sktime_forecasting_pipeline_missing_13p2.ipynb

sktime_forecasting_pipeline_missing_13p2.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyPWdToY80IyRY9M0iQj0cAX",
      "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/ngupta23/fe385efcad52b1d6c4c11f955d13da8e/sktime_forecasting_pipeline_missing_13p2.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "dd0XW1sgtCkh"
      },
      "outputs": [],
      "source": [
        "try:\n",
        "    import sktime\n",
        "except ModuleNotFoundError:\n",
        "    !pip install sktime==0.13.2"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "from sktime.datasets import load_longley\n",
        "from sktime.forecasting.trend import TrendForecaster\n",
        "from sktime.transformations.compose import TransformerPipeline\n",
        "from sktime.forecasting.compose import ForecastingPipeline, TransformedTargetForecaster\n",
        "from sktime.transformations.series.impute import Imputer"
      ],
      "metadata": {
        "id": "2xRDC6ButLBC"
      },
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "y, X = load_longley()\n",
        "y[10] = np.nan"
      ],
      "metadata": {
        "id": "PvBHcEBytQHQ"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "transformer_y = TransformerPipeline(steps = [(\"imputer\", Imputer())])\n",
        "\n",
        "forecaster = TransformedTargetForecaster(\n",
        "    steps = [\n",
        "        (\"transformer_y\", transformer_y),\n",
        "        (\"model\", TrendForecaster())\n",
        "    ]\n",
        ")\n",
        "\n",
        "pipe = ForecastingPipeline(steps = [(\"forecaster\", forecaster)])"
      ],
      "metadata": {
        "id": "D_E8_F2TtQ1g"
      },
      "execution_count": 4,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "pipe.fit(y, X)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CV_wOcRntVQQ",
        "outputId": "497a2f84-7f3a-48f2-e07e-158212efd017"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sktime/forecasting/trend.py:76: FutureWarning: casting period[A-DEC] values to int64 with .astype(...) is deprecated and will raise in a future version. Use .view(...) instead.\n",
            "  X = y.index.astype(\"int\").to_numpy().reshape(-1, 1)\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "ForecastingPipeline(steps=[('forecaster',\n",
              "                            TransformedTargetForecaster(steps=[('transformer_y',\n",
              "                                                                TransformerPipeline(steps=[('imputer',\n",
              "                                                                                            Imputer())])),\n",
              "                                                               ('model',\n",
              "                                                                TrendForecaster())]))])"
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    }
  ]
}