commit 71a2dd41d9bd8d861762941b56d26b2f03295050 Author: Stephen Mildenhall Date: Mon Jan 20 15:42:42 2025 +0000 Initial commit diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dfe0770 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,2 @@ +# Auto detect text files and perform LF normalization +* text=auto diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..68bc17f --- /dev/null +++ b/.gitignore @@ -0,0 +1,160 @@ +# 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 + +# Sphinx documentation +docs/_build/ + +# 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/ diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..381e2eb --- /dev/null +++ b/LICENSE @@ -0,0 +1,21 @@ +MIT License + +Copyright (c) 2025 Stephen Mildenhall + +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. diff --git a/README.md b/README.md new file mode 100644 index 0000000..5623002 --- /dev/null +++ b/README.md @@ -0,0 +1,2 @@ +# Greater Tables + diff --git a/greater_tables.py b/greater_tables.py new file mode 100644 index 0000000..f60b487 --- /dev/null +++ b/greater_tables.py @@ -0,0 +1,203 @@ +# table formatting again +import pandas as pd +# from IPython.display import HTML + + +def gtqd(df, col_align='', formatters=None, ratio_cols=None, **kwargs): + """Better HTML output for a DataFrame.""" + table_id = f'T{id(df):x}'[::2].upper() + style = [] + + def r(x): + """Default ratio format.""" + try: + return f'{x:.1%}' + except: + return x + + def _float(x): + try: + return f'{x:,.3f}' + except: + return x + + def _int(x): + try: + return f'{x:,.3f}' + except: + return x + + # see if index col names in formatters? + dt = df.dtypes + if ratio_cols is None: + ratio_cols = [] + elif not isinstance(ratio_cols, (list, tuple)): + ratio_cols = list(ratio_cols) + + float_cols = df.select_dtypes(include='float').columns + integer_cols = df.select_dtypes(include='int').columns + if formatters is None: + formatters = {} + + for c in df.columns: + if c not in formatters.keys(): + # set a default + formatters[c] = r if c in ratio_cols else ( + _float if c in float_cols else ( + _int if c in integer_cols else + lambda x: x) + ) + + html = df.to_html(table_id=table_id, formatters=formatters, **kwargs) + + if col_align == '': + # guess: index l, numeric r rest l + idx = 'l' * df.index.nlevels + numeric_cols = df.select_dtypes('number').columns + rc = ''.join('r' if c in numeric_cols else 'l' for c in df.columns) + col_align = idx + rc + + # col no -> lrc -> spell out + d = {'l': 'left', 'r': 'right', 'c':'center'} + ca = col_align + ca = dict(zip(range(1, 1+len(ca)), map(d.get, ca))) + style.append('\n') + + if len(style): + style = '\n'.join(style) + else: + style = '' + + out = f'{style}{html}' + + return out + + +# def pf(df, *, ratio_cols=None, precision=3, pef_lower=-3, pef_upper=16, +# format_index=True): +# """Format a DataFrame.""" + +# df = df.copy() + +# _ratio_names = ['max_LR', 'gross_LR', 'net_LR', 'ceded_LR', 'LR', +# 'COC'] + +# if ratio_cols == 'all': +# ratio_cols = [i for i in df.columns] + +# elif ratio_cols is not None and type(ratio_cols) != list: +# ratio_cols = [ratio_cols] + +# def pef(x): +# """Pandas engineering formatter.""" +# return pd.io.formats.format.EngFormatter(accuracy=2, use_eng_prefix=True)(x) + +# pl = 10.**pef_lower +# pu = 10.**pef_upper + +# def nf(x): +# """Number formatter.""" +# try: +# if x == int(x): +# return f'{x:,.0f}' +# elif abs(x - 1) < 1e-3: +# return f"1-{1 - x:.3g}" +# elif abs(x) < pl or abs(x) > pu: +# return pef(x) +# elif abs(x) > 1e2: +# fmt = f'{{x:,.{precision - 1}f}}' +# return fmt.format(x=x) +# # return f'{x:,.1f}' +# else: +# fmt = f'{{x:,.{precision}f}}' +# return fmt.format(x=x) +# except: +# return x + +# def ratio(x): +# try: +# return f'{x:.1%}' +# except: +# return x + +# def integer(x): +# return f'{x:,d}' + +# # convert into string +# col_list = [f'{c}' for c in df.columns] + +# if ratio_cols is None: +# ratio_cols = [c for c in col_list if c in _ratio_names] +# if len(ratio_cols) == 0: +# ratio_cols = None +# if ratio_cols is not None: +# col_list = list(set(col_list) - set(ratio_cols)) + +# number_cols = df.select_dtypes(include='number').columns + +# index_cache = None +# if format_index: +# index_cache = df.index.names +# df = df. reset_index(drop=False) + +# float_cols = df.select_dtypes(include='float').columns +# integer_cols = df.select_dtypes(include='int').columns + +# for c in df: +# # if df.dtypes[c] in (int, float) +# if c in ratio_cols: +# df[c] = df[c].map(ratio) +# elif c in float_cols: +# df[c] = df[c].map(nf) +# elif c in integer_cols: +# df[c] = df[c].map(integer) +# else: +# print(f'Col {c} not treated') + +# if format_index and index_cache is not None: +# df = df.set_index(index_cache) + +# # align number columns +# # method 1 +# # sdf = ( +# # df.style +# # .applymap(lambda x: 'text-align: right;', subset=number_cols +# # ) +# # ) + +# # Define styles for specific columns +# # styles = [ +# # {'selector': f'td.col{i}', 'props': [('text-align', 'right')]} # Apply to specific columns +# # for i in number_cols +# # ] + +# # # Apply styles +# # styled_df = df.style.set_table_styles(styles) + +# # display(styled_df) + + +# # Generate table HTML with inline CSS +# table_html = df.to_html(index=True, classes="dataframe") + + +# return HTML(table_html) diff --git a/pyproject.toml b/pyproject.toml new file mode 100644 index 0000000..b8fb03a --- /dev/null +++ b/pyproject.toml @@ -0,0 +1,13 @@ +[build-system] +requires = ["setuptools", "wheel"] # Tools needed to build the package +build-backend = "setuptools.build_meta" + +[project] +name = "greater_tables" +version = "1.0.0" +description = "Perfect tables from pandas" +authors = [{name = "Stephen J Mildehall", email = "mynl@me.com" }] +readme = "README.md" +license = { text = "BSD 3-Clause" } +requires-python = ">=3.10" +dependencies = ["pandas"]