체험 문제 3유형

setwd('c:/data')
df<-read.csv("example_titanic.csv")
library(dplyr)

## 
## 다음의 패키지를 부착합니다: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

glimpse(df)

## Rows: 891
## Columns: 12
## $ PassengerId <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17,…
## $ Survived    <int> 0, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1…
## $ Pclass      <int> 3, 1, 3, 1, 3, 3, 1, 3, 3, 2, 3, 1, 3, 3, 3, 2, 3, 2, 3, 3…
## $ Name        <chr> "Braund, Mr. Owen Harris", "Cumings, Mrs. John Bradley (Fl…
## $ Sex         <chr> "male", "female", "female", "female", "male", "male", "mal…
## $ Age         <dbl> 22, 38, 26, 35, 35, NA, 54, 2, 27, 14, 4, 58, 20, 39, 14, …
## $ SibSp       <int> 1, 1, 0, 1, 0, 0, 0, 3, 0, 1, 1, 0, 0, 1, 0, 0, 4, 0, 1, 0…
## $ Parch       <int> 0, 0, 0, 0, 0, 0, 0, 1, 2, 0, 1, 0, 0, 5, 0, 0, 1, 0, 0, 0…
## $ Ticket      <chr> "A/5 21171", "PC 17599", "STON/O2. 3101282", "113803", "37…
## $ Fare        <dbl> 7.2500, 71.2833, 7.9250, 53.1000, 8.0500, 8.4583, 51.8625,…
## $ Cabin       <chr> "", "C85", "", "C123", "", "", "E46", "", "", "", "G6", "C…
## $ Embarked    <chr> "S", "C", "S", "S", "S", "Q", "S", "S", "S", "C", "S", "S"…

library(caret)

## 필요한 패키지를 로딩중입니다: ggplot2

## 필요한 패키지를 로딩중입니다: lattice

df$Survived<-as.factor(df$Survived)
df$Sex<-as.factor(df$Sex)


model<-glm(Survived~Sex+SibSp+Parch+Fare,data=df, 
          family = "binomial")

summary(model)

## 
## Call:
## glm(formula = Survived ~ Sex + SibSp + Parch + Fare, family = "binomial", 
##     data = df)
## 
## Coefficients:
##              Estimate Std. Error z value Pr(>|z|)    
## (Intercept)  0.946635   0.169354   5.590 2.28e-08 ***
## Sexmale     -2.642219   0.186114 -14.197  < 2e-16 ***
## SibSp       -0.353892   0.098185  -3.604 0.000313 ***
## Parch       -0.200724   0.112037  -1.792 0.073200 .  
## Fare         0.014685   0.002644   5.553 2.80e-08 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 1186.66  on 890  degrees of freedom
## Residual deviance:  859.04  on 886  degrees of freedom
## AIC: 869.04
## 
## Number of Fisher Scoring iterations: 5

exp(coef(model))

## (Intercept)     Sexmale       SibSp       Parch        Fare 
##  2.57702407  0.07120312  0.70195082  0.81813853  1.01479386