91 lines
2.0 KiB
Plaintext
91 lines
2.0 KiB
Plaintext
---
|
|
title: "Lab7: Logistic regression"
|
|
author: "Vladislav Litvinov <vlad@sek1ro>"
|
|
output:
|
|
pdf_document:
|
|
toc_float: TRUE
|
|
---
|
|
# Logit
|
|
|
|
```{r}
|
|
n = 500
|
|
breaks = 100
|
|
odds = numeric(n)
|
|
logit = numeric(n)
|
|
for (i in 1:n) {
|
|
p = runif(1)
|
|
odds[i] = p / (1 - p)
|
|
logit[i] = log(odds[i])
|
|
}
|
|
hist(odds, breaks = breaks)
|
|
hist(logit, breaks = breaks)
|
|
|
|
data <- matrix(nrow=4, ncol=2, byrow=TRUE,
|
|
data=c(2, 3,
|
|
0, 3,
|
|
0, 2,
|
|
1, 2))
|
|
|
|
fisher.test(data)
|
|
```
|
|
# Data preparation
|
|
```{r}
|
|
setwd('/home/sek1ro/git/public/lab/ds/25-1/r')
|
|
surve = read.csv('survey.csv')
|
|
|
|
head(survey)
|
|
|
|
survey$price20 = ifelse(survey$Price == 20, 1, 0)
|
|
survey$price30 = ifelse(survey$Price == 30, 1, 0)
|
|
head(survey)
|
|
```
|
|
# Model training
|
|
|
|
Residuals are the differences between what we observe and what our model predicts.
|
|
Residuals greater than the absolute value of 3 are in the tails of a standard normal distribution and usually indicate strain in the model.
|
|
|
|
https://stats.stackexchange.com/questions/48178/how-to-interpret-the-intercept-term-in-a-glm
|
|
https://library.virginia.edu/data/articles/understanding-deviance-residuals
|
|
```{r}
|
|
model = glm(
|
|
MYDEPV ~ Income + Age + price20 + price30,
|
|
binomial(link = "logit"),
|
|
survey
|
|
)
|
|
summary(model)
|
|
quantile(residuals(model))
|
|
```
|
|
# Predicts for the model
|
|
```{r}
|
|
survey$odds_ratio = exp(predict(model))
|
|
survey$prediction = survey$odds_ratio / (1 + survey$odds_ratio)
|
|
head(survey)
|
|
|
|
sum(survey$MYDEPV)
|
|
sum(survey$prediction)
|
|
|
|
new_person = data.frame(
|
|
Income = 58,
|
|
Age = 25,
|
|
price20 = 1,
|
|
price30 = 0
|
|
)
|
|
|
|
prob = predict(model, new_person, type="response")
|
|
prob
|
|
```
|
|
|
|
```{r}
|
|
library(ggplot2)
|
|
predicted <- data.frame(
|
|
prob=model$fitted.values,
|
|
MYDEPV=survey$MYDEPV)
|
|
|
|
predicted <- predicted[order(predicted$prob, decreasing=FALSE),]
|
|
predicted$rank <- 1:nrow(predicted)
|
|
|
|
ggplot(data=predicted, aes(x=rank, y=prob)) +
|
|
geom_point(aes(color=MYDEPV), alpha=0.5, shape=4, stroke=1) +
|
|
xlab("Index") +
|
|
ylab("MYDEPV")
|
|
``` |