{ "cells": [ { "cell_type": "markdown", "id": "670316b8-460c-4009-a5da-94278f4ac9a9", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "source": [ "# Time Series" ] }, { "cell_type": "code", "execution_count": 1, "id": "52af59bb-083c-46c6-989a-bd4c65137a1a", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "outputs": [], "source": [ "# Import to be able to import python package from src\n", "import sys\n", "sys.path.insert(0, '../src')" ] }, { "cell_type": "code", "execution_count": 2, "id": "4aed48a7-3452-4632-b1d5-e501893c6078", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "['../src', '/usr/lib/python310.zip', '/usr/lib/python3.10', '/usr/lib/python3.10/lib-dynload', '', '/home/benjy/.cache/pypoetry/virtualenvs/ontime-2OQVvbNf-py3.10/lib/python3.10/site-packages', '/home/benjy/projects_dev/ontime/src']\n" ] } ], "source": [ "print(sys.path)" ] }, { "cell_type": "code", "execution_count": 3, "id": "d6fc731f-3f50-4e9a-a24c-b2ab01d4fa31", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "import ontime as on" ] }, { "cell_type": "markdown", "id": "831f1944-599b-4761-a071-2a682346610a", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "source": [ "---\n", "## Generation of random time series" ] }, { "cell_type": "code", "execution_count": 4, "id": "ef3e03e1-c247-4b5a-a27a-a13361e673b0", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "outputs": [], "source": [ "ts = on.generators.random_walk().generate(start=pd.Timestamp('2022-01-01'), end=pd.Timestamp('2022-12-31'))" ] }, { "cell_type": "code", "execution_count": 5, "id": "01962643-33af-4adf-8bfa-7d0163e4e41c", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "
<TimeSeries (DataArray) (time: 5, component: 1, sample: 1)> Size: 40B\n",
       "array([[[0.18681962]],\n",
       "\n",
       "       [[1.38205429]],\n",
       "\n",
       "       [[1.85408518]],\n",
       "\n",
       "       [[1.01011117]],\n",
       "\n",
       "       [[0.37180233]]])\n",
       "Coordinates:\n",
       "  * time       (time) datetime64[ns] 40B 2022-01-01 2022-01-02 ... 2022-01-05\n",
       "  * component  (component) object 8B 'random_walk'\n",
       "Dimensions without coordinates: sample\n",
       "Attributes:\n",
       "    static_covariates:  None\n",
       "    hierarchy:          None
" ], "text/plain": [ " Size: 40B\n", "array([[[0.18681962]],\n", "\n", " [[1.38205429]],\n", "\n", " [[1.85408518]],\n", "\n", " [[1.01011117]],\n", "\n", " [[0.37180233]]])\n", "Coordinates:\n", " * time (time) datetime64[ns] 40B 2022-01-01 2022-01-02 ... 2022-01-05\n", " * component (component) object 8B 'random_walk'\n", "Dimensions without coordinates: sample\n", "Attributes:\n", " static_covariates: None\n", " hierarchy: None" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ts[0:5]" ] }, { "cell_type": "markdown", "id": "0cbd8da5-81fd-4b2d-8b7d-8394ad87348b", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "source": [ "---\n", "## Use `TimeSeries` object" ] }, { "cell_type": "code", "execution_count": 7, "id": "1cbbd4f4-035d-43fa-93a7-6801b944835f", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "
\n", "" ], "text/plain": [ "alt.LayerChart(...)" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ts.plot()" ] }, { "cell_type": "markdown", "id": "06a8a724-7142-4077-b8b6-afafa8950d7b", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "source": [ "---\n", "## Custom Class Creation" ] }, { "cell_type": "markdown", "id": "cd126529-3b5e-4a22-a871-60d221b6df6d", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "source": [ "### Create custom detector" ] }, { "cell_type": "code", "execution_count": 8, "id": "40a0dd53-0fe9-40a7-86d9-ee551e4c5e6e", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "outputs": [], "source": [ "from ontime.core.detection.abstract_detector import AbstractDetector\n", "\n", "class MyAE(AbstractDetector):\n", "\n", " def __init__(self):\n", " super().__init__()\n", "\n", " def detect(self, ts):\n", " print('I detected')\n", " " ] }, { "cell_type": "markdown", "id": "55bc256f-0ca3-4087-b7a9-bf563f26ffe7", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "source": [ "Load custom detector in OnTime" ] }, { "cell_type": "code", "execution_count": 9, "id": "6a8dd074-6350-4c3a-a8a7-7d901b790f95", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "outputs": [ { "data": { "text/plain": [ "['threshold', 'quantile']" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "on.detectors.get_all()" ] }, { "cell_type": "code", "execution_count": 10, "id": "91bdf719-f451-4d07-aaed-c2f5f7b4fa1b", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "outputs": [], "source": [ "on.detectors.load('my_ae', MyAE)" ] }, { "cell_type": "code", "execution_count": 11, "id": "bb636aa5-f155-46e4-8038-027d5f5db78a", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "outputs": [ { "data": { "text/plain": [ "['threshold', 'quantile', 'my_ae']" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "on.detectors.get_all()" ] }, { "cell_type": "code", "execution_count": 12, "id": "f16ac090-142d-4d1b-8351-40b443275c72", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "I detected\n" ] } ], "source": [ "on.detectors.my_ae().detect(ts)" ] }, { "cell_type": "markdown", "id": "74a24176-7c9b-4790-9e5c-ac71e8517872", "metadata": { "papermill": { "duration": null, "end_time": null, "exception": null, "start_time": null, "status": "completed" }, "tags": [] }, "source": [ "---\n", "## Data Loading Helpers\n", "\n", "\n", "### From Darts to onTime\n", "You can convert a timeseries from Darts' TimeSeries object type to ontime's TimeSeries type." ] }, { "cell_type": "code", "execution_count": 13, "id": "fe6b4821-9365-4356-b53d-cd5f1fb222ef", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "
<TimeSeries (DataArray) (Month: 5, component: 1, sample: 1)> Size: 40B\n",
       "array([[[112.]],\n",
       "\n",
       "       [[118.]],\n",
       "\n",
       "       [[132.]],\n",
       "\n",
       "       [[129.]],\n",
       "\n",
       "       [[121.]]])\n",
       "Coordinates:\n",
       "  * Month      (Month) datetime64[ns] 40B 1949-01-01 1949-02-01 ... 1949-05-01\n",
       "  * component  (component) object 8B '#Passengers'\n",
       "Dimensions without coordinates: sample\n",
       "Attributes:\n",
       "    static_covariates:  None\n",
       "    hierarchy:          None
" ], "text/plain": [ " Size: 40B\n", "array([[[112.]],\n", "\n", " [[118.]],\n", "\n", " [[132.]],\n", "\n", " [[129.]],\n", "\n", " [[121.]]])\n", "Coordinates:\n", " * Month (Month) datetime64[ns] 40B 1949-01-01 1949-02-01 ... 1949-05-01\n", " * component (component) object 8B '#Passengers'\n", "Dimensions without coordinates: sample\n", "Attributes:\n", " static_covariates: None\n", " hierarchy: None" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from darts import datasets as dd\n", "\n", "dartsAirPassengers = dd.AirPassengersDataset().load()\n", "print(type(dartsAirPassengers))\n", "dartsAirPassengers.head()" ] }, { "cell_type": "code", "execution_count": 14, "id": "dd88e23a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n" ] }, { "data": { "text/html": [ "
\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "
<TimeSeries (DataArray) (Month: 5, component: 1, sample: 1)> Size: 40B\n",
       "array([[[112.]],\n",
       "\n",
       "       [[118.]],\n",
       "\n",
       "       [[132.]],\n",
       "\n",
       "       [[129.]],\n",
       "\n",
       "       [[121.]]])\n",
       "Coordinates:\n",
       "  * Month      (Month) datetime64[ns] 40B 1949-01-01 1949-02-01 ... 1949-05-01\n",
       "  * component  (component) object 8B '#Passengers'\n",
       "Dimensions without coordinates: sample\n",
       "Attributes:\n",
       "    static_covariates:  None\n",
       "    hierarchy:          None
" ], "text/plain": [ " Size: 40B\n", "array([[[112.]],\n", "\n", " [[118.]],\n", "\n", " [[132.]],\n", "\n", " [[129.]],\n", "\n", " [[121.]]])\n", "Coordinates:\n", " * Month (Month) datetime64[ns] 40B 1949-01-01 1949-02-01 ... 1949-05-01\n", " * component (component) object 8B '#Passengers'\n", "Dimensions without coordinates: sample\n", "Attributes:\n", " static_covariates: None\n", " hierarchy: None" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ontimeAirPassengers = on.TimeSeries.from_darts(dartsAirPassengers)\n", "print(type(ontimeAirPassengers))\n", "ontimeAirPassengers.head()" ] }, { "cell_type": "markdown", "id": "15ac77fc-681f-4087-a816-aa17841b3273", "metadata": {}, "source": [ "### From Pandas to onTime\n", "\n", "You can convert a Pandas DataFrame to onTime's TimeSeries format, provided the DataFrame's index is time-based." ] }, { "cell_type": "code", "execution_count": 23, "id": "3de25cf0-c333-48e1-b34b-c82724fc5ec9", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n" ] }, { "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", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
OpenHighLowCloseAdj_CloseVolume
time
1980-03-170.03.3020833.1250003.1458333.145833219600
1980-03-180.03.1250002.9375003.0312503.031250727200
1980-03-190.03.0833333.0208333.0416673.041667295200
1980-03-200.03.0625003.0104173.0104173.010417159600
1980-03-210.03.0208332.9062502.9166672.916667130800
\n", "
" ], "text/plain": [ " Open High Low Close Adj_Close Volume\n", "time \n", "1980-03-17 0.0 3.302083 3.125000 3.145833 3.145833 219600\n", "1980-03-18 0.0 3.125000 2.937500 3.031250 3.031250 727200\n", "1980-03-19 0.0 3.083333 3.020833 3.041667 3.041667 295200\n", "1980-03-20 0.0 3.062500 3.010417 3.010417 3.010417 159600\n", "1980-03-21 0.0 3.020833 2.906250 2.916667 2.916667 130800" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.datasets import fetch_openml\n", "\n", "pandasAmd = fetch_openml(\"AMD-Stock-Prices-Historical-Data\", version=1, as_frame=True, parser=\"pandas\").frame\n", "print(type(pandasAmd))\n", "# set index to be compliant with TimeEval's canonical format\n", "pandasAmd.index= pandasAmd['Date'].astype('datetime64[ns]')\n", "del pandasAmd['Date']\n", "pandasAmd = pandasAmd.rename_axis(\"time\")\n", "pandasAmd.head()" ] }, { "cell_type": "code", "execution_count": 24, "id": "ba52b0d5-804e-4839-a2a6-c4060e8c5f72", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "
<TimeSeries (DataArray) (time: 5, component: 6, sample: 1)> Size: 240B\n",
       "array([[[0.00000000e+00],\n",
       "        [3.30208302e+00],\n",
       "        [3.12500000e+00],\n",
       "        [3.14583302e+00],\n",
       "        [3.14583302e+00],\n",
       "        [2.19600000e+05]],\n",
       "\n",
       "       [[0.00000000e+00],\n",
       "        [3.12500000e+00],\n",
       "        [2.93750000e+00],\n",
       "        [3.03125000e+00],\n",
       "        [3.03125000e+00],\n",
       "        [7.27200000e+05]],\n",
       "\n",
       "       [[0.00000000e+00],\n",
       "        [3.08333302e+00],\n",
       "        [3.02083302e+00],\n",
       "        [3.04166698e+00],\n",
       "        [3.04166698e+00],\n",
       "        [2.95200000e+05]],\n",
       "\n",
       "       [[0.00000000e+00],\n",
       "        [3.06250000e+00],\n",
       "        [3.01041698e+00],\n",
       "        [3.01041698e+00],\n",
       "        [3.01041698e+00],\n",
       "        [1.59600000e+05]],\n",
       "\n",
       "       [[0.00000000e+00],\n",
       "        [3.02083302e+00],\n",
       "        [2.90625000e+00],\n",
       "        [2.91666698e+00],\n",
       "        [2.91666698e+00],\n",
       "        [1.30800000e+05]]])\n",
       "Coordinates:\n",
       "  * time       (time) datetime64[ns] 40B 1980-03-17 1980-03-18 ... 1980-03-21\n",
       "  * component  (component) object 48B 'Open' 'High' ... 'Adj_Close' 'Volume'\n",
       "Dimensions without coordinates: sample\n",
       "Attributes:\n",
       "    static_covariates:  None\n",
       "    hierarchy:          None
" ], "text/plain": [ " Size: 240B\n", "array([[[0.00000000e+00],\n", " [3.30208302e+00],\n", " [3.12500000e+00],\n", " [3.14583302e+00],\n", " [3.14583302e+00],\n", " [2.19600000e+05]],\n", "\n", " [[0.00000000e+00],\n", " [3.12500000e+00],\n", " [2.93750000e+00],\n", " [3.03125000e+00],\n", " [3.03125000e+00],\n", " [7.27200000e+05]],\n", "\n", " [[0.00000000e+00],\n", " [3.08333302e+00],\n", " [3.02083302e+00],\n", " [3.04166698e+00],\n", " [3.04166698e+00],\n", " [2.95200000e+05]],\n", "\n", " [[0.00000000e+00],\n", " [3.06250000e+00],\n", " [3.01041698e+00],\n", " [3.01041698e+00],\n", " [3.01041698e+00],\n", " [1.59600000e+05]],\n", "\n", " [[0.00000000e+00],\n", " [3.02083302e+00],\n", " [2.90625000e+00],\n", " [2.91666698e+00],\n", " [2.91666698e+00],\n", " [1.30800000e+05]]])\n", "Coordinates:\n", " * time (time) datetime64[ns] 40B 1980-03-17 1980-03-18 ... 1980-03-21\n", " * component (component) object 48B 'Open' 'High' ... 'Adj_Close' 'Volume'\n", "Dimensions without coordinates: sample\n", "Attributes:\n", " static_covariates: None\n", " hierarchy: None" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ontimeAmd = on.TimeSeries.from_pandas(pandasAmd, freq='D')\n", "ontimeAmd.head()" ] }, { "cell_type": "code", "execution_count": 25, "id": "fdc114d4-e8a0-4093-9556-c02a4ca81a18", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "
\n", "" ], "text/plain": [ "alt.LayerChart(...)" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" } ], "source": [ "ontimeAmd.plot()" ] }, { "cell_type": "markdown", "id": "0253d7eb-1227-41ed-9a03-f5f331a5dfed", "metadata": {}, "source": [ "### CSV to onTime\n", "\n", "You can convert data from a CSV file to onTime's TimeSeries format, provided the index is time-based and correctly formatted." ] }, { "cell_type": "code", "execution_count": 26, "id": "1217800d-503b-4939-adc0-3f7cd96c7a49", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "
\n", "" ], "text/plain": [ "alt.LayerChart(...)" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# let's generate some sample data\n", "ts = on.generators.random_walk().generate(start=pd.Timestamp('2022-01-01'), end=pd.Timestamp('2022-12-31'))\n", "ts.pd_dataframe().to_csv('sample_series.csv')\n", "\n", "# load that sample data\n", "ts = on.TimeSeries.from_csv('sample_series.csv', index_col='time')\n", "ts.plot()" ] }, { "cell_type": "markdown", "id": "f27bf901-d1b6-460e-b9cb-c7900144510d", "metadata": {}, "source": [ "### Data (e.g. Numpy) to onTime" ] }, { "cell_type": "markdown", "id": "c7b1d6b2-a146-4052-9613-ba9e6bca1645", "metadata": {}, "source": [ "You can assemble a TimeSeries if you have a data table and column names, provided the index is time-based and correctly formatted." ] }, { "cell_type": "code", "execution_count": 27, "id": "c9d57d37-6c6a-4d0f-9fc7-f34a95f0cd8f", "metadata": {}, "outputs": [], "source": [ "# generate some data\n", "from datetime import datetime\n", "data = np.random.rand(200,3)\n", "index = pd.date_range(datetime.today(), periods=200).tolist()\n", "columns = ['col1', 'col2', 'col3']" ] }, { "cell_type": "code", "execution_count": 28, "id": "5798d402-abd5-4eb1-b8ee-fdf3523703fc", "metadata": {}, "outputs": [ { "data": { "text/html": [ "\n", "\n", "
\n", "" ], "text/plain": [ "alt.LayerChart(...)" ] }, "execution_count": 28, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# assemble into a timeseries\n", "ts = on.TimeSeries.from_data(data, index = index, columns = columns)\n", "ts.plot()" ] }, { "cell_type": "code", "execution_count": null, "id": "56e89083-7642-4ef6-ac06-1cbe4e1de7d0", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "ontime-2OQVvbNf-py3.10", "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": "3.10.12" }, "papermill": { "default_parameters": {}, "duration": 60.248854, "end_time": "2024-01-31T17:51:31.161244", "environment_variables": {}, "exception": null, "input_path": "docs/user_guide/0_core/0.1-time-series-custom-class.ipynb", "output_path": "docs/user_guide/0_core/0.1-time-series-custom-class.ipynb", "parameters": {}, "start_time": "2024-01-31T17:50:30.912390", "version": "2.5.0" } }, "nbformat": 4, "nbformat_minor": 5 }