Hi! I run my logistic regression model but I get an error message. Here is the message through this screenshot:
or
Something is wrong; all the Accuracy metric values are missing:
Accuracy Kappa
Min. : NA Min. : NA
1st Qu.: NA 1st Qu.: NA
Median : NA Median : NA
Mean :NaN Mean :NaN
3rd Qu.: NA 3rd Qu.: NA
Max. : NA Max. : NA
NA's :1 NA's :1
Error: Stopping
In addition: There were 26 warnings (use warnings() to see them)
Hi! I run my logistic regression model but I get an error message. Here is the message through this screenshot:
or
Something is wrong; all the Accuracy metric values are missing: Accuracy Kappa
Min. : NA Min. : NA
1st Qu.: NA 1st Qu.: NA
Median : NA Median : NA
Mean :NaN Mean :NaN
3rd Qu.: NA 3rd Qu.: NA
Max. : NA Max. : NA
NA's :1 NA's :1
Error: Stopping In addition: There were 26 warnings (use warnings() to see them)
Here are my data sources :
test.csv train.csv gender_submission.csv
Look at my codes :
`#The objective : Predict survival on the Titanic and get familiar with ML basics
Step :
Data import
Data Cleaning
Descrptives statistcs
Creation of the model
Estimating model quality
---------------------------------------------------------------------------------
------------------ Step 1 : Data import -----------------------------------------
---------------------------------------------------------------------------------
Download packages
library(readr) #Import data library(dplyr) #Data manipulation library(tidyr) #Data manipulation library(ggplot2) library(lattice) library(caret) #Machine Learning library(recipes) #Machine Learning
test <- read_csv("titanic/test.csv") #Data for building the model train <- read_csv("titanic/train.csv") #Data for testing the model
---------------------------------------------------------------------------------
------------------ Step 2 : Data manipulation -----------------------------------
---------------------------------------------------------------------------------
full <- bind_rows(train, test) #Gather into one dataset
head(full) #Visualize the five first data
sum(is.na(full)) # total number of missing data
colMeans(is.na(full)) # Percentage of missing values for each column
full<- full[!is.na(full$Embarked),] #Delete missing values from Embarked variable full<- full[!is.na(full$Survived),] #Delete missing values from Survived variable
full[is.na(full$Age),]$Age <- median(full$Age, na.rm = T) #Replace missings values with the median of the column "Age"
Select the data we save for the rest of the analysis
full <- full %>% select("Survived","Pclass", "Sex", "Age", "SibSp", "Parch", "Fare", "Embarked")
---------------------------------------------------------------------------------
------------------ Step 3 : Creation of the model -------------------------------
---------------------------------------------------------------------------------
set.seed(222)#Set up a random seed
Redivide the data in train(75%) et test
smp_size <- floor(0.75 * nrow(full)) train_ind <-sample(seq_len(nrow(full)), size = smp_size)
train <- full[train_ind,] #Filter of each row which are in "train_ind" test <- full[-train_ind,] #Filter of each row which aren't in "train_ind"
---------------------------------------------------------------------------------
------------------ Step 4 : Creation of the model -------------------------------
---------------------------------------------------------------------------------
fitControl <- trainControl(method="cv", number=10, savePredictions = TRUE) #Parameters of the module Survived <- full$Survived Survived <- as.factor(Survived) lr_model <- train(Survived~ ., data = train, method = "glm", family = binomial(), trainControl = fitControl)
summary(lr_model`
Thank you so much for your answers and supports.