diff --git a/exploratory_analysis.ipynb b/exploratory_analysis.ipynb index 95980198da73e76af8876733bcea4609316f130f..7a6c71ca09b05f0ff76f2540c99b75349fce933c 100644 --- a/exploratory_analysis.ipynb +++ b/exploratory_analysis.ipynb @@ -24,7 +24,8 @@ " \n", "<sup>1</sup> Fritz Haber Institute of the Max Planck Society, Faradayweg 4-6, D-14195 Berlin, Germany <br>\n", "\n", - " \n", + "<span class=\"nomad--last-updated\" data-version=\"v1.0.0\">[Last updated: Jan 11, 2021]</span>\n", + "\n", "<div> \n", "<img style=\"float: left;\" src=\"assets/exploratory_analysis/Logo_MPG.png\" width=\"200\"> \n", "<img style=\"float: right;\" src=\"assets/exploratory_analysis/Logo_NOMAD.png\" width=\"250\">\n", @@ -95,8 +96,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:07.755442Z", - "start_time": "2021-01-04T16:28:07.095624Z" + "end_time": "2021-01-11T15:53:02.015171Z", + "start_time": "2021-01-11T15:53:01.112302Z" } }, "outputs": [], @@ -113,7 +114,6 @@ "import plotly.graph_objects as go\n", "import ipywidgets as widgets\n", "from IPython.display import display, clear_output\n", - "from pydpc import Cluster as DPCClustering\n", "import matplotlib.pyplot as plt" ] }, @@ -138,8 +138,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:07.870608Z", - "start_time": "2021-01-04T16:28:07.760577Z" + "end_time": "2021-01-11T15:53:02.157388Z", + "start_time": "2021-01-11T15:53:02.017288Z" }, "scrolled": true }, @@ -198,8 +198,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:07.876974Z", - "start_time": "2021-01-04T16:28:07.872057Z" + "end_time": "2021-01-11T15:53:02.166149Z", + "start_time": "2021-01-11T15:53:02.161280Z" } }, "outputs": [], @@ -219,8 +219,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:07.896229Z", - "start_time": "2021-01-04T16:28:07.878762Z" + "end_time": "2021-01-11T15:53:02.177904Z", + "start_time": "2021-01-11T15:53:02.167618Z" } }, "outputs": [], @@ -292,8 +292,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:07.911638Z", - "start_time": "2021-01-04T16:28:07.898218Z" + "end_time": "2021-01-11T15:53:02.192386Z", + "start_time": "2021-01-11T15:53:02.179061Z" } }, "outputs": [], @@ -393,8 +393,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:07.926241Z", - "start_time": "2021-01-04T16:28:07.913288Z" + "end_time": "2021-01-11T15:53:02.208304Z", + "start_time": "2021-01-11T15:53:02.193631Z" } }, "outputs": [], @@ -430,8 +430,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:07.946990Z", - "start_time": "2021-01-04T16:28:07.928697Z" + "end_time": "2021-01-11T15:53:02.230702Z", + "start_time": "2021-01-11T15:53:02.210369Z" }, "scrolled": true }, @@ -452,8 +452,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:09.611115Z", - "start_time": "2021-01-04T16:28:07.948604Z" + "end_time": "2021-01-11T15:53:04.051823Z", + "start_time": "2021-01-11T15:53:02.232495Z" }, "scrolled": false }, @@ -489,8 +489,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:09.633401Z", - "start_time": "2021-01-04T16:28:09.612488Z" + "end_time": "2021-01-11T15:53:04.098830Z", + "start_time": "2021-01-11T15:53:04.053211Z" }, "scrolled": true }, @@ -506,8 +506,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:09.638358Z", - "start_time": "2021-01-04T16:28:09.634718Z" + "end_time": "2021-01-11T15:53:04.103571Z", + "start_time": "2021-01-11T15:53:04.100015Z" } }, "outputs": [], @@ -531,8 +531,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:09.891273Z", - "start_time": "2021-01-04T16:28:09.639781Z" + "end_time": "2021-01-11T15:53:04.544980Z", + "start_time": "2021-01-11T15:53:04.105052Z" }, "scrolled": false }, @@ -562,8 +562,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:09.898070Z", - "start_time": "2021-01-04T16:28:09.892737Z" + "end_time": "2021-01-11T15:53:04.551280Z", + "start_time": "2021-01-11T15:53:04.546575Z" } }, "outputs": [], @@ -589,8 +589,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:09.932800Z", - "start_time": "2021-01-04T16:28:09.899348Z" + "end_time": "2021-01-11T15:53:04.593403Z", + "start_time": "2021-01-11T15:53:04.552797Z" }, "scrolled": true }, @@ -629,8 +629,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:09.945953Z", - "start_time": "2021-01-04T16:28:09.934125Z" + "end_time": "2021-01-11T15:53:04.609880Z", + "start_time": "2021-01-11T15:53:04.595116Z" }, "scrolled": true }, @@ -646,8 +646,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:10.020006Z", - "start_time": "2021-01-04T16:28:09.947670Z" + "end_time": "2021-01-11T15:53:04.679670Z", + "start_time": "2021-01-11T15:53:04.611082Z" }, "scrolled": false }, @@ -661,8 +661,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:10.049290Z", - "start_time": "2021-01-04T16:28:10.021782Z" + "end_time": "2021-01-11T15:53:04.698436Z", + "start_time": "2021-01-11T15:53:04.681267Z" }, "scrolled": true }, @@ -685,8 +685,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:10.213386Z", - "start_time": "2021-01-04T16:28:10.051024Z" + "end_time": "2021-01-11T15:53:04.860896Z", + "start_time": "2021-01-11T15:53:04.699651Z" } }, "outputs": [], @@ -724,8 +724,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:10.219907Z", - "start_time": "2021-01-04T16:28:10.214805Z" + "end_time": "2021-01-11T15:53:04.875231Z", + "start_time": "2021-01-11T15:53:04.862303Z" } }, "outputs": [], @@ -740,8 +740,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:10.300990Z", - "start_time": "2021-01-04T16:28:10.221245Z" + "end_time": "2021-01-11T15:53:04.952255Z", + "start_time": "2021-01-11T15:53:04.876744Z" }, "scrolled": false }, @@ -755,8 +755,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:10.328403Z", - "start_time": "2021-01-04T16:28:10.302447Z" + "end_time": "2021-01-11T15:53:04.973008Z", + "start_time": "2021-01-11T15:53:04.953629Z" } }, "outputs": [], @@ -784,6 +784,36 @@ "---" ] }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2021-01-11T15:46:17.939242Z", + "start_time": "2021-01-11T15:46:17.930533Z" + } + }, + "source": [ + "The HDBSCAN clustering algorithm is introduced in:\n", + "\n", + "R.J.G.B. Campello, D. Moulavi, J. Sander: <span style=\"font-style: italic;\">Density-Based Clustering Based on Hierarchical Density Estimates</span>, Springer Berlin Heidelberg, (2013).\n", + "\n", + "The implementation of the algorithm that we use is taken from https://pypi.org/project/hdbscan/." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "ExecuteTime": { + "end_time": "2021-01-11T15:53:04.983731Z", + "start_time": "2021-01-11T15:53:04.974426Z" + } + }, + "outputs": [], + "source": [ + "import hdbscan" + ] + }, { "cell_type": "markdown", "metadata": {}, @@ -800,8 +830,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:10.349230Z", - "start_time": "2021-01-04T16:28:10.329658Z" + "end_time": "2021-01-11T15:53:04.999542Z", + "start_time": "2021-01-11T15:53:04.985911Z" } }, "outputs": [], @@ -816,8 +846,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:10.427573Z", - "start_time": "2021-01-04T16:28:10.351211Z" + "end_time": "2021-01-11T15:53:05.076766Z", + "start_time": "2021-01-11T15:53:05.001053Z" } }, "outputs": [], @@ -830,8 +860,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:10.447426Z", - "start_time": "2021-01-04T16:28:10.429033Z" + "end_time": "2021-01-11T15:53:05.100245Z", + "start_time": "2021-01-11T15:53:05.078247Z" } }, "outputs": [], @@ -856,6 +886,36 @@ "---" ] }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2021-01-11T15:46:17.939242Z", + "start_time": "2021-01-11T15:46:17.930533Z" + } + }, + "source": [ + "The fast search and find of density peaks algorithm is introduced in:\n", + "\n", + "R.J.G.B. Campello, D. Moulavi, J. Sander: <span style=\"font-style: italic;\">Density-Based Clustering Based on Hierarchical Density Estimates</span>, Springer Berlin Heidelberg, (2013).\n", + "\n", + "The implementation of the algorithm that we use is taken from https://pypi.org/project/pydpc/." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "ExecuteTime": { + "end_time": "2021-01-11T15:53:05.117794Z", + "start_time": "2021-01-11T15:53:05.101544Z" + } + }, + "outputs": [], + "source": [ + "from pydpc import Cluster as DPCClustering" + ] + }, { "cell_type": "markdown", "metadata": {}, @@ -868,8 +928,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:10.588857Z", - "start_time": "2021-01-04T16:28:10.448746Z" + "end_time": "2021-01-11T15:53:05.260554Z", + "start_time": "2021-01-11T15:53:05.119149Z" } }, "outputs": [], @@ -893,8 +953,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:10.705792Z", - "start_time": "2021-01-04T16:28:10.590212Z" + "end_time": "2021-01-11T15:53:05.384426Z", + "start_time": "2021-01-11T15:53:05.262028Z" } }, "outputs": [], @@ -907,8 +967,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:10.772478Z", - "start_time": "2021-01-04T16:28:10.707090Z" + "end_time": "2021-01-11T15:53:05.463062Z", + "start_time": "2021-01-11T15:53:05.386217Z" }, "scrolled": false }, @@ -922,8 +982,8 @@ "execution_count": null, "metadata": { "ExecuteTime": { - "end_time": "2021-01-04T16:28:10.803036Z", - "start_time": "2021-01-04T16:28:10.773905Z" + "end_time": "2021-01-11T15:53:05.486286Z", + "start_time": "2021-01-11T15:53:05.464830Z" } }, "outputs": [], diff --git a/metainfo.json b/metainfo.json index 4ab520ac8cef5fc844a2768302ef76b36b18b562..d98303360fec1cee2a912d19f4274641b65a02f5 100644 --- a/metainfo.json +++ b/metainfo.json @@ -9,7 +9,7 @@ "url": "https://gitlab.mpcdf.mpg.de/nomad-lab/analytics-exploratory-analysis", "link": "https://analytics-toolkit.nomad-coe.eu/hub/user-redirect/notebooks/tutorials/exploratory_analysis_tutorial.ipynb", "link_public": "https://analytics-toolkit.nomad-coe.eu/public/user-redirect/notebooks/tutorials/exploratory_analysis_tutorial.ipynb", - "updated": "2021-01-04", + "updated": "2021-01-11", "flags":{ "featured": true, "top_of_list": false diff --git a/setup.py b/setup.py index c356db2449699c09051bd4ae531d415feaaf0594..18187f9b78545e949b2cf2c477dbd2c4f9b3ec68 100644 --- a/setup.py +++ b/setup.py @@ -13,5 +13,5 @@ setup( description=metainfo['title'], long_description=metainfo['description'], packages=find_packages(), - install_requires=['numpy', 'pandas', 'matplotlib', 'scikit-learn', 'scipy', 'hdbscan'], + install_requires=['numpy', 'pandas', 'matplotlib', 'scikit-learn', 'scipy', 'hdbscan', 'ase', 'pydpc'], )