diff --git a/exploratory_analysis.ipynb b/exploratory_analysis.ipynb index f0ac253b4adadcadedaee1c86c108bc1eb8e927a..95980198da73e76af8876733bcea4609316f130f 100644 --- a/exploratory_analysis.ipynb +++ b/exploratory_analysis.ipynb @@ -109,10 +109,7 @@ "from sklearn.cluster import KMeans, DBSCAN, AgglomerativeClustering\n", "from sklearn.decomposition import PCA\n", "from sklearn.manifold import TSNE, MDS\n", - "# from sklearn.svm import SVC\n", - "# from sklearn.model_selection import train_test_split\n", "import hdbscan\n", - "# import plotly.express as px\n", "import plotly.graph_objects as go\n", "import ipywidgets as widgets\n", "from IPython.display import display, clear_output\n", @@ -120,22 +117,6 @@ "import matplotlib.pyplot as plt" ] }, - { - "cell_type": "code", - "execution_count": null, - "metadata": { - "ExecuteTime": { - "end_time": "2021-01-04T16:28:07.758936Z", - "start_time": "2021-01-04T16:28:07.756961Z" - } - }, - "outputs": [], - "source": [ - "# import warnings\n", - "# warnings.filterwarnings(\"ignore\", category=DeprecationWarning) \n", - "# pd.options.mode.chained_assignment = None" - ] - }, { "cell_type": "markdown", "metadata": {}, diff --git a/metainfo.json b/metainfo.json new file mode 100644 index 0000000000000000000000000000000000000000..4ab520ac8cef5fc844a2768302ef76b36b18b562 --- /dev/null +++ b/metainfo.json @@ -0,0 +1,46 @@ +{ + "authors": [ + "Sbailò, Luigi", + "Ghiringhelli, Luca M." + ], + "email": "sbailo@fhi-berlin.mpg.de", + "title": "Exploratory analysis of octet-binary compounds ", + "description": "Exploratory analyses make use of unsupervised learning techniques to extract information from unknown datasets. In this tutorial, we make use of some of the most popular clustering and dimension reduction algorithms to analyze a dataset composed of 82 octet-binary compounds.", + "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", + "flags":{ + "featured": true, + "top_of_list": false + }, + "labels": { + "application_keyword": [ + "k-means", + "Hierarchical clustering", + "DBSCAN", + "HDBSCAN", + "DenPeak", + "PCA", + "t-SNE", + "MDS", + "Octet binaries" + ], + "application_section": [ + "Tutorials for artificial-intelligence methods" + ], + "application_system": [ + "octet-binary materials" + ], + "category": [ + "Tutorial" + ], + "data_analytics_method": [ + "Clustering", + "Dimension reduction" + ], + "platform": [ + "jupyter" + ] + } +} diff --git a/setup.py b/setup.py new file mode 100644 index 0000000000000000000000000000000000000000..c356db2449699c09051bd4ae531d415feaaf0594 --- /dev/null +++ b/setup.py @@ -0,0 +1,17 @@ +import json +from setuptools import setup, find_packages + +with open('metainfo.json') as file: + metainfo = json.load(file) + +setup( + name='exploratory_analysis', + version='1.0', + author=', '.join(metainfo['authors']), + author_email=metainfo['email'], + url=metainfo['url'], + description=metainfo['title'], + long_description=metainfo['description'], + packages=find_packages(), + install_requires=['numpy', 'pandas', 'matplotlib', 'scikit-learn', 'scipy', 'hdbscan'], +)