library(readr)
housing <- read_csv("~/Desktop/STA 108/housing.csv")
## Rows: 195 Columns: 6
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (1): county
## dbl (5): price, br, lsqft, bsqft, year
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
To include: scatterplot, histogram, boxplot, summary of value
names(housing)[c(1,2)] = c("Y", "X1")#Renames the first two columnns
the.model = lm(Y ~ X1, data = housing)
par(mfrow= c(2,2)) #Makes a 2 x 2 grid which plots will fill in to
#scatterplot
plot(housing$X1, housing$Y, main = "Price vs # Bedrooms", ylab = "Price",xlab = "# Bedrooms", pch = 19,font = 2,font.lab = 2,cex = 0.75)
#histogram
hist(housing$X1, main = "Frequency of # Bedrooms", ylab = "Frequency", xlab = "# Bedrooms",pch = 19,font = 2,font.lab = 2,cex = 0.75)
#boxplot
boxplot(housing$X1, main = "Price vs # Bedrooms", ylab = "Price", xlab = "# Bedrooms", horizontal = TRUE, pch = 19,font = 2,font.lab = 2,cex = 0.75)
abline(h = 0, lwd = 2, col = "purple")
# summary statistics
summary_stats <- data.frame(
X_bar = mean(housing$X1),
Y_bar = mean(housing$Y),
SD_X = sd(housing$X1),
SD_Y = sd(housing$Y),
#ask this from prof/DOUBLE CHECK
Error_Y = sd(housing$Y)/sqrt(nrow(housing))
)
# Print summary statistics table
print(summary_stats)
## X_bar Y_bar SD_X SD_Y Error_Y
## 1 2.907692 538.5487 0.8919412 342.4182 24.52108
names(housing)[c(1,3)] = c("Y","X2")#Renames the first two columnns
the.model = lm(Y ~ X2, data = housing)
par(mfrow= c(2,2)) #Makes a 2 x 2 grid which plots will fill in to
#scatterplot
plot(housing$X2, housing$Y, main = "Price vs # Lot Sqft", ylab = "Price",xlab = "Lot Sqft", pch = 19,font = 2,font.lab = 2,cex = 0.75)
#histogram
hist(housing$X2, main = "Frequency of Lot Sqft ", ylab = "Frequency", xlab = "Lot Sqft",pch = 19,font = 2,font.lab = 2,cex = 0.75)
#boxplot
boxplot(housing$X2, main = "Price vs # Lot Sqft", ylab = "Price", xlab = "Lot Sqft", horizontal = TRUE, pch = 19,font = 2,font.lab = 2,cex = 0.75)
abline(h = 0, lwd = 2, col = "purple")
# summary statistics
summary_stats <- data.frame(
X_bar = mean(housing$X2),
Y_bar = mean(housing$Y),
SD_X = sd(housing$X2),
SD_Y = sd(housing$Y),
Error_Y = sd(housing$Y)/sqrt(nrow(housing))
)
# Print summary statistics table
print(summary_stats)
## X_bar Y_bar SD_X SD_Y Error_Y
## 1 25419.28 538.5487 88973.11 342.4182 24.52108
names(housing)[c(1,4)] = c("Y","X3")#Renames the first two columnns
the.model = lm(Y ~ X3, data = housing)
par(mfrow= c(2,2)) #Makes a 2 x 2 grid which plots will fill in to
#scatterplot
plot(housing$X3, housing$Y, main = "Price vs # House Sqft", ylab = "Price",xlab = "House Sqft", pch = 19,font = 2,font.lab = 2,cex = 0.75)
#histogram
hist(housing$X3, main = "Frequency of House Sqft ", ylab = "Frequency", xlab = "House Sqft",pch = 19,font = 2,font.lab = 2,cex = 0.75)
#boxplot
boxplot(housing$X3, main = "Price vs # House Sqft", ylab = "Price", xlab = "Lot Sqft", horizontal = TRUE, pch = 19,font = 2,font.lab = 2,cex = 0.75)
abline(h = 0, lwd = 2, col = "purple")
# summary statistics
summary_stats <- data.frame(
X_bar = mean(housing$X3),
Y_bar = mean(housing$Y),
SD_X = sd(housing$X3),
SD_Y = sd(housing$Y),
Error_Y = sd(housing$Y)/sqrt(nrow(housing))
)
# Print summary statistics table
print(summary_stats)
## X_bar Y_bar SD_X SD_Y Error_Y
## 1 1579.195 538.5487 645.4697 342.4182 24.52108
names(housing)[c(1,5)] = c("Y","X4")#Renames the first two columnns
the.model = lm(Y ~ X4, data = housing)
par(mfrow= c(2,2)) #Makes a 2 x 2 grid which plots will fill in to
#scatterplot
plot(housing$X4, housing$Y, main = "Price vs Year", ylab = "Price",xlab = "Year", pch = 19,font = 2,font.lab = 2,cex = 0.75)
#histogram
hist(housing$X4, main = "Frequency of Year ", ylab = "Frequency", xlab = "Year",pch = 19,font = 2,font.lab = 2,cex = 0.75)
#boxplot
boxplot(housing$X4, main = "Price vs Year", ylab = "Price", xlab = "Year", horizontal = TRUE, pch = 19,font = 2,font.lab = 2,cex = 0.75)
abline(h = 0, lwd = 2, col = "purple")
# summary statistics
summary_stats <- data.frame(
X_bar = mean(housing$X4),
Y_bar = mean(housing$Y),
SD_X = sd(housing$X4),
SD_Y = sd(housing$Y),
Error_Y = sd(housing$Y)/sqrt(nrow(housing))
)
# Print summary statistics table
print(summary_stats)
## X_bar Y_bar SD_X SD_Y Error_Y
## 1 1971.077 538.5487 20.03474 342.4182 24.52108
names(housing)[c(1,6)] = c("Y","X5")#Renames the first two columnns
the.model = lm(Y ~ X5, data = housing)
# Histograms for each county's prices
par(mfrow = c(1, 3)) # Set the plotting layout to one row with three columns
# Histogram for Solano county
hist(housing$Y[housing$X5 == "Solano"], main = "Solano", xlab = "Price", ylab = "Frequency", col = "skyblue")
# Histogram for Sonoma county
hist(housing$Y[housing$X5 == "Sonoma"], main = "Sonoma", xlab = "Price", ylab = "Frequency", col = "skyblue")
# Histogram for Napa county
hist(housing$Y[housing$X5 == "Napa"], main = "Napa", xlab = "Price", ylab = "Frequency", col = "skyblue")
## Scatterplot(FIX)
# Convert the categorical variable 'County' to a factor
housing$X5 <- factor(housing$X5, levels = c("Solano", "Sonoma", "Napa"))
# Plot scatterplot
plot(housing$X5, housing$Y,
main = "Price vs County",
xlab = "County",
ylab = "Price",
col = "blue",
pch = 19)
# Adding labels for each category
legend("topright",
legend = levels(housing$X5),
col = "blue",
pch = 19,
title = "County")
## BoxPlot(FIX)
# Convert the categorical variable 'County' to a factor
housing$X5 <- factor(housing$X5, levels = c("Solano", "Sonoma", "Napa"))
# Plot boxplot
boxplot(Y ~ X5, data = housing,
main = "Price vs County",
xlab = "County",
ylab = "Price",
col = "blue",
border = "black")
# Adding a legend for the counties
legend("topright",
legend = levels(housing$X5),
fill = "blue",
title = "County")