{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "ylPOlAXV2LpA" }, "source": [ "# Utilizando a biblioteca DARTS para forecasting\n", "## Notebook desenvolvido para o curso Financial Analytics - Insper\n", "Referências:\n", "- https://unit8.com/resources/darts-time-series-made-easy-in-python/\n", "- https://levelup.gitconnected.com/a-python-library-that-makes-it-simple-to-forecast-time-series-6a403da71542\n", "- https://pypi.org/project/statsforecast/" ] }, { "cell_type": "markdown", "metadata": { "id": "DTLnFuIlOveo" }, "source": [ "### 1. Imports and data upload" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 1000 }, "id": "XuQeF4vFZPG_", "outputId": "3a4d44a5-9c42-4cbc-d7fd-40a29e248f3f" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Requirement already satisfied: darts in /usr/local/lib/python3.12/dist-packages (0.38.0)\n", "Requirement already satisfied: holidays>=0.11.1 in /usr/local/lib/python3.12/dist-packages (from darts) (0.82)\n", "Requirement already satisfied: joblib>=0.16.0 in /usr/local/lib/python3.12/dist-packages (from darts) (1.5.2)\n", "Requirement already satisfied: matplotlib>=3.3.0 in /usr/local/lib/python3.12/dist-packages (from darts) (3.10.0)\n", "Requirement already satisfied: narwhals>=1.25.1 in /usr/local/lib/python3.12/dist-packages (from darts) (2.9.0)\n", "Requirement already satisfied: nfoursid>=1.0.0 in /usr/local/lib/python3.12/dist-packages (from darts) (1.0.2)\n", "Requirement already satisfied: numpy>=1.19.0 in /usr/local/lib/python3.12/dist-packages (from darts) (2.0.2)\n", "Requirement already satisfied: pandas>=1.0.5 in /usr/local/lib/python3.12/dist-packages (from darts) (2.2.2)\n", "Requirement already satisfied: pyod>=0.9.5 in /usr/local/lib/python3.12/dist-packages (from darts) (2.0.5)\n", "Requirement already satisfied: requests>=2.22.0 in /usr/local/lib/python3.12/dist-packages (from darts) (2.32.4)\n", "Requirement already satisfied: scikit-learn>=1.6.0 in /usr/local/lib/python3.12/dist-packages (from darts) (1.6.1)\n", "Requirement already satisfied: scipy>=1.3.2 in /usr/local/lib/python3.12/dist-packages (from darts) (1.16.2)\n", "Requirement already satisfied: shap>=0.40.0 in /usr/local/lib/python3.12/dist-packages (from darts) (0.49.1)\n", "Requirement already satisfied: statsmodels>=0.14.0 in /usr/local/lib/python3.12/dist-packages (from darts) (0.14.5)\n", "Requirement already satisfied: tqdm>=4.60.0 in /usr/local/lib/python3.12/dist-packages (from darts) (4.67.1)\n", "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.12/dist-packages (from darts) (4.15.0)\n", "Requirement already satisfied: xarray>=0.17.0 in /usr/local/lib/python3.12/dist-packages (from darts) (2025.10.1)\n", "Requirement already satisfied: pytorch-lightning<2.5.3,>=2.0.0 in /usr/local/lib/python3.12/dist-packages (from darts) (2.5.2)\n", "Requirement already satisfied: tensorboardX>=2.1 in /usr/local/lib/python3.12/dist-packages (from darts) (2.6.4)\n", "Requirement already satisfied: torch>=1.8.0 in /usr/local/lib/python3.12/dist-packages (from darts) (2.8.0+cu126)\n", "Requirement already satisfied: python-dateutil in /usr/local/lib/python3.12/dist-packages (from holidays>=0.11.1->darts) (2.9.0.post0)\n", "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->darts) (1.3.3)\n", "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->darts) (0.12.1)\n", "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->darts) (4.60.1)\n", "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->darts) (1.4.9)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->darts) (25.0)\n", "Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->darts) (11.3.0)\n", "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=3.3.0->darts) (3.2.5)\n", "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas>=1.0.5->darts) (2025.2)\n", "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas>=1.0.5->darts) (2025.2)\n", "Requirement already satisfied: numba>=0.51 in /usr/local/lib/python3.12/dist-packages (from pyod>=0.9.5->darts) (0.60.0)\n", "Requirement already satisfied: PyYAML>=5.4 in /usr/local/lib/python3.12/dist-packages (from pytorch-lightning<2.5.3,>=2.0.0->darts) (6.0.3)\n", "Requirement already satisfied: fsspec>=2022.5.0 in /usr/local/lib/python3.12/dist-packages (from fsspec[http]>=2022.5.0->pytorch-lightning<2.5.3,>=2.0.0->darts) (2025.3.0)\n", "Requirement already satisfied: torchmetrics>=0.7.0 in /usr/local/lib/python3.12/dist-packages (from pytorch-lightning<2.5.3,>=2.0.0->darts) (1.8.2)\n", "Requirement already satisfied: lightning-utilities>=0.10.0 in /usr/local/lib/python3.12/dist-packages (from pytorch-lightning<2.5.3,>=2.0.0->darts) (0.15.2)\n", "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests>=2.22.0->darts) (3.4.4)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests>=2.22.0->darts) (3.11)\n", "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests>=2.22.0->darts) (2.5.0)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests>=2.22.0->darts) (2025.10.5)\n", "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn>=1.6.0->darts) (3.6.0)\n", "Requirement already satisfied: slicer==0.0.8 in /usr/local/lib/python3.12/dist-packages (from shap>=0.40.0->darts) (0.0.8)\n", "Requirement already satisfied: cloudpickle in /usr/local/lib/python3.12/dist-packages (from shap>=0.40.0->darts) (3.1.1)\n", "Requirement already satisfied: patsy>=0.5.6 in /usr/local/lib/python3.12/dist-packages (from statsmodels>=0.14.0->darts) (1.0.2)\n", "Requirement already satisfied: protobuf>=3.20 in /usr/local/lib/python3.12/dist-packages (from tensorboardX>=2.1->darts) (5.29.5)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (3.20.0)\n", "Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (75.2.0)\n", "Requirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (1.13.3)\n", "Requirement already satisfied: networkx in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (3.5)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (3.1.6)\n", "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (12.6.77)\n", "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (12.6.77)\n", "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.6.80 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (12.6.80)\n", "Requirement already satisfied: nvidia-cudnn-cu12==9.10.2.21 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (9.10.2.21)\n", "Requirement already satisfied: nvidia-cublas-cu12==12.6.4.1 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (12.6.4.1)\n", "Requirement already satisfied: nvidia-cufft-cu12==11.3.0.4 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (11.3.0.4)\n", "Requirement already satisfied: nvidia-curand-cu12==10.3.7.77 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (10.3.7.77)\n", "Requirement already satisfied: nvidia-cusolver-cu12==11.7.1.2 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (11.7.1.2)\n", "Requirement already satisfied: nvidia-cusparse-cu12==12.5.4.2 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (12.5.4.2)\n", "Requirement already satisfied: nvidia-cusparselt-cu12==0.7.1 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (0.7.1)\n", "Requirement already satisfied: nvidia-nccl-cu12==2.27.3 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (2.27.3)\n", "Requirement already satisfied: nvidia-nvtx-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (12.6.77)\n", "Requirement already satisfied: nvidia-nvjitlink-cu12==12.6.85 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (12.6.85)\n", "Requirement already satisfied: nvidia-cufile-cu12==1.11.1.6 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (1.11.1.6)\n", "Requirement already satisfied: triton==3.4.0 in /usr/local/lib/python3.12/dist-packages (from torch>=1.8.0->darts) (3.4.0)\n", "Requirement already satisfied: aiohttp!=4.0.0a0,!=4.0.0a1 in /usr/local/lib/python3.12/dist-packages (from fsspec[http]>=2022.5.0->pytorch-lightning<2.5.3,>=2.0.0->darts) (3.13.1)\n", "Requirement already satisfied: llvmlite<0.44,>=0.43.0dev0 in /usr/local/lib/python3.12/dist-packages (from numba>=0.51->pyod>=0.9.5->darts) (0.43.0)\n", "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil->holidays>=0.11.1->darts) (1.17.0)\n", "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy>=1.13.3->torch>=1.8.0->darts) (1.3.0)\n", "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->torch>=1.8.0->darts) (3.0.3)\n", "Requirement already satisfied: aiohappyeyeballs>=2.5.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch-lightning<2.5.3,>=2.0.0->darts) (2.6.1)\n", "Requirement already satisfied: aiosignal>=1.4.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch-lightning<2.5.3,>=2.0.0->darts) (1.4.0)\n", "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch-lightning<2.5.3,>=2.0.0->darts) (25.4.0)\n", "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch-lightning<2.5.3,>=2.0.0->darts) (1.8.0)\n", "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch-lightning<2.5.3,>=2.0.0->darts) (6.7.0)\n", "Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch-lightning<2.5.3,>=2.0.0->darts) (0.4.1)\n", "Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]>=2022.5.0->pytorch-lightning<2.5.3,>=2.0.0->darts) (1.22.0)\n", "Requirement already satisfied: prophet in /usr/local/lib/python3.12/dist-packages (1.1.7)\n", "Requirement already satisfied: cmdstanpy>=1.0.4 in /usr/local/lib/python3.12/dist-packages (from prophet) (1.2.5)\n", "Requirement already satisfied: numpy>=1.15.4 in /usr/local/lib/python3.12/dist-packages (from prophet) (2.0.2)\n", "Requirement already satisfied: matplotlib>=2.0.0 in /usr/local/lib/python3.12/dist-packages (from prophet) (3.10.0)\n", "Requirement already satisfied: pandas>=1.0.4 in /usr/local/lib/python3.12/dist-packages (from prophet) (2.2.2)\n", "Requirement already satisfied: holidays<1,>=0.25 in /usr/local/lib/python3.12/dist-packages (from prophet) (0.82)\n", "Requirement already satisfied: tqdm>=4.36.1 in /usr/local/lib/python3.12/dist-packages (from prophet) (4.67.1)\n", "Requirement already satisfied: importlib_resources in /usr/local/lib/python3.12/dist-packages (from prophet) (6.5.2)\n", "Requirement already satisfied: stanio<2.0.0,>=0.4.0 in /usr/local/lib/python3.12/dist-packages (from cmdstanpy>=1.0.4->prophet) (0.5.1)\n", "Requirement already satisfied: python-dateutil in /usr/local/lib/python3.12/dist-packages (from holidays<1,>=0.25->prophet) (2.9.0.post0)\n", "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=2.0.0->prophet) (1.3.3)\n", "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=2.0.0->prophet) (0.12.1)\n", "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=2.0.0->prophet) (4.60.1)\n", "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=2.0.0->prophet) (1.4.9)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=2.0.0->prophet) (25.0)\n", "Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=2.0.0->prophet) (11.3.0)\n", "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib>=2.0.0->prophet) (3.2.5)\n", "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas>=1.0.4->prophet) (2025.2)\n", "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas>=1.0.4->prophet) (2025.2)\n", "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil->holidays<1,>=0.25->prophet) (1.17.0)\n", "Collecting statsforecast\n", " Downloading statsforecast-2.0.2-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl.metadata (29 kB)\n", "Requirement already satisfied: cloudpickle in /usr/local/lib/python3.12/dist-packages (from statsforecast) (3.1.1)\n", "Collecting coreforecast>=0.0.12 (from statsforecast)\n", " Downloading coreforecast-0.0.16-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.7 kB)\n", "Requirement already satisfied: numba>=0.55.0 in /usr/local/lib/python3.12/dist-packages (from statsforecast) (0.60.0)\n", "Requirement already satisfied: numpy>=1.21.6 in /usr/local/lib/python3.12/dist-packages (from statsforecast) (2.0.2)\n", "Requirement already satisfied: pandas>=1.3.5 in /usr/local/lib/python3.12/dist-packages (from statsforecast) (2.2.2)\n", "Collecting scipy<1.16.0,>=1.7.3 (from statsforecast)\n", " Downloading scipy-1.15.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (61 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.0/62.0 kB\u001b[0m \u001b[31m5.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: statsmodels>=0.13.2 in /usr/local/lib/python3.12/dist-packages (from statsforecast) (0.14.5)\n", "Requirement already satisfied: tqdm in /usr/local/lib/python3.12/dist-packages (from statsforecast) (4.67.1)\n", "Collecting fugue>=0.8.1 (from statsforecast)\n", " Downloading fugue-0.9.1-py3-none-any.whl.metadata (18 kB)\n", "Collecting utilsforecast>=0.1.4 (from statsforecast)\n", " Downloading utilsforecast-0.2.14-py3-none-any.whl.metadata (5.5 kB)\n", "Requirement already satisfied: threadpoolctl>=3 in /usr/local/lib/python3.12/dist-packages (from statsforecast) (3.6.0)\n", "Collecting triad>=0.9.7 (from fugue>=0.8.1->statsforecast)\n", " Downloading triad-0.9.8-py3-none-any.whl.metadata (6.3 kB)\n", "Collecting adagio>=0.2.4 (from fugue>=0.8.1->statsforecast)\n", " Downloading adagio-0.2.6-py3-none-any.whl.metadata (1.8 kB)\n", "Requirement already satisfied: llvmlite<0.44,>=0.43.0dev0 in /usr/local/lib/python3.12/dist-packages (from numba>=0.55.0->statsforecast) (0.43.0)\n", "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas>=1.3.5->statsforecast) (2.9.0.post0)\n", "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas>=1.3.5->statsforecast) (2025.2)\n", "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas>=1.3.5->statsforecast) (2025.2)\n", "Requirement already satisfied: patsy>=0.5.6 in /usr/local/lib/python3.12/dist-packages (from statsmodels>=0.13.2->statsforecast) (1.0.2)\n", "Requirement already satisfied: packaging>=21.3 in /usr/local/lib/python3.12/dist-packages (from statsmodels>=0.13.2->statsforecast) (25.0)\n", "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas>=1.3.5->statsforecast) (1.17.0)\n", "Requirement already satisfied: pyarrow>=6.0.1 in /usr/local/lib/python3.12/dist-packages (from triad>=0.9.7->fugue>=0.8.1->statsforecast) (18.1.0)\n", "Requirement already satisfied: fsspec>=2022.5.0 in /usr/local/lib/python3.12/dist-packages (from triad>=0.9.7->fugue>=0.8.1->statsforecast) (2025.3.0)\n", "Collecting fs (from triad>=0.9.7->fugue>=0.8.1->statsforecast)\n", " Downloading fs-2.4.16-py2.py3-none-any.whl.metadata (6.3 kB)\n", "Collecting appdirs~=1.4.3 (from fs->triad>=0.9.7->fugue>=0.8.1->statsforecast)\n", " Downloading appdirs-1.4.4-py2.py3-none-any.whl.metadata (9.0 kB)\n", "Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from fs->triad>=0.9.7->fugue>=0.8.1->statsforecast) (75.2.0)\n", "Downloading statsforecast-2.0.2-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (344 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m344.8/344.8 kB\u001b[0m \u001b[31m17.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading coreforecast-0.0.16-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (287 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m287.4/287.4 kB\u001b[0m \u001b[31m24.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading fugue-0.9.1-py3-none-any.whl (278 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m278.2/278.2 kB\u001b[0m \u001b[31m22.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading scipy-1.15.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (37.3 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m37.3/37.3 MB\u001b[0m \u001b[31m23.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading utilsforecast-0.2.14-py3-none-any.whl (41 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m41.0/41.0 kB\u001b[0m \u001b[31m2.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading adagio-0.2.6-py3-none-any.whl (19 kB)\n", "Downloading triad-0.9.8-py3-none-any.whl (62 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.3/62.3 kB\u001b[0m \u001b[31m5.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading fs-2.4.16-py2.py3-none-any.whl (135 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m135.3/135.3 kB\u001b[0m \u001b[31m12.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hDownloading appdirs-1.4.4-py2.py3-none-any.whl (9.6 kB)\n", "Installing collected packages: appdirs, scipy, fs, coreforecast, utilsforecast, triad, adagio, fugue, statsforecast\n", " Attempting uninstall: scipy\n", " Found existing installation: scipy 1.16.2\n", " Uninstalling scipy-1.16.2:\n", " Successfully uninstalled scipy-1.16.2\n", "Successfully installed adagio-0.2.6 appdirs-1.4.4 coreforecast-0.0.16 fs-2.4.16 fugue-0.9.1 scipy-1.15.3 statsforecast-2.0.2 triad-0.9.8 utilsforecast-0.2.14\n" ] }, { "data": { "application/vnd.colab-display-data+json": { "id": "1607e068c7ce4658ad3a96d39cad4d06", "pip_warning": { "packages": [ "scipy" ] } } }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# DARTS now is lightweight install: please see https://github.com/unit8co/darts/blob/master/INSTALL.md#enabling-optional-dependencies\n", "# you have to install manually some dependencies:\n", "\n", "!pip install darts # descomentar para instalação inicial\n", "!pip install prophet\n", "!pip install statsforecast" ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "collapsed": true, "id": "_eQ3qsd92Rks" }, "outputs": [], "source": [ "from darts.models import (\n", " NaiveSeasonal,\n", " NaiveDrift,\n", " Prophet,\n", " ExponentialSmoothing,\n", " ARIMA,\n", " AutoARIMA,\n", " TBATS\n", ")\n", "\n", "from darts import TimeSeries\n", "from darts.metrics import mape, mase, mae, mse, ope, r2_score, rmse, rmsle\n", "from statsmodels.tsa.stattools import adfuller\n", "\n", "import time\n", "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "id": "396WjS0r2an5" }, "outputs": [], "source": [ "# importing data\n", "url = \"https://raw.githubusercontent.com/jbrownlee/Datasets/master/airline-passengers.csv\"\n", "df = pd.read_csv(url, parse_dates = ['Month'],index_col = ['Month'])\n", "series = TimeSeries.from_dataframe(df)" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 455 }, "id": "9hlKp0aHDnS8", "outputId": "46a1a9fd-5a6f-42c6-8768-3044edc62e10" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "summary": "{\n \"name\": \"df\",\n \"rows\": 144,\n \"fields\": [\n {\n \"column\": \"Month\",\n \"properties\": {\n \"dtype\": \"date\",\n \"min\": \"1949-01-01 00:00:00\",\n \"max\": \"1960-12-01 00:00:00\",\n \"num_unique_values\": 144,\n \"samples\": [\n \"1958-10-01 00:00:00\",\n \"1950-08-01 00:00:00\",\n \"1955-11-01 00:00:00\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"Passengers\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 119,\n \"min\": 104,\n \"max\": 622,\n \"num_unique_values\": 118,\n \"samples\": [\n 293,\n 340,\n 121\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", "type": "dataframe", "variable_name": "df" }, "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Passengers
Month
1949-01-01112
1949-02-01118
1949-03-01132
1949-04-01129
1949-05-01121
......
1960-08-01606
1960-09-01508
1960-10-01461
1960-11-01390
1960-12-01432
\n", "

144 rows × 1 columns

\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", " \n", " \n", " \n", "
\n", "\n", "
\n", "
\n" ], "text/plain": [ " Passengers\n", "Month \n", "1949-01-01 112\n", "1949-02-01 118\n", "1949-03-01 132\n", "1949-04-01 129\n", "1949-05-01 121\n", "... ...\n", "1960-08-01 606\n", "1960-09-01 508\n", "1960-10-01 461\n", "1960-11-01 390\n", "1960-12-01 432\n", "\n", "[144 rows x 1 columns]" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "id": "OtSiPHDE94et" }, "outputs": [], "source": [ "# split train and test using DARTS split features\n", "train, val = series.split_before(pd.Timestamp('19600101'))" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 1000 }, "collapsed": true, "id": "NGsBVzXi4quV", "outputId": "b3172fd3-33e5-486b-c5d8-0a86380dcb41" }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "
<TimeSeries (Month: 132, component: 1, sample: 1)> Size: 1kB\n",
       "array([[[112.]],\n",
       "\n",
       "       [[118.]],\n",
       "\n",
       "       [[132.]],\n",
       "\n",
       "       [[129.]],\n",
       "\n",
       "       [[121.]],\n",
       "\n",
       "       [[135.]],\n",
       "\n",
       "       [[148.]],\n",
       "\n",
       "       [[148.]],\n",
       "\n",
       "       [[136.]],\n",
       "\n",
       "       [[119.]],\n",
       "\n",
       "...\n",
       "\n",
       "       [[406.]],\n",
       "\n",
       "       [[396.]],\n",
       "\n",
       "       [[420.]],\n",
       "\n",
       "       [[472.]],\n",
       "\n",
       "       [[548.]],\n",
       "\n",
       "       [[559.]],\n",
       "\n",
       "       [[463.]],\n",
       "\n",
       "       [[407.]],\n",
       "\n",
       "       [[362.]],\n",
       "\n",
       "       [[405.]]])\n",
       "Coordinates:\n",
       "  * Month      (Month) datetime64[ns] 1kB 1949-01-01 1949-02-01 ... 1959-12-01\n",
       "  * component  (component) object 8B 'Passengers'\n",
       "Dimensions without coordinates: sample\n",
       "Attributes:\n",
       "    static_covariates:  None\n",
       "    hierarchy:          None\n",
       "    metadata:           None
" ], "text/plain": [ " Size: 1kB\n", "array([[[112.]],\n", "\n", " [[118.]],\n", "\n", " [[132.]],\n", "\n", " [[129.]],\n", "\n", " [[121.]],\n", "\n", " [[135.]],\n", "\n", " [[148.]],\n", "\n", " [[148.]],\n", "\n", " [[136.]],\n", "\n", " [[119.]],\n", "\n", "...\n", "\n", " [[406.]],\n", "\n", " [[396.]],\n", "\n", " [[420.]],\n", "\n", " [[472.]],\n", "\n", " [[548.]],\n", "\n", " [[559.]],\n", "\n", " [[463.]],\n", "\n", " [[407.]],\n", "\n", " [[362.]],\n", "\n", " [[405.]]])\n", "Coordinates:\n", " * Month (Month) datetime64[ns] 1kB 1949-01-01 1949-02-01 ... 1959-12-01\n", " * component (component) object 8B 'Passengers'\n", "Dimensions without coordinates: sample\n", "Attributes:\n", " static_covariates: None\n", " hierarchy: None\n", " metadata: None" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train" ] }, { "cell_type": "markdown", "metadata": { "id": "-Ka8Ynu8O3Dj" }, "source": [ "### 2. Quick example on how to use DARTS" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 448 }, "id": "X7GBYHti-AU5", "outputId": "db8d613e-be15-4f63-aa46-72c0c2d42981" }, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# training a Exponential Smoothing model and plotting prediction\n", "model = ExponentialSmoothing()\n", "model.fit(train)\n", "prediction = model.predict(len(val))\n", "\n", "series.plot(label='actual')\n", "prediction.plot(label='forecast', lw=3)\n", "plt.legend();\n", "\n" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 1000 }, "id": "lJfCNOcvYKav", "outputId": "9e74a7e4-f7c4-4364-b8e4-16eac07f6bc7" }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "
<TimeSeries (Month: 144, component: 1, sample: 1)> Size: 1kB\n",
       "array([[[112.]],\n",
       "\n",
       "       [[118.]],\n",
       "\n",
       "       [[132.]],\n",
       "\n",
       "       [[129.]],\n",
       "\n",
       "       [[121.]],\n",
       "\n",
       "       [[135.]],\n",
       "\n",
       "       [[148.]],\n",
       "\n",
       "       [[148.]],\n",
       "\n",
       "       [[136.]],\n",
       "\n",
       "       [[119.]],\n",
       "\n",
       "...\n",
       "\n",
       "       [[419.]],\n",
       "\n",
       "       [[461.]],\n",
       "\n",
       "       [[472.]],\n",
       "\n",
       "       [[535.]],\n",
       "\n",
       "       [[622.]],\n",
       "\n",
       "       [[606.]],\n",
       "\n",
       "       [[508.]],\n",
       "\n",
       "       [[461.]],\n",
       "\n",
       "       [[390.]],\n",
       "\n",
       "       [[432.]]])\n",
       "Coordinates:\n",
       "  * Month      (Month) datetime64[ns] 1kB 1949-01-01 1949-02-01 ... 1960-12-01\n",
       "  * component  (component) object 8B 'Passengers'\n",
       "Dimensions without coordinates: sample\n",
       "Attributes:\n",
       "    static_covariates:  None\n",
       "    hierarchy:          None\n",
       "    metadata:           None
" ], "text/plain": [ " Size: 1kB\n", "array([[[112.]],\n", "\n", " [[118.]],\n", "\n", " [[132.]],\n", "\n", " [[129.]],\n", "\n", " [[121.]],\n", "\n", " [[135.]],\n", "\n", " [[148.]],\n", "\n", " [[148.]],\n", "\n", " [[136.]],\n", "\n", " [[119.]],\n", "\n", "...\n", "\n", " [[419.]],\n", "\n", " [[461.]],\n", "\n", " [[472.]],\n", "\n", " [[535.]],\n", "\n", " [[622.]],\n", "\n", " [[606.]],\n", "\n", " [[508.]],\n", "\n", " [[461.]],\n", "\n", " [[390.]],\n", "\n", " [[432.]]])\n", "Coordinates:\n", " * Month (Month) datetime64[ns] 1kB 1949-01-01 1949-02-01 ... 1960-12-01\n", " * component (component) object 8B 'Passengers'\n", "Dimensions without coordinates: sample\n", "Attributes:\n", " static_covariates: None\n", " hierarchy: None\n", " metadata: None" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "series" ] }, { "cell_type": "markdown", "metadata": { "id": "PHvuwYxSO8fL" }, "source": [ "### 3. Testing for stationarity" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "l_2v3n5P-9mG", "outputId": "501d7afb-2aee-4d14-9c8c-e95945370764" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "ADF Statistic: 0.815369\n", "p-value: 0.991880\n", "Critical Values:\n", "\t1%: -3.482\n", "\t5%: -2.884\n", "\t10%: -2.579\n", "Fail to reject the null hypothesis: The series is non-stationary\n" ] } ], "source": [ "# get order of first differencing: the higher of KPSS and ADF test results\n", "result = adfuller(series.to_dataframe())\n", "print('ADF Statistic: %f' % result[0])\n", "print('p-value: %f' % result[1])\n", "print('Critical Values:')\n", "for key, value in result[4].items():\n", " print('\\t%s: %.3f' % (key, value))\n", "if result[1] <= 0.05:\n", " print(\"Reject the null hypothesis: The series is stationary\")\n", "else:\n", " print(\"Fail to reject the null hypothesis: The series is non-stationary\")" ] }, { "cell_type": "markdown", "metadata": { "id": "_rpMNq02PEJj" }, "source": [ "### 4. Algorithms setup: setting the algorithm's hyparameters" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "id": "Ka_elqHHA9GG" }, "outputs": [], "source": [ "# exponential smoothing\n", "m_expon = ExponentialSmoothing()\n", "\n", "# prepare Prophet forecaster: multiplicative seas\n", "m_prophet_m = Prophet(seasonality_mode=\"multiplicative\")\n", "\n", "# prepare Prophet forecaster: additive seas\n", "m_prophet_a = Prophet(seasonality_mode=\"additive\")\n", "\n", "# prepare autoARIMA from StatsForecast\n", "m_autoarima_stats = AutoARIMA(season_length=12)" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "id": "VEOV65OcBwCC" }, "outputs": [], "source": [ "# list of models to be evaluated\n", "\n", "models = [\n", " m_expon,\n", " m_prophet_m,\n", " m_prophet_a,\n", " m_autoarima_stats]" ] }, { "cell_type": "markdown", "metadata": { "id": "1C6WeWrSPUAp" }, "source": [ "### 5. Creating an evaluating function to run many models" ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "id": "gsqbXc5GB6x_" }, "outputs": [], "source": [ "## fit the chosen forecaster model and compute predictions\n", "\n", "def eval_model(model, train, val):\n", " t_start = time.perf_counter()\n", " print(\"beginning: \" + str(model))\n", "\n", "\n", " # fit the model and compute predictions\n", " res = model.fit(train)\n", " forecast = model.predict(len(val))\n", "\n", " # compute accuracy metrics and processing time\n", " res_mape = mape(val, forecast)\n", " res_mae = mae(val, forecast)\n", " res_r2 = r2_score(val, forecast)\n", " res_rmse = rmse(val, forecast)\n", " res_rmsle = rmsle(val, forecast)\n", " res_time = time.perf_counter() - t_start\n", " res_accuracy = {\"MAPE\":res_mape, \"MAE\":res_mae, \"R squared\":-res_r2, \"RMSE\":res_rmse, \"RMSLE\":res_rmsle, \"time\":res_time}\n", "\n", " results = [forecast, res_accuracy, res]\n", " print(\"completed: \" + str(model) + \":\" + str(res_time) + \"sec\")\n", " return results" ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "a0Cc2ynpC5qk", "outputId": "98f0e281-6d39-4f74-adaa-257a9f40947d" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "INFO:prophet:Disabling weekly seasonality. Run prophet with weekly_seasonality=True to override this.\n", "INFO:prophet:Disabling daily seasonality. Run prophet with daily_seasonality=True to override this.\n", "DEBUG:cmdstanpy:input tempfile: /tmp/tmpsmrsqidc/46addqmn.json\n", "DEBUG:cmdstanpy:input tempfile: /tmp/tmpsmrsqidc/go38u1f_.json\n", "DEBUG:cmdstanpy:idx 0\n", "DEBUG:cmdstanpy:running CmdStan, num_threads: None\n", "DEBUG:cmdstanpy:CmdStan args: ['/usr/local/lib/python3.12/dist-packages/prophet/stan_model/prophet_model.bin', 'random', 'seed=93078', 'data', 'file=/tmp/tmpsmrsqidc/46addqmn.json', 'init=/tmp/tmpsmrsqidc/go38u1f_.json', 'output', 'file=/tmp/tmpsmrsqidc/prophet_modelsh24rfd8/prophet_model-20251027112503.csv', 'method=optimize', 'algorithm=lbfgs', 'iter=10000']\n", "11:25:03 - cmdstanpy - INFO - Chain [1] start processing\n", "INFO:cmdstanpy:Chain [1] start processing\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "beginning: Prophet(seasonality_mode=multiplicative)\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "11:25:03 - cmdstanpy - INFO - Chain [1] done processing\n", "INFO:cmdstanpy:Chain [1] done processing\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "completed: Prophet(seasonality_mode=multiplicative):0.27867658200011647sec\n" ] }, { "data": { "text/plain": [ "{'MAPE': np.float64(4.443829749162533),\n", " 'MAE': np.float64(21.908813279003937),\n", " 'R squared': np.float64(-0.8794305116779759),\n", " 'RMSE': np.float64(25.84359362409569),\n", " 'RMSLE': np.float64(0.05137792905621055),\n", " 'time': 0.27867658200011647}" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "eval_model(m_prophet_m, train, val)[1]" ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "Ax9AUdjFC_TV", "outputId": "f628c424-a250-45dd-8f11-87af29ba7a1f" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "beginning: AutoARIMA(season_length=12)\n", "completed: AutoARIMA(season_length=12):0.7895365719998608sec\n" ] }, { "data": { "text/plain": [ "{'MAPE': np.float64(4.1796926177437514),\n", " 'MAE': np.float64(18.515823497791207),\n", " 'R squared': np.float64(-0.8967154852992124),\n", " 'RMSE': np.float64(23.919483693648484),\n", " 'RMSLE': np.float64(0.05350335125515268),\n", " 'time': 0.7895365719998608}" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "eval_model(m_autoarima_stats, train, val)[1]" ] }, { "cell_type": "markdown", "metadata": { "id": "DcuaTmiEQMYv" }, "source": [ "Running all the models" ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "bjgTDd3ND--t", "outputId": "be89fa84-feec-44d1-ee80-8fc26c4f3df2" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "INFO:prophet:Disabling weekly seasonality. Run prophet with weekly_seasonality=True to override this.\n", "INFO:prophet:Disabling daily seasonality. Run prophet with daily_seasonality=True to override this.\n", "DEBUG:cmdstanpy:input tempfile: /tmp/tmpsmrsqidc/br4f6u2o.json\n", "DEBUG:cmdstanpy:input tempfile: /tmp/tmpsmrsqidc/ndqs0vnm.json\n", "DEBUG:cmdstanpy:idx 0\n", "DEBUG:cmdstanpy:running CmdStan, num_threads: None\n", "DEBUG:cmdstanpy:CmdStan args: ['/usr/local/lib/python3.12/dist-packages/prophet/stan_model/prophet_model.bin', 'random', 'seed=99610', 'data', 'file=/tmp/tmpsmrsqidc/br4f6u2o.json', 'init=/tmp/tmpsmrsqidc/ndqs0vnm.json', 'output', 'file=/tmp/tmpsmrsqidc/prophet_model7l53bls7/prophet_model-20251027112533.csv', 'method=optimize', 'algorithm=lbfgs', 'iter=10000']\n", "11:25:33 - cmdstanpy - INFO - Chain [1] start processing\n", "INFO:cmdstanpy:Chain [1] start processing\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "beginning: ExponentialSmoothing()\n", "completed: ExponentialSmoothing():0.12557467699980407sec\n", "beginning: Prophet(seasonality_mode=multiplicative)\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "11:25:33 - cmdstanpy - INFO - Chain [1] done processing\n", "INFO:cmdstanpy:Chain [1] done processing\n", "INFO:prophet:Disabling weekly seasonality. Run prophet with weekly_seasonality=True to override this.\n", "INFO:prophet:Disabling daily seasonality. Run prophet with daily_seasonality=True to override this.\n", "DEBUG:cmdstanpy:input tempfile: /tmp/tmpsmrsqidc/a5aacn1w.json\n", "DEBUG:cmdstanpy:input tempfile: /tmp/tmpsmrsqidc/t23uv7jp.json\n", "DEBUG:cmdstanpy:idx 0\n", "DEBUG:cmdstanpy:running CmdStan, num_threads: None\n", "DEBUG:cmdstanpy:CmdStan args: ['/usr/local/lib/python3.12/dist-packages/prophet/stan_model/prophet_model.bin', 'random', 'seed=15503', 'data', 'file=/tmp/tmpsmrsqidc/a5aacn1w.json', 'init=/tmp/tmpsmrsqidc/t23uv7jp.json', 'output', 'file=/tmp/tmpsmrsqidc/prophet_modelhvm5g455/prophet_model-20251027112533.csv', 'method=optimize', 'algorithm=lbfgs', 'iter=10000']\n", "11:25:33 - cmdstanpy - INFO - Chain [1] start processing\n", "INFO:cmdstanpy:Chain [1] start processing\n", "11:25:33 - cmdstanpy - INFO - Chain [1] done processing\n", "INFO:cmdstanpy:Chain [1] done processing\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "completed: Prophet(seasonality_mode=multiplicative):0.13173181999991357sec\n", "beginning: Prophet(seasonality_mode=additive)\n", "completed: Prophet(seasonality_mode=additive):0.09849881199988886sec\n", "beginning: AutoARIMA(season_length=12)\n", "completed: AutoARIMA(season_length=12):0.37064578100012113sec\n" ] } ], "source": [ "# call the forecasters one after the other\n", "model_predictions = [eval_model(model, train, val) for model in models]" ] }, { "cell_type": "code", "execution_count": 19, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 238 }, "id": "UzKJmz6DQRRN", "outputId": "e8c9cde4-84e2-428b-8eff-3efe2b4c9787" }, "outputs": [ { "data": { "text/html": [ "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
 ExponentialSmoothing()Prophet(seasonality_mode=multiplicative)Prophet(seasonality_mode=additive)AutoARIMA(season_length=12)
MAPE2.8031364.4438306.6142274.179693
MAE13.38216221.90881333.43448518.515823
R squared-0.947945-0.879431-0.665160-0.896715
RMSE16.98106825.84359443.06779923.919484
RMSLE0.0355010.0513780.0819150.053503
time0.1255750.1317320.0984990.370646
\n" ], "text/plain": [ "" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# RUN the forecasters and tabulate their prediction accuracy and processing time\n", "\n", "df_acc = pd.DataFrame.from_dict(model_predictions[0][1], orient=\"index\")\n", "df_acc.columns = [str(models[0])]\n", "\n", "for i, m in enumerate(models):\n", " if i > 0:\n", " df = pd.DataFrame.from_dict(model_predictions[i][1], orient=\"index\")\n", " df.columns = [str(m)]\n", " df_acc = pd.concat([df_acc, df], axis=1)\n", " i +=1\n", "\n", "pd.set_option(\"display.precision\",3)\n", "df_acc.style.highlight_min(color=\"lightgreen\", axis=1).highlight_max(color=\"yellow\", axis=1)\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "lmovK3Km7EQQ" }, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": { "id": "hPBS6hjURflN" }, "source": [ "### 6. Cross validation using DARTS" ] }, { "cell_type": "code", "execution_count": 26, "metadata": { "id": "EHYE6WY7bpSE" }, "outputs": [], "source": [ "import logging\n", "\n", "logging.getLogger(\"prophet\").setLevel(logging.WARNING)\n", "logging.getLogger(\"cmdstanpy\").disabled=True" ] }, { "cell_type": "code", "execution_count": 27, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 581 }, "id": "GJ0fCtt4QRlM", "outputId": "18adabd8-3e0b-48ff-9d3f-d3dab62908bf" }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "models_backtest = [m_expon, m_prophet_m, m_autoarima_stats]\n", "backtests = [model.historical_forecasts(series, start=.5, forecast_horizon=12) for model in models_backtest]\n", "\n", "plt.figure(figsize=(10, 6))\n", "series.plot(label='data')\n", "for i, m in enumerate(models_backtest):\n", " err = mape(backtests[i], series)\n", " backtests[i].plot(lw=3, label='{}, MAPE={:.2f}%'.format(m, err))\n", "\n", "plt.title('Backtests with 12-months forecast horizon')\n", "plt.legend()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "yF-zMbW1chx-" }, "outputs": [], "source": [] } ], "metadata": { "colab": { "provenance": [] }, "kernelspec": { "display_name": "Python 3", "name": "python3" }, "language_info": { "name": "python" }, "execute": { "enabled": false } }, "nbformat": 4, "nbformat_minor": 0 }