Merge develop

ontime-re · Nov 17, 2023 · db4d2a9 · db4d2a9
2 parents aa75f10 + 0999bd7
commit db4d2a9
Show file tree

Hide file tree

Showing 73 changed files with 2,776 additions and 3,846 deletions.
diff --git a/notebooks/demo.ipynb b/notebooks/demo.ipynb
diff --git a/notebooks/docs/0.1-time-series-custom-class.ipynb b/notebooks/docs/0.1-time-series-custom-class.ipynb
diff --git a/notebooks/docs/0.2-detectors-generators.ipynb b/notebooks/docs/0.2-detectors-generators.ipynb
diff --git a/notebooks/docs/0_core/0.1-time-series-custom-class.ipynb b/notebooks/docs/0_core/0.1-time-series-custom-class.ipynb
diff --git a/notebooks/docs/0_core/0.2-detectors-generators.ipynb b/notebooks/docs/0_core/0.2-detectors-generators.ipynb
diff --git a/notebooks/docs/0.3-processing.ipynb → notebooks/docs/0_core/0.3-processing.ipynb b/notebooks/docs/0.3-processing.ipynb → notebooks/docs/0_core/0.3-processing.ipynb
diff --git a/notebooks/docs/0.4-modelling-libraries.ipynb → notebooks/docs/0_core/0.4-modelling.ipynb b/notebooks/docs/0.4-modelling-libraries.ipynb → notebooks/docs/0_core/0.4-modelling.ipynb
diff --git a/notebooks/docs/0.6-plots.ipynb → notebooks/docs/0_core/0.5-plots.ipynb b/notebooks/docs/0.6-plots.ipynb → notebooks/docs/0_core/0.5-plots.ipynb
diff --git a/notebooks/docs/0.7-anomaly-frequency.ipynb → ...s/docs/0_core/0.6-anomaly-frequency.ipynb b/notebooks/docs/0.7-anomaly-frequency.ipynb → ...s/docs/0_core/0.6-anomaly-frequency.ipynb
diff --git a/notebooks/docs/1_module/1.0-preprocessing-common.ipynb b/notebooks/docs/1_module/1.0-preprocessing-common.ipynb
@@ -0,0 +1,251 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "41296cc6-9d84-47c5-8a92-2d292f6f3c4a",
+   "metadata": {},
+   "source": [
+    "# Module - Preprocessing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "9286e0b8-3c78-4b0f-943c-d219e9840dfe",
+   "metadata": {},
+   "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": 5,
+   "id": "2028eed7-b1c3-4c9e-b6a0-00433caa7d0f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from darts.datasets import EnergyDataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "4733b4e6-71a2-42b2-93fd-a5615b84ac1a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import ontime as on"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e24da8ab-6a83-4c2f-9ff0-c633d4693a91",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "## Load data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "e9a96d79-0423-4d79-b01d-726193216238",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ts = EnergyDataset().load()\n",
+    "ts = ts.astype(np.float32)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1d4bec6b-eedb-4a88-ba68-dbeae5f0644e",
+   "metadata": {},
+   "source": [
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c2c873dd-8643-40cd-895b-fddd7a515c6d",
+   "metadata": {},
+   "source": [
+    "## Common Preprocessing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "a630af5c-687e-48e2-a6d4-5a8cb1d1ec66",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from ontime.module import preprocessing"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9b508ee5-7c7e-4793-904e-45a40df354db",
+   "metadata": {},
+   "source": [
+    "### Normalize"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "a4b12f07-8a97-403a-a554-89e166574120",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/fred.montet/Library/Caches/pypoetry/virtualenvs/ontime-FpQu8-YN-py3.10/lib/python3.10/site-packages/sklearn/preprocessing/_data.py:479: RuntimeWarning: All-NaN slice encountered\n",
+      "  data_min = np.nanmin(X, axis=0)\n",
+      "/Users/fred.montet/Library/Caches/pypoetry/virtualenvs/ontime-FpQu8-YN-py3.10/lib/python3.10/site-packages/sklearn/preprocessing/_data.py:480: RuntimeWarning: All-NaN slice encountered\n",
+      "  data_max = np.nanmax(X, axis=0)\n"
+     ]
+    }
+   ],
+   "source": [
+    "ts_t = preprocessing.common.normalize(ts)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "42428ed1-7556-4341-9675-bad6dca0ecac",
+   "metadata": {},
+   "source": [
+    "### Train test split (for time series)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "8b67892d-db8c-4f12-93b6-147016da4186",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train, test = preprocessing.common.train_test_split(ts_t, train_split=0.8)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "498b0e13-04bc-45ee-ab1a-3996fbfd1df2",
+   "metadata": {},
+   "source": [
+    "### Split time series in chunks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "500e954a-82d6-4eff-bbdd-0b889c2a10f8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_list = preprocessing.common.split_by_length(train, 6)\n",
+    "test_list = preprocessing.common.split_by_length(test, 6)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b4a88496-6b33-4bff-abb7-1d5ff4c81597",
+   "metadata": {},
+   "source": [
+    "### Split in X and y"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "f7897c44-71ba-4752-86c6-547387245ae4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train, y_train = preprocessing.common.split_inputs_from_targets(train_list, 4, 2)\n",
+    "X_test, y_test = preprocessing.common.split_inputs_from_targets(test_list, 4, 2)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9626370a-e4ba-4421-b40b-d6e7c5787beb",
+   "metadata": {},
+   "source": [
+    "### Transform in generic data type "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "a4ab9cfa-289d-4d8e-be40-d5d4247f5ab5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X_train = preprocessing.common.timeseries_list_to_numpy(X_train)\n",
+    "y_train = preprocessing.common.timeseries_list_to_numpy(y_train)\n",
+    "X_test = preprocessing.common.timeseries_list_to_numpy(X_test)\n",
+    "y_test = preprocessing.common.timeseries_list_to_numpy(y_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "1b0a2843-6d02-4b08-96f8-91712e521bf5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(4675, 4, 28)\n",
+      "(4675, 2, 28)\n",
+      "(1168, 4, 28)\n",
+      "(1168, 2, 28)\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(X_train.shape)\n",
+    "print(y_train.shape)\n",
+    "print(X_test.shape)\n",
+    "print(y_test.shape)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "54b0dfbd-be2f-4a3e-b152-f0bab31bb372",
+   "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": "3.10.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}