Python Machine Learning Advanced

This hands-on course explores Natural Language Processing (NLP) and building Flask web apps that put machine learning into action. You’ll clean and process text with RegEx and lemmatization, perform sentiment analysis with Naive Bayes, TextBlob, and Vader, and build a movie recommendation system using TF–IDF and cosine similarity. Along the way, you’ll learn Flask fundamentals, dynamic HTML templating, and API integration to bring in live data. By the end, you’ll deploy a full Movie Recommender App, giving you real-world experience in applied ML and web development.

What You Will Learn

• Build a complete NLP pipeline, including cleaning with RegEx, removing stopwords, lemmatizing, and vectorizing text.
• Train and evaluate a Naive Bayes machine learning model to classify movie reviews as positive or negative.
• Compare and apply pre-trained sentiment scoring systems such as TextBlob and Vader.
• Develop a recommendation engine that suggests similar products using NLP techniques.
• Learn Flask fundamentals by creating search apps, integrating APIs, and serving ML models in the browser.
• Complete a capstone project by building a Flask-powered Movie Recommender App that brings together NLP, machine learning, and web development.

Course Outline

1. NLP & Sentiment Analysis

Environment Setup & NLP Fundamentals

• VS Code environment configuration, NLP libraries installation
• Tokenization, stopword removal, stemming, lemmatization
• Text representation with Bag of Words and TF-IDF

Sentiment Analysis Project

• Logistic Regression for sentiment classification
• Data splitting, model evaluation metrics (accuracy, precision, recall, confusion matrix)

2. Recommendation Systems

Collaborative Filtering

• User-based and item-based filtering
• Cosine similarity for personalized recommendations

Content-Based Movie Recommender

• Vectorizing text using TF-IDF
• Implementing content similarity algorithms

3. Flask App for Recommendations

Building an ML-Powered Web App

• Flask basics and web serving
• Developing a recommendation system Flask app

4. Forecasting & Deep Learning

Time Series with Facebook Prophet

• Trend forecasting and visualization (e.g., market prices)

Deep Learning with PyTorch

• CNN basics, image classification using the CIFAR-10 dataset
• Model training, accuracy assessment, and confusion matrix interpretation

5. Object Detection

Real-Time Object Detection with YOLO

• Image detection and labeling with pretrained models
• Adapting YOLO models to video streams and real-time webcam input