Ayoub HAIDA's Projects
Analyze the Pollution index from 1999 to 2012 in the USA using R.
Programming assignments for the Stanford University Algorithms Specialization
Analzye steps data using R
:atom: The hackable text editor
Pythonic Bayesian Belief Network Package, supporting creation of and exact inference on Bayesian Belief Networks specified as pure python functions.
Constructing Bayesian Networks for Genetic Inheritance
An interactive Bash program that stores rental information for your bike rental shop using PostgreSQL.
Bitcoin Core integration/staging tree
A book recommendation algorithm using K-Nearest Neighbors.
This Matlab code implements a branching diffusion method for solving partial differential equations (PDEs). The method uses Monte Carlo simulation and the branching process to approximate the solution of PDEs. The code provides a set of functions to calculate the mean, standard deviation, and L2 approximation error of the solution.
Classify images of dogs and cats using TensorFlow 2.0 and Keras to create a convolutional neural network that correctly classifies images of cats and dogs at least 70% of the time.
SUBTASKS You should create a database named universe Be sure to connect to your database with \c universe. Then, you should add tables named galaxy, star, planet, and moon Each table should have a primary key Each primary key should automatically increment Each table should have a name column You should use the INT data type for at least two columns that are not a primary or foreign key You should use the NUMERIC data type at least once You should use the TEXT data type at least once You should use the BOOLEAN data type on at least two columns Each "star" should have a foreign key that references one of the rows in galaxy Each "planet" should have a foreign key that references one of the rows in star Each "moon" should have a foreign key that references one of the rows in planet Your database should have at least five tables Each table should have at least three rows The galaxy and star tables should each have at least six rows The planet table should have at least 12 rows The moon table should have at least 20 rows Each table should have at least three columns The galaxy, star, planet, and moon tables should each have at least five columns At least two columns per table should not accept NULL values At least one column from each table should be required to be UNIQUE All columns named name should be of type VARCHAR Each primary key column should follow the naming convention table_name_id. For example, the moon table should have a primary key column named moon_id Each foreign key column should have the same name as the column it is referencing
This function generates a sample of numRepl exponential random variables with rate lambda then the probabilities (P { X > s } ) , (P { X > t } ) and (P { X > s+t / X > t} ) are estimated empirically
This MATLAB code implements the classical Monte Carlo method for solving partial differential equations (PDEs). The code uses the log function of the norm of a random vector as an example PDE and computes the solution at time T=1 and initial condition x0=0.
Course materials for the Data Science Specialization: https://www.coursera.org/specialization/jhudatascience/1
cpp11 helps you to interact with R objects using C++ code.
CUDA Random Forest implementation for Image Labeling tasks
This code will allow you to switch your graphics to dark mode
The Exercise solution of the 1st chapter (Data Visualization with ggplot2) of Hadley Wickham's book "R for Data Science"
Data Science Repo and blog for John Hopkins Coursera Courses. Please let me know if you have any questions.
An open source multi-tool for exploring and publishing data
The Leek group guide to data sharing
Python code for solving partial differential equations (PDEs) using deep learning. Specifically, we provide implementations for solving the following PDEs
we must analyze demographic data using Pandas using a given dataset of demographic data that was extracted from the 1994 Census database.
Detection of Fraudulent Transactions using Machine learning and deep learning based classification models
The idea is to randomly throw (n) times a needle of length (l) on a floor consisting of wood strips of width (t>l), and to observe the number of times (h) that the needle crosses the border between two strips.
This project aims to predict the future price of Ethereum using various machine learning models, including deep learning. The project is implemented using Python and Jupyter notebooks.
Plotting Assignment 1 for Exploratory Data Analysis