Evidently AI Tutorial-Open Source ML Models Monitoring and Observability

Показать описание

Evidently is an open-source Python library for data scientists and ML engineers.It helps evaluate, test, and monitor data and ML models from validation to production. It works with tabular, text data and embeddings.
vidently helps evaluate and test data and ML model quality throughout the model lifecycle.
Evidently has a modular approach with 3 components: Reports, Test Suites, and a Monitoring Dashboard. They cover different usage scenarios: from ad hoc analysis to automated pipeline testing and continuous monitoring.
Evidently has a simple, declarative API and a library of in-built metrics, tests, and visualizations.

Timestamp:

00:00:00 Introduction
00:02:25 What is Evidently AI
00:05:25 Model Monitoring Using Evidently AI
00:14:17 Model Performance Check Using Evidently AI
00:25:53 Target Drift Using Evidently AI
-------------------------------------------------------------------------------------------------------------
Support me by joining membership so that I can upload these kind of videos
------------------------------------------------------------------------------------------------------------------------------
►Data Science Projects:

►Learn In One Tutorials

►Learn In a Week Playlist

►Detailed Playlist:

Рекомендации по теме

Комментарии

Birthday 24th ko hai bhai log…Lets target to 800k before that :)

krishnaik

Great video, Krish! I love the Evidently reports. And this tutorial is very comprehensive! They also have a new feature that allows parsing data from each week's report to build a live monitoring dashboard and track the metrics over time. Maybe you can show it in your future videos!

trendyboymx

Happy birthday sir in advance 🎁, from Pakistan

imranroshan

happy b'day Krish Sir. Wish you great success ahead

umarfarooque

Happy birthday, Krish! Your videos have been incredibly beneficial leading AI/Data Science to so many people, including myself.🎂

MrGovi

pls make video on data extraction from various sources

mohsinkh

Thank you Krish! It would be great if you can create a video on how to put this in production

ajaygopireddy

complete lecture on Kubernetes to also required? kindly please do it

Prashanthsheri-lx

Advance Happy Birthday to krish naik🎉🎉🎉

venkatasurya

If somebody complete your one shot videos(5hr+) for ml, stats, dl, nlp and projects
Will they be able to get internships ?

Eswar.

@Krish, How to detect and handle Concept drift?

chuzabhai

Small correction in the video at 20.19 seconds. Instead of writing .save, we need to use .save_html

gunasekharvenkatachennaiah

Hello Krish, Could you please take a session on how to combine multiple json of nested conditions file into a single json file from a directory and converting it into a data frame ?

manojthanu

FYI need to manually run pip install evidently==0.6.4 if doing this tutorial after Feb 2025 as newer versions of the library changed the import statements

IanRahwan

Sir BentoMl, Mlflow, DVC or Evidently sab mlops mw use ho rahe he what is good to learn in terms of job ... nye tools kuch hi company me use honge ig

dubstepboi

15:56 Krish are you sure that in we will put creferance data in current_data, and current data in referance? Because it is not given so in documentation and also doesn't look corrent intuitively...

Okay so earlier he was taking the old data as current because he wasn't comparing with new one, at 21:09 he shows that when new data is coming then referance data goes in referance and currrent data goes in current... Then it is fine 👍

harshitkedia

tried it for classification but it unable to replicate what sklearn classification models were doing.

ransinghray

Will you be able to create a complete end-to-end project on feature stores for ML?

techandprogramming

Hi Krish, A issue is coming up.

When i am running
"regression _performance.show()"

It is showing " ReferenceError:requiredjs is not defined"

Could you pls help, It's urgent as I am implementing this in my current project.

SanatanKaBeta

I have an Excel file with a table of ~500 rows and ~14 columns. I'm using Python to plot a graph in Excel using Matplotlib library. My header row in the Excel file is like title row with text-cum-numeric mixed data. So, I named X-axis labels row as
x_axis = excelfile.iloc[0] #in order to call the header info as X-axis labels.
ax1=plt.subplot()
ax1.set_xticks(x_axis)
plt.show()
But, this is throwing me "posx and posy should be finite values" error. How to fix this issue? Kindly help.

phaniy

Evidently AI Tutorial-Open Source ML Models Monitoring and Observability

Evidently AI Tutorial-Open Source ML Models Monitoring and Observability

Introducing Evidently, an open-source tool for ML model monitoring

Evidently - Open-source tool for ML monitoring - 2min demo for Jupyter notebook

How to Monitor Machine Learning Models (Evidently AI)

Open-Source ML Observability Course - Welcome Video

Drift Detection with Evidently AI

Open-Source Spotlight - Evidently AI - Emeli Dral

Evidently 0.2 - Getting Started Tutorial

Drift Monitoring and Evaluation for LLM Apps | Evidently AI

How to run Evidently using the Command Line

Evidently - Core Concepts - Metric, Report, Test, Test Suite, Preset

6.1. How to deploy a live ML monitoring dashboard

ML monitoring with Evidently. A tutorial from CS 329S: Machine Learning Systems Design.

Machine Learning Monitoring: What Is Data Drift?

1.1. ML lifecycle. What can go wrong with ML in production?

Open-source LLM Evaluation with Evidently - Intro

2.1. How to evaluate ML model quality.

Using column mapping in Evidently reports

Testing an LLM | Exploring Tools For Testing LLMs | Part 3 | Evidently AI

1.4. Key considerations for ML monitoring setup.

Evidently AI Intro - Hello World, and Happy Holidays

Deepchecks - Open Source Tool for Testing & Validating Your ML Model & Data

Data Quality Meetup #5: Data Drift & Early Monitoring for ML Models by Emeli (Evidently AI)

PyCaret and Evidently AI