This project, titled "YouTube Pulse: Tracking Trends & Engagement," aims to leverage Python’s robust visualization libraries to derive deep insights from YouTube video trends data. Using the 'youtube.csv' dataset, this analysis explores the dynamics of YouTube video attributes such as views, likes, dislikes, and comment counts to understand user engagement across different content types.
The primary goals of this project are to :-
i.) Conduct an exhaustive exploratory data analysis (EDA) to identify patterns, correlations, and dependencies.
ii.) Visualize key features and their distribution, such as views, likes, and dislikes, to understand current trends on YouTube.
iii.) Utilize statistical and machine learning techniques to predict future trends based on historical data.
DATA SET :-
i.) The project utilizes the 'youtube.csv' dataset, containing data on YouTube videos, including metrics like views, likes, dislikes, and comment counts, along with categorical data about video titles, channel names, and publication details.
ii.) This dataset comprises 160,000 rows with various attributes spanning numerical, categorical, and boolean types.
Key Technologies :-
i.) Python : Primary programming language for analysis and visualization.
ii.) Dash : Used for building interactive web-based visualizations.
iii.) Plotly : For creating interactive plots.
iv.) Google Cloud Platform (GCP) : For deploying the interactive dashboard.