Python for Data science

This course is for students or professionals who wish to choose a career in Data Science. Hands on working with Python plus machine learning fundamentals are explained easily to induce interest among the students.

Contents:

1) Introduction to Python->

Fundamentals,

motivation to use python in data science,

installing packages using pip/conda

2) Installing Jupyter notebook (using Python and R kernels)

running notebooks, checking for errors, visualising data,

Handling missing data, attributing them to values.

3) Machine learning fundamentals:

Introduction to linear regression,

Introduction to logistic regression, classification problems, decision trees random forests, clustering, principal component analysis, non-linear PCA.

4) Time series, neural network basics

5) Object-oriented programming in Python

motivation for deep learning

The course will give an excellent overview of the industry expectations and tackle challenging problems. After this course, reading journal articles, using a package in python, learning to debug fundamental errors will be less intimidating.

Attempting kaggle competitions will not be daunting.

Prerequisites:

No prior experience in data science is assumed.

Some exposure to programming would make things easier, but it is not necessary at all. Python is much easier.

The road ahead:

Advanced concepts like deep learning, adversarial networks, image/speech/video processing can be dealt with less scariness.