{ "cells": [ { "cell_type": "markdown", "id": "c5046cdf", "metadata": {}, "source": [ "# Inference: using saved pipeline on a new data\n", "\n", "\n", " \n", "" ] }, { "cell_type": "markdown", "id": "b74c7dff", "metadata": {}, "source": [ "This notebook contains the example of usage already fitted and saved pipeline on a new data.\n", "\n", "**Table of Contents**\n", "\n", "* [Preparing data](#chapter1)\n", "* [Fitting and saving pipeline](#chapter2)\n", " * [Fitting pipeline](#section_2_1)\n", " * [Saving pipeline](#section_2_2)\n", " * [Method `to_dict`](#section_2_2)\n", "* [Using saved pipeline on a new data](#chapter3)\n", " * [Loading pipeline](#section_3_1)\n", " * [Forecast on a new data](#section_3_2)" ] }, { "cell_type": "code", "execution_count": 1, "id": "c1053781", "metadata": {}, "outputs": [], "source": [ "import warnings\n", "\n", "warnings.filterwarnings(action=\"ignore\", message=\"Torchmetrics v0.9\")\n", "warnings.filterwarnings(action=\"ignore\", message=\"`tsfresh` is not available\")" ] }, { "cell_type": "code", "execution_count": 2, "id": "fc24b98c", "metadata": {}, "outputs": [], "source": [ "import pathlib\n", "\n", "HORIZON = 30\n", "SAVE_DIR = pathlib.Path(\"tmp\")\n", "SAVE_DIR.mkdir(exist_ok=True)" ] }, { "cell_type": "markdown", "id": "81e670c8", "metadata": {}, "source": [ "## 1. Preparing data " ] }, { "cell_type": "markdown", "id": "ed4a8e77", "metadata": {}, "source": [ "Let's load data and prepare it for our pipeline." ] }, { "cell_type": "code", "execution_count": 3, "id": "f4455ad2", "metadata": {}, "outputs": [], "source": [ "import pandas as pd" ] }, { "cell_type": "code", "execution_count": 4, "id": "9e8659fc", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | timestamp | \n", "segment | \n", "target | \n", "
---|---|---|---|
0 | \n", "2019-01-01 | \n", "segment_a | \n", "170 | \n", "
1 | \n", "2019-01-02 | \n", "segment_a | \n", "243 | \n", "
2 | \n", "2019-01-03 | \n", "segment_a | \n", "267 | \n", "
3 | \n", "2019-01-04 | \n", "segment_a | \n", "287 | \n", "
4 | \n", "2019-01-05 | \n", "segment_a | \n", "279 | \n", "