Data Science and Machine Learning Course in India

This unit serves as a primer for data science, introducing key tools and concepts. It’s designed to equip non-programmers with foundational Python skills, facilitating a deeper understanding and practical application throughout the course.

Module 1: Introduction To Data Science and Machine Learning

• Introduction to tools, key concepts, and definitions
• Real-time project applications in different domains
• Practical applications of data science in various industries

Module 2: Fundamentals of Python Programming

• Introduction to Python tools
• Installation of Python
• Python Fundamentals

Tools Covered: Python, Anaconda, Jupyter, Google Colab

Module 3: Fundamentals of Statistics

• Importance and Use of Statistics in Data Science
• Descriptive Statistics & Predictive Statistics
• Learn how predictive Statistics connects with Machine Learning

Note:

Module 2 and Module 3 of Unit 1 are specially designed for non-programmers to understand the basics of computer programming and math.

This unit provides an extensive roadmap for building a robust portfolio in data science. You’ll master GitHub, a version control system, for efficient collaboration and project management. Additionally, you’ll harness LinkedIn‘s power for networking and career advancement.

Module 1: Git & GitHub (VCS)

• Introduction to Version Control Systems
• Installing and Configuring Git
• Git Essentials

• Branching and Merging
• GitHub Essentials

• Collaborating on GitHub
• Forking repositories
• Creating pull requests

• Best Practices and Workflows

Class Hands-On: Initiate, collaborate, and work on a real-time project

Tools Covered: Git, GitHub

Module 2: LinkedIn Profile building

• Introduction to LinkedIn as a Professional Networking Platform
• Crafting a Compelling LinkedIn Profile

• Leveraging LinkedIn Features for Engagement

• Growing Your Network on LinkedIn

• Increasing Followers and Engagement

• Enhancing Professional Branding on LinkedIn

• Leveraging LinkedIn for Career Advancement

This Python course introduces fundamental to advanced concepts tailored for data science applications. Learn Python step by step from basics to advanced. Learn all libraries, functions, and modules to perform data science projects by analyzing and building ML models using Python.

Module 1: Core Python Programming

• Python Environment
• Data types & Operators
• Operators & Loop controls

Project: Build a simple calculator

Module 2: Advanced Python Programming

• Functions & Modules
• Regular Expressions (RegEx)
• File Handling & Exception Handling
• Generators & Decorators

Class Hands-on:

25+ programs/coding exercises on data types, loops, operators, functions, generators, file I/O, reg-ex, and exception handling

Module 3: Web Scraping using Python

• Introduction to Web Scraping
• Web Requests & HTTP
• Parsing HTML with Beautiful Soup

Project: Scrape and Analyze Data from a Website (2-3 Projects)

Module 4: OOPs in Python

• Classes and Objects
• Encapsulation, Inheritance, and Polymorphism
• Abstraction and Interfaces
• Method Overriding and Overloading
• Class Variables and Instance Variables

Module 5: Python For Data Science

• Data Analysis using NumPy (Array Operations)
• Data Analysis using Pandas (On Dataframes)
• Data Visualization using Matplotlib
• Data Visualization using Seaborn

Tools Covered: NumPy, Pandas, MatplotLib, Seaborn, Beautiful Soup

EDA Project (Create Insights using Data Analytics)

2 Full-Length Projects on Data Analytics using Pandas, MatplotLib & Seaborn to analyze Data to Gain Insights and Identify Patterns.

Learn practically data mining, using SQL and NoSQL databases like MongoDB. Data visualization and analytics using Power BI & Tableau and big data analytics using Hadoop preparing students for diverse data roles.

Module 1: SQL – Structured Query Language 

• Introduction to SQL
• SQL & RDBMS
• SQL Syantax and data types
• CRUD operations in SQL
• Retrieving Data with SQL
• Filtering, sorting & formatting query results
• Advanced SQL Queries
• Database Design and Normalization
• Advanced Database Concepts
• Stored Procedures
• Integrating SQL with Python for Data

Hands-on practice:

• Joins, Sub-queries, Aggregation query
• Views, Filtering, Sorting
• Group By and Having clause

Module 2: MongoDB 

• Introduction to MongoDB
• MongoDB essentials
• Structure of MongoDB
• Advanced MongoDB Queries

• Integrating MongoDB with Python for Data

Tools Covered: MySQL, SQL Server, MongoDB

Module 3: Power BI 

• Introduction to Power BI
• Data Preparation and Modeling
• Clean, transform & load data in Power BI
• Data Visualization Techniques
• Advanced Analytics in Power BI
• Designing Interactive Dashboards

• Power Query

• Design Power BI Reports
• Connecting Power BI to SQL
• Create, Share, and Collaborate on Power BI Dashboards

Class Project & Assignments:

Project 1: Education Institute’s student data analysis

Project 2: Sales Data Analysis

– Learn to visualize data to find patterns & insights using interactive charts

Module 4: Tableau

• Introduction to Tableau
• Connecting Tableau to data sources
• Data Types in Tableau
• Data Preparation and Transformation
• Building Visualizations in Tableau

• Advanced Analytics in Tableau
• Tableau Dashboards and Storytelling
• Connecting Tableau to SQL
• Tableau Online to collaborate, share & publish dashboards

Class Project & Assignments:

Project 1: Supermarket data analysis

Project 2: Covid Data Analysis

– Learn to visualize data to find patterns & insights using interactive charts

– Deployment of Predictive model in Tableau

Tools Covered: Power BI, Tableau, Excel

Module 5: Excel for Analytics 

• Introduction to Excel for Analytics
• Basic Formulas & Function
• Data Preparation and Cleaning
• Charts & Graphs in Excel
• Data Analysis Techniques in Excel
• PivotTables and PivotCharts for data summarization
• Data visualization techniques in Excel
• Excel’s data analysis add-ins

Module 6: Apache Hadoop – Big Data Analytics

• Overview of Big Data and Distributed Computing
• The Hadoop ecosystem and its components
• Architecture: HDFS and MapReduce
• Setting Up Hadoop Environment
• Managing files and directories in HDFS
• Performing HDFS operations
• MapReduce paradigm: mapper, reducer, and shuffle phases
• Running and monitoring MapReduce jobs on Hadoop clusters
• YARN and Hadoop Ecosystem
• Hadoop ecosystem projects: Hive, Pig, HBase, etc.
• SQOOP (SQL in HADOOP)
• Integrating Hadoop with other Big Data technologies

Tools Covered: Hadoop, Pig, Hive, HBase, Yarn MapReduce

This course provides a comprehensive overview of statistical concepts for analytics & machine learning techniques with their practical applications.

Module 1: Statistics & Probability

• Fundamentals of Math, Probability & Statistics
• Descriptive vs inferential statistics
• Types of data, Sample and Population
• Descriptive Statistics
• Handling outliers & missing values in data
• Discrete and continuous probability distributions
• Normal distribution and central limit theorem
• Linear Algebra, Sampling and Estimation
• Hypothesis Testing Workflow
• Confusion Matrix, Performance Metrics
• P-values, Z Scores, Confidence Level
• Significance Level, Sampling Techniques
• Parametric Tests: T-test, Z-test, F-test, ANOVA test
• Non-Parametric Tests: Chi-square test, Man Whitney U Test & Wilcoxon Rank Sum Test
• Regression & Classification Analysis

Class Hands-on:

Problem-solving for central tendency, ANOVA, central limit theorem & hypothesis testing Case study

You will learn machine learning algorithms, and model building from scratch to advance exploring various case studies to practice on real-world applications to reinforce your learning.

Module 1: Machine Learning using Python

• Set Theory
• Data Preprocessing
• Traditional coding vs Machine learning
• Supervised and unsupervised learning
• Model evaluation
• Exploratory Data Analysis
• Data Analysis & Visualisation
• Feature Engineering
• Machine learning model building & evaluation
  • Linear Regression Model & Evaluation
  • L1 & L2 Regularization (Lasso and Ridge Regression)
  • Logistic Regression Model & Evaluation
  • K Nearest Neighbours (KNN) & Evaluation
  • Decision Tree Classifier & Regressor
  • Random Forest Classifier & Regressor
  • Naive Bayes Classifier
• Overfitting, bias-variance tradeoff
• Cross-validation

Project:

• EDA for Weight Prediction task from Height (Regression task)

• 1 project each for Regression & Classification

Module 2: Advanced Machine Learning

• Clustering & K-means
• K-Means Clustering Model
• Ensemble approach
• Bootstrapping + Aggregation = Bagging
• Bagging vs Boosting
• Hyperparameter Tuning for GridSearchCV
• XGBoost Explanatory Model Building
• Boosting Ensemble Models
• Adaptive Boosting (AdaBoost)
• Handling Imbalanced Dataset
  • Resampling (Oversampling & Undersampling)
  • Oversampling Technique (SMOTE)
• Gradient Boosting
• CatBoost
• LightGBM
• Support Vector Classifier (SVC) & Support Vector Machines (SVM)
• Principal Component Analysis (PCA)
  • Use of Dimensionality Reduction Technique
  • Difference with Feature Selection Techniques
• Density-based Spatial Clustering of Applications with Noise (DBSCAN)
• Hyperparameter Tuning

Tools Covered: Pandas, Matplotlib, Sk Learn, LightGBM

Class Projects:

• Project with practical application of Regression, Classification, and Clustering algorithms using Machine Learning concepts.
• Case studies in various domains (e.g., healthcare, finance, marketing, supply chain, etc.) like:

• Spam Mail Classifier using Naive Bayes Algorithm
• Detect car Insurance Fraud Claims
• Heart disease detection using ML

Note: All Machine Learning Algorithms will be covered in depth with real-time projects & case studies for each algorithm. Once Machine learning is completed, the Capstone Project will be released for the batch.

Module 3: Time-Series Forecasting

• Introduction to time series data
• Linear Regression Vs ARIMA model
• Time series visualization and exploration
• Time series decomposition
• Stationarity and its tests
• Autoregressive (AR) Models
• Moving Average (MA) Models
• Autoregressive Integrated Moving Average (ARIMA) Models
• Seasonal ARIMA (SARIMA) models
• Exponential smoothing methods

Class Projects:

• Project to predict the number of customers of an Airline organization using Time Series Model ARIMA & SARIMAX
• Financial Market Stock Price analysis and forecasting
• Sales data forecasting to understand trend and seasonality

Tools Covered: SciKit Learn, Pandas, Matplotlib

The NLP specialization will help you gain experience in techniques such as; text preprocessing, sentiment analysis, and building text-based models. These concepts will further help us build Machine Learning & AI models like Grammarly, ChatGPT, and Alexa.

Module 1: NLP

• Introduction to Natural Language Processing
• Text Preprocessing
• Text Embedding Techniques
• Word2Vec Text Embedding
• Topic modeling (LDA, LSA)
• Named Entity Recognition (NER)
• Part-of-Speech Tagging (POS Tagging)
• Transformer architecture and BERT model
• Text classification models

Class Projects:

• To classify an email as spam or not spam
• Social media sentiment analysis
• Translation & summarization of News
• Generate optimized title/headline
• Case Study on Recommendation Engine

Tools Covered: NLTK, Spacy, BERT

Deep Learning, focuses on training neural networks to build a model by studying hierarchical patterns and features from the input data. On the other hand, Prompt engineering is an act of engineering a suitable output with an efficient prompt on Generative AI tools like ChatGPT.

Module 1: Introduction to Deep Learning 

• Introduction to Deep Learning
• Forward Propagation in ANN
• Backpropagation in ANN
• Artificial Neural Network (ANN)

Class Projects

• Diabetes detection using Artificial Neural Network (ANN)

Tools Covered: Tensorflow, Keras, PyTorch

Module 2: Prompt Engineering 

• Exploring prompt tools
• Understanding prompt tools & their architecture
• Future advancement in AI and Large Language tools
• Overview of tools like (GPT, Dall E, Midjourney Etc.)

ChatGPT: Prompt for text Generation (Natural Language Processing)

• Introduction to NLP concept and role in GPT tools
• ChatGPT and its architecture
• Hands-on with ChatGPT / Microsoft Copilot prompt for Text Generation
• Tuning ChatGPT for desired output and application

Dall E / Midjourney: Prompt for image Generation

• Introduction to image generation using prompt
• Exploring Midjourney / Dall E 2 & 3 / Gencraft prompt for Image generation
• Tuning prompt for the desired output
• Ethical consideration for AI-generated images

Synthesia for Video Generation & Slides AI for PPT creation

• Learning prompt with Slides AI (from Google) / Simplified.com for PPT generation
• Using prompt on Synthesia / Invideo AI for Video Generation

Tools Covered: ChatGPT, Midjourney, Dall E, MS Copilot, Synthesia, Invideo AI, Slides AI

In this cloud deployment unit, you will learn to deploy machine learning models using AWS and Azure, two leading cloud platforms. You’ll gain proficiency in deploying, scaling, and managing models in the cloud environments through practical exercises.

Module 1: AWS

• Introduction to Cloud Deployment for ML and AI Models
• AWS cloud platform and its services for model deployment
• Understanding deployment architectures and best practices
• AWS IAM (Identity and Access Management)
• Elastic Compute Cloud (Amazon EC2)
• Elastic Block Storage (EBS) and Elastic File System (EFS)
• Model Deployment with AWS
• Model Deployment using Python on AWS using Flask
• Model Deployment using Python on AWS using Django

Module 2: Azure

• Azure cloud platform and its services for model deployment
• Understanding deployment architectures and best practices
• Fundamental Principles of Machine Learning on Azure
• Model Deployment on Azure
• Model Deployment using Python on Azure using Flask
• Model Deployment using Python on Azure using Django

Tools Covered: AWS, EC2, S3, ECS, Sagemaker, Lambda, Azure, Azure ML, Flask, Django