A Python notebook with helper functions. `set_dtypes` to update column data types. `display_df` displays dataframes (with truncation) in the desired number format. Sets Jupyter notebook precision to the same number format.

$ Pandas formatter for Jupyter notebooks.md

Pandas formatter for Jupyter notebooks.ipynb

See boilercv.docs for updated implementation

Pandas formatter for Jupyter notebooks.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from typing import Callable\n",
    "\n",
    "import pandas as pd\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "FLOAT_SPEC = \"#.4g\"\n",
    "\n",
    "pd.options.display.min_rows = pd.options.display.max_rows = 20\n",
    "pd.options.display.float_format = f\"{{:{FLOAT_SPEC}}}\".format\n",
    "%precision %$FLOAT_SPEC\n",
    "\n",
    "\n",
    "def set_dtypes(df: pd.DataFrame, dtypes: dict[str, str]) -> pd.DataFrame:\n",
    "    \"\"\"Set column datatypes in a dataframe.\"\"\"\n",
    "    return df.assign(**{name: df[name].astype(dtype) for name, dtype in dtypes.items()})\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def display_df(*dfs: pd.DataFrame | pd.Series):\n",
    "    \"\"\"Display a formatted DataFrame.\n",
    "    \n",
    "    When a mapping of column names to callables is given to the Pandas styler, the\n",
    "    callable will be used internally by Pandas to produce formatted strings. This\n",
    "    differs from elementwise formatting, in which Pandas expects the callable to\n",
    "    actually process the value and return the formatted string.\n",
    "    \"\"\"\n",
    "    for df in dfs:\n",
    "        if isinstance(df, pd.Series):\n",
    "            df = df.to_frame()\n",
    "        df, truncated = truncate(df)\n",
    "        formatter = format_cell if truncated else get_df_formatter(df)\n",
    "        display(df.style.format(formatter))\n",
    "\n",
    "\n",
    "def get_df_formatter(df: pd.DataFrame) -> dict[str, Callable]:\n",
    "    \"\"\"Get formatter for the dataframe.\"\"\"\n",
    "    cols = df.columns\n",
    "    types = {col: dtype.type for col, dtype in zip(cols, df.dtypes)}\n",
    "    return {col: get_formatter(types[col]()) for col in cols}\n",
    "\n",
    "\n",
    "def format_cell(cell) -> str:\n",
    "    \"\"\"Format individual cells.\"\"\"\n",
    "    return get_formatter(cell)(cell)\n",
    "\n",
    "\n",
    "def get_formatter(instance) -> str:\n",
    "    \"\"\"Get the formatter depending on the type of the instance.\"\"\"\n",
    "    match instance:\n",
    "        case float():\n",
    "            return lambda cell: f\"{cell:{FLOAT_SPEC}}\"\n",
    "        case _:\n",
    "            return lambda cell: f\"{cell}\"\n",
    "\n",
    "\n",
    "def truncate(df: pd.DataFrame | pd.Series) -> tuple[pd.DataFrame, bool]:\n",
    "    \"\"\"Truncate long dataframes, showing only the head and tail.\"\"\"\n",
    "\n",
    "    if len(df) <= pd.options.display.max_rows:\n",
    "        return df, False\n",
    "\n",
    "    df_truncated = pd.concat(\n",
    "        [\n",
    "            df.head(pd.options.display.min_rows // 2),\n",
    "            pd.Series(name=\"...\", dtype=object).to_frame().T,\n",
    "            df.tail(pd.options.display.min_rows // 2),\n",
    "        ]\n",
    "    )\n",
    "    df_truncated.loc[\"...\", :] = \"...\"\n",
    "\n",
    "    return df_truncated, True\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.10.4 ('data')",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.6"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "71731e66821fe2c6da416d2ded4a1ef99f386126a5584fcd16f8e3a2b440f5bd"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}