2D fluid simulation implementation of Jos Stam paper on real-time fuild dynamics, including some suggested extensions.

Overview

Fluid Simulation

image

Usage

  1. Download this repo and store it in your computer.
  2. Open a terminal and go to the root directory of this folder.
  3. Make sure you have installed the needed dependencies by typing:
$ pip install numpy
$ pip install matplotlib
$ pip install ffmpeg

Note: Go to Install FFmpeg on Windows section if you haven't installed FFmpeg software locally before. It must be added to PATH so that videos can be saved.

  1. Type to run:
$ python fluid.py -i config.json

Where the config.json file is the input file inside the same folder as main.py file.

The Development Log file is also located in the root directory of this repository, where all the logic and structure of the programming done is explained.

Input

The config.json file is the input file you must provide as a command parameter. The structure of the file must be the following:

  1. color: string that contains any of the available options in colors.py.

  2. frames: integer that determines the frame duration of the video.

  3. sources: an array of dictionaries. Each dictionary in the array represents an emitter, which is a source of density and velocity. There cannot be emitters of just velocity or just density, because it would not make sense. Emitters must contain:

    • position: x and y integers, which are the top left position.
    • size: integer that defines an NxN square emitter.
    • density: integer that represents the amount of density of the emitter.
    • velocity:
      • x and y float/integer numbers that represent the velocity direction of the emitter.
      • behaviour: string that contains any of the available options in behaviours.py.
      • factor: float integer/float number that will act as a parameter depending on the behaviour chosen.
  4. objects: an array of dictionaries. Each dictionary in the array represents an object, where each of the objects must contain:

    • position: x and y integers, which are the top left position.
    • size: height and width integers, which will be the shape of a height x width rectangular object.
    • density: integer that represents the amount of density of the object. An object is indeed having a constant amount of density that will not be modified by the liquid, since it's a solid, but you need to determine the density or 'color' the object will have visually.

The folder evidences contains a series of example JSON files and their output videos, with both simple and complex examples of the output.

Features

  • Color Scheme

Inside the config.json file, change the color property and write the color scheme you want from the list below.

image

For example, by having 'hot' as the color property in the json file, you get the following:

image

  • Sources Placement

Inside the config.json file, you can specify the characteristics of an emitter you want to place. An emitter is a source of density and certain velocity.

image

  • Objects Placement

Inside the config.json file, you can specify the position and shape of a solid object inside the fluid.

image

  • Velocity Behaviours

Inside the config.json file, change the behaviour property inside velocity and write the behaviour of the velocity of said emitter you wish for. Supported options are:

  1. zigzag vertical,

image

  1. zigzag horizontal, that works the same as the above but horizontally.

  2. vortex,

image

  1. noise,

image

  1. fourier (left), which is a bit like a zigzag (right) but noisier.

image

  1. motor

image

Install FFmpeg on Windows

Apart from the pip installation of ffmpeg, you need to install ffmpeg for your machine OS (in my case, Windows 10) by going to either of the following links:

  • ffmpeg.org

    • Click on the Windows icon.
    • Click on gyan dev option.
  • gyan.dev

    • Go to the Git section and click on the first link.
    • Extract the folder from the zip.
    • Cut and paste the folder in your C: disk.
    • Add C:\FFmpeg\bin to PATH by typing in a terminal with admin rights:
     $ setx /m PATH "C:\FFmpeg\bin;%PATH%"
    
    • Open another terminal and test the installation by typing:
     $ ffmpeg -version
    

Handy Links

Owner
Mariana Ávalos Arce
I like code and math. I like football too. [Software & Computer Graphics]
Mariana Ávalos Arce
A data preprocessing and feature engineering script for a machine learning pipeline is prepared.

FEATURE ENGINEERING Business Problem: A data preprocessing and feature engineering script for a machine learning pipeline needs to be prepared. It is

Pinar Oner 7 Dec 18, 2021
A Lightweight Hyperparameter Optimization Tool 🚀

The mle-hyperopt package provides a simple and intuitive API for hyperparameter optimization of your Machine Learning Experiment (MLE) pipeline.

Robert Lange 137 Dec 02, 2022
A high performance and generic framework for distributed DNN training

BytePS BytePS is a high performance and general distributed training framework. It supports TensorFlow, Keras, PyTorch, and MXNet, and can run on eith

Bytedance Inc. 3.3k Dec 28, 2022
Cool Python features for machine learning that I used to be too afraid to use. Will be updated as I have more time / learn more.

python-is-cool A gentle guide to the Python features that I didn't know existed or was too afraid to use. This will be updated as I learn more and bec

Chip Huyen 3.3k Jan 05, 2023
SynapseML - an open source library to simplify the creation of scalable machine learning pipelines

Synapse Machine Learning SynapseML (previously MMLSpark) is an open source library to simplify the creation of scalable machine learning pipelines. Sy

Microsoft 3.9k Dec 30, 2022
Iris species predictor app is used to classify iris species created using python's scikit-learn, fastapi, numpy and joblib packages.

Iris Species Predictor Iris species predictor app is used to classify iris species using their sepal length, sepal width, petal length and petal width

Siva Prakash 5 Apr 05, 2022
NumPy-based implementation of a multilayer perceptron (MLP)

My own NumPy-based implementation of a multilayer perceptron (MLP). Several of its components can be tuned and played with, such as layer depth and size, hidden and output layer activation functions,

1 Feb 10, 2022
CinnaMon is a Python library which offers a number of tools to detect, explain, and correct data drift in a machine learning system

CinnaMon is a Python library which offers a number of tools to detect, explain, and correct data drift in a machine learning system

Zelros 67 Dec 28, 2022
A simple and lightweight genetic algorithm for optimization of any machine learning model

geneticml This package contains a simple and lightweight genetic algorithm for optimization of any machine learning model. Installation Use pip to ins

Allan Barcelos 8 Aug 10, 2022
Data science, Data manipulation and Machine learning package.

duality Data science, Data manipulation and Machine learning package. Use permitted according to the terms of use and conditions set by the attached l

David Kundih 3 Oct 19, 2022
easyNeuron is a simple way to create powerful machine learning models, analyze data and research cutting-edge AI.

easyNeuron is a simple way to create powerful machine learning models, analyze data and research cutting-edge AI.

Neuron AI 5 Jun 18, 2022
Katana project is a template for ASAP 🚀 ML application deployment

Katana project is a FastAPI template for ASAP 🚀 ML API deployment

Mohammad Shahebaz 100 Dec 26, 2022
A Python package to preprocess time series

Disclaimer: This package is WIP. Do not take any APIs for granted. tspreprocess Time series can contain noise, may be sampled under a non fitting rate

Maximilian Christ 57 Dec 17, 2022
Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)

Karate Club is an unsupervised machine learning extension library for NetworkX. Please look at the Documentation, relevant Paper, Promo Video, and Ext

Benedek Rozemberczki 1.8k Jan 03, 2023
Machine Learning Algorithms ( Desion Tree, XG Boost, Random Forest )

implementation of machine learning Algorithms such as decision tree and random forest and xgboost on darasets then compare results for each and implement ant colony and genetic algorithms on tsp map,

Mohamadreza Rezaei 1 Jan 19, 2022
monolish: MONOlithic Liner equation Solvers for Highly-parallel architecture

monolish is a linear equation solver library that monolithically fuses variable data type, matrix structures, matrix data format, vendor specific data transfer APIs, and vendor specific numerical alg

RICOS Co. Ltd. 179 Dec 21, 2022
scikit-multimodallearn is a Python package implementing algorithms multimodal data.

scikit-multimodallearn is a Python package implementing algorithms multimodal data. It is compatible with scikit-learn, a popul

12 Jun 29, 2022
DistML is a Ray extension library to support large-scale distributed ML training on heterogeneous multi-node multi-GPU clusters

DistML is a Ray extension library to support large-scale distributed ML training on heterogeneous multi-node multi-GPU clusters

27 Aug 19, 2022
pandas, scikit-learn, xgboost and seaborn integration

pandas, scikit-learn and xgboost integration.

299 Dec 30, 2022
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow

eXtreme Gradient Boosting Community | Documentation | Resources | Contributors | Release Notes XGBoost is an optimized distributed gradient boosting l

Distributed (Deep) Machine Learning Community 23.6k Jan 03, 2023