/Machine_Learning_and_Deep_Learning

Primary LanguageJupyter NotebookGNU General Public License v3.0GPL-3.0

Getting started with Machine Learning and Deep Learning

Star this repo if you find it useful ⭐


Module 1 - Python Programming

Topic Name What's Covered
Intro to Python Applications and Features of Python, Hello World Program, Identifiers and Rules to define identifiers, Data Types (numeric, boolean, strings, list, tuple, set and dict), Comments, Input and Output, Operators - Arithmatic, Reltaional, Equality, Logical, Bitwise, Assignment, Ternary, Identity and Membership
Data Structures in Python (Strings, List, Tuple, Set, Dictionary) Strings - Creating a string, Indexing, Slicing, Split, Join, etc, List - Initialization, Indexing, Slicing, Sorting, Appending, etc, Tuple - Initialization, Indexing, Slicing, Count, Index, etc, Set - Initialization, Unordered Sequence, Set Opertaions, etc, Dictionary - Initialization, Updating, Keys, Values, Items, etc
Control Statements (Conditionals and Loops) Conditional Statements - Introducing Indentation, if statement, if...else statement, if..elif...else statement, Nested if else statement, Loops - while loops, while...else loop, Membership operator, for loop, for...else loop, Nested Loops, Break and Continue Statement, Why else?
Functions and Modules Functions - Introduction to Python Functions, Function Definition and Calling, Functions with Arguments/Parameters, Return Statement, Scope of a Variable, Global Variables, Modules - Introduction to Modules, Importing a Module, Aliasing, from...import statement, import everything, Some important modules - math, platform, random, webbrowser, etc
Object Oriented Programming Classes and Objects - Creating a class, Instantiating an Object, Constructor, Class Members - Variables and Mentods, Types of Variables - Instance, Static and Local Variables, Types of Methods - Instance, Class and Static Methods, Access Modifiers - Public, Private and Protected, Pillars of Object Oriented Programming - Inheritance, Polymorphism, Abstraction and Encapsulation, Setters and Getters, Inheritance vs Association
Exception Handling Errors vs Exception, Syntax and Indentation Errors, try...except block, Control Flow in try...except block, try with multiple except, finally block, try...except...else, Nested try...except...finally, User Defined Exception
File Handling Introduction to File Handling, Opening and Closing a File, File Object Properties, Read Data from Text Files, Write Data to Text Files, with statement, Renaming and Deleting Files
Web API Application Programming Interface, Indian Space Station API, API Request, Status Code, Query Parameters, Getting JSON from an API Request, Working with JSON - dump and load, Working with Twitter API
Databases Introduction to Databases, SQLite3 - Connecting Python with SQLite3, Performing CRUD Opertations, MySQL - Connecting Python with MySQL, Performing CRUD Opertations, MongoDB - Connecting Python with MongoDB, Performing CRUD Opertations, Object Relation Mapping - SQLAlchemy ORM, CRUD operations and Complex DB operations
List Comprehension, Lambda, Filter, Map, Reduce List Comprehension, Anonymous Functions, Filter, Map, Reduce, Function Aliasing
Problem Solving for Interviews Swapping two numbers, Factorial of a number, Prime Number, Fibbonnacci Sequence, Armstrong Number, Palindrome Number, etc

Module 2 - Python for Data Analysis

Topic Name What's Covered
Data Analytics Framework Data Collection, Business Understanding, Exploratory Data Analysis, Data Preparation, Model Building, Model Evaluation, Deployment, Understanding Cross Industry Standard Process for Data Mining (CRISP-DM) and Microsoft's Team Data Science Process (TDSP)
Numpy Array Oriented Numerical Computations using Numpy, Creating a Numpy Array, Basic Operations on Numpy Array - Check Dimensions, Shape, Datatypes and ItemSize, Why Numpy, Various ways to create Numpy Array, Numpy arange() function, Numpy Random Module - rand(), randn(), randint(), uniform(), etc, Indexing and Slicing in Numpy Arrays, Applying Mathematical Operations on Numpy Array - add(), subtract(), multiply(), divide(), dot(), matmul(), sum(), log(), exp(), etc, Statistical Operations on Numpy Array - min(), max(), mean(), median(), var(), std(), corrcoef(), etc, Reshaping a Numpy Array, Miscellaneous Topics - Linspace, Sorting, Stacking, Concatenation, Append, Where and Numpy Broadcasting
Pandas for Beginners Pandas Data Structures - Series, Dataframe and Panel, Creating a Series, Data Access, Creating a Dataframe using Tuples and Dictionaries, DataFrame Attributes - columns, shape, dtypes, axes, values, etc, DataFrame Methods - head(), tail(), info(), describe(), Working with .csv and .xlsx - read_csv() and read_excel(), DataFrame to .csv and .xlsx - to_csv() and to_excel()
Advance Pandas Operations What's Covered
Case Study - Pandas Manipulation What's Covered
Missing Value Treatment What's Covered
Visuallization Basics - Matplotlib and Seaborn What's Covered
Case Study - Covid_19_TimeSeries What's Covered
Plotly and Express What's Covered
Outliers - Coming Soon What's Covered

Module 3 - Statistics for Data Analysis

Topic Name What's Covered
Normal Distribution What's Covered
Central Limit Theorem What's Covered
Hypothesis Testing What's Covered
Chi Square Testing What's Covered
Performing Statistical Test What's Covered

Module 4 - Machine Learning

  1. Data Preparation and Modelling with SKLearn
  2. Working with Text Data
  3. Working with Image Data
  4. Supervised ML Algorithms
    - K - Nearest Neighbours
    - Linear Regression
    - Logistic Regression
    - Gradient Descent
    - Decision Trees
    - Support Vector Machines
    - Models with Feature Engineering
    - Hyperparameter Tuning
    - Ensembles
  5. Unsupervised ML Algorithms
    - Clustering
    - Principal Component Analysis

Module 5 - MLOPs

Topic Name What's Covered
Model Serialization and Deserialization What's Covered
Application Integration What's Covered
MLFlow - Experiment Tracking and Model Management What's Covered
Prefect - Orchestrate ML Pipeline What's Covered

Module 6 - Case Studies

Topic Name What's Covered
Car Price Prediction (Regression) What's Covered
Airline Sentiment Analysis (NLP - Classification) What's Covered
Adult Income Prediction (Classification) What's Covered
Web App Development + Serialization and Deserialization What's Covered
AWS Deployment What's Covered
Streamlit Heroku Deployment What's Covered
Customer Segmentation What's Covered
Web Scrapping What's Covered

Module 7 - Deep Learning

Topic Name What's Covered
Introduction to Deep Learning What's Covered
Training a Deep Neural Network + TensorFlow.Keras What's Covered
Convolutional Neural Network + TensorFlow.Keras What's Covered
Auto Encoders for Image Compression What's Covered
Recurrent Neural Network (Coming Soon) What's Covered