Netflix Movies and TV Shows Analysis (Python Implementation)

1. Importing Libraries and Dataset
2. Data Cleaning and Preprocessing
3. Data Visualization

#python #datavisualization #netflix #python3 #pythonprogramming #pythonprogramminglanguage #datascience

Credit: Nirmal Gaud


Team
@data_enthusiasts

Harvard CS109A #DataScience course materials — huge collection free & open!

1. Lecture notes
2. R code, #Python notebooks
3. Lab material
4. Advanced sections
and more ...

https://harvard-iacs.github.io/2019-CS109A/pages/materials.html

Team
@data_enthusiasts

Pornhub - Exploratory Data Analysis (Python Implementation)

1. Loading the libraries
2. Loading the data
3. Some preprocessing
4. Most viewed videos
5. Most viewed categories
6. Most voted categories
7. Length of video vs Number of views
8. Quality of video vs Number of views
9. Length of video vs Voting of video
10. Quality of video vs Voting of video
12. Most used words in Tags
13. Most used words in Categories
14. Most used words in Titles


#dataanalysis #data #quality #video #dataanalysis #dataanalytics #datascientist #datasciencetraining #datascience #exploratorydataanalysis #pornhub #python #pythonprogramming #pythonfordatascience #pythonprogramminglanguage

Team
@data_enthusiasts

Python for Econometrics

Team
@data_enthusiasts

🔥 Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks

Masked "language" modeling on images (Imglish), texts (English), and image-text pairs ("parallel sentences") in a unified manner.

Github: https://github.com/microsoft/unilm/tree/master/beit

Paper: https://arxiv.org/pdf/2208.10442v1

Datasets: https://paperswithcode.com/dataset/visual-genome

Team
@data_enthusiasts

Python for Probability, Statistics and Machine Learning

Team
@data_enthusiasts

➡️ Prompt Tuning for Generative Multimodal Pretrained Models

Code: https://github.com/ofa-sys/ofa

Paper: https://arxiv.org/pdf/2208.02532v1

Dataset: https://paperswithcode.com/dataset/snli-ve

Demo: https://huggingface.co/spaces/OFA-Sys/OFA-Generic_Interface

Team
@data_enthusiasts

The Evolution of Netflix ML Technology!

Netflix strives to give recommendations that are relevant to our subscribers' interests, and they rely on Machine Learning (ML) methods to accomplish this. 


However, ML algorithms are only as good as the data we feed them. Axion fact store is a component of the Machine Learning Platform, which serves machine learning needs across Netflix. The blog concentrates on the vast number of high-quality data kept in Axion, our fact store used to compute ML features offline. 

Axion was created largely to reduce any training-serving bias and to accelerate offline experimentation.

The image below depicts how Axion interacts with Netflix's ML platform. The whole ML platform comprises tens of components, and the figure below only illustrates a subset of them.  More information is available at Read here


#artificialintelligence #machinelearning #datascience #innovation #technology

Team
@data_enthusiasts

Mathematics of Machine Learning by Philippe Rigollet.

These lecture notes would teach you all that you need about the math behind machine learning!

#math #ml #datascience

Team
@data_enthusiasts

Think Like (a) Git

A guide for the perplexed.

https://think-like-a-git.net

#learn #git #github #gitlab

Team
@data_enthusiasts

#deeplearning #cheatsheet #DL

Team
@data_enthusiasts

🗣 Robust Speech Recognition via Large-Scale Weak Supervision

Whisper is a general-purpose speech recognition model by Open AI.

pip install git+https://github.com/openai/whisper.git

⚙️ Github
💡 Colab
💻 Model
🗒 Paper
🦾 Dataset
✴️ HABR

Team
@data_enthusiasts

🔄 VToonify: Controllable High-Resolution Portrait Video Style Transfer


git clone https://github.com/williamyang1991/VToonify.git
cd VToonify

⚙️ Github
💡 Colab
💻 Project
🗒 Paper
🦾 Dataset
🎞 Video

Team
@data_enthusiasts

🎓 YATO: Yet Another deep learning based Text analysis Open toolkit

pip install ylab-yato

⚙️ Github
📋 Paper
📌 Dataset

Team
@data_enthusiasts

🖥 PDEBENCH: An Extensive Benchmark for Scientific Machine Learning

🖥 Github: Click Me

🗒 Paper: Click Me

⚙️ Dataset: Click Me

↪️ Pre-Trained Models : Click Me

Team
@data_enthusiasts

🗣 NNSVS: A Neural Network-Based Singing Voice Synthesis Toolkit

Neural network-based singing voice synthesis library for research

⭐️ Docs: https://nnsvs.github.io/

🔩Github: https://github.com/nnsvs/nnsvs

📄Paper: https://arxiv.org/pdf/2210.15987v1

↪️ Samples by r9y9: Click Me

👣 Demo: Click Me

Team
@data_enthusiasts

Storytelling & Communication is an important aspect of any Data Scientist. it's important to convey the information that is learned and much more important to let your audience Understand what value the idea possesses.

Conveying ideas in the real world is a highly important skill. More than that it's mostly important to properly visualize it.

This cheat sheet from datacamp.com, has all possible things one can imbibe in order to make things easier for their storytelling. it talks about these three important things to generate a narrative. What is data storytelling Crafting Effective Visuals Crafting Effective Narratives with data

Team
@data_enthusiasts

⭐️ Traffic4cast 2022 Competition: from few public vehicle counters to entire city-wide traffic

🖥 Github: Click me

🗒 Paper: Click me

➡️ Dataset: Click me

Team
@data_enthusiasts

Team
@data_enthusiasts