Course Duration: 180 hours (3 hours per session, 3 sessions per week, 5 months in total)

Course Description:

The Data Science Bootcamp is an immersive program designed for participants with an introductory background in Python programming. This course provides a comprehensive introduction to data science, with an emphasis on practical applications and hands-on experience. Participants will explore Python classes, data manipulation, visualization, database access, machine learning, and advanced topics such as LangChain for language model applications, ML pipelines, backend development with FastAPI, and interactive interfaces with Gradio.

Course Outline:

Month 1: Python and Object-Oriented Programming

Session 1: Python Classes and Object-Oriented Programming (9 hours)

- Review of Python programming fundamentals

- Introduction to object-oriented programming (OOP) concepts

- Creating and using Python classes

- Inheritance, polymorphism, and encapsulation

Session 2: Advanced Python Concepts (9 hours)

- Inheritance, polymorphism, and encapsulation (continuation)

- Python modules and packages (remember)

- File handling and data serialization

- Error handling and exceptions

- Decorators and context managers

- Structural typing

Session 3: Python Multi-threading (9 hours)

- Introduction to multi-threading in Python

- Creating and managing threads

- Synchronization and thread safety

- Thread communication and coordination

Month 2: Data Manipulation and Visualization

Session 4: Data Manipulation with Pandas (9 hours)

- Introduction to Pandas library for data manipulation

- Loading and cleaning data

- Exploratory data analysis (EDA) techniques with Pandas

- Transforming and aggregating data

- Data mining and web scraping for data enrichment

Session 5: Data Visualization with Matplotlib and Seaborn (9 hours)

- Principles of data visualization

- Plotting with Matplotlib

- Creating statistical visualizations with Seaborn

- Customizing and enhancing visualizations

Session 6: Interactive Visualization with Plotly and Gradio (9 hours)

- Creating interactive visualizations with Plotly

- Building user-friendly interfaces with Gradio

- Deploying interactive visualizations and interfaces

Month 3: Backend Development and Interactive Interfaces

Session 7: Backend Development with FastAPI (9 hours)

- Introduction to FastAPI for backend development

- Building RESTful APIs for data retrieval and manipulation

- Handling authentication and authorization

Session 8: Building Interactive Interfaces with Gradio (9 hours)

- Introduction to Gradio for creating interactive UIs

- Developing user-friendly interfaces for data exploration and model interaction

- Deploying Gradio interfaces for easy access and usage

Month 4: Machine Learning Fundamentals

Session 9: Introduction to Pre-Built Machine Learning Models (9 hours)

- Understanding pre-built models and their use cases

- Difference between custom and pre-built models

- Introduction to Scikit-learn, XGBoost, and other relevant libraries

- Applying pre-built models to data

Session 10: ML Pipelines and Data Preprocessing (9 hours)

- Introduction to ML pipelines for data preprocessing

- Handling missing data and outliers

- Feature selection and engineering

- Encoding categorical variables

- Synthetic data generation

Session 11: Application of Pre-Built Supervised Learning Models (9 hours)

- Applying regression models from Scikit-learn

- Applying classification models from Scikit-learn

- Understanding pre-built ensemble methods (Random Forest, Gradient Boosting)

- Applying SVMs from Scikit-learn

Month 5: Advanced Data Science Techniques

Session 12: Introduction to LangChain for Language Models (9 hours)

- Overview of LangChain framework for language model-powered applications

- Connecting language models to data sources

- Enabling language models to interact with their environment

Session 13: Natural Language Processing (NLP) and Pre

-Built Text Analytics Models (9 hours)

- Text preprocessing and tokenization

- Using pre-built models for sentiment analysis and text classification

- Applying pre-built models for Named Entity Recognition (NER) and topic modeling

- Using pre-built language models for text summarization and translation

Session 14: ML Pipelines and Model Deployment (9 hours)

- Building end-to-end ML pipelines for model training and deployment

- Model packaging and deployment best practices

- Integration of ML models into web applications

Session 15: Capstone Project (18 hours)

- Working on a comprehensive data science project from start to finish

- Applying acquired skills and knowledge to solve real-world problems

- Data exploration, model training, evaluation, and presentation

By moving the backend modules before the machine learning fundamentals, participants can gain an understanding of how to implement and deploy models in a backend setting. This will allow them to apply their knowledge of machine learning in a more practical manner when they reach the machine learning sections of the course.

Prediction:

• Movie genre prediction from Hugging Faces. Predict movie genre from title and review

Clustering

We've already told you we're looking for highly driven people with lots of will to learn! Aside from that, you should also be passionate about technology, fairly comfortable with both written and spoken English, and have completed the minimum mandatory schooling.

You will have the opportunity to take a course within a tech company, learn from people with experience in the area and experience Mindera's unique culture.