{
    "cells": [
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "# cd/gt03/Summary Table\n",
                "\n"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "To import the module"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": null,
            "metadata": {},
            "outputs": [
                {
                    "ename": "ModuleNotFoundError",
                    "evalue": "No module named 'mtbp3cd'",
                    "output_type": "error",
                    "traceback": [
                        "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
                        "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
                        "Cell \u001b[0;32mIn[2], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mmtbp3cd\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mutil\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mgt03summary\u001b[39;00m\n",
                        "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'mtbp3cd'"
                    ]
                }
            ],
            "source": [
                "import pandas as pd\n",
                "from mtbp3cd.util.gt03summary import crosstab_from_lists"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "## Example - 1 Generate data summary tables\n",
                "\n",
                "The output includes:\n",
                "\n",
                "1. Count of rows of input data by output-col-columns and output-row-columns\n",
                "2. Normalized counts by perct_within_index\n",
                "3. Report with format \"count (%)\" \n",
                "\n",
                "To create a dataset:"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": null,
            "metadata": {},
            "outputs": [],
            "source": [
                "data = {\n",
                "    'A': ['foo','foo', 'foo', 'foo', 'foo', 'foo', 'bar', 'bar', 'baz', 'baz', 'baz'],\n",
                "    'B': ['one','one','one','one', 'one', 'two', 'two', 'one', 'one', 'two', 'two'],\n",
                "    'C': ['y','x','x','x', 'y', 'x', 'y', 'x', 'y', 'x', 'y'],\n",
                "    'D': ['apple','apple','apple','apple', 'banana', 'apple', 'banana', 'apple', 'banana', 'apple', 'banana'],\n",
                "    'E': ['red','blue','red','red', 'red', 'blue', 'blue', 'red', 'blue', 'red', 'blue'],\n",
                "    'value': [0,1,1,1, 2, 3, 4, 5, 6, 7, 8]\n",
                "}\n",
                "df = pd.DataFrame(data)\n",
                "\n",
                "# Use crosstab_from_lists with 3-level multi-index for rows and columns\n",
                "rows = ['A', 'B', 'C']\n",
                "cols = ['D', 'E']"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {
                "vscode": {
                    "languageId": "plaintext"
                }
            },
            "source": [
                "To create a frequency (count) table:"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": null,
            "metadata": {},
            "outputs": [],
            "source": [
                "(crosstab_from_lists(df, rows, cols))['count']\n"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "To create a table with row-wise percentage:"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": null,
            "metadata": {},
            "outputs": [],
            "source": [
                "(crosstab_from_lists(df, rows, cols, rows, col_margin_perct=True))['report']"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {
                "vscode": {
                    "languageId": "plaintext"
                }
            },
            "source": [
                "To create a table with grouped row-wise percentage:"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": null,
            "metadata": {},
            "outputs": [],
            "source": [
                "(crosstab_from_lists(df, rows, cols, ['A','B'], col_margin_perct=True))['report']"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "To create a table with column-wise percentage:"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": null,
            "metadata": {},
            "outputs": [],
            "source": [
                "(crosstab_from_lists(df, rows, cols, cols, row_margin_perct=True))['report']"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "To create a table with grouped column-wise percentage:"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": null,
            "metadata": {},
            "outputs": [],
            "source": [
                "(crosstab_from_lists(df, rows, cols, ['D'], row_margin_perct=True))['report']"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "To create a table with grouped row-and-column-wise percentage:"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": null,
            "metadata": {},
            "outputs": [],
            "source": [
                "(crosstab_from_lists(df, rows, cols, ['A', 'D']))['report']"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "To create a table with grouped row-and-column-wise percentage:"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": null,
            "metadata": {},
            "outputs": [],
            "source": [
                "(crosstab_from_lists(df, rows, cols, ['A', 'D'], row_margin_perct=True, col_margin_perct=True))['report']"
            ]
        },
        {
            "cell_type": "markdown",
            "metadata": {},
            "source": [
                "To create a table with grouped row-wise percentage and total:\n"
            ]
        },
        {
            "cell_type": "code",
            "execution_count": null,
            "metadata": {},
            "outputs": [],
            "source": [
                "(crosstab_from_lists(df, rows, cols, ['A','B'], col_margin_perct=True, report_type=2))['report']"
            ]
        }
    ],
    "metadata": {
        "kernelspec": {
            "display_name": "Python 3",
            "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": "3.12.2"
        }
    },
    "nbformat": 4,
    "nbformat_minor": 4
}