Introduction

This course aims to cover the fundamentals of data science and develop a practical competency oriented to solve real problems using Python as a language. It seeks to correctly structure knowledge about algorithms and associated techniques to deliver automated data-driven business solutions.

Objectives

At the end of the course, students will have the basic notions of the following concepts and will know how to use the Python language to solve real problems:

• What exactly is (and what is not) data science
• The main differences and uses of supervised and unsupervised learning.
• How to correctly orient a data project
• The main classification and regression algorithms
• The primary clustering and recommender algorithms
• How to improve and optimize Machine Learning models
• The use of simulation in data science

Student profile

This course is designed for all types of professionals who wish to learn how to implement business solutions based on data science, and plan to use the Python programming language.

Prerequisites

It is recommended that students have a basic command of Python or a good level in another programming language such as Java, R, C++…

Course Materials

Students will receive a copy of the Documentation prepared by BIT by Netmind.

Methodology

The course is face-to-face, participatory and practical. The teacher will introduce the contents through realistic problems. The participants will assimilate the knowledge through the resolution of adaptive level activities.

Certification

The evaluation is continuous, based on group and individual activities. The trainer will give constant feedback to each participant.

During the course, participants will complete an evaluation test that they must pass with more than 70%. They will have 30 minutes for its completion.

The conditions for additional certification services are subject to the terms of the license owner or the approved certification authority.

Accreditation

A Certificate of Attendance will be issued only to students with an attendance of more than 75% and a Diploma of Achievement if they also pass the evaluation test.

Python for Data Science

1. Introduction to Data Science

• Differences between Data Science, Business Intelligence and Big Data
• Supervised vs. unsupervised learning
• Python data types and their particularities
• Introduction to Scikitlearn
• Data preprocessing
• Variable engineering

2. Main Regression Algorithms

• Linear regression and numerical model evaluation
• Regression trees
• Random Forests
• Neural networks
• Internal, external and cross-validation

3. Main Classification Algorithms

• Logistic regression and category-based model evaluation
• Classification trees
• KNN
• Support Vector Machine
• Automatic parameter selection

 4. Other data science techniques

• Dimensionality Reduction (PCA)
• Clustering (K-means, Hierarchical, Spectral)
• Recommenders
• Introduction to simulation

JDB 206 | JDB206 | JDB-206