Seed Programming

Menu
School of Seed Programming Logo
Menu

Python For Data Science - Summer 2024

Live: Online

Rs 10,000/- PKR

Register Now !
  • Duration: 5 weeks
  • Stating 20 July 2024
  • Mode: Online
  • For CS Students 2 year+
  • Saturday: 12:00 pm - 3:00 pm

About Course

“Python for Data Science” is a comprehensive course designed to equip learners with the essential tools and techniques needed in the field. The first session introduces Python, covering basic syntax, data types, control flow, functions, and error handling. It also guides through the setup and usage of Jupyter Notebooks and VS Code, emphasizing their importance in data science workflows. Additionally, the session delves into NumPy, teaching array manipulation, basic operations, and its applications in linear algebra and statistics. Subsequent sessions build on this foundation, covering advanced topics like feature engineering, data visualization with Matplotlib and Plotly, dimensionality reduction techniques like PCA and t-SNE, and the fundamentals of neural networks using PyTorch. The course progresses to specialized topics, including computer vision, deep learning for image and video processing, and working with large language models such as OpenAI’s GPT and Meta’s LLaMA. By the end of the course, participants will have a solid grounding in Python for data science, equipped to handle various data-centric tasks and challenges.

"Python for Data Science" is a comprehensive course designed to equip learners with the essential tools and techniques needed in the field. The first session introduces Python, covering basic syntax, data types, control flow, functions, and error handling. It also guides through the setup and usage of Jupyter Notebooks and VS Code, emphasizing their importance in data science workflows. Additionally, the session delves into NumPy, teaching array manipulation, basic operations, and its applications in linear algebra and statistics. Subsequent sessions build on this foundation, covering advanced topics like feature engineering, data visualization with Matplotlib and Plotly, dimensionality reduction techniques like PCA and t-SNE, and the fundamentals of neural networks using PyTorch. The course progresses to specialized topics, including computer vision, deep learning for image and video processing, and working with large language models such as OpenAI's GPT and Meta's LLaMA. By the end of the course, participants will have a solid grounding in Python for data science, equipped to handle various data-centric tasks and challenges.

  • Session 1: Introduction to Python, Jupyter and VS Code, and Numpy
    • 1. Introduction to Python
      • 1.1 Python Basics
        • Syntax and semantics
        • Data types (integers, floats, strings, lists, tuples, dictionaries)
        • Control flow (if statements, loops)
        • Functions and modules
        • Error handling and exceptions
    • 2. Working with Jupyter Notebooks and VS Code
      • 2.1 Jupyter Notebooks
        • Installation and setup
        • Notebook interface and features
        • Running and saving notebooks
        • Markdown and code cells
      • 2.2 Visual Studio Code (VS Code)
        • Installation and setup
        • Python extensions and environment setup
        • Debugging and version control with Git
    • 3. Introduction to Numpy
      • 3.1 Basics of Numpy
        • Numpy arrays: creation, indexing, slicing, and reshaping
        • Basic operations: mathematical functions, broadcasting
        • Numpy for linear algebra
        • Numpy for statistical operations
  • Session 2: Feature Engineering and Data Visualization
    • 1. Feature Engineering
      • 1.1 Basics of Feature Engineering
        • Handling missing data
        • Encoding categorical variables
        • Feature scaling (normalization and standardization)
        • Feature selection techniques
        • Feature extraction techniques
    • 2. Data Visualization
      • 2.1 Matplotlib
        • Basic plots: line, scatter, bar, histogram
        • Customizing plots: titles, labels, legends, styles
        • Subplots and grid layouts
        • Saving and exporting figures
      • 2.2 Plotly
        • Interactive plots: scatter, line, bar, pie charts
        • Customizing and updating figures
        • 3D plots and surface plots
        • Dashboards with Plotly Dash
    • 3. Dimensionality Reduction
      • 3.1 Principal Component Analysis (PCA)
        • Introduction and intuition
        • Implementing PCA with Numpy and Scikit-learn
        • Visualizing PCA results
      • 3.2 t-SNE
        • Introduction and intuition
        • Implementing t-SNE with Scikit-learn
        • Visualizing high-dimensional data
      • 3.3 AutoEncoders
        • Introduction to neural network-based feature extraction
        • Implementing AutoEncoders with PyTorch or TensorFlow
        • Visualizing and interpreting latent spaces
  • Session 3: Neural Networks Fundamentals and Autograd using PyTorch
    • 1. Fundamentals of Neural Networks
      • 1.1 Basics of Neural Networks
        • Neurons and layers
        • Activation functions
        • Loss functions
        • Forward and backward propagation
      • 1.2 Building Neural Networks with PyTorch
        • PyTorch basics: tensors and operations
        • Defining neural network architectures
        • Training and evaluating neural networks
    • 2. Autograd in PyTorch
      • 2.1 Introduction to Autograd
        • Concept of automatic differentiation
        • Implementing autograd in PyTorch
        • Custom gradients and backward functions
      • 2.2 Optimizing Neural Networks
        • Optimization algorithms: SGD, Adam, RMSprop
        • Hyperparameter tuning
        • Regularization techniques: dropout, weight decay
  • Session 4: Computer Vision, Images, Videos, Object Detection, Instance
    Segmentation
    • 1. Introduction to Computer Vision
      • 1.1 Basics of Image Processing
        • Reading and displaying images
        • Image transformations and augmentations
        • Feature detection and extraction
    • 2. Deep Learning for Computer Vision
      • 2.1 Convolutional Neural Networks (CNNs)
        • Introduction to CNNs
        • Building CNNs with PyTorch
        • Transfer learning with pre-trained models
    • 3. Advanced Topics in Computer Vision
      • 3.1 Object Detection
        • Introduction to object detection
        • Implementing object detection models (YOLO, SSD)
      • 3.2 Instance Segmentation
        • Introduction to instance segmentation
        • Implementing instance segmentation models (Mask R-CNN)
    • 4. Working with Videos
      • 4.1 Video Processing Basics
        • Reading and writing videos
        • Frame extraction and processing
        • Video classification and activity recognition
  • Session 5: Large Language Models, OpenAI, Meta LLaMA, ChromaDB,
    Unstructured, Chatbots
    • 1. Large Language Models (LLMs)
      • 1.1 Introduction to LLMs
        • Overview of large language models
        • Applications and use cases
      • 1.2 Working with OpenAI Models
        • Introduction to OpenAI’s GPT models
        • Using OpenAI API for text generation
      • 1.3 Meta’s LLaMA
        • Overview of Meta’s LLaMA
        • Applications and use cases
    • 2. Advanced NLP Techniques
      • 2.1 ChromaDB
        • Introduction to ChromaDB
        • Implementing text search and retrieval
      • 2.2 Unstructured Data Processing
        • Handling unstructured text data
        • Text preprocessing techniques
        • Named Entity Recognition (NER)
    • 3. Building Chatbots
      • 3.1 Chatbot Fundamentals
        • Overview of chatbots
        • Designing conversation flows
      • 3.2 Implementing Chatbots
        • Building chatbots with Python
        • Integrating NLP models into chatbots
        • Deploying chatbots on different platforms
Show All Collapse

What Will You Learn?

  • Python Basics: Syntax and Semantics

  • Python Basics: Data Types

  • Python Basics: Control Flow

  • Python Basics: Functions and Modules

  • Python Basics: Error Handling and Exceptions

  • Working with Jupyter Notebooks

  • Jupyter Notebooks: Installation and Setup

  • Jupyter Notebooks: Notebook Interface and Features

  • Jupyter Notebooks: Running and Saving Notebooks

  • Jupyter Notebooks: Markdown and Code Cells

  • Working with Visual Studio Code (VS Code)

  • Visual Studio Code: Installation and Setup

  • Visual Studio Code: Python Extensions and Environment Setup

  • Visual Studio Code: Debugging and Version Control with Git

  • Introduction to Numpy

  • Numpy Arrays: Creation, Indexing, Slicing, and Reshaping

  • Numpy: Basic Operations and Broadcasting

  • Numpy for Linear Algebra

  • Numpy for Statistical Operations

  • Basics of Feature Engineering

Registration Queries

FOR ANY REGISTRATION QUERIES FEEL FREE TO REACH OUT TO OUR TEAM​
Whatsapp Envelope

Nourishing the Programmer in you!

schoolofseedprogramming@gmail.com

query@seedprogramming.org

Open chat
Powered by Joinchat
Hello 👋
Can we help you?
Need more information about Python for Data Science