0310 Final project Rentable Property Metric

# Read the CSV data
data <- read.csv("/Users/liuyutong/Desktop/0310INFS/housing.csv", header = TRUE, stringsAsFactors = FALSE)

# View the structure of the data to understand the column names and types
str(data)

'data.frame':   90 obs. of  28 variables:
 $ Neighborhood                             : chr  "Allegheny Center" "Allegheny West" "Allentown" "Arlington" ...
 $ Sector..                                 : int  3 3 6 7 7 5 15 5 6 12 ...
 $ Population..2010.                        : chr  "933" "462" "2,500" "1,869" ...
 $ Total...Units..2000.                     : chr  "675" "390" "1,505" "880" ...
 $ Total_Units_2010                         : chr  "1,052" "355" "1,291" "886" ...
 $ X..Occupied.Units..2010.                 : chr  "51.5%" "74.9%" "80.0%" "86.6%" ...
 $ X..Vacant.Units..2010.                   : chr  "48.5%" "25.1%" "20.0%" "13.4%" ...
 $ X..Occupied.Units..2010..1               : chr  "535" "203" "953" "754" ...
 $ X..Owner.Occupied.Units..2010.           : chr  "10.1%" "18.2%" "59.2%" "65.4%" ...
 $ Percent_Renter_Occupied_Units_2010       : chr  "89.9%" "81.8%" "40.8%" "34.6%" ...
 $ Est..Avg..Yrs..of.Residence..2010.       : int  0 15 5 11 2 5 2 6 17 3 ...
 $ X..Living.in.Household..2010.            : chr  "100.0%" "100.0%" "92.1%" "100.0%" ...
 $ X..Living.in.Group.Quarters..2010.       : chr  "0.0%" "0.0%" "7.9%" "0.0%" ...
 $ X..Units.Built.00.09                     : chr  "4.6%" "0.0%" "0.0%" "0.0%" ...
 $ X..Units.Built.90.99                     : chr  "2.1%" "3.6%" "1.5%" "1.1%" ...
 $ X..Units.Built.80.89                     : chr  "7.4%" "0.0%" "8.2%" "1.6%" ...
 $ X..Units.Built.60.79                     : chr  "67.3%" "7.9%" "7.1%" "0.5%" ...
 $ X..Units.Built.40.59                     : chr  "17.3%" "31.0%" "20.3%" "24.5%" ...
 $ X..Units.Built.before.1939               : chr  "1.3%" "57.4%" "62.9%" "72.3%" ...
 $ Median.Home.Value..2000.                 : chr  "US$86,500" "US$159,700" "US$34,300" "US$38,800" ...
 $ Med..Val....00.in..10.Dollars.           : chr  "US$109,535" "US$202,228" "US$43,434" "US$49,132" ...
 $ Median.Home..Value..2010.                : chr  "US$136,300" "US$123,600" "US$42,200" "US$44,200" ...
 $ X..Change.Real.Value.2000.2010           : chr  "24.4%" "-38.9%" "-2.8%" "-10.0%" ...
 $ Median.Sale.Price..2010.                 : chr  "N/A" "US$309,940" "US$8,500" "US$15,397" ...
 $ X..Sales.Counted..2010.                  : int  0 7 70 34 0 40 1 128 39 118 ...
 $ Foreclosures..2008.                      : int  0 0 27 12 0 7 0 64 12 18 ...
 $ Foreclosures..2010.                      : int  0 1 11 13 0 5 1 40 11 12 ...
 $ X..of.all.Housing.Units.Foreclosed..2010.: chr  "0.0%" "0.3%" "0.9%" "1.5%" ...

# Convert 'Total_Units_2010' to numeric. This is important if it's not already numeric.
# If the column is a factor or character, this step will convert it to numeric.
data$Total_Units_2010 <- as.numeric(as.character(data$Total_Units_2010))

Warning: NAs introduced by coercion

# Convert 'Percent_Renter_Occupied_Units_2010' to numeric after removing the percent sign.
# This step will remove the '%' sign and convert the result to numeric.
data$Percent_Renter_Occupied_Units_2010 <- as.numeric(gsub("%", "", data$Percent_Renter_Occupied_Units_2010))

# Check for any conversion errors that might have resulted in NAs in either column
sum(is.na(data$Total_Units_2010))

[1] 56

sum(is.na(data$Percent_Renter_Occupied_Units_2010))

[1] 0

# Calculate the rentable properties
rentable_properties <- data$Total_Units_2010 * (data$Percent_Renter_Occupied_Units_2010 / 100)

# Print the calculated rentable properties
print(rentable_properties)

 [1]      NA 290.390      NA 306.556 120.324      NA 689.304      NA      NA      NA 243.664
[12]  58.437      NA      NA 220.080      NA      NA      NA      NA      NA  23.128   4.000
[23]      NA      NA      NA      NA  70.531      NA      NA      NA  61.752 289.440 341.240
[34]      NA      NA 228.333      NA  41.818      NA      NA      NA      NA 379.848      NA
[45] 418.348      NA      NA      NA      NA      NA      NA      NA      NA  75.168  41.184
[56]      NA 241.000 723.000 320.902      NA      NA      NA      NA      NA 376.107 116.876
[67]  51.666      NA      NA      NA  15.000      NA      NA 268.824      NA      NA      NA
[78]  91.575      NA 297.990 180.030  81.250      NA      NA      NA      NA 109.065 423.192
[89]      NA  59.719

# Assuming there's a column 'Neighborhood' in your data
# Create a new data frame with relevant information
result_df <- data.frame(
  Neighborhood = data$Neighborhood, 
  Total_Units = data$Total_Units_2010, 
  Percent_Renter_Occupied = data$Percent_Renter_Occupied_Units_2010, 
  RentableProperty = rentable_properties
)

# Remove rows with NA in RentableProperty
result_df <- na.omit(result_df)

# Print the first few rows of the result
print(result_df)

# Round down the RentableProperty values to the nearest whole number
result_df$RentableProperty <- floor(result_df$RentableProperty)

# Now, let's print the first few rows of the updated result
print(result_df)

NA

# Continuing from where we calculated rentable_properties

# Replace NA values in rentable_properties with 0
rentable_properties[is.na(rentable_properties)] <- 0

# Round down the RentableProperty values to the nearest whole number
rentable_properties <- floor(rentable_properties)

# Create a new data frame with relevant information
result_df <- data.frame(
  Neighborhood = data$Neighborhood, 
  Total_Units = data$Total_Units_2010, 
  Percent_Renter_Occupied = data$Percent_Renter_Occupied_Units_2010, 
  RentableProperty = rentable_properties
)

# Now, let's print the first few rows of the result
print(result_df)

NA

# Read the CSV data
data <- read.csv("/Users/liuyutong/Desktop/0310INFS/housing.csv", header = TRUE, stringsAsFactors = FALSE)

# Remove quotes from 'Total_Units_2010' and convert to numeric
# This strips out double quotes and then converts the result to numeric
data$Total_Units_2010 <- as.numeric(gsub("\"", "", data$Total_Units_2010))

Warning: NAs introduced by coercion

# Remove percent sign from 'Percent_Renter_Occupied_Units_2010' and convert to numeric
data$Percent_Renter_Occupied_Units_2010 <- as.numeric(gsub("%", "", data$Percent_Renter_Occupied_Units_2010))

# Calculate the rentable properties, handling NAs
rentable_properties <- with(data, Total_Units_2010 * (Percent_Renter_Occupied_Units_2010 / 100))
rentable_properties[is.na(rentable_properties)] <- 0

# Round down the RentableProperty values to the nearest whole number
rentable_properties <- floor(rentable_properties)

# Create a new data frame with relevant information
result_df <- data.frame(
  Neighborhood = data$Neighborhood, 
  Total_Units = data$Total_Units_2010, 
  Percent_Renter_Occupied = data$Percent_Renter_Occupied_Units_2010, 
  RentableProperty = rentable_properties
)

# Print the first few rows of the result
print(result_df)

# Load necessary libraries
library(tidyverse)
library(conflicted)
# Try reading the file with fill = TRUE to handle rows with different lengths
data <- read.csv("~/Desktop/0310INFS/project_dataset.csv", header = TRUE, fill = TRUE)

# Check the structure of the loaded data
str(data)

'data.frame':   39 obs. of  6 variables:
 $ Neighborhood              : chr  "Central Business Center" "Bluff" "Strip District" "Crawford-Roberts" ...
 $ Mean.Incidents.reported   : num  300.2 56.2 45.6 57 25 ...
 $ Average.rent....          : int  1966 1840 1961 1840 1840 1840 1786 1751 1786 1751 ...
 $ Distance.to.Campus..Miles.: num  3.3 2.2 3.7 2.3 2 2.1 1.1 0.4 0.8 0.5 ...
 $ Rentable.Property         : int  1779 243 297 958 689 623 1462 2659 423 2181 ...
 $ Population                : int  5477 5882 1845 2293 1386 1757 2320 10691 2534 5835 ...

# Simple Linear Regression
model <- lm(Mean.Incidents.reported ~ Rentable.Property, data = data)

# Display the summary of the model
summary(model)

Call:
lm(formula = Mean.Incidents.reported ~ Rentable.Property, data = data)

Residuals:
    Min      1Q  Median      3Q     Max 
-31.707 -18.274 -10.902   3.935 248.784 

Coefficients:
                   Estimate Std. Error t value Pr(>|t|)  
(Intercept)       24.989248  10.044926   2.488   0.0175 *
Rentable.Property  0.014855   0.006025   2.466   0.0184 *
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 44.99 on 37 degrees of freedom
Multiple R-squared:  0.1411,    Adjusted R-squared:  0.1179 
F-statistic: 6.079 on 1 and 37 DF,  p-value: 0.01844

# Diagnostic plots
par(mfrow = c(2, 2))
plot(model)

# Load necessary libraries
library(ggplot2)

# Assuming you have a dataframe called 'data' with the variables of interest
# data <- read.csv('path_to_your_data.csv')  # Uncomment and set path to your data file

# Simple Linear Regression
model <- lm(Mean.Incidents.reported ~ Rentable.Property, data = data)

# Summary of the model
summary(model)

Call:
lm(formula = Mean.Incidents.reported ~ Rentable.Property, data = data)

Residuals:
    Min      1Q  Median      3Q     Max 
-31.707 -18.274 -10.902   3.935 248.784 

Coefficients:
                   Estimate Std. Error t value Pr(>|t|)  
(Intercept)       24.989248  10.044926   2.488   0.0175 *
Rentable.Property  0.014855   0.006025   2.466   0.0184 *
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 44.99 on 37 degrees of freedom
Multiple R-squared:  0.1411,    Adjusted R-squared:  0.1179 
F-statistic: 6.079 on 1 and 37 DF,  p-value: 0.01844

# Plotting the data with ggplot2
ggplot(data, aes(x=Mean.Incidents.reported, y=Rentable.Property)) +
  geom_point() +  # This adds the scatter plot points
  geom_smooth(method='lm', se=FALSE) +  # This adds the regression line
  labs(title='Linear Regression of Incident Reports on Number of Rentable Properties',
       x='Number of Rentable Properties', 
       y='Number of Incident Reports') +
  theme_minimal()

# Save the plot to a file
ggsave('regression_plot.png', width=8, height=6)

# Load necessary library
library(dplyr)

# First, sort the neighborhoods by the number of rentable properties
sorted_data <- data %>%
  arrange(desc(Rentable.Property))

# Print the top 5 neighborhoods
top_5_neighborhoods <- head(sorted_data, 5)
print(top_5_neighborhoods)

# Create a bar graph of all neighborhoods ranked by rentable properties
ggplot(sorted_data, aes(x=reorder(Neighborhood, Rentable.Property), y=Rentable.Property)) +
  geom_bar(stat='identity') +
  labs(title='Neighborhoods Ranked by Number of Rentable Properties',
       x='Neighborhood', 
       y='Number of Rentable Properties') +
  theme(axis.text.x = element_text(angle = 90, hjust = 1))  # Rotate the x labels for readability