[Solved] GU4206-GR5206 Homework1-Data cleaning, EDA, R graphics

Data cleaning, EDA, R graphics, more practice with filtering and vectorized commands.

Data Description:

The data set NYChousing.csv contains property-level data on privately-owned, subsidized rental properties in New York City collected by the Furman Center. The data can be found here: http://www.furmancenter.org. The dataset contains financial and physical information on the properties including geographic, subsidy, ownership, physical, and financial information. Note that this dataset is a few years old.

Perform the following tasks:

Part 1: Loading, Cleaning the Exploring Data in R

1. Load the data into a dataframe called housing.
2. How many rows and columns does the dataframe have?

• Run the appropriate function to display the variable names of the dataframe.

1. Run this command, and explain, in words, what this does:

apply(is.na(housing), 2, sum).

1. Remove the rows of the dataset for which the variable Value is NA.
2. How many rows did you remove with the previous call? Does this agree with your result from (iv)?

• Calculate the third quartile of the property values, i.e., the third quartile Q₃ is the 75th percentile. Use the quantile() function to complete this task.
• Create a new variable in the dataset called HighValue that is equal to High if the propertys value is greater than Q₃ and is equal to NotHigh if the propertys value is less than or equal to Q₃.

1. Display a contingency table that shows the proprtions of HighValue split by Borough. Note that the table() function is the easiest way to tackle this problem but the table() function gives raw counts.
2. What is the proportion of properties whose values are in the upper quartile and are located in The Bronx? Solve this question in two ways: (1) by using the table from (ix), and (2) by using logical/relational commands and using the function mean().
3. Given a randomly selected property is in The Bronx, what is the probability that its value is in the upper quartile? Solve this question in two ways: (1) by using the table from (ix), and (2) by using logical/relational/filtering commands and using the function mean().

• Create a new variable in the dataset called logValue that is equal to the logarithm of the propertys Value. What are the minimum, median, mean, and maximum values of logValue?
• Create a new variable in the dataset called logUnits that is equal to the logarithm of the number of units in the property. The number of units in each piece of property is stored in the variable UnitCount.
• Finally create a new variable in the dataset called after1950 which equals TRUE if the property was built in or after 1950 and FALSE Youll want to use the YearBuilt variable here. This can be done in a single line of code.

Part 2: EDA

2i. Create a multiple boxplot (side-by-side boxplots) comparing property value across the five boroughs. Create a multiple boxplot (side-by-side boxplots) comparing property logValue across the five boroughs. Make sure to label the plots appropriately.

2ii. Plot property logValue against property logUnits. Name the x and y labels of the plot appropriately. logValue should be on the y-axis.

2iii. Make the same plot as above, but now include the argument col = factor(housing$after1950). Describe this plot and the covariation between the two variables. What does the coloring in the plot tell us?

Hint: legend(bottomright, legend = levels(factor(housing$after1950)), fill = unique(factor(housing$after1950))).