5-Week Data Science Bootcamp
DETAILED SYLLABUS
Overview
In our endeavour to build data culture and democratize Data Science learning, we are
launching a 5-week Data Science Bootcamp with the help of resources contributed by
academia and industry experts. The online bootcamp will have a series of day-wise learning
modules along with intuitive practice quizzes/challenges.
This is a community initiative, driven by experts and mentors, and you have the
opportunity to attend it for free.
Prerequisites
● Nil, anyone with a passion for learning can make it to the finish line :)
Format
Tutors will provide learners with guided learning paths, resources and exercises to solve. The
entire schedule, practical details, registration details will be put up very soon. A brief summary
of the format can be found below:
● Day-wise modules: Trainers will post day-wise challenges and learning modules (mostly
some of the best-curated content available on the internet that would allow you to have
a structured learning path)
1 dphi.tech <Democratizing Data Science Learning>
● For real-time communication, we will be using Discord. This medium will help learners
to clear doubts on a real-time basis if they are stuck somewhere. In addition, this will
also allow learners to interact with the mentors and fellow learners
● Live doubt clearing and mentorship sessions will be organized every week based on the
requirements of the learners
Schedule
Week #0 - Python Crash Course and Intro to Data Science (Optional)
● Intro to Data Science - its prominence and use-cases
● Environment setup - python installation - anaconda ide
● Python for Data Science
○ Basics of Python
■ Print a string "Hello World"
■ Python basic syntax
■ Data structures and types
○ Python Lists & Strings
○ Intro to Functions
○ Brief Intro to Python Libraries for Data Science - Numpy and Pandas
Week #1 - Data Analysis and Data Visualization (Release on: 11th March)
● Dive Deep into Numpy and Pandas libraries
● Python Web Scraping
● Exploratory Data Analysis
● Intro to Data Visualization
● Graded Quiz 1 - 18th March
Week #2 - Advanced Exploratory Analysis and Data Pre-Processing (Release on:
18th March)
(Data Cleaning, Outlier detection etc.)
● Basic Statistics
● Charts and Visualization
2 dphi.tech <Democratizing Data Science Learning>
● Outlier Analysis
● Handling Missing Values
● Handling Imbalanced datasets, Oversampling - SMOTE
● Standardization/Normalization of data - what, why and when?
● Graded Quiz 2
Week #3 - Feature Selection and Building ML Models (Release on: 25th March)
● Intro to feature extraction and feature selection - explain how they are different
● Elaborate more on Feature Extraction
● Feature selection and its importance
○ Various feature selection/engineering techniques
○ Boruta
● Building efficient and effective models
● Splitting data into test and train datasets
● ML Algorithms:
○ Linear Regression
○ Logistic Regression
○ Cost function & Gradient Descent
● Overfitting & Underfitting
Week #4 - Model tuning and ML Algorithms (Release on: 1st April)
● Other ML Algorithms
○ Tree-based models
■ Decision trees
■ Random forest
■ A brief intro to other boosting and bagging techniques/algorithms
● Model tuning
○ Hyperparameter tuning
○ Evaluation Metrics (Model evaluation)
● Project - solve real-world data science problem on Ed-tech and Fintech.
● Graded Assignment (Released around 8th April)
Week #5 - Applied Data Science & ML - Problem-solving (Release on: 8th April)
● HR Analytics problem - predicting employee churn
● Ed-tech customer analysis - predicting user churn
3 dphi.tech <Democratizing Data Science Learning>
● Fraud analytics - predicting fraud detection
● Anti-money laundering analytics - predicting money laundering cases in transactions
data
● Real-estate price analysis - problem
● Getting started with Data Science competitions - Kaggle
4 dphi.tech <Democratizing Data Science Learning>
