 +1,42 @@
+# showstats: quick and compact summary statistics
+
+
+**showstats** produces summary statistic tables with vertical
+orientation.
+
+``` python
+from showstats import show_stats
+
+show_stats(df)
+```
+
+    | Var; N = 100  | Missing      | Mean         | Median       | Std.  | Min          | Max          |
+    |---------------|--------------|--------------|--------------|-------|--------------|--------------|
+    | int_col       | 0 (0.0%)     | 49.5         | 49.5         | 29.01 | 0.0          | 99.0         |
+    | int_with_miss | 20 (20.0%)   | 57.0         | 59.5         | 27.6  | 0.0          | 99.0         |
+    | ing           |              |              |              |       |              |              |
+    | float_col     | 0 (0.0%)     | 0.5          | 0.5          | 0.29  | 0.0          | 0.99         |
+    | float_col_wit | 0 (0.0%)     | 2.0          | 2.06         | 0.94  | -0.79        | 4.44         |
+    | h_mean_2      |              |              |              |       |              |              |
+    | float_col_wit | 0 (0.0%)     | -0.11        | 0.02         | 2.0   | -6.01        | 5.06         |
+    | h_std_2       |              |              |              |       |              |              |
+    | float_col_wit | 0 (0.0%)     | 9.79         | 9.85         | 0.94  | 7.0          | 12.22        |
+    | h_min_7       |              |              |              |       |              |              |
+    | float_col_wit | 0 (0.0%)     | 14.56        | 14.62        | 0.94  | 11.78        | 17.0         |
+    | h_max_17      |              |              |              |       |              |              |
+    | bool_col      | 0 (0.0%)     | 0.5          | 0.5          | 0.5   | 0.0          | 1.0          |
+    | datetime_col  | 0 (0.0%)     | 2022-01-01   | 2022-01-01   |       | 2022-01-01   | 2022-01-01   |
+    |               |              | 00:00:49     | 00:00:49     |       | 00:00:00     | 00:01:39     |
+    | datetime_col_ | 0 (0.0%)     | 1995-01-01   | 1995-01-01   |       | 1995-01-01   | 1995-01-01   |
+    | 2             |              | 00:00:49     | 00:00:49     |       | 00:00:00     | 00:01:39     |
+    | date_col      | 0 (0.0%)     |              |              |       | 2022-01-01   | 2022-04-10   |
+    | date_col_2    | 0 (0.0%)     |              |              |       | 1500-01-01   | 1500-04-10   |
+    | str_col       | 0 (0.0%)     |              |              |       | ABC          | foo          |
+    | enum_col      | 0 (0.0%)     |              |              |       | low          | high         |
+    | categorical_c | 0 (0.0%)     |              |              |       | low          | medium       |
+    | ol            |              |              |              |       |              |              |
+    | null_col      | 100 (100.0%) |              |              |       |              |              |
+
+Primarily built for polars data frames. **showstats** converts other
+inputs, for compatibility with pandas.DataFrames install as
+`pip install showstats[pandas]`

showstats-0.0.1/README.qmd

@@ -0,0 +1,31 @@
+---
+title: "showstats: quick and compact summary statistics"
+format: gfm
+jupyter: python3
+---
+
+**showstats** produces summary statistic tables with vertical orientation.
+
+```{python}
+# | output: false
+# | echo: false
+import polars as pl
+import sys
+
+sys.path.append("src/")
+sys.path.append("tests/")
+from pathlib import Path
+from conftest import sample_df_
+
+df = sample_df_()
+import showstats
+```
+
+```{python}
+
+from showstats import show_stats
+
+show_stats(df)
+```
+
+Primarily built for polars data frames. **showstats** converts other inputs, for compatibility with pandas.DataFrames install as ``pip install showstats[pandas]`` 

showstats-0.0.1/changelog.md

@@ -0,0 +1,12 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [0.0.2] - 2024-08-05
+
+### Fixed
+
+- Exports

showstats-0.0.1/data/README.md

@@ -0,0 +1,11 @@
+# Data
+
+Structure:
+
+```
+├── data               # Data, by default ignored
+│   ├── external       # Data from third party sources.
+│   ├── interim        # Transformed data
+│   ├── processed      # Final model data
+│   └── raw            # Immutable data dump, possibly
+```

showstats-0.0.1/dev-requirements.txt

@@ -0,0 +1,13 @@
+build>=1.2.1
+hatchling>=1.25.0
+jupyter>=1.0.0
+nbclient==0.10.0
+nbformat==5.10.4
+nox==2024.4.15
+polars>=0.20.23
+pandas>=1.5.3
+pyarrow>=17.0.0
+pytest==8.3.2
+ruff==0.5.6
+twine>=5.1.1
+uv==0.2.33

showstats-0.0.1/noxfile.py

@@ -0,0 +1,31 @@
+import nox
+
+nox.options.default_venv_backend = "uv"
+
+
+@nox.session
+def lint(session):
+    session.install("ruff")
+    session.run("ruff", "check")
+
+
+@nox.session(name="python_versions", python=["3.8", "3.9", "3.10", "3.11", "3.12"])
+def test(session):
+    session.install(
+        "pytest>=8.3.2", "polars>=0.20.21", "pandas>=1.5.3", "pyarrow>=10.0.0"
+    )
+
+    session.run("pytest", "tests/")
+
+
+@nox.parametrize("polars_version", ["0.20.21", "1.4.1"])
+@nox.parametrize("pandas_version", ["1.5.3"])
+@nox.session(name="polars_pandas", python="3.9")
+def test_polars_versions(session, polars_version, pandas_version):
+    session.install(
+        "pytest>=8.3.2",
+        f"polars=={polars_version}",
+        f"pandas>={pandas_version}",
+        "pyarrow>=10.0.0",
+    )
+    session.run("pytest", "tests/")

showstats-0.0.1/pyproject.toml

@@ -0,0 +1,31 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+dependencies = ["polars >= 0.20.21"]
+name = "showstats"
+description = "Vertical summary statistics for data frames"
+authors = [{ name = "Matthias Kaeding" }]
+classifiers = [
+  "Programming Language :: Python :: 3",
+  "License :: OSI Approved :: MIT License",
+  "Operating System :: OS Independent",
+]
+version = "0.0.1"
+readme = "README.md"
+requires-python = ">= 3.8"
+
+[project.optional-dependencies]
+pandas = ["pandas>=1.5.3", "pyarrow>=10.0.0"]
+
+
+[tool.ruff]
+extend-include = ["*.ipynb"]
+
+[tool.pytest.ini_options]
+pythonpath = ["src"]
+
+[project.urls]
+Homepage = "https://github.com/matthiaskaeding/showstats"
+Issues = "https://github.com/matthiaskaeding/showstats/issues"

showstats-0.0.1/references/README.md

@@ -0,0 +1 @@
+# Explanatory materials

showstats-0.0.1/scripts/README.md

@@ -0,0 +1 @@
+# Utility scripts

showstats-0.0.1/src/showstats/__init__.py

@@ -0,0 +1,3 @@
+from .showstats import show_stats
+
+__all__ = ["show_stats"]

showstats-0.0.1/src/showstats/showstats.py

@@ -0,0 +1,208 @@
+# Central functions for table making
+from typing import TYPE_CHECKING, Dict, Union
+
+import polars as pl
+
+from showstats.utils import _format_num_rows
+
+if TYPE_CHECKING:
+    import pandas
+
+
+def _make_tables(
+    df: Union[pl.DataFrame, "pandas.DataFrame"],
+) -> Dict[str, pl.DataFrame]:
+    """
+    Calculate summary statistics for a DataFrame.
+
+    Args:
+        df (pl.DataFrame): The input DataFrame. If not a polars.DataFrame, will try
+        to cast
+
+    Returns:
+        Dict[str, pl.DataFrame]: A dictionary of summary statistics DataFrames for each data type.
+    """
+    from polars import selectors as cs
+
+    functions = {}
+    functions_all = ["null_count", "min", "max"]
+
+    # Map vars to functions
+    vars = {}
+    cols_num = df.select(
+        pl.col(
+            pl.Decimal,
+            pl.Float32,
+            pl.Float64,
+            pl.Int16,
+            pl.Int32,
+            pl.Int64,
+            pl.Int8,
+            pl.UInt16,
+            pl.UInt32,
+            pl.UInt64,
+            pl.UInt8,
+            pl.Boolean,
+        )
+    ).columns
+    if len(cols_num) > 0:
+        vars["num"] = cols_num
+        functions["num"] = functions_all + ["mean", "median", "std"]
+
+    vars_cat = df.select(
+        pl.col(pl.String), pl.col(pl.Enum), pl.col(pl.Categorical)
+    ).columns
+    if len(vars_cat) > 0:
+        vars["cat"] = vars_cat
+        functions["cat"] = functions_all + ["n_unique"]
+
+    vars_datetime = df.select(cs.datetime()).columns
+    if len(vars_datetime) > 0:
+        vars["datetime"] = vars_datetime
+        functions["datetime"] = functions_all + ["mean", "median"]
+
+    vars_date = df.select(cs.date()).columns
+    if len(vars_date) > 0:
+        vars["date"] = vars_date
+        functions["date"] = functions_all
+
+    vars_null = df.select(pl.col(pl.Null)).columns
+    if len(vars_null) > 0:
+        vars["null"] = vars_null
+        functions["null"] = ["null_count"]
+
+    exprs = []
+    for var_type in vars:
+        functions_var_type = functions[var_type]
+        vars_var_type = vars[var_type]
+        for var in vars_var_type:
+            for fun in functions_var_type:
+                varname = f"{fun}_{var}"
+                expr = getattr(pl.col(var), fun)().alias(varname)
+                exprs.append(expr)
+
+    # Compute summary statistics in one go, leveraging Polars' query planner
+    stats = df.select(exprs).row(0, named=True)
+
+    # Make split summary tables
+    dfs = {}
+    for var_type in vars:
+        functions_var_type = functions[var_type]
+        vars_var_type = vars[var_type]
+        rows = []
+        for var in vars_var_type:
+            row = {"Variable": var}
+            for fun in functions_var_type:
+                row[fun] = stats[f"{fun}_{var}"]
+            rows.append(row)
+        dfs[var_type] = pl.DataFrame(rows)
+
+    return dfs
+
+
+def make_stats_df(df: Union[pl.DataFrame, "pandas.DataFrame"]) -> pl.DataFrame:
+    """
+    Create a summary table for the given DataFrame.
+
+    Args:
+        df (pl.DataFrame): The input DataFrame.
+
+    Returns:
+        pl.DataFrame: A summary table with statistics for each variable.
+    """
+
+    if isinstance(df, pl.DataFrame) is False:
+        print("Attempting to convert input to polars.DataFrame")
+        try:
+            df = pl.DataFrame(df)
+        except Exception as e:
+            print(f"Error occurred during attempted conversion: {e}")
+
+    dfs = _make_tables(df)
+    num_rows = df.height
+    varnames = [
+        "Variable",
+        "null_count",
+        "mean",
+        "median",
+        "std",
+        "min",
+        "max",
+    ]
+    var_types = [x for x in ["num", "datetime", "date", "cat", "null"] if x in dfs]
+
+    # Order
+    for var_type in var_types:
+        df_var_type = dfs[var_type].lazy()
+        df_var_type = (
+            df_var_type.with_columns(pl.selectors.float().round(2))
+            .with_columns(
+                pl.col("null_count")
+                .truediv(num_rows)
+                .alias("perc_missing")
+                .mul(100)
+                .round(1)
+            )
+            .with_columns(
+                pl.format("{} ({}%)", pl.col("null_count"), pl.col("perc_missing"))
+            )
+        )
+        # Special conversion for datetimes
+        if var_type == "datetime":
+            df_var_type = df_var_type.with_columns(
+                pl.col("mean", "median", "min", "max").dt.to_string("%Y-%m-%d %H:%M:%S")
+            )
+        else:
+            df_var_type = df_var_type.with_columns(pl.col("*").cast(pl.String))
+        # Add missing values as ""
+        for col_name in varnames:
+            if col_name not in dfs[var_type].columns:
+                df_var_type = df_var_type.with_columns(pl.lit("").alias(col_name))
+        dfs[var_type] = df_var_type.select(varnames)
+
+    thr = 100_000
+    if num_rows < thr:
+        name_var = f"Var; N = {_format_num_rows(num_rows, thr)}"
+    else:
+        name_var = f"Var; N \u2248 {_format_num_rows(num_rows, thr)}"
+    return (
+        pl.concat([dfs[key] for key in var_types])
+        .rename(
+            {
+                "Variable": name_var,
+                "null_count": "Missing",
+                "mean": "Mean",
+                "median": "Median",
+                "std": "Std.",
+                "min": "Min",
+                "max": "Max",
+            }
+        )
+        .collect()
+    )
+
+
+def show_stats(df: Union[pl.DataFrame, "pandas.DataFrame"]) -> None:
+    """
+    Print a summary table for the given DataF‚rame.
+
+    Args:
+        df (pl.DataFrame): The input DataFrame.
+    """
+    from polars import Config
+
+    if df.height == 0 or df.width == 0:
+        raise ValueError("Input data frame must have rows and columns")
+
+    stats_df = make_stats_df(df)
+    cfg = Config(
+        tbl_hide_dataframe_shape=True,
+        tbl_formatting="ASCII_MARKDOWN",
+        tbl_hide_column_data_types=True,
+        float_precision=2,
+        fmt_str_lengths=100,
+        set_tbl_rows=stats_df.height,
+    )
+
+    with cfg:
+        print(stats_df)

showstats-0.0.1/src/showstats/utils.py

@@ -0,0 +1,37 @@
+# Utility functions
+
+
+def _format_num_rows(num: int, thr: float) -> str:
+    """
+    Formats a number nicely, using scientific notation for large numbers.
+
+    Args:
+        num (int): The number to format.
+        thr (int): The threshold above which to use scientific notation.
+
+    Returns:
+        str: The formatted number as a string.
+    """
+    import math
+
+    if num < thr:
+        return f"{num:,.0f}"
+
+    exponent = int(math.floor(math.log10(abs(num))))
+    coefficient = num / 10**exponent
+
+    # Unicode superscript digits
+    superscripts = "⁰¹²³⁴⁵⁶⁷⁸⁹"
+
+    # Convert exponent to superscript
+    exp_superscript = "".join(superscripts[int(d)] for d in str(abs(exponent)))
+    if exponent < 0:
+        exp_superscript = "⁻" + exp_superscript
+
+    return f"{coefficient:.2f}×10{exp_superscript}"
+
+
+def _is_pkg_available(pkg: str) -> None:
+    import importlib
+
+    return importlib.util.find_spec(pkg) is not None

showstats-0.0.1/tests/conftest.py

@@ -0,0 +1,119 @@
+import polars as pl
+import pytest
+
+
+def sample_series(
+    seed: int = 1,
+    n: int = 100,
+    min: float = None,
+    max: float = None,
+    std: float = None,
+    mean: float = None,
+) -> pl.Series:
+    """
+    Samples a pl.Series with known moments.
+    seed (int): Random seed
+    min (float): Minimum
+    max (float): Maximum
+    std (float): Standard deviation
+    mean (float): Mean
+
+    """
+    import random
+
+    random.seed(seed)
+
+    data = [random.gauss(mu=0.0, sigma=1.0) for _ in range(n)]
+    sr = pl.Series(data)
+    if mean is not None:
+        sr_mean = sr.mean()
+        sr = (sr - sr_mean) + mean
+    if std is not None:
+        st_std = sr.std()
+        sr = sr * std / st_std
+    if min is not None:
+        sr_min = sr.min()
+        sr = sr - sr_min + min
+    if max is not None:
+        sr_max = sr.max()
+        sr = sr - sr_max + max
+
+    return sr
+
+
+def sample_df_(n: int = 100, seed: int = 1) -> pl.DataFrame:
+    """
+    Generate a sample DataFrame with various data types.
+
+    Args:
+        n (int): Number of rows to generate. Default is 100.
+
+    Returns:
+        pl.DataFrame: A DataFrame with sample data.
+    """
+    import random
+    from datetime import date, datetime, timedelta
+
+    assert n >= 100, "There must be >= 100 rows"
+
+    random.seed(a=seed, version=2)
+    int_data = range(n)
+    float_data = [i / 100 for i in range(n)]
+    bool_data = [i % 2 == 0 for i in range(n)]
+    str_data = random.choices(["foo", "bar", "baz", "ABC"], k=n)
+    date_col = pl.date_range(
+        start=date(2022, 1, 1),
+        end=date(2022, 1, 1) + timedelta(days=n - 1),
+        eager=True,
+    )
+    date_col_2 = pl.date_range(
+        start=date(1500, 1, 1),
+        end=date(1500, 1, 1) + timedelta(days=n - 1),
+        eager=True,
+    )
+    datetime_col = pl.datetime_range(
+        start=datetime(2022, 1, 1),
+        end=datetime(2022, 1, 1) + timedelta(seconds=n - 1),
+        interval="1s",
+        eager=True,
+    )
+    datetime_col_2 = pl.datetime_range(
+        start=datetime(1995, 1, 1),
+        end=datetime(1995, 1, 1) + timedelta(seconds=n - 1),
+        interval="1s",
+        eager=True,
+    )
+
+    cats = ["low", "medium", "high"]
+    categorical_data = random.choices(cats, k=n)
+    null_data = [None] * n
+
+    int_with_missing_data = list(int_data)
+    for i in range(10, 30):
+        int_with_missing_data[i] = None
+
+    return pl.DataFrame(
+        {
+            "int_col": int_data,
+            "int_with_missing": int_with_missing_data,
+            "float_col": float_data,
+            "float_col_with_mean_2": sample_series(n=n, seed=seed, mean=2),
+            "float_col_with_std_2": sample_series(n=n, seed=seed, std=2),
+            "float_col_with_min_7": sample_series(n=n, seed=seed, min=7),
+            "float_col_with_max_17": sample_series(n=n, seed=seed, max=17),
+            "bool_col": bool_data,
+            "str_col": str_data,
+            "date_col": date_col,
+            "date_col_2": date_col_2,
+            "datetime_col": datetime_col,
+            "datetime_col_2": datetime_col_2,
+            "categorical_col": pl.Series(categorical_data, dtype=pl.Categorical),
+            "enum_col": pl.Series(categorical_data, dtype=pl.Enum(cats)),
+            "null_col": pl.Series(null_data),
+        }
+    )
+
+
+@pytest.fixture(scope="session")
+def sample_df():
+    return sample_df_(n=500)

showstats-0.0.1/tests/test_dfstats.py

@@ -0,0 +1,29 @@
+import polars as pl
+from showstats.showstats import make_stats_df
+
+
+def testmake_stats_df(sample_df):
+    summary_table = make_stats_df(sample_df)
+    col_0 = summary_table.columns[0]
+    sorted_cols = sorted(sample_df.columns)
+    assert sorted(summary_table.get_column(col_0)) == sorted_cols
+
+    assert (
+        summary_table.filter(pl.col(col_0).eq("float_col_with_mean_2")).item(0, "Mean")
+        == "2.0"
+    )
+    assert (
+        summary_table.filter(pl.col(col_0).eq("float_col_with_std_2")).item(0, "Std.")
+        == "2.0"
+    )
+    assert (
+        summary_table.filter(pl.col(col_0).eq("float_col_with_min_7")).item(0, "Min")
+        == "7.0"
+    )
+    assert (
+        summary_table.filter(pl.col(col_0).eq("float_col_with_max_17")).item(0, "Max")
+        == "17.0"
+    )
+
+    summary_table_pandas = make_stats_df(sample_df.to_pandas())
+    assert sorted(summary_table_pandas.get_column(col_0)) == sorted_cols

showstats-0.0.1/tests/test_make_stats_df.py

@@ -0,0 +1,29 @@
+import polars as pl
+from showstats.showstats import make_stats_df
+
+
+def testmake_stats_df(sample_df):
+    summary_table = make_stats_df(sample_df)
+    col_0 = summary_table.columns[0]
+    sorted_cols = sorted(sample_df.columns)
+    assert sorted(summary_table.get_column(col_0)) == sorted_cols
+
+    assert (
+        summary_table.filter(pl.col(col_0).eq("float_col_with_mean_2")).item(0, "Mean")
+        == "2.0"
+    )
+    assert (
+        summary_table.filter(pl.col(col_0).eq("float_col_with_std_2")).item(0, "Std.")
+        == "2.0"
+    )
+    assert (
+        summary_table.filter(pl.col(col_0).eq("float_col_with_min_7")).item(0, "Min")
+        == "7.0"
+    )
+    assert (
+        summary_table.filter(pl.col(col_0).eq("float_col_with_max_17")).item(0, "Max")
+        == "17.0"
+    )
+
+    summary_table_pandas = make_stats_df(sample_df.to_pandas())
+    assert sorted(summary_table_pandas.get_column(col_0)) == sorted_cols

showstats-0.0.1/tests/test_make_tables.py

@@ -0,0 +1,71 @@
+import polars as pl
+from showstats.showstats import _make_tables
+
+
+def test_make_tables(sample_df):
+    result = _make_tables(sample_df)
+
+    assert isinstance(result, dict)
+    assert set(result.keys()) == {"num", "cat", "datetime", "date", "null"}
+
+    for key, df in result.items():
+        assert isinstance(df, pl.DataFrame)
+        assert "Variable" in df.columns
+        assert "null_count" in df.columns
+        if key != "null":
+            assert "min" in df.columns
+            assert "max" in df.columns
+
+    # Check specific data-frames
+    num_df = result["num"]
+    assert set(num_df["Variable"]) == {
+        "int_col",
+        "float_col",
+        "bool_col",
+        "int_with_missing",
+        "float_col_with_mean_2",
+        "float_col_with_std_2",
+        "float_col_with_min_7",
+        "float_col_with_max_17",
+    }
+    assert "mean" in num_df.columns
+    assert "median" in num_df.columns
+    assert "std" in num_df.columns
+
+    cat_df = result["cat"]
+    assert set(cat_df.get_column("Variable")) == {
+        "str_col",
+        "categorical_col",
+        "enum_col",
+    }
+    assert "n_unique" in cat_df.columns
+
+    datetime_df = result["datetime"]
+    assert set(datetime_df.get_column("Variable")) == {"datetime_col", "datetime_col_2"}
+    assert "mean" in datetime_df.columns
+    assert "median" in datetime_df.columns
+
+    date_df = result["date"]
+    assert set(date_df["Variable"]) == {"date_col", "date_col_2"}
+
+
+def test_all_null_column():
+    null_df = pl.DataFrame({"null_col": [None] * 10})
+    result = _make_tables(null_df)
+    assert isinstance(result, dict)
+    assert "cat" not in result
+    assert len(result) == 1
+    assert "null" in result
+    assert "null_col" in result["null"].get_column("Variable")
+    assert (
+        result["null"].filter(pl.col("Variable") == "null_col").item(0, "null_count")
+        == 10
+    )
+
+
+def test_single_column_dataframe():
+    single_col_df = pl.DataFrame({"test_col": range(10)})
+    result = _make_tables(single_col_df)
+    assert isinstance(result, dict)
+    assert "num" in result
+    assert "test_col" in result["num"]["Variable"]

showstats-0.0.1/tests/test_show.py

@@ -0,0 +1,31 @@
+import polars as pl
+import pytest
+from showstats.showstats import show_stats
+
+
+def test_print_summary(sample_df, capsys):
+    pl.Config.set_fmt_str_lengths(n=10000).set_tbl_width_chars(10000)
+    show_stats(sample_df)
+    captured = capsys.readouterr()
+    output = captured.out
+
+    # Check if the output contains expected column names
+    expected_columns = ["Missing", "Mean", "Median", "Std.", "Min", "Max"]
+    for col in expected_columns:
+        assert col in output, f"{col} not in output"
+    assert "Var" in output
+
+    # Check if all variable names are in the output
+    for col in sample_df.columns:
+        assert col in output
+
+    # Check if the output is formatted as an ASCII markdown table
+    assert "|" in output
+    assert "-" in output
+
+
+def test_empty_dataframe():
+    with pytest.raises(ValueError) as err:
+        empty_df = pl.DataFrame()
+        show_stats(empty_df)
+        assert "Input data frame must have rows and columns" in str(err.value)