Three datasets were used for this project which I gathered using different methods. To start this project, I imported different libraries which include; (pandas, tweepy, seaborn, matplotlib, JSON, request, etc.). The first dataset was a csv file which I read using the pandas library, the second data set was obtained using the request library. While for the last dataset, I scraped from twitter using tweepy to access the Twitter API.

From the data, I noticed the golden retriever had the most predictions from two prediction algorithms and got the second most predictions by one algorithm. While the Labrador retriever was the second most predicted by two algorithms and the most predicted by one algorithm. Other popular species include the Pembroke, which was predicted third by two algorithms and the Chihuahua was predicted to be fourth by the three algorithms In general, the retrievers are the most predicted species and the golden retriever is the most predicted specie. While the Pembroke and the Chihuahua came in as the third and the fourth most predicted species

From my visualizations, I observed that the iPhone accounts for the source of about 90% of the tweets. The golden retriever dog specie was the most predicted specie of dog and the Labrador retriever was the second most predicted dog specie.