Data Science Basic Course
Python Basic
9lectures
From Basics to Advanced From setting up your coding environment to mastering algorithms, join me in this comprehensive Python lecture series. Build a strong foundation in Python's fundamentals, dive into functional and object-oriented programming, handle files and errors, explore libraries, and complete a practical data analysis project. Elevate your coding skills with hands-on exercises and earn your Zeroney certificate.
#1 Basics of Python
-
1. Message from the instructor
2. Introduction to Python and its features
3. Setting up the development environment and using Python in interactive mode
4. Running Python scripts and basic input/output
5. Understanding Python's interactive mode for quick experimentation
6. Exploring the Python Integrated Development Environment (IDE) options
7. Hands-on exercises and puzzles to reinforce understanding
#2 Variable Functional Programming
-
1. Execution of Variable and Data types
2. Fundamental of bollen, expression etc
3. Data Types of Operation
4. Explore functionality, such as strings, tuples etc
5. Practical coding Problem
6. Exercise
#3 Array and Object Oriented Programming
-
1. Define Class and object
2. Defining array and multidimensional array concept
3. Custom method of creating the class
4. Polymorphism concept and design object based pattern
5. How to tackle the error or your custom defining
6. Exercise
#4 Accessing Files
-
1. Principle of file system
2. How to access the files for writing and reading purpose
3. Develop software capable of extracting or saving information from/to a simple text
document
4. Generate applications capable of parsing or generating JSON data
5. Craft programs enable the manipulation of CSV data through reading or writing operations
6. Exercise
#5 Iterative processing
-
1. How to use looping function
2. How to use "while"
3. How to use "for"
4. Ternary operators
5. How we can save results of our file and back to file
6. Exercises
#6 How to use Libraries in Python
-
1. How to use open-source Libraries
2. Common libraries packages use in python Libraries
3. How to we know which libraries and packages need as per our virtual environment
4. Data Utilization
5. Downloading external Files to system
6. Exercise practice 1
7. Exercise practice 2
#7 Handling error and Exception
-
1. Reading and writing files in Python
2. Handling the exception and error gracefully
3. Real -world applications: data processing
4. Logging and debugging
5. Exercise
#8 Overview of Libraries
-
1. Library Basics
2. Popular Libraries
3. Application Scenario
4. Library documentation and Resources
5. Exercise
#9 Introduction to Algorithm
-
1. Basic algorithms and their efficiency
2. Analyzing data with Python
3. Google Colab
4. Final project: Creating a mini data analysis tool
Git/GitHub, Command line
6lectures
This subject is designed to introduce students/ engineers to the fundamental concepts of control using Git and collaboration through GitHub. Whether you're a coding newbie or have some experience, this subject will equip you with the skills needed to manage your code and work effectively in collaborative software development projects. Through a combination of lectures and hands-on exercises, you'll gain confidence in using Git and GitHub for control , also we include command line use with teamwork.
#1 Understanding the Need for Version Control
-
1. What is Git
2. Git Workflow
3. Commands
4. What is GitHub
5. Command Line
6. References
#2 Introduction to Git
-
1. Installing Git on different platforms
2. Configuring user information
3. Creating a new repository
4. Adding files and making the first commit
5. Creating a GitHub account
6. Pushing changes to a remote repository
7. Introduction to the command line
8. Basic commands for navigating and interacting with files
#3 Collaborating with Git and GitHub
-
1. Project Initialize on git
2. Password authentication error solving
3. Git commit
4. Git add
5. Git push
6. Github interface
#4 Direct use on GitHub
-
1. Website https://github.com
2. Version control benefits
3. Profile updation
4. Architecture
5. Merging
6. Fork
#5 Git and Command Line Hand on
-
1. Git access
2. File Creation
3. Branching and its Conflicts
4. Merging
5. Merge Conflicts
6. Pulling and accessing Request
#6 Incorporate Advanced Strategies for Git Success
-
1. Command line git
2. Advance git commands
3. Git cheat sheet
Mathematical Foundations
15lectures
This module provides foundational knowledge in three key areas: Linear Algebra, exploring vectors, determinants, eigenvalues, and matrices; Calculus, covering limits, derivatives, integrals, and multivariate analysis; and Probability and Statistics. These essential concepts form the basis for engineering fields, including data analysis and machine learning.
#1 Vector
-
Vectors represent multidimensional data; their computation and interpretation in Euclidean space help solve problems involving distances and directions.
░░░░░░░░░░░░░░░░░░
• Handle multidimensional data• Vector computation
• Interpretation in Euclidean space
• Metrics
#2 Matrix
-
Matrices represent linear transformations and systems of equations. Key operations like addition, multiplication, and finding determinants are fundamental.
Contents:
• Characteristics of matrices
• Types of matrices
• Matrix computation
#3 Determinant and Inverse
-
• Introduction to determinants
• Calculating determinants for 2x2 matrices
• Determinant calculation for generic cases
• Row reduction method for inverse
#4 Rank and Linear independence
-
• Definition of rank
• Methods to calculate rank
• Linear independence and rank
#5 Simultaneous equations
-
• Introduction to simultaneous equations
• Conditions for solvability
• Methods for solving simultaneous equations
#6 Linear Map
-
• What is a map?
• Definition of a linear map
• Expression of linear maps
• Image and kernel of linear maps
#7 Eigenvalues and Eigenvectors
-
• Definition of eigenvalues and eigenvectors
• Visualizing eigenvectors and eigenvalues
#8 Diagonalization
-
• What is diagonalization?
• Conditions for diagonalization
• Concrete steps to diagonalize a matrix
#9 Continuity
-
• What is continuity?
• Various definitions of continuity
• Relation to calculus
#10 Limit
-
• Limits of sequences and functions
• Calculating limits
• Continuity and limits
• Extreme value theorem
#11 Differentials
-
• Definition of differentials
• Calculating differentials
• Mean value theorem and Rolle’s theorem
• Taylor and Maclaurin series
• L'Hôpital's rule
• Analyzing extrema
#12 Integrals
-
• Riemann sum and its significance
• Indefinite and definite integrals
• Techniques for calculating integrals
#13 Multivariate calculus
-
• Limits of multivariable functions
• Tangent planes and their applications
• Jacobian matrix and its significance
• Taylor and Maclaurin series for multivariable functions
• Maxima and minima in multivariable functions
• Lagrange multipliers
• Multivariable integrals
#14 Probability
-
• Definition of sets and sample spaces
• Probability in finite sample spaces
• Probability distributions
• Expectation, variance, and standard deviation
#15 Random variables
-
• In-depth look at random variables
• Probability in infinite sample spaces
Applied Math in Machine-Learning
8lectures
This module builds on previously learned concepts to explore key ideas in probability and statistics, forming the foundation for constructing machine learning applications.
#1 Probability Mass Functions and Probability Density Functions
-
• Visualizing probabilities with PMF and PDF
• Expectation, variance, and standard deviation for PMF and PDF
#2 Independence in probability
-
• Multivariate probability
• Concept of independence
• Covariance and correlation
• Joint probability distribution
#3 Conditional probability
-
• Dependent random variables
• Marginal probability
• Expectation, variance, and standard deviation of conditional probability
#4 Bayes theory
-
• Concept of Bayes' theorem
• Bayes' theorem in infinite sample spaces
#5 Transformation of random variables
-
• Constructing new random variables
• Calculating expectation and variance of transformed variables
#6 Maximum liklihood estimation
-
• Overview of probabilistic distributions
• Definition of likelihood
• Maximum likelihood estimation (MLE)
#7 Loss function & Gradient descent
-
• Regressions in neural networks
• Defining loss functions
• Minimizing the loss function using gradient descent
#8 Principal Component Analysis (PCA)
-
• Challenge of High-Dimensional Data
• Covariance Matrix Calculation
• Eigenvalues and Eigenvectors for Dimensionality Reduction
Deep Learning Basic
9lectures
Delve into the essence of Deep Learning, exploring its unique characteristics and the pivotal role of neural networks. Get a sneak peek into the syllabus, guiding your exploration of this captivating field. Plus, we've got you covered with Python installation guidance.
#1 Introduction to Deep Learning
-
Embark on an exciting journey as we introduce the significance of this course. Delve into the essence of Deep Learning, exploring its unique characteristics and the pivotal role of neural networks. Get a sneak peek into the syllabus, guiding your exploration of this captivating field. Plus, we've got you covered with Python installation guidance.
#2 Perceptron
-
Uncover the core of neural networks through the lens of the perceptron. Engage in thought-provoking exercises involving logical gates like OR, AND, NAND, and XOR. Unlock the multilayer perceptron's magic as you peer into neural network behavior and its intriguing intricacies.
#3 Activation Function
-
Enter the realm of activation functions, the heartbeat of neural networks. Traverse through the landscape of Sigmoid, Hyperbolic tangent, ReLU, Mish, and Softmax functions. Grasp the art of differentiation and its application in these functions. Elevate your prowess with stimulating activation function exercises.
#4 Neural Network
-
Construct a sturdy foundation in neural networks, their architecture, and design. Witness the orchestration of output layers and unravel the mechanics of forward propagation. Navigate the world of error functions, a crucial compass guiding neural network evolution. Immerse yourself in practical exercises refining your grasp of forward propagation.
#5 Learning Algorithms
-
Embark on the dynamic path of learning algorithms and their power in weight updates. Unveil the secrets of gradient descent and its speedster, the Fastest Descent Method. Engage in an enlightening journey through diverse learning algorithms, igniting your practical skills with captivating exercises.
#6 Error Back Propagation Method
-
Embark on an odyssey into the profound landscape of error back propagation. Master the intricate dance of neural networks and the chain rule of derivatives. Conquer the realm of gradient descent in neural networks, enriched by insightful practical exercises.
#7 Convolutional Layer/Pooling Layer
-
Step into the mesmerizing world of Convolutional Neural Networks (CNNs). Decode the enigmatic convolutional and pooling layers. Witness the marvel of learning features layer by layer, as we demystify CNNs and their role in image recognition.
#8 General Image Classification
-
Open the door to transfer learning and witness the transformation of your Python programs through the magic of libraries. Embrace the treasure trove of open-source code, elevating your coding endeavors for machine learning and statistics. Elevate your programming prowess with the wisdom of libraries.
#9 Transfer Learning
-
Embark on a voyage through the landscapes of transfer learning and fine-tuning. Discern the art of leveraging pre-trained models and enhancing their applicability. Immerse yourself in the finesse of practical exercises that bring the power of transfer learning to life.
Introduction to a Data Challenge in Image Processing
4lectures
This module guides you through solving a single image recognition challenge using a real competition dataset. You will learn practical techniques, including loading and preprocessing image data, preparing datasets, selecting models, and applying transfer learning with pre-trained models, culminating in submitting your predictions.
#1 Introduction
-
• Load and explore image data
• Understand the structure and characteristics of image data
#2 Data processing
-
• Apply image normalization techniques
• Prepare and split datasets for training and evaluation
#3 Model selection
-
• Understand different machine learning models for image data
• Choose the appropriate model for specific tasks
#4 Use of pre-trained model
-
• Implement transfer learning for efficient training
Data Challenge and Competition: Text Data Processing and Analysis
7lectures
This module covers essential techniques for processing and analyzing text data, including loading text, tokenization, cleansing, sentiment analysis, and feature extraction using frequency-based approaches like TF-IDF. You will also explore semantic-based approaches with transformers, culminating in the development of a practical solution for a data challenge.
#1 Introduction to text data
-
- Load Text Data
- Import text from files, APIs, or web scraping.
- Basics of text structure: words, sentences, and paragraphs.
- Explore data using frequency counts and simple visualizations (e.g., word clouds).
#2 Tokenization & Cleansing
-
- Breaking text into smaller parts (words, sentences).
- Hands-on with tokenization using beginner-friendly tools (e.g., Python’s nltk or spaCy).
- Removing unnecessary characters (e.g., punctuation, emojis).
- Lowercasing, removing stopwords, and handling missing data.
#3 Frequency-Based Approach
-
- Visualizing frequent words
- Concepts of representing words as numbers
- TF-IDF (Term Frequency-Inverse Document Frequency)
#4 Spam Mail Classification
-
- Build a spam classifier using TF-IDF and Naive Bayes
- Step-by-step coding session with small datasets.
- Use frequency-based features to group similar text together
#5 Sentiment Analysis
-
- Rule-based sentiment scoring using a simple lexicon
- Classifying positive and negative reviews.
- "attention" in text analysis.
#6 Using Pre-Trained Models
-
- What pre-trained models are and why they’re useful.
- Text Classification
- Classify text into categories (e.g., genres, product types).
#7 Submit a Project to Kaggle
-
- Walk through submission in a classification challenge
Data Challenge and Competition: Demand Forecasting
7lectures
This module focuses on analyzing and visualizing time series data, applying rule-based and advanced forecasting techniques such as Long Short-Term Memory (LSTM) models, and developing practical solutions for predicting future demand trends in real-world scenarios.
#1 Introduction to time series data
-
- What is forecasting?
- Handling of time seriese data
#2 Analyzing and Visualizing Time Series Data
-
- Explore data using descriptive statistics (e.g., mean, variance).
- Visualizing time series data:
Line plots, seasonal decomposition (STL), autocorrelation plots.
#3 Data Preprocessing & Feature Engineering
-
- Handling missing values and outliers in time series.
- Scaling and normalizing time series data.
- Splitting time series data into training and testing sets.
- Extract features like lag values, rolling averages, and seasonal indices.
- Construct new features to capture trends and periodicity.
#4 Forecasting with Rule-Based Approaches
-
- Introduction to decision trees for forecasting.
- LightGBM for time series data:
- Converting time series into a supervised learning problem.
- Practical example: Forecasting sales or stock prices.
#5 Overview of Recurrent Neural Networks (RNNs)
-
- Simplified explanation of how RNNs work for sequential data.
- Highlight their advantage in capturing time dependencies.
- Use a visual demo or interactive tool to explain RNNs.
#6 Forecasting with Long Short-Term Memory (LSTM)
-
- Introduction to LSTMs: A beginner-friendly explanation of how they handle long-term dependencies.
- Hands-on:
- Train a basic LSTM model for time series forecasting.
- Use of TensorFlow
#7 Kaggle Challenge Submission
-
- Preprocess the dataset.
- Build a forecasting model (e.g., LightGBM or LSTM).
- Make predictions and prepare the submission file.