#!/usr/bin/env Rscript

df <- read.csv("zeta.csv")
df <- subset(df, sex == "F")
df <- subset(df, select = -c(zcta, sex))
df <- subset(df, 8 < meaneducation & meaneducation < 18)
df <- subset(df, 10000 < meanhouseholdincome & meanhouseholdincome < 200000)
df <- subset(df, 10000 < meanhouseholdincome & meanhouseholdincome < 200000)
df <- subset(df, 20 < meanage & meanage < 60)

df$log_income <- log10(df$meanhouseholdincome)


names(df) <- c("X", "age", "education", "employment", "income", "log_income")

library(ggplot2)

ggplot(df, aes(x = age, y = log_income)) +
  geom_point(alpha = 0.2) +
  labs(x = "age", y = "income", title = "log_income(age)")

model <- lm(log_income ~ age, df)


print(model)
summary(model)