Created
March 10, 2018 15:50
-
-
Save thejefflarson/0232dfe82ea37037584206f30bad5d7a to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library("readr") | |
data <-read_csv("https://raw.githubusercontent.com/propublica/compas-analysis/master/compas-scores-two-years.csv") | |
library("dplyr") | |
data <- filter(data, type_of_assessment=="Risk of Recidivism") | |
library("ggplot2") | |
ggplot(data=filter(data, race =="African-American"), aes(ordered(decile_score))) + geom_bar() | |
ggplot(data=filter(data, race =="Caucasian"), aes(ordered(decile_score))) + geom_bar() | |
ggplot(data, aes(race, decile_score)) + geom_boxplot(notch=TRUE) | |
means <- filter(data, race == "Caucasian" | race == "African-American") | |
means <- mutate(data, white = race == "Caucasian") | |
t.test(decile_score ~ white, data=means) | |
model <- lm(decile_score ~ race + age + sex + two_year_recid + priors_count + | |
c_charge_degree, data = data) | |
summary(model) | |
preds <- predict(model, data=data) | |
ggplot(data, aes(decile_score, predict(model, data=data))) + geom_point() + | |
geom_smooth() + xlim(0,10) + ylim(0, 10) | |
model <- lm(decile_score ~ race + age + sex + two_year_recid + priors_count + | |
c_charge_degree + is_recid, data = data) | |
summary(model) | |
model <- glm(I(decile_score > 4) ~ race + age + sex + two_year_recid + priors_count + | |
c_charge_degree + is_recid, data=data, family="binomial") | |
summary(model) | |
control <- exp(2.097299) / (1 + exp(-2.097299)) | |
exp(-0.451861) / (1 - control + (control * exp(-0.451861))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment