-
Урок 1.
00:08:20
Introduction to the course
-
Урок 2.
00:08:52
What is the goal of this course?
-
Урок 3.
00:15:17
Why Rust?
-
Урок 4.
00:10:43
Our plan
-
Урок 5.
00:16:28
Installing the tools: rustc, cargo, rust-analyzer
-
Урок 6.
00:21:04
How to generate and run the binaries
-
Урок 7.
00:10:00
Steps to train an ML model in Rust
-
Урок 8.
00:26:56
How to download the CSV file - Part 1
-
Урок 9.
00:20:22
How to handle errors and Results with anyhow and ?
-
Урок 10.
00:23:10
Generic types, traits and trait bounds in function definitions
-
Урок 11.
00:10:37
How to download the CSV file - Part 2
-
Урок 12.
00:03:17
Wrap up
-
Урок 13.
00:05:04
Goals for today
-
Урок 14.
00:18:15
Load the CSV file into memory with Polars Rust
-
Урок 15.
00:05:11
Extract functions to lib.rs
-
Урок 16.
00:25:31
Splitting the data into training and test - Part 1
-
Урок 17.
00:18:33
Splitting the data into training and test - Part 2
-
Урок 18.
00:04:06
Questions and answers
-
Урок 19.
00:12:21
Split datasets into features and targets
-
Урок 20.
00:24:43
Transforming Polars DataFrame to DMatrix for XGBoost training
-
Урок 21.
00:20:48
Training the XGBoost model - Part 1
-
Урок 22.
00:02:53
Questions and answers
-
Урок 23.
00:12:04
Training the XGBoost model - Part 2
-
Урок 24.
00:18:41
Pushing the model artifact to AWS S3 bucket
-
Урок 25.
00:01:48
How to set up your AWS credentials to talk to your S3 bucket
-
Урок 26.
00:01:49
Wrap up
-
Урок 27.
00:03:35
Goals for today
-
Урок 28.
00:05:08
Tip -> devcontainers
-
Урок 29.
00:05:55
Add 2 entry points, one for training, one for REST API
-
Урок 30.
00:02:35
Questions and answers
-
Урок 31.
00:19:55
Building a minimal API with health endpoint - Part 1
-
Урок 32.
00:10:25
Building a minimal API with health endpoint - Part 2
-
Урок 33.
00:22:20
Adding a predict endpoint to our REST API
-
Урок 34.
00:02:34
Tip -> How to break a large problem into smaller (easier) ones
-
Урок 35.
00:23:37
Download model artifact from AWS S3 bucket
-
Урок 36.
00:17:27
Refactorings -> Break our lib.rs into separate files
-
Урок 37.
00:11:24
Adding CLI parameters for training using Clap
-
Урок 38.
00:07:39
Loading the model from S3 into memory
-
Урок 39.
00:21:03
Adding model to the AppState so we can use it in our predict functions - Part 1
-
Урок 40.
00:07:46
Adding model to the AppState so we can use it in our predict functions - Part 2
-
Урок 41.
00:02:32
Wrap up
-
Урок 42.
00:02:17
Plan for today
-
Урок 43.
00:21:04
Transform input payload to dmatrix for XGBoost
-
Урок 44.
00:15:42
Formatting the response with the prediction
-
Урок 45.
00:07:26
Extracting the port number as input argument
-
Урок 46.
00:11:22
Two challenges for you
-
Урок 47.
00:20:40
Dockerizing the API - Part 1
-
Урок 48.
00:06:49
Trick -> How to solve Docker no space left problems
-
Урок 49.
00:23:00
Dockerizing the API - Part 2
-
Урок 50.
00:22:35
Dockerizing the API - Part 3
-
Урок 51.
00:21:47
Dockerizing the API - Part 4
-
Урок 52.
00:07:43
Dockerizing the API - Part 5
-
Урок 53.
00:01:51
Dockerizing the API - Part 6
-
Урок 54.
00:02:37
Wrap up
-
Урок 55.
00:02:49
00 - Intro
-
Урок 56.
00:04:27
01 - Bootstrap the project
-
Урок 57.
00:21:43
02 - Hello world with a /health endpoint
-
Урок 58.
00:02:58
03 - A bit of refactoring
-
Урок 59.
00:08:39
04 - Add a /predictions endpoint
-
Урок 60.
00:08:28
05 - Break down project in several files
-
Урок 61.
00:07:52
06 - Start Postgres DB with Docker
-
Урок 62.
00:20:28
07 - Fetch data from Postgres
-
Урок 63.
00:02:07
08 - Loading environment variables
-
Урок 64.
00:04:57
09 - Add GET parameter to the /predictions endpoint and compile for release
Много раз в комментах вижу уже)