Build a Demand Forecasting ML App: Python Data Science

ML QUEST #1: Demand Forecasting - Full course on Patreon ► https://www.patreon.com/ZazenCodes/shop/ml-quest-1-demand-forecasting-full-344393 ML QUEST #1: Demand Forecasting - GitHub source code ► https://github.com/zazencodes/ml-quest-1-demand-forecasting ZAZENCODES COURSES [ 🚀 level up ] ► https://zazencodes.com/ DISCORD [ 🎭 come hang out ] ► https://discord.gg/e4zVza46CQ 0:00 - Introduction to ML Quest #1 - Demand Forecasting 10:18 - Understanding the Dataset & the Problem to Model 13:54 - Data Exploration - Loading the Dataset 20:56 - Data Exploration - Handling Missing Data 27:21 - Data Exploration - Anomaly and Outlier Detection 38:30 - Data Exploration - Temporal Coverage and Distribution Analysis 54:23 - Feature Engineering - Our Goal & General Considerations 59:36 - Feature Engineering - One-Hot Encoding 1:05:38 - Feature Engineering - Custom Ordered Categorical Encoder 1:14:48 - Feature Engineering - Numeric & Date Features 1:19:17 - Feature Engineering - Moving Average & Lag Features 1:39:29 - Bonus - Data Imputation for Temporal Gaps 1:52:25 - Modeling - Introduction 1:53:15 - Modeling - Create a Model Using Simple Heuristics 1:56:26 - Modeling - General Considerations 1:59:10 - Modeling - Grid Search for Hyperparameter Optimization 2:02:30 - Modeling - Gradient Boosted Regression 2:04:10 - Modeling - Train-Test Split for Timeseries Data 2:05:49 - Modeling - Grid Search Continued 2:08:10 - Modeling - Visualizing & Interpreting Grid Search Results 2:15:00 - Modeling - Training the "Final Model" 2:19:46 - Modeling - Training a Stack of Models 2:25:03 - Modeling - Generating the Forecast 2:34:03 - Modeling - Visualizing the Forecast 2:41:06 - Modeling - Uploading Forecast to Postgres 2:50:38 - Hands-On App Implementation - Introduction 2:51:45 - Hands-On App Implementation - ML App Overview 2:55:55 - Hands-On App Implementation - Docker Compose App Overview 3:00:24 - Hands-On App Implementation - Data Loading & Cleanup Module 3:09:50 - Hands-On App Implementation - Feature Encoding Module 3:20:57 - Hands-On App Implementation - Numeric Features Module 3:27:04 - Hands-On App Implementation - Model Training Module 3:35:45 - Hands-On App Implementation - Model Forecast Module 3:49:49 - Hands-On App Implementation - Forecast Database Integration 3:56:45 - ML App Demo / Walk-Through - Model Library Docker App 4:02:42 - ML App Demo / Walk-Through - Model Train Module 4:10:03 - ML App Demo / Walk-Through - Running the Model Train Module 4:17:13 - ML App Demo / Walk-Through - Model Forecast Module 4:27:49 - ML App Demo / Walk-Through - Running the Model Forecast Module 4:30:08 - User App Demo / Walk-Through - Model API with FastAPI on Docker 4:43:40 - User App Demo / Walk-Through - Model Dashboard with Streamlit on Docker 4:48:26 - User App Demo / Walk-Through - Model Dashboard Insights 4:54:20 - User App Demo / Walk-Through - Streamlit Dashboard Code 5:14:34 - User App Demo / Walk-Through - Course Summary & Conclusion