Industrial activities have been one of the primary source of Global Warming as the unregulated energy consumption in industries lead to emission of greenhouse gases in atmosphere. Though the problem may appear easy to solve, identifying right time, volume and area of savings have always been challenging in saving energy. This kit provides the best libraries to build your solution for improving the energy efficiency. The libraries are listed in different sections based on the functionality they provide e.g. - OLAP data visualization - Exploratory Data Analysis - Data Labeling - AutoML Depending on your solution needs, you can pick the needed libraries from the below options and build your solution with them. This kit also acts as a template for submitting your hackathon solution in the form of a kandi kit. You should create relevant solution sections in your kit and add the libraries used under those sections. You must add the two important sections Kit Solution Source and Kit Deployment Instructions. Please see the sections below to understand this better. Problem statement: Jumpstart and create an application which can be used by energy management professionals using the below data set. https://github.com/jojo62000/Smarter_Decisions/raw/master/Chapter%206/Data/Final_SolarData.csv https://github.com/jojo62000/Smarter_Decisions/blob/master/Chapter%203/Data/BO5341_IoTData.csv Expected outcome in the application 1. OLAP operation of the data in front end (dice, slice, roll up/ down, filter) 2. Ability to notify significant changes in the time series dataset imported in the tool 3. Ability to select from and to time stamp in the time series visualization and give a label or annotation 4. Annotation tool - Data labelling where the customer can import the data and the multiple columns render it in the chart where they can select from all and to frame and labelled the part and save in the database. 5. Exploratory data analysis- Where they can explore the data and find its relationship with the different parameters. 6. Prediction Analysis/ modelling - Where they can pass the data and application has to automatically select which model is best and show it’s all the model accuracy results. 7. Have a dashboard to display aggregated values. 8. Results should be in pictorial representation. 9. Data cleaning/Data sanitisation must be done (Should not have null values). 10. Working video of the application is expected.
OLAP data visualization
OLAP data visualization libraries can be used to drill down, roll up or slice and dice the data from OLAP databases.
An easy to use, self-service open BI reporting and BI dashboard platform.
Explore and visualize analytical datasets
Apache Superset is a Data Visualization and Data Exploration Platform
Python 31662 Version:0.38.0 License: Permissive (Apache-2.0)
The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more.
TypeScript 54622 Version:v8.5.22 License: Strong Copyleft (AGPL-3.0)
Bring data to life with SVG, Canvas and HTML. :bar_chart::chart_with_upwards_trend::tada:
Exploratory Data Analysis
The data exploration helps in doing extensive analysis of different data types and in assisting to understand the patterns. Data visualisation helps in representing the insights graphically. Libraries in this section are used for analysis and visualisation of data.
Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more
Python 37428 Version:v2.0.0rc1 License: Permissive (BSD-3-Clause)
The fundamental package for scientific computing with Python.
Python 23036 Version:v1.24.2 License: Permissive (BSD-3-Clause)
scikit-learn: machine learning in Python
Python 53544 Version:1.2.2 License: Permissive (BSD-3-Clause)
Statistical data visualization in Python
Python 10513 Version:v0.12.2 License: Permissive (BSD-3-Clause)
Libraries in this section are used for annotating data for creating training data for machine learning.
Label Studio is a multi-type data labeling and annotation tool with standardized output format
Python 12415 Version:1.7.2 License: Permissive (Apache-2.0)
Visual Object Tagging Tool: An electron app for building end to end Object Detection Models from Images and Videos.
TypeScript 4009 Version:v2.2.0 License: Permissive (MIT)
Collaborate & label any type of data, images, text, or documents, in an easy web interface or desktop app.
🐝 A fast, easy and collaborative open source image annotation tool for teams and individuals.
TypeScript 2653 Version:v1.3.2 License: Permissive (MIT)
Labelbox is the fastest way to annotate data to build and ship computer vision applications.
Use ML-Annotate to label data for machine learning purposes
Python 79 Version:Current License: Permissive (MIT)
Web UI for labelling dataset for supervised learning.
Python 72 Version:Current License: Permissive (Apache-2.0)
Listed libraries can be used for auto machine learning. AutoML will pick the best machine learning algorithm based on the dataset.
Automated Machine Learning with scikit-learn
Python 6802 Version:v0.15.0 License: Permissive (BSD-3-Clause)
Automatic architecture search and hyperparameter optimization for PyTorch
Python 1955 Version:v0.2.1 License: Permissive (Apache-2.0)
An open-source, low-code machine learning library in Python
Jupyter Notebook 7086 Version:3.0.0 License: Permissive (MIT)
H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.
Jupyter Notebook 6189 Version:Current License: Permissive (Apache-2.0)
A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.
Python 8988 Version:v0.11.7 License: Weak Copyleft (LGPL-3.0)
Kit Solution Source
This repo helps beginners and citizen data scientists to build machine learning models
Jupyter Notebook 0 Version:Current License: Permissive (MIT)
This sections has the instructions to install the kit. For the Auto ML kit source, the deployment instructions are: 1. Clone the automl-starter from the source: https://github.com/kandikits/automl-starter 2. Install the required libraries by 'pip install -r requirements.txt' 3. Navigate to the 'automl-classification-pycaret.ipynb' and open and run each cells
Sustainability Hackathon RapidHack initiative in partnership with VIT Chennai and IAEMP
Special Thanks to our organizers, Dr.S.Angalaeswari & Dr.K.Jamuna, VIT-IAEMP Coordinators, Vellore Institute of Technology, Chennai. Dr.B.Somasundaram, Vice-President, IAEMP Ms.Sahaana .V, Executive Council Member,IAEMP Coimbatore Chapter. Mr.Gokul Ganesan, Executive Council Member, IAEMP Coimbatore Chapter.