Course outline for Data Science(AI and ML) With Python

Goal:

The goal of this course is to examine large amounts of data to uncover hidden patterns, correlations and other insights. This help in preparing machine learning model using AI fundamentals

Audience:

This course is designed for any one willing to make career in Data Analytics and Machine Learning .

Pre-requisites:

Any Graduate or Post-Graduate having affinity with Data, Information, Knowledge and Wisdom

Basics of Python

Duration:

60 hours

Course Structure

1. Python Data Science Overview

What is Data Science
What Is Data Science and Machine Learning?
Introduction of Python Data Science Tools
Setting up environment for this course
Python Data Science Packages to be used

2. Fundamental of Statistics

Overview
Basic Terminology of Statistics

Variables
Data
Statistics
Dispersion
Scattering
Observation
Time Series Data
Population
Sample
Variation
Shape

Data Collections
Descriptive Statistics
Data Distribution
Confidence Interval

3. Statistical Inferences and Relationship Between Variables

Hypothesis Testing
Correlation Theory
Linear regression theory
Polynomial Regression
Logistic Regression

4. Introduction to NumPy (Numerical Python)

Numpy: Introduction
Create Numpy Arrays
Numpy Operations
Matrix Airthmetic and Linear Systems
Numpy for Basic Matrix Airthmetic
Broadcasting with Numpy
Solve Equation with Numpy
Statistical Operations

5. Pandas

Introduction to Data Structures

Series
DataFrame
Panel

Reading Data

CSV Data
Excel Data
JSON Data
HTML Data

Data pre-Processing/Wrangling/Cleaning

Removing NAs /No Values from data
Basic Data Handling: Starting with conditional data section
Drop Column/Rows
Subset and Index Data
Basic Data Grouping Based on Qualitative Attributes
Cross tabulation
Reshaping
Pivoting
Rank and sort Data
Concatenate
Merging and Joining frames

4. Data Visualization (plotLib)

Introduction
Histograms
Box Plots
Scatter Plots
Bar Plot
Pie Chart
Line Chart

7. Machine Learning: Overview

Machine Learning Languages, Types, and Examples
Machine Learning vs Statistical Modelling
Supervised vs Unsupervised Learning
Python Libraries : skLearn, TensorFlow

8. Supervised Learnings

K Nearest neighbours
Decision Trees
Using Logistic Regression as Classification Model
RF-Classification
SVM Linear Classification
Knn Regression
Gradient Boosting

9. Unsupervised Learning

K-Means Clustering plus Advantages & Disadvantages
Hierarchical Clustering plus Advantages & Disadvantages
Measuring the Distances Between Clusters - Single Linkage Clustering
Measuring the Distances Between Clusters - Algorithms for Hierarchy Clustering
Density-Based Clustering

10. Time Series Forecasting

Time series
Estimating and Eliminating the Deterministic Components if they are present in the Model.
Estimating and Eliminating Seasonality if it is present in the Model
Modeling the Remainder using Auto Regressive Moving Average (ARMA) Models
Identify ‘order’ of the ARMA model
‘Forecast’ or Predict for Future Values