This project aims to to get insightful information about dog ratings from the twitter page WeRateDogs™, while demonstrating advanced data wrangling and visualization techniques using various Python libraries. WeRateDogs™ is a community page on twitter designated to rating dogs on their appearences and stories, and which was formed by the user @dog_rates in 2015. The page has since grown extremely in popularity, with many users sharing its content and requesting their dogs being rated aswell. The site is a driving force for the development of the 'dog culture', with it's famous terms like "pupper", "mlem", "floof" etc. They also developed their own unusual rating system over time, in which almost every dog is rated above 10/10, because "they're good dogs".
To achieve the goals of the analysis, data have been gathered from different sources, including the twitter api as well as other web data. The potentials of Python's pandas library has been used extensively on the assessment and data cleaning parts. For the conclusion part, statements regarding the performance of each dog breed and dog stage (age group) have been given. To sum up the conclusions, visualizations in forms of word clouds have been plotted in accordance to the observations.