Data Science With Python

Course Objectives

After taking the course, students will be able to:

• perform data analysis and visualization
• use tools and techniques for data transformation
• understand the working mechanism of machine learning algorithm
• apply machine learning algorithm to solve real-world problems

Prerequisites

The audience should have a basic understanding of the python programming language and statistics.

Contents

Web Scraping for Data Collection

• BeautifulSoup
• Python Requests
• parsing - JSON,XML

Numpy Python

• NumPy Tutorial Basics
• NumPy Attributes and Functions
• Creating Arrays from Existing Data
• Creating Array from Ranges
• Indexing and Slicing in NumPy
• Advanced Slicing in NumPy
• Numpy Broadcasting
• Array Manipulation Functions
• NumPy Unique()
• NumPy Delete() 
• NumPy Insert Function
• Numpy RAVEL() SWAPAXES()
• NumPy Trigonometric Functions
• NumPy Round Functions
• NumPy Arithmetic Functions
• NumPy Power and Reciprocal Functions
• NumPy Power and Mod Functions

Data Preprocessing with Pandas

• Dataframe
• Series

Data Visualization with Matplotlib

• Barchart
• Scatter Plot
• HeatMap
• Histogram
• Line Chart
• Time Series Graph

Exploratory Data Analysis

Descriptive Statistics

• Distribution function
• Measure of Central Tendency
• Measure of Dispersion

Fundamentals of Deep Learning

• Artificial intelligence, machine learning, and deep learning
• Why deep learning?

The mathematical building blocks of neural networks

• Neural Network
• Data representations for neural networks
• The gears of neural networks: tensor operations
• The engine of neural networks: gradient-based optimization

Introduction to Keras and Tensorflow

Setting up a deep-learning workstation

Fundamentals of machine learning

• Four branches of machine learning
• Evaluating machine-learning models
• Data preprocessing, feature engineering, and feature learning
• Overfitting and underfitting

Binary Classification - Example

Multi-Class Classification - Example

Regression - Example 

Deep learning for computer vision

• Introduction to convnets
• Training a convnet from scratch on a small dataset
• Visualizing what convnets learn

Deep learning for text and sequences

• Working with text data
• Understanding recurrent neural networks
• Advanced use of recurrent neural networks
• Sequence processing with convnets

Inspecting and monitoring deep-learning models using Keras callbacks and TensorBoard

Generative deep learning

• Text generation with LSTM
• Generating images with variational autoencoders

The limitations of deep learning

The future of deep learning

PROJECT WORK

• solving real-world problems using deep learning

RESEARCH PAPER PUBLICATION