Skip to content

Latest commit

 

History

History
30 lines (21 loc) · 1.03 KB

README.md

File metadata and controls

30 lines (21 loc) · 1.03 KB
Raw

instagramDataScienceProject

Data-Science Project , Crawling data , Cleaning data , Visualization and ML model

IDEs : Pycharm community . Jupyter Notebook.

Modules uses : pandas , selenium , instascrape , colorgram , PIL(python imaging library) , sklearn , numpy , time , matplotlib and seaborn

Purpose: Analyzing instagram posts data - likes , followers , comments and the most dominant colors in the photo.

Questions for ML:

  1. Does colors have an effect on instagram post behaviour ( Likes , Engagement etc) ?
  2. Can we predict the amount of the next posts likes by knowing the dominant colors and the amount of followers ?

Acquisition:

  1. Crawling data from instagram posts using Selenium & Instascrape.
  2. Clustering RGB tuples from string (r,g,b) - to numbers between 0-9 . With Kmeans algorithm.
  3. duplicates and null handeling.

Visualization and ML:

  1. Visualizing data for deeper understanding.
  2. Correlation examination.
  3. Fitting Linear Model and predicting the Likes.
  4. understanding the number and deeper error examinations.