Completed
32:17 - Hyperparameter Tuning
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Real-World Machine Learning Project with XGBoost and NVIDIA GPU
Automatically move to the next video in the Classroom when playback concludes
- 1 01:08 - Download Dataset
- 2 01:43 - Solving Big Data Problems with GPU Processing
- 3 02:46 - Google Colab Setup with Free T4 GPU
- 4 03:02 - Local Setup with NVIDIA GPU
- 5 03:43 - RAPIDS Installation Guide
- 6 05:07 - Solving Jupyter Kernel Crash with cuDF Pandas
- 7 05:29 - Handling Missing Values
- 8 05:53 - Detect Missing Values
- 9 06:29 - Replace with Zero
- 10 07:31 - Replace with Mean
- 11 08:57 - Investigate Columns with Ambiguous Names
- 12 11:21 - Drop Columns If No Other Option
- 13 12:01 - Split Data For Training & Testing
- 14 12:07 - Shuffle Data
- 15 13:39 - Features & Targets Split
- 16 14:02 - Train & Test Split
- 17 16:20 - Load XGBoost Model on GPU
- 18 17:55 - Train XGBoost Model
- 19 18:08 - Test XGBoost Model and Get Predictions
- 20 18:45 - Solve ValueError : DataFrame.dtypes must be int float bool or category
- 21 20:15 - Evaluate Trained Model
- 22 22:39 - Data Optimization & Anomalies
- 23 22:41 - Detect Data Anomalies with Aggregation
- 24 23:47 - Solve XGBoostError : No GPU Memory Left with RMM
- 25 25:04 - Handle Negative Charges and Unrealistic Distances
- 26 28:19 - Detect and Handle Unrealistic Transactions
- 27 30:28 - Second Train Run on Optimized Data
- 28 31:45 - Best Practices
- 29 31:45 - Plot Training Results & Feature Importance
- 30 32:17 - Hyperparameter Tuning
- 31 32:49 - Date Extraction : From String to Int or Category
- 32 33:05 - K-Fold Validation
- 33 33:45 - Thanks for Watching!
