Workshops - SuperDataScience - Big Data | Analytics Careers | Mentors | Success


WORKSHOP 040 [Deep Learning] Highway Traffic Classification

16 December 2017

In this workshop, we take a look at trying to classify traffic on a highway into heavy, medium or light. We try and harness the power of pre-trained networks trained on imagenet and show how a small network can be powerful with great features.

  • 2391
  • 0

WORKSHOP 053 [Tableau] Runstarter

17 April 2018

In this workshop, we look at the often neglected topic of filters. We will be using each of the filter types available in Tableau to solve a real-life business case. The workshop has been designed to not only give you an overview of the different types of projects but also show you some pitfalls to avoid!

  • 2343
  • 0

WORKSHOP 050 [Tableau] Cape Town Water

17 March 2018

A more real-life example is not possible. The City of Cape Town is undergoing major water shortages, and we need to help to create maps that makes an impact!

In this tutorial, we create spectacular looking maps using custom shapefiles. We will also learn what polygons are and how they form the base of shapefiles. Lastly, and most importantly, we will look at one of the best-kept secrets in map layers. Your eyes will not believe what you are able to create in Tableau.

  • 2337
  • 0

WORKSHOP 047 [Tableau] Billy Bonka Candies

13 February 2018

In this case study, we put our knowledge of table calculations to the test, as we assist our client with an analysis of their sales KPI’s (key performance indicators) by comparing it across different dimensions and views. We will even attempt a custom Lollipop chart and use it correctly in the business context.

  • 2270
  • 0

WORKSHOP 044 [Tableau] ACME Motor Industries

13 January 2018

In this tutorial we are challenged to provide insights on specific questions posed. Using historic German Automobile data, we derive insights in the manufacturing and export of German private vehicles. We will be required to use table calculations and level of detail calculations, and ensure to incorporate specific formatting into the graphs.

  • 2246
  • 0

WORKSHOP 054 [Python] Visualizations with Seaborn

17 April 2018

Welcome! In this workshop we will be using the modern and highly popular library called Seaborn to build attractive visualizations while answering some specific challenges. You will also receive some practice working with Pandas and data frames that always come in handy while working with Python and Seaborn! In addition, we will be working with a data set produced by the Food and Agriculture Organization of the United Nations (FAO) that has a huge impact and relevancy to numerous companies throughout the world. This workshop will be a fun, informative and will help you learn or build upon your skills to become an even more powerful Data Scientist!

  • 2079
  • 0

WORKSHOP 051 [Python] Car Prices Linear Regression Model

26 March 2018

In this case study, we will build a linear regression model from scratch, learning different ways of load data and dealing with real-world problems like missing data, data imputation and encoding of categorical variables.

The dataset used in this problem is a classic from the UCI machine learning repository, containing the price and characteristics of automobiles.

Using Python to perform this task, we will learn how to use sci-kit learn models, split our dataset between the train and test sets and assess our model’s performance.

  • 2010
  • 0

WORKSHOP 048 [Python] Proving the Secretary Problem using Python

22 February 2018

In this Case Study we will prove that the optimal stopping theory is the best strategy to solve the Secretary Problem, also known as best choice problem.

The basic form of the problem is the following: imagine an administrator who wants to hire the best secretary out of n rankable applicants for a position. The applicants are interviewed one by one in random order. A decision about each particular applicant is to be made immediately after the interview. So how to choose the best applicant?

We will use numpy to create random arranges, learn a bit of the theory behind the problem and apply coding best practices through the use of functions and avoiding loops.

  • 1996
  • 0

WORKSHOP 045 [Python] Birthday Paradox

13 January 2018

In this Case Study we will prove the converging probabilities of the problem called birthday paradox (or birthday problem). This paradox is created due to the fact that in a relatively small group of people (23, for instance) the chance of at least two people share the same day and month of birth is 50%. In a bit bigger group like 60, the probability is more than 99%.

We will use the athletes dataset from the last Olympics and practice how to load, treat and build random samples usign Pandas and create functions in Python.

  • 1964
  • 0

WORKSHOP 049 [R] Web Scraping with rvest

17 March 2018

In this case study, we’ll use the rvest package to scrape historical weather data

  • 3703
  • 0
What are you waiting for?


as seen on: