After meeting with the project manager, I learn that the bikes are never leased out for more than 5 hours, so any higher values are erroneous. Labs( title = "Distribution of Ride Duration ",Īt this point, I seek out the advice of my colleagues. Ggplot( tripdata2,aes( member_casual, ride_length)) + Wow! The standard deviation for casuals is 245 while that of members is only 28. Summarize(mean( ride_length),sd( ride_length)) In fact, let's see if there's a difference between casuals and members. Interestingly, even with the extreme outlier, the average trip duration is about ```19.75``` minutes. Yeah, that's probably the most skewed-left graph I've ever seen. Labs( title = "Ride Durations Distribution ", face = "bold ") + Geom_histogram( binwidth = 50, fill = "blue ") + Library( ggplot2) # Data visualization package # Convert start/end times to datetime (POSIXlt) format Tripdata ``` we want to convert them to datetime format also known as POSIXlt. Here's a quick look at the structure data: Using Excel or Sheets would be tedious unless you had current quarterly data.Īfter importing the data, some columns such as ```end_station_id``` and ```end_lat``` are removed because they're irrelevant to the business task. Some of the upcoming operations take a **long** time to load. However SQL may be more efficient at processing such a large dataset. I've chosen to use R for this because R handles all stages of the analysis process, including cleaning, visualization and this presentation. The result is saved as ```combined.csv```in ```data-copy``` which is a back-up of the raw data.Īll data must be processed, or *cleaned* before analysis. To get the most recent data from September 2022 and the 12 months before, I've stitched together 12 CSV files using ```cat *.csv >combined.csv```in the Mac terminal. There is quarterly data that could be merged together, but it's from 2020 so it's outdated. It contains several ZIP files organized in different ways. Sensitive personal and financial data has been omitted to respect privacy. This data is available for public use by Motivate International Inc (i.e. To summarize, our business task is to *develop a marketing strategy to convert annual members into casual members* and *present our solutions to the executive team*. Historical data has been uploaded to Amazon Web Services, contained in CSV files exported from the company database that can be found (). Data is gathered automatically using geotracking services on each of the 5878 bicycle leased by the company Cyclistic. Historical trip data from the past 12 months, so we can identify trends and ensure our analysis is up-to-date. The executive team at Cyclistic who will approve of our proposed strategy. How annual members and casual riders' bike usage differs. How can we maximize profit by converting casual riders into annual members. Must approve your recommendations, so they must be backed up with compelling data insights and professional dataīefore we begin analyzing the data, there are five questions we should answer to consider the scope, audience and objectives of the project. Your team will design a new marketing strategy to convert casual riders into annual members. Your team wants to understand how casual riders and annual members use Cyclistic bikes differently. Of marketing believes the company’s future success depends on maximizing the number of annual memberships. >You are a junior data analyst working in the marketing analyst team at Cyclistic, a bike-share company in Chicago. All the work you see is my own unless otherwise specified and reflects my own skills, abilities and knowledge. The advantage is that I'll improve familiarity with the tools and stages of the data analysis process: ask, prepare, process, analyze, share, and act, while not being bogged down by technical difficulties, and begin developing my professional portfolio.Īlthough these case studies have a specific question to answer and a roadmap with guided questions and objectives, all the details have been provided by me, Garian Rice. Title: 'Case Study 1: Selling Annual Bike Subscriptions 'Īlthough I'm eager to use data of personal interest to answer my own questions about the world, like what's the key to happiness, I've decided to save these passions for next time and first follow two guided case studies offered in the Google Data Analytics certificate.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |