Titanic Logistic Regression Prediction with R Notebook Showcase

This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.
Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Ctrl+Shift+Enter.
Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Ctrl+Alt+I.
When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Ctrl+Shift+K to preview the HTML file).
The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.

install packages

if (!require(tidyverse)) install.packages("tidyverse")

Loading required package: tidyverse
Warning: package ‘tidyverse’ was built under R version 4.4.1
Warning: package ‘ggplot2’ was built under R version 4.4.1
Warning: package ‘tibble’ was built under R version 4.4.1
Warning: package ‘tidyr’ was built under R version 4.4.1
Warning: package ‘readr’ was built under R version 4.4.1
Warning: package ‘purrr’ was built under R version 4.4.1
Warning: package ‘dplyr’ was built under R version 4.4.1
Warning: package ‘forcats’ was built under R version 4.4.1
Warning: package ‘lubridate’ was built under R version 4.4.1

── Attaching core tidyverse packages ─────────────────
✔ dplyr     1.1.4     ✔ readr     2.1.5
✔ forcats   1.0.0     ✔ stringr   1.5.1
✔ ggplot2   3.5.1     ✔ tibble    3.2.1
✔ lubridate 1.9.3     ✔ tidyr     1.3.1
✔ purrr     1.0.2     
── Conflicts ──────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errors

if (!require(readr)) install.packages("readr")
if (!require(dplyr)) install.packages("dplyr")

Train Dataset

# Define the URL of the training data
train_url <- "http://s3.amazonaws.com/assets.datacamp.com/course/Kaggle/train.csv"

# Read the data from the URL using readr::read_csv
train <- read_csv(train_url)

Rows: 891 Columns: 12
── Column specification ──────────────────────────────
Delimiter: ","
chr (5): Name, Sex, Ticket, Cabin, Embarked
dbl (7): PassengerId, Survived, Pclass, Age, SibSp...

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.

head(train)

# Get summary statistics
summary(train)

  PassengerId       Survived          Pclass     
 Min.   :  1.0   Min.   :0.0000   Min.   :1.000  
 1st Qu.:223.5   1st Qu.:0.0000   1st Qu.:2.000  
 Median :446.0   Median :0.0000   Median :3.000  
 Mean   :446.0   Mean   :0.3838   Mean   :2.309  
 3rd Qu.:668.5   3rd Qu.:1.0000   3rd Qu.:3.000  
 Max.   :891.0   Max.   :1.0000   Max.   :3.000  
                                                 
     Name               Sex           
 Length:891         Length:891        
 Class :character   Class :character  
 Mode  :character   Mode  :character  
                                      
                                      
                                      
                                      
      Age            SibSp           Parch       
 Min.   : 0.42   Min.   :0.000   Min.   :0.0000  
 1st Qu.:20.12   1st Qu.:0.000   1st Qu.:0.0000  
 Median :28.00   Median :0.000   Median :0.0000  
 Mean   :29.70   Mean   :0.523   Mean   :0.3816  
 3rd Qu.:38.00   3rd Qu.:1.000   3rd Qu.:0.0000  
 Max.   :80.00   Max.   :8.000   Max.   :6.0000  
 NA's   :177                                     
    Ticket               Fare       
 Length:891         Min.   :  0.00  
 Class :character   1st Qu.:  7.91  
 Mode  :character   Median : 14.45  
                    Mean   : 32.20  
                    3rd Qu.: 31.00  
                    Max.   :512.33  
                                    
    Cabin             Embarked        
 Length:891         Length:891        
 Class :character   Class :character  
 Mode  :character   Mode  :character  
                                      
                                      
                                      
                                      

Replace missing values : Age replaced with median, Embarked,Sex are categorical we need to convert into numeric and replaced with mode.

if(!(require(mice)))install.packages("mice")
library(imputeR)  # For imputation
# Assuming 'train' is your data frame in R

# Define replacements as a named vector
replacements_embarked <- c("S" = 0, "C" = 1, "Q" = 2)
replacements_sex <- c(male = 0, female = 1)

# Handle missing values (replace with mode)
train$Age <- replace(train$Age, is.na(train$Age), median(train$Age, na.rm = TRUE))

train$Embarked[is.na(train$Embarked)] <- mode(train$Embarked)

train$Sex[is.na(train$Sex)] <- mode(train$Sex)
# Convert Embarked and Sex to numeric
train$Embarked <- as.numeric(factor(train$Embarked))

train$Sex <- as.numeric(factor(train$Sex))

is.na(train)

# Install required packages if not already installed
if (!require(glmnet)) install.packages("glmnet")
# Load libraries
library(glmnet)  # Consider using glmnet for compatibility with statsmodels

# Prepare data (assuming train is a data.frame)
data <- train[c("Pclass", "Sex", "Age", "Embarked","Survived")]

# Create logistic regression model
model <- glm(formula = Survived ~ Pclass + Sex + Age + Embarked, data = data, family = binomial(link = "logit"))

# Set random state (equivalent to setting seed in Python)
set.seed(16)

Testing Dataset

# Download test data (replace with your download method)
test_url <- "http://s3.amazonaws.com/assets.datacamp.com/course/Kaggle/test.csv"
test <- read.csv(test_url)

Replace missing values: Age replace with median, Embarked, Sex are categorical we need to convert into numeric and replace with mode.

# Impute missing values in Age
test$Age <- with(test, replace(test$Age, is.na(test$Age), median(test$Age)))

# Convert Sex to factor and assign values
test$Sex[is.na(test$Sex)] <- mode(test$Sex)
test$Embarked[is.na(test$Embarked)] <- mode(test$Embarked)

test$Embarked <- as.numeric(factor(test$Embarked))
test$Sex <- as.numeric(factor(test$Sex))

Check is any missing value left?

is.na(test)

# Select features for prediction
X_test <- test[c("Pclass", "Sex", "Age", "Embarked")]

# Predict using your model (assuming model is already trained)
y_pred <- predict(model, newdata = X_test, type = "response")  # type argument for probabilities

# Create submission dataframe
df <- data.frame(PassengerId = test$PassengerId, Survived = y_pred)

# Save predictions as CSV
write.csv(df, file = "predictions.csv", row.names = FALSE)

print("CSV file saved successfully!")