add_datepart.ipynb

add_datepart.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "add_datepart.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyOxr6Ca+pNh38aSyMs94dr7",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/tcvieira/681c036ff4f169473a9651b6d3cbbd58/add_datepart.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "OSCTNCXyFLLY"
      },
      "source": [
        "# add_datepart\n",
        "\n",
        "Função extraída da lib fastai"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "PK2IxkmQFEdY"
      },
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import re\n",
        "\n",
        "def ifnone(a,b):\n",
        "    \"`a` if `a` is not None, otherwise `b`.\"\n",
        "    return b if a is None else a\n",
        "\n",
        "def make_date(df, date_field):\n",
        "    \"Make sure `df[date_field]` is of the right date type.\"\n",
        "    field_dtype = df[date_field].dtype\n",
        "    if isinstance(field_dtype, pd.core.dtypes.dtypes.DatetimeTZDtype):\n",
        "        field_dtype = np.datetime64\n",
        "    if not np.issubdtype(field_dtype, np.datetime64):\n",
        "        df[date_field] = pd.to_datetime(df[date_field], infer_datetime_format=True)\n",
        "\n",
        "def add_datepart(df, field_name, prefix=None, drop=True, time=False):\n",
        "    \"Helper function that adds columns relevant to a date in the column `field_name` of `df`.\"\n",
        "    make_date(df, field_name)\n",
        "    field = df[field_name]\n",
        "    prefix = ifnone(prefix, re.sub('[Dd]ate$', '', field_name))\n",
        "    attr = ['Year', 'Month', 'Week', 'Day', 'Dayofweek', 'Dayofyear', 'Is_month_end', 'Is_month_start',\n",
        "            'Is_quarter_end', 'Is_quarter_start', 'Is_year_end', 'Is_year_start']\n",
        "    if time: attr = attr + ['Hour', 'Minute', 'Second']\n",
        "    # Pandas removed `dt.week` in v1.1.10\n",
        "    week = field.dt.isocalendar().week.astype(field.dt.day.dtype) if hasattr(field.dt, 'isocalendar') else field.dt.week\n",
        "    for n in attr: df[prefix + n] = getattr(field.dt, n.lower()) if n != 'Week' else week\n",
        "    mask = ~field.isna()\n",
        "    df[prefix + 'Elapsed'] = np.where(mask,field.values.astype(np.int64) // 10 ** 9,np.nan)\n",
        "    if drop: df.drop(field_name, axis=1, inplace=True)\n",
        "    return df"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "UtI_fNkqFHkp"
      },
      "source": [
        "df = pd.DataFrame({'date': ['2019-12-04', None, '2019-11-15', '2019-10-24']})\n",
        "df = add_datepart(df, 'date')\n",
        "df.head()"
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}