Data Science and Zombies

Overview:

Today, most companies are capable of building their own data science teams and most people looking to become data scientists have a myriad of educational options. Yet data science adoption at a majority of organizations continues at a glacial pace. Fast Lane’s Zombie Apocalypse curriculum is a dynamic and fun way to upskill the non-data scientists in your organization so that you can start reaping the benefits.

The Problem:

In a recent report, Gartner estimated that 85% of big data science projects fail! We believe this is due in fact to a “Last Mile” divide between data scientists and their project stakeholder /subject matter expert counterparts. Data scientists are generalists who need these stakeholders to frame the problems that need solving and to provide them with the data they need in order to solve those problems. The stakeholders understand their business requirements, maintain stewardship of the data resources to meet those requirements, possess fundamental analytics skills but generally lack programming experience and/or data science literacy. The result is an inability for both sides to effectively communicate their respective needs, disconnects, time wasted attempting to source data, and the increasing probability that the project will fail to meet its goals.

The Solution:

Upskill the employees and stakeholders with basic coding skills and data science literacy that will empower them to bridge the gap. That doesn’t mean that they need to become data scientists (a costly and impractical solution). And ensure that they have FUN doing it: What’s better than identifying and destroying zombies before they eat your brain?

Instead, they will learn:

  • The fundamental components and process of a data science project
  • How to frame their requirements through the lens of machine learning
  • The vocabulary needed to communicate their requirements

The Results:

  • By acquiring these skills, an organization can work toward realizing the strategic and financial benefits of integrating machine learning into their business processes
  • Leverage their data science teams more efficiently
  • Increase critical collaboration between teams
  • Boost morale by eliminating friction points and by defining a role for non-technical employees

How Do These Courses Work?

This course aims to give non-technical stakeholders the skills and data science literacy to participate as a core member of a data science project team. Over the five days, students will be tasked with saving the world from the Zombie Apocalypse using basic Python, Pandas/Excel, and machine learning skills.

Who Should Attend?

  • Any stakeholder with no or limited technical background who participates in digital transformation or data analytics projects
  • Non-technical professionals who have a need to partner with their data science team
  • Business Intelligence professionals who want to gain experience using Python’s data analytics tools
  • Non-technical business managers

Prerequisities:

  • Basic knowledge of Python

Course Content:

Module # Description Lessons & Labs
1 Python Fundamentals Review
  • Lists
  • Dictionaries
  • Loops
  • Functions

What Data Science Is & Is Not
  • Anaconda environment setup completion
  • Navigating the Terminal/Command Prompt
  • Git/Github
  • Jupyter Notebooks
2 Pandas
  • Data Visualization
    • Seaborn Visualisation Tool
  • OSEMN framework overview
  • Obtaining our Data
    • Importing Data into a Dataframe
  • Scrubbing
    • Checking for Null Values
    • Fixing Data Types
    • Removing "Dirty" Data
  • EDA
    • Using Seaborn, students will explore their daataset and create visualizations in order to understand critical information such as where zombies & humans are located and how much ammo is needed to survive
3
  • Data Science Algorithms & Modeling
  • Linear Regression
  • Model Interpretation
  • Model Prepping
    • Normalization/Scaling
    • Creating Training and Test Datasets
  • Linear Regression
    • Predicting the bounty for killing zombies in your neighborhood
4
  • Classification Algorithms
    • Model Interpretation
    • Confusion Matricies
    • ROC
    • F-Score
We'll use the following classification algorithms to determine whether or not someone is a zombie:
  • Logistic Regression
  • Decision Trees
  • Random Forests
  • XGBoost
5
  • Time-Series Algorithms
Team-Based Capstone Project:
  • Build an end-to-end project using the OSEMN framework
  • Students can bring their own work-related dataset or select from one of our curated offerings