Coders Packet

Project on YouTube Advertisement view Prediction

By Vishal Singh

The project is to train various regression models and choose the best one to predict the number of advertisement views using Python.

The programing language used here is Python.

YouTube advertisers pay You tubers based on ad views and clicks for the goods and services being marketed. YouTube advertisers want to estimate the ad view based on other metrics like comments, likes, etc. Therefore, the project is to train various models and choose the best one to predict the number of ad views or so-called advertisements. The data or information based on different attributes is needed to be refined or filtered and cleaned before feeding in the algorithms to get better results.

Train.csv file is taken for training and fitting into different algorithms in this project. I have taken the details on each video using a unique identification ID for each video, the file train.csv contains data or information based on different attributes and other details of about 15000 YouTube videos. The data or information or entities or attribute contains the number of views, likes, dislikes, comments and apart from that published date, duration and category are also included. The train.csv file also contains the data or information of ad views which is our target attribute for prediction. After training the data it is tested with test.csv and the best result is used for completing this project.

Attribute Information

'VIDID’: This attribute contains the Unique Identification ID for each video

'AD VIEW': This attribute contains the number of ad views for each video Project

'VIEWS': This attribute contains the number of unique views for each video

'LIKES': This attribute contains the number of likes for each video

'DISLIKES': This attribute contains the number of likes for each video

'COMMENT': This attribute contains the number of unique comments for each video

'PUBLISHED': This attribute contains data of uploading the video

'DURATION': This attribute contains the duration of the video (in min. and seconds)

'CATEGORY': This attribute contains category niche of each of the video

Python Libraries Required

NumPy, Pandas, Matplotlib, TensorFlow, Seaborn, Sklearn, Keras, Joblib

Download project

Reviews Report

Submitted by Vishal Singh (VishalSingh)

Download packets of source code on Coders Packet