Analyze real data sets from a bike sharing company to find how casual and member riders use company bikes differently. The analysis should be an important tool for the marketing analyst team to figure out a strategy that converts casual riders into annual members.
Imported data from Excel to Google sheets
Checked for data errors (Nulls, Misspellings, Wrong Data Types, Etc.) by sorting and filtering
Made copies of the data before manipulating the data
Froze the header row
Formatted column to have matching data types
Created two new columns (ride_length, day_of_the_week) where I calculated the day of the week and the duration of each bike ride using functions
Found the Mean and Max for "ride_length", and the Mode for "day_of_the_week" using functions
Created pivot tables comparing the average ride duration and the total number of bike rides between casual and member riders for each day of the week
Imported data to BigQuery
Created data sets and then tables from the data sets
Created queries to find the total number of rides from casual and member riders for each day of the week
Used SELECT, FROM, WHERE, COUNTIF, INNER JOIN, DISTINCT, AND, and AS
Used JOIN to collect the total number of member riders from two different data sets (the April data set and the December data set)
Installed and loaded necessary packages
Set the working directory
Uploaded four CSV files (data sets)
Compared the column names of data sets column and then renamed them to match each other
Compared the data types of each column and mutated them to match each other
Stacked all four data sets and created one big data frame
Got a summary of the data
Reassigned observations
Added columns to the data frame
Created a copy of the data frame and deleted unnecessary columns
Collected the mean, median, max, and the min of the ride length
Created visuals from RStudio and exported them to a local file
Wrote over 200 lines of code
The Director of Marketing claims that maximizing the number of annual members is essential for the success of the company. Analyzing customer bike rides from the previous twelve months is a key part of helping the marketing analyst team identify how casual and member riders use bikes differently and ultimately come up with a strategy to convert casual riders into annual members. After asking the right questions, preparing, processing, and analyzing the data with multiple tools such as Google sheets, Excel, SQL, and R it was clear that casual bike riders have a tendency to ride fewer times than an annual member but for longer periods of time.