In this Data Wrangling project analyses more than 5000 tweets from the twitter account @dog_rates. I used Python to gather data from a twitter API and also from an online repository containing dogs predicted breeds. I Found out that breed and age were the main predictors for the number of retweets, among other insights.
In the jupyter notebook wrangle_act.ipynb it is possible to find the whole process of gathering, assesing, cleaning and storing data. A more detailed explanation is available in the wrangle_report.html file.
After cleanig the messy and dirty data, some analyses and findings are provided. To see more details please refer to the act_report.html file.
The contents of this repository are covered under the MIT License.