Statistical Analysis

In today’s world, decisions are based on data. Hypothesis plays a major role in that decision making process. It is one of the most important concepts in the field of data science. There are so many fields such as the health sector, business world, academia etc, Hypothesis testing is used…

Three strategies, three months, and getting ready for more. — For 3 months now, Signalytic provides 3 signal broadcasting strategies that have ran over and been maintained over January. There has been a couple of random stops in the broadcasting of the signals, but it’s been looked into. With our dedicated Telegram group counting now 97 followers, compared to 76 last month, and we continue to support followers and newcomers have a good landing place where they can benefits from the support of the team and the community.

Introduction: According to WHO, mental health is well defined as a state of mental well-being that enables people to cope with the stresses of life, realize their abilities, learn well, work well, and contribute to their community. Mental Health includes our emotional, psychological, and social well-being. Mental illness is the absence…

This is part 2 of the python bootstraps series. We will finish our inference pipeline using two-tail bootstrapped significance tests. This article does not cover bootstraps. …

Whether you want to deploy your AI model to production or launch a new feature on your app, you probably wish to assess its effectiveness. One way to evaluate the effectiveness of a model in the real world is through an A/B Test, or at its most formal term, a…

There are several approaches that data scientists can use to identify and handle outliers in their data sets: Visualization: One of the simplest ways to identify outliers is by creating visualizations of the data, such as scatter plots or box plots. Outliers will typically appear as points that are distant…

The math behind Logistic Regression — with code. The following article gives a summarized version of the Stanford CS229 Machine Learning course on logistic regression. In addition, code for the corresponding mathematical equations is included. For an in-depth understanding of the algorithm, you should check out the material. CS229: Machine Learning - The Summer Edition! Introduction and Pre-requisites review (3 lectures) Supervised Learning (8 lectures) Lecture 4 [ YouTube] 7/1 Linear…cs229.stanford.edu

We strengthen our intuition Part 2/application library(ggplot2) library(imager) img <- load.image("C:/Users/ACER/Desktop/RIZA/ARTIST.png") points <- which(img > 0, arr.ind = TRUE) img_dims <- dim(img) height <- img_dims[1] width <- img_dims[2] sampled_points <- points[sample(nrow(points), size = 100174), ] sampled_points_df <- data.frame(sampled_points, stringsAsFactors = FALSE) colnames(sampled_points_df) <- c("y", "x") sampled_points_df[,2] <- width - sampled_points_df[,2] ggplot(sampled_points_df, aes(x = x, y = y)) +…

What is matrix factorization ? In simple matrix factorization is the method of decomposing a single matrix into a product of two matrix eg : a matrix of dimension mxn can be decomposed as mxd and dxn Think of any dataset of user-item interaction as a matrix which has real values(ratings) what it actually does to our dataset of user item interaction ? It helps us in…