In this article, my top 6 obvious but not always applied coding tips that I wish someone forced me to follow 3 years ago and that I will share with my son when he starts coding.

Image for post
Image for post
Photo by Nghia Le on Unsplash

Ok, let’s go!

I will do my best to keep this article as clear, concise and neat as possible. I want to share with you the essence of these tips and not go on too much wordiness.

These pieces of advice are coming from my own experience and can be used by anyone coding on R, Python, VBA or SQL.

I have been working as a data scientist for 3 years and these pieces of advice have been given to me from people who managed me since I started my career after graduation. …


I have tested in real-time the implementation coded with Python of a famous mathematical technics to predict market movement (Bollinger Band) to check the gap between theory and reality. And here is the result.

Image for post
Image for post
Photo by Thomas Habr on Unsplash

Before to get started, let’s take a quick look at what we have covered during the previous articles. If you have not read my previous articles, you should cover these articles first. To get more details on how to draw Bollinger Bands and to get live market data with your API. (Link at the end of this article).

Otherwise, if you are too lazy to cover these articles, let’s have a short brief of what we covered along with these articles.

Let’s start by defining what the Bollinger Bands are.

Bollinger Bands?

Created in the early 80s and named after its developer (John Bollinger), Bollinger Bands represent a key technical trading tool for financial traders. …


In this article, I will give you my top3 data visualisation tips using Python and PlotLy (as a data scientist), which will make your audience ecstatic. Tested and approved.

Image for post
Image for post
Photo by Alexander Kagan on Unsplash

Along with this article, I will try to enhance Python possibilities to make your graph interactive, good looking and let your boss impressed. The goal behind these tips is to give a better impression and enhance the user/client experience. It works!

As a summary, the 3 goals will be:

  • 1. Interactivity (Tips#1, #2 and #3)
  • 2. Good looking graphs (Tips #3)
  • 3. Impress your boss (Tips#1, #2 and #3)
Gif from Giphy.com

These three tips are coming from my experience in front of clients after working for 3 years as a data scientist. …


This article is going to be a bit special. I am going to test the latest release from Yahoo Finance API for Python, which provide the possibility to get live data with less than a second lag for free.

Image for post
Image for post
Photo by ActionVance on Unsplash

In this article, you will learn how to get live stock market data, using Python packages without calling an expensive API such as Bloomberg. I have tested it for you. Does that work? Let’s see.


This article will introduce us to the tools and techniques developed to make sense of unstructured data and discover hidden patterns.

Image for post
Image for post
Photo by Alexander Sinn on Unsplash

Nowadays, nearly everything in our lives can be quantified by data. Whether it involves search engine results, social media usage, weather trackers, cars, or sports, data is always being collected to enhance our quality of life. How do we get from all this raw data to improve the level of performance? This article will introduce us to the tools and techniques developed to make sense of unstructured data and discover hidden patterns. …


In this article, you will learn to get the stock market data such as price, volume and fundamental data using Python packages. (In less than 3 lines of code)

Image for post
Image for post
Photo by Aditya Vyas on Unsplash

In this article, you will learn to get the stock market data such as price, volume and fundamental data using Python packages. ()

First of all, before to start, you will need to have installed a Python 3 version and the following packages:

  • Pandas
  • Pandas_datareader
  • DateTime

If any of these packages are not already installed, you can use the pip command as shown below. …


Image for post
Image for post
Photo by Roberto Junior — Unsplash

In this article, we are going to analyze quantitatively, how Covid19 has impacted the US stock exchange, and the way of trading. The result is surprising.

The analysis will be focused on market volatility.

Prerequisite

If you are keen to develop step by step this analysis with me, you will need Python3 and three different Python…


In this article, we are going to cover how it is possible to use mathematics to beat the market.

Image for post
Image for post
Image copyright: Austin Distel — unsplash

The mathematical algorithm which we are going to use is called Bollinger Bands.

The Bollinger Bands

Bollinger Bands are an indicator of volatility.

They are based on the correlation between the normal distribution and the evolution of a share’s value.

As a result, Bollinger Bands can be used to draw a support curve and a resistance curve that will frame the evolution of a share value.

The Normal Distribution :

The normal distribution is a probability distribution that describes the fact that values evolve between -2*σ and +2*σ of the average for 95% of the time. The value will exceed this fluctuation for only 5% of the time. (2.5% …


Deep Learning, Neural Network and Python(Part2/3)

Image for post
Image for post

I hope you are doing well and welcome in this second article. Today we will solve a real case proposed by New York University, Microsoft Research Lab, and Google Lab, grouping a massive amount of handwriting numbers.

You can download the library following this link :

http://yann.lecun.com/exdb/mnist/

Let’s go!

What is the MNIST Database?

The MNIST database groups amount of handwritten digits. The database is composed of a training set of 60,000 examples and a test set of 10,000 samples. It is a subset of a more extensive set available from NIST. The digits have been size-normalized and centered in a fixed-size image.

It is an excellent database for people who want to try learning techniques and pattern recognition methods on real-world data while spending minimal efforts on preprocessing and formatting. …


This is a complementary article related to my data science articles bringing more understanding for my readers.

Image for post
Image for post

In a dataset, a training set is implemented to build up a model, while a test (or validation) set is to validate the model built. Data points in the training set are excluded from the test (validation) set. Usually, a dataset is divided into a training set, a validation set (some people use ‘test set’ instead) in each iteration, or divided into a training set, a validation set and a test set in each iteration.

In Machine Learning, we basically try to create a model to predict the test data. So, we use the training data to fit the model and testing data to test it. The models generated are to predict the results unknown which is named as the test set. As you pointed out, the dataset is divided into train and test set in order to check accuracies, precisions by training and testing it on it. …

About

Sajid Lhessani

Data scientist working in Banking and Capital market. Follow me on YouTube: https://www.youtube.com/channel/UCZorZ8KWmTON7aO84JJBwlQ

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store