Machine Learning Classroom

This repository contains the material used for Machine Learning sessions conducted at Helpshift. Most of the content will be in the form of Jupyter notebooks & we will use Python 3.

Table of Content

Python 3

Beginner level proficiency is enough to understand the concepts & material used in this repository/class. In case you haven't used Python recently, please refer to following chapters from A Byte of Python to understand the Python concepts which will be useful in understanding & exploring the code in this class/repository.

• Basics
• Operators and Expressions
• Control Flow
• Functions
• Data Structures
• Object Oriented Programming

Also try to read the full book if possible.

Roadmap

1. Exploratory Data Analysis using Covid19 Dataset
2. Text classification using Naive Bayes
3. Text classification using Logistic Regression
4. Tuning Logistic Regression model using Regularization techniques
5. Text classification using Ensemble Model
6. Mini Project: Sentiment Analysis of IMDB Movie Reviews

Setup

Using Docker(Recommended method)

1. Install Docker by following the instructions given for different platforms on this page.

2. You can either pull the existing docker image or build your own image

   2.1 Using Docker

   make pull

   2.2 Build image

   make build

3. Verify that docker image exists

   docker images | grep ml_classroom

4. Start the Docker container

   make run

5. Verify by visiting URL in browser.

Using Virtual Env

1. Install Python3 using the instructions given on this page.

2. Create Virtual Env

   virtualenv venv

3. Activate the Virtual Env

   source venv/bin/activate

4. Install required dependencies

   pip install -r requirements.txt

5. Launch Jupyter notebook

   jupyter notebook --port 4545

6. Verify by visiting URL in browser.

Datasets References

• Kaggle: Novel Corona Virus 2019 Dataset
• Kaggle: Consumer Finance Complaints Dataset
• Kaggle: IMDB Dataset of 50K Movie Reviews