#Loading packages
suppressWarnings({
library(tidyverse)
library(openintro)
})Loading dataset
url <- "https://raw.githubusercontent.com/lburenkov/Diabetes/main/diabetes_012_health_indicators_BRFSS2015.csv" # Replace with the URL of your CSV data
data <- read.csv(url)Can we predict diabetes based on health indicators?
# Using the dim() function to get the number of rows and columns
dimensions <- dim(data)
# Extracting the number of rows and columns
num_rows <- dimensions[1]
num_columns <- dimensions[2]
# Printing the number of rows and columns
cat("Number of rows:", num_rows, "\n")## Number of rows: 253680cat("Number of columns:", num_columns, "\n")## Number of columns: 22The Behavioral Risk Factor Surveillance System (BRFSS) is a health-related telephone survey that is collected annually by the CDC. Each year, the survey collects responses from over 400,000 Americans on health-related risk behaviors, chronic health conditions, and the use of preventative services. It has been conducted every year since 1984. https://www.kaggle.com/datasets/alexteboul/diabetes-health-indicators-dataset
This is an observational study.
Dataset is available in Kaggle https://www.kaggle.com/datasets/alexteboul/diabetes-health-indicators-dataset
The response variable is categorical.
The explanatory variable is numerical.
# Print summary statistics for the entire dataset
summary(data)## Diabetes_012 HighBP HighChol CholCheck
## Min. :0.0000 Min. :0.000 Min. :0.0000 Min. :0.0000
## 1st Qu.:0.0000 1st Qu.:0.000 1st Qu.:0.0000 1st Qu.:1.0000
## Median :0.0000 Median :0.000 Median :0.0000 Median :1.0000
## Mean :0.2969 Mean :0.429 Mean :0.4241 Mean :0.9627
## 3rd Qu.:0.0000 3rd Qu.:1.000 3rd Qu.:1.0000 3rd Qu.:1.0000
## Max. :2.0000 Max. :1.000 Max. :1.0000 Max. :1.0000
## BMI Smoker Stroke HeartDiseaseorAttack
## Min. :12.00 Min. :0.0000 Min. :0.00000 Min. :0.00000
## 1st Qu.:24.00 1st Qu.:0.0000 1st Qu.:0.00000 1st Qu.:0.00000
## Median :27.00 Median :0.0000 Median :0.00000 Median :0.00000
## Mean :28.38 Mean :0.4432 Mean :0.04057 Mean :0.09419
## 3rd Qu.:31.00 3rd Qu.:1.0000 3rd Qu.:0.00000 3rd Qu.:0.00000
## Max. :98.00 Max. :1.0000 Max. :1.00000 Max. :1.00000
## PhysActivity Fruits Veggies HvyAlcoholConsump
## Min. :0.0000 Min. :0.0000 Min. :0.0000 Min. :0.0000
## 1st Qu.:1.0000 1st Qu.:0.0000 1st Qu.:1.0000 1st Qu.:0.0000
## Median :1.0000 Median :1.0000 Median :1.0000 Median :0.0000
## Mean :0.7565 Mean :0.6343 Mean :0.8114 Mean :0.0562
## 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:1.0000 3rd Qu.:0.0000
## Max. :1.0000 Max. :1.0000 Max. :1.0000 Max. :1.0000
## AnyHealthcare NoDocbcCost GenHlth MentHlth
## Min. :0.0000 Min. :0.00000 Min. :1.000 Min. : 0.000
## 1st Qu.:1.0000 1st Qu.:0.00000 1st Qu.:2.000 1st Qu.: 0.000
## Median :1.0000 Median :0.00000 Median :2.000 Median : 0.000
## Mean :0.9511 Mean :0.08418 Mean :2.511 Mean : 3.185
## 3rd Qu.:1.0000 3rd Qu.:0.00000 3rd Qu.:3.000 3rd Qu.: 2.000
## Max. :1.0000 Max. :1.00000 Max. :5.000 Max. :30.000
## PhysHlth DiffWalk Sex Age
## Min. : 0.000 Min. :0.0000 Min. :0.0000 Min. : 1.000
## 1st Qu.: 0.000 1st Qu.:0.0000 1st Qu.:0.0000 1st Qu.: 6.000
## Median : 0.000 Median :0.0000 Median :0.0000 Median : 8.000
## Mean : 4.242 Mean :0.1682 Mean :0.4403 Mean : 8.032
## 3rd Qu.: 3.000 3rd Qu.:0.0000 3rd Qu.:1.0000 3rd Qu.:10.000
## Max. :30.000 Max. :1.0000 Max. :1.0000 Max. :13.000
## Education Income
## Min. :1.00 Min. :1.000
## 1st Qu.:4.00 1st Qu.:5.000
## Median :5.00 Median :7.000
## Mean :5.05 Mean :6.054
## 3rd Qu.:6.00 3rd Qu.:8.000
## Max. :6.00 Max. :8.000…