![]() Given the weather patterns in Chicago, it is no surprise that the number of trips is drastically higher in the summer than in the winter months. Throughout the entire year 3,603,082 trips were completed, Figure1 shows how those trips were distributed daily. This project began with some exploratory data analysis, the analysis was only completed on the most recent complete year of data, 2018. Temperature (in Kelvin, later converted to Celsius) There were a wide variety of features to choose from, but for this project the following features were used: Divvy bikes chicago free#As Weather Underground stopped with their free API’s in February 2019, historical weather was downloaded from Dark Sky ( ) in a bulk format. Weather can be a great influence as to whether or not someone wants to ride a bike around downtown Chicago or not. to_datetime() function is able to read multiple formats and convert them all to the same.Īnyone that has ever been to the Midwest, Chicago in particular, knows that weather can vary greatly by the day. Finally, the date format for the years varied, but pandas’. ![]() This was a minor inconvenience, but the individual files just needed to be concatenated into one file. Another situation was that in 2015, the data for second quarter was split into data for the months of April, May and June. In each year, there is at least one quarter whose column headers were slightly different such as ‘start_time’ vs ‘starttime.’ This was an easy column rename fix. The data is very clean with a few exceptions.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |