{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# N-BEATS\n", "In this notebook, we show an example of how **N-BEATS** can be used with darts. If you are new to darts, we recommend you first follow the [quick start](https://unit8co.github.io/darts/quickstart/00-quickstart.html) notebook. \n", "\n", "**N-BEATS** is a state-of-the-art model that shows the potential of **pure DL architectures** in the context of the time-series forecasting. It outperforms well-established statistical approaches on the *M3*, and *M4* competitions. For more details on the model, see: https://arxiv.org/pdf/1905.10437.pdf." ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "# fix python path if working locally\n", "from utils import fix_pythonpath_if_working_locally\n", "\n", "fix_pythonpath_if_working_locally()\n", "%matplotlib inline" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "import warnings\n", "\n", "import matplotlib.pyplot as plt\n", "import numpy as np\n", "import pandas as pd\n", "\n", "from darts import TimeSeries, concatenate\n", "from darts.dataprocessing.transformers import MissingValuesFiller, Scaler\n", "from darts.datasets import EnergyDataset\n", "from darts.metrics import r2_score\n", "from darts.models import NBEATSModel\n", "from darts.utils.callbacks import TFMProgressBar\n", "\n", "warnings.filterwarnings(\"ignore\")\n", "import logging\n", "\n", "logging.disable(logging.CRITICAL)\n", "\n", "\n", "def generate_torch_kwargs():\n", " # run torch models on CPU, and disable progress bars for all model stages except training.\n", " return {\n", " \"pl_trainer_kwargs\": {\n", " \"accelerator\": \"cpu\",\n", " \"callbacks\": [TFMProgressBar(enable_train_bar_only=True)],\n", " }\n", " }" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "def display_forecast(pred_series, ts_transformed, forecast_type, start_date=None):\n", " plt.figure(figsize=(8, 5))\n", " if start_date:\n", " ts_transformed = ts_transformed.drop_before(start_date)\n", " ts_transformed.univariate_component(0).plot(label=\"actual\")\n", " pred_series.plot(label=(\"historic \" + forecast_type + \" forecasts\"))\n", " plt.title(f\"R2: {r2_score(ts_transformed.univariate_component(0), pred_series)}\")\n", " plt.legend()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Daily energy generation example" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We test NBEATS on a daily energy generation dataset from a Run-of-river power plant, as it exhibits various levels of seasonalities" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Text(0.5, 1.0, 'Hourly generation hydro run-of-river and poundage')" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "df = EnergyDataset().load().to_dataframe()\n", "df[\"generation hydro run-of-river and poundage\"].plot()\n", "plt.title(\"Hourly generation hydro run-of-river and poundage\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "To simplify things, we work with the daily generation, and we fill the missing values present in the data by using the `MissingValuesFiller`:" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Text(0.5, 1.0, 'Daily generation hydro run-of-river and poundage')" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "df_day_avg = df.groupby(df.index.astype(str).str.split(\" \").str[0]).mean().reset_index()\n", "filler = MissingValuesFiller()\n", "scaler = Scaler()\n", "series = filler.transform(\n", " TimeSeries.from_dataframe(\n", " df_day_avg, \"time\", [\"generation hydro run-of-river and poundage\"]\n", " )\n", ").astype(np.float32)\n", "\n", "train, val = series.split_after(pd.Timestamp(\"20170901\"))\n", "\n", "train_scaled = scaler.fit_transform(train)\n", "val_scaled = scaler.transform(val)\n", "series_scaled = scaler.transform(series)\n", "\n", "\n", "train_scaled.plot(label=\"training\")\n", "val_scaled.plot(label=\"val\")\n", "plt.title(\"Daily generation hydro run-of-river and poundage\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We split the data into train and validation sets. Normally we would need to use an additional test set to validate the model on unseen data, but we will skip it for this example." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Generic architecture" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "N-BEATS is a univariate model architecture that offers two configurations: a *generic* one and a *interpretable* one. The **generic architecture** uses as little prior knowledge as possible, with no feature engineering, no scaling and no internal architectural components that may be considered time-series-specific. " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "To start off, we use a model with the generic architecture of N-BEATS:" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "model_name = \"nbeats_run\"\n", "model_nbeats = NBEATSModel(\n", " input_chunk_length=30,\n", " output_chunk_length=7,\n", " generic_architecture=True,\n", " num_stacks=10,\n", " num_blocks=1,\n", " num_layers=4,\n", " layer_widths=512,\n", " n_epochs=100,\n", " nr_epochs_val_period=1,\n", " batch_size=800,\n", " random_state=42,\n", " model_name=model_name,\n", " save_checkpoints=True,\n", " force_reset=True,\n", " **generate_torch_kwargs(),\n", ")" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "b1d7887232854d218c2c985af1f68549", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Training: 0it [00:00, ?it/s]" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [ "NBEATSModel(generic_architecture=True, num_stacks=10, num_blocks=1, num_layers=4, layer_widths=512, expansion_coefficient_dim=5, trend_polynomial_degree=2, dropout=0.0, activation=ReLU, input_chunk_length=30, output_chunk_length=7, n_epochs=100, nr_epochs_val_period=1, batch_size=800, random_state=42, model_name=nbeats_run, save_checkpoints=True, force_reset=True, pl_trainer_kwargs={'accelerator': 'cpu', 'callbacks': []})" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "model_nbeats.fit(train_scaled, val_series=val_scaled)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let's load the model from the checkpoint that performed best on the validation set. " ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "model_nbeats = NBEATSModel.load_from_checkpoint(model_name=model_name, best=True)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let's see the historical forecasts the model would have produced with an expanding training window, and a forecasting horizon of 7:" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "59ba1c2b2fcd4550b11c21b2c0e8730d", "version_major": 2, "version_minor": 0 }, "text/plain": [ " 0%| | 0/69 [00:00" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "display_forecast(\n", " pred_series,\n", " series_scaled,\n", " \"7 day\",\n", " start_date=val.start_time(),\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Interpretable model" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "N-BEATS offers an *interpretable architecture* consisting of two stacks: A **trend** stack and a **seasonality** stack. The architecture is designed so that:\n", "\n", "- The trend component is removed from the input before it is fed into the seasonality stack \n", "- The **partial forecasts of trend and seasonality are available** as separate interpretable outputs" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "model_name = \"nbeats_interpretable_run\"\n", "model_nbeats = NBEATSModel(\n", " input_chunk_length=30,\n", " output_chunk_length=7,\n", " generic_architecture=False,\n", " num_blocks=3,\n", " num_layers=4,\n", " layer_widths=512,\n", " n_epochs=100,\n", " nr_epochs_val_period=1,\n", " batch_size=800,\n", " random_state=42,\n", " model_name=model_name,\n", " save_checkpoints=True,\n", " force_reset=True,\n", " **generate_torch_kwargs(),\n", ")" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "c8617c1398ef4c6e9589310cb501d8ec", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Training: 0it [00:00, ?it/s]" ] }, "metadata": {}, "output_type": "display_data" }, { "data": { "text/plain": [ "NBEATSModel(generic_architecture=False, num_stacks=30, num_blocks=3, num_layers=4, layer_widths=512, expansion_coefficient_dim=5, trend_polynomial_degree=2, dropout=0.0, activation=ReLU, input_chunk_length=30, output_chunk_length=7, n_epochs=100, nr_epochs_val_period=1, batch_size=800, random_state=42, model_name=nbeats_interpretable_run, save_checkpoints=True, force_reset=True, pl_trainer_kwargs={'accelerator': 'cpu', 'callbacks': []})" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "model_nbeats.fit(series=train_scaled, val_series=val_scaled)" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [], "source": [ "model_nbeats = NBEATSModel.load_from_checkpoint(model_name=model_name, best=True)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Let's see the historical forecasts the model would have produced with an expanding training window, and a forecasting horizon of 7:" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "80997b3a992b4daa85838a21c5cdaade", "version_major": 2, "version_minor": 0 }, "text/plain": [ " 0%| | 0/69 [00:00" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "display_forecast(\n", " pred_series, series_scaled, \"7 day\", start_date=val_scaled.start_time()\n", ")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "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": "3.10.13" } }, "nbformat": 4, "nbformat_minor": 4 }