Swipe to view full content

WEEK 1 WHAT'S IN THERE TASK 1 TASK 2 TASK 3
Day 0 Getting Started by setting up Anaconda environment.

Installing anaconda for Windows Installing anaconda for Mac Installing anaconda for Linux
Day 1
Hey there, excited to start learning?
First,  we will begin with learning the basics of Python.

Beginner Tutorial for Python Programming.(videos 1-3)
Moving Ahead (videos 4 - 6)
Wrapping up on basics (videos 7 - 10)
Day 2 Gaining an overview of NumPy and Pandas. You will be using them extensively in your Data Science journey.

Basics of Numpy (till 40 mins is sufficient)

Numpy Notebook
Intro to Pandas (videos 1 to 10) Data Analysis with Pandas (videos 11 to 20)
Day 3 Continuing with Pandas, let's use it for data cleaning and transformations

Diving into Pandas (videos 25 to 33) Pandas Notebook Kaggle Micro-course on Pandas (only exercise)
Day 4 Data Visualization helps us in gaining insights from the data through visuals like graphs and maps. We would look into some common libraries which are Matplotlib, Seaborn, and Plotly.

Intro to Matplotlib

GFG article on Matplotlib (optional but helpful)
Intro to Seaborn

GFG Tutorial on Seaborn
Intro to Plotly (required till 1 hr)

Day 5 Dealing with large tables can at times become overwhelming. Thus we may want to summarize the content of tables using Descriptive Statistics.

Data Types in Statistics. Measurement of Central Tendency. (videos 3 - 7) Normal Distribution (videos 18 - 20)

Quantile Plots

Swipe to view full content

WEEK 2 WHAT'S IN THERE TASK 1 TASK 2 TASK 3
Day 1
Hey, excited for Week 2? Often the data we deal with can have various issues like missing values, categorical values and outliers. Today we will learn about basic techniques to deal with such issues!

Introduction to Feature Engineering

Outlier Analysis

Handling Missing Values

Practical Handling Missing Values

Exploratory Data Analysis

Handling Categorical Variables

Day 2 Today we aren't going to be too technical, let us just motivate ourselves about Machine Learning, get to know its application, and have a rudimentary understanding of what Machine Learning is.

What is ML , common problems solved by ML

Supervised and unsupervised learning (optional)[Linear Algebra, Refresher required for those who don't have mathematical base]
Day 3 Starting at the grassroots level, we study in depth the simplest ML model Linear Regression, alongwith Cost function and Gradient Descent. Don't worry if it sounds too hard, trust us it isn't.
Linear Regression Blog Linear Regression with One Variable
(Videos 9 - 14)
Linear Regression with One Variable
(Videos 15 - 20)
Day 4 Let us spice things up a bit, we study Linear regression again but this time with Multiple features.

Linear Regression with Multiple Variables (Videos 21 - 24) Linear Regression without Scikit-learn Linear Regression with Scikit-learn

Linear Regression with 1 variable from scratch
Day 5 Today we will be introduced to our first ever classification model, Logistic Regression. Let's get to it. Logistic Regression
Videos 31 - 36
Logistic Regression Blog Logistic Regression with Scikit-learn

Logistic Regression from scratch

Swipe to view full content

WEEK 3 WHAT'S IN THERE TASK 1 TASK 2 TASK 3
Day 1
Since we have covered 2 basic ML models, let us take a break and learn about Overfitting, Underfitting and the Bias-Variance Tradeoff. These can help in telling you the complexity of your model - how well your model has used your data. This will be followed by Regularization.   Bias-Variance Video

Blog

Overfitting and Regularisation (37 - 41)

L1 L2 Regularization

Lasso and Ridge Regression
Day 2 Today we will give you an introduction to Feature Transforations and how these are used for different types of data All Feature Transformation

Scaling methods Categorical Encoding

Bag of Words
Day 3 Today, we'll take a closer look at what the AUC-ROC Score is and various other Evaluation Metrics to evaluate our machine leaning algorithms. AUC - ROC curve

AUC - ROC curve Blog
Confusion Matrix

Confusion Matrix Blog
Evaluation Metrics

Evaluation Metrics (Optional Topics included)
Day 4 Today, we look into Naive and Gaussian Naive Baye's Algorithms. Naïve Bayes algorithm is a supervised learning algorithm, which is based on Bayes theorem and used for solving classification problems.

Multinomial Naive Bias Classifier Gaussian Naive Bias

Naive Bias implementation using Scikit-learn
Day 5 Let's have a look at Support Vector Machine (SVM) SVM 1 SVM 2

SVM 3

SVM Blog with code implementation

Swipe to view full content

WEEK 4 WHAT'S IN THERE TASK 1 TASK 2 TASK 3
Day 1
A model's performance can be greatly increased by tuning its hyperparameters and at the same time it is also important to look for how accurate our model is. For this, we can use Grid search methods and Cross-Validation. Cross Validation

Code Implementation
What is hyperparameter tuning ?

Implementing Random Search method.

Day 2 Today, we shall learn about Decision Trees and Random Forest which will create the foundation for many advanced Machine Learning Algorithms. DecisionTrees (videos 46 -49) Random Forest (videos 52 - 53)

Decision Trees Notebook

Random Forest implementation

Day 3 Let's explore what boosting is and some of its variations Gradient Boosting (videos 59 - 61)

XGBoost

XGBoost continued

Catboost 1

Catboost 2
Day 4 Let's look at some more variations of boosting algorithms and how they can be used for specialized tasks. Adaboost

Kaggle Intermediate microcourse

LightGBM

AdaBoost implementation

Day 5 Today we learn about KNN. K-Nearest Neighbour is one of the simplest Machine Learning algorithms based on Supervised Learning technique.

KNN video
KNN Blog



KNN Implementation



Swipe to view full content

WEEK 5 WHAT'S IN THERE TASK 1 TASK 2 TASK 3
Day 1 Welcome to the final week of Learning, as next week is Capstone Project This week we will discuss Neural Networks and Unsupervised Learning. Today Let us go into the foundations of Neural Networks

Neural Networks
(1 - 23)
 








Day 2 Today we will first get an intuitive understanding of how Neural Networks work and then implement a small Neural Network from scratch using Python Understanding Neural Networks

Neural Networks with Python




Day 3 Today we will learn how to use the Keras library to implement Neural Networks. Keras is a popular Deep learning library which makes using Neural Networks very simple for us Regression with Keras Classification with Keras




Day 4 Let us have a look at unsupervised learning, its uses and types. We will also look at one particular algorithm the K-means method Unsupervised Learning K-means Clustering




Day 5 Today we will discuss PCA and its application through scikit-learn Tools and techniques for Deep Learning.
24 - 43
PCA using sklearn




LINK DEADLINE INSTRUCTIONS
Capstone Project




July 14, 2024
WHAT'S IN THERE LINK(S)

 Kaggle Microcourses

Link

 Advanced Plotly Notebook

Link