# data science with python

Let’s start by stating: Python is the new Excel. In fact, arguably it is much better than Excel, as Python is actively applied by organisations, Facebook, Google, Netflix, PayPal, NASA and to name a few.

Hence, with increasing demand which one of the main reason due to its flexibility and huge library to refer, without a doubt, this will soon be triumph as Data Scientist’s first choice of tools.

#### Key takeaways

- Understand how Python works and how to use it for digital applications.
- Learn to use Numpy Matplotlib, Pandas, Seaborn for Data analysis.
- Learn to use Sklearn library to solve classification and regression problems.
- Learn to use Tensorflow to build Deep learning engine.
- Learn to use Malaya to do local text language analytics.

#### requirement

- A decent enough laptop with modern browsers like Chrome and Firefox.
- Google account for Google Colab, https://colab.research.google.com/
- A good internet infrastructure.
- Required understanding Mathematics and basic Statistics in Diploma / Foundation / A-Level

#### day 1: training topics

Refreshing Python programming language

- Python language fundamentals, including basic syntax, data types, lists, dictionaries, sets, tuples.

Introduction to linear algebra library, Numpy, and vector programming

- What is numpy and why linear algebra is very crucial for data science.

Introduction to dataframe library, Pandas

- What is pandas and it offers data structures and operations for manipulating numerical tables and time series.

Pandas Data Structure and important functions

- Manipulating 1D and 2D data in Pandas and how to use important functions to do basic data cleaning.

Pandas grouping for aggregation, filtration and transformation

- What is aggregation and how to aggregate using Pandas.

Pandas fast indexing and selecting data

- We will focus on how to slice, dice, and generally get and set subsets of pandas objects.

Pandas time frame type manipulation

- We will focus on how to use Pandas time series and dates functionality for time series dataset.

#### day 2: training topics

Introduction to Machine learning

- How to use Multinomial bayes theorem, decision trees, random forests, and various ensemble tree based algorithm to solve simple classification problem.

Introduction to Deep learning

- Why current industry move towards deep learning as base AI engine and how to use Tensorflow to build simple feed-forward deep learning to solve simple classification problem.

Introduction to Regression problem

- We will learn data exploration on house pricing dataset, and solve regression problem to predict house prices using various machine learning models.

Introduction to Classification problem

- We will learn data exploration on telco churn dataset, and solve classification problem to predict which customers will churn for next payment period.

#### who should attend?

This professional training is designed for Technical Professionals as below:

- CTO
- CIO
- Data Scientist
- Data Engineer
- Data Analyst
- Big Data Department Staff
- Big Data Project Lead
- Solution Architect
- Big Data Executive
- Software Engineer

From various local and global organizations