# ============================================================================
# HW1 R INTRO EXERCISE- PATIENTS DATASET
# Biostats 2026 - Introduction to R Programming
# Name: ________Liliana Vega________
# Date: _______6.8.26_________
# ============================================================================
#
# Instructions:
# - Complete all exercises below
# - Test your code by running it line by line
# - Compile your report
# - Submit your html report with all answers
# - Use the provided dataset: patients.csv
# ============================================================================
# EXERCISE 1: LOAD THE DATA
# ============================================================================
# Load the patients.csv file and store it in a variable called patients
patients<-read.csv("C:/Users/liliv/Downloads/patients.csv")
# TODO: use read.csv() to load "patients.csv"
# EXERCISE 2: NUMBER OF OBSERVATIONS/RECORDS
# ============================================================================
# How many observations (rows) are in the patients dataset?
# TODO: use nrow() or dim() to find the number of rows
dim(patients)
## [1] 25 8
# EXERCISE 3: NUMBER OF VARIABLES
# ============================================================================
# How many variables (columns) are in the patients dataset?
# TODO: use ncol() or dim() to find the number of columns
ncol(patients)
## [1] 8
# EXERCISE 4: IDENTIFY CONTINUOUS VARIABLES
# ============================================================================
# Continuous variables are numeric measurements that can take many values.
# Examples: Age, Cholesterol, BMI, Blood Pressure
#
# List all the continuous variables in the patients dataset:
# TODO: List the continuous variable names as a character vector
# Hint: You might need to use names() and/or view the data with head()
names(patients)
## [1] "PatientID" "Age" "Gender" "SystolicBP" "DiastolicBP"
## [6] "Cholesterol" "BMI" "Smoker"
head(patients)
## PatientID Age Gender SystolicBP DiastolicBP Cholesterol BMI Smoker
## 1 1 45 M 125 78 210 24.5 0
## 2 2 52 F 142 88 245 26.8 1
## 3 3 38 M 118 75 195 23.2 0
## 4 4 61 F 148 92 268 28.1 1
## 5 5 42 M 130 82 220 25.1 0
## 6 6 55 F 138 85 235 27.3 0
# EXERCISE 5: IDENTIFY BINARY VARIABLES
# ============================================================================
# Binary variables are categorical with exactly 2 possible values (e.g., Yes/No, 0/1, M/F).
#
# List all the binary variables in the patients dataset:
# TODO: List the binary variable names as a character vector
# ============================================================================
# OPTIONAL: explore your dataset
# ============================================================================
# Uncomment and run the commands below
# View the first 6 rows:
head(patients)
## PatientID Age Gender SystolicBP DiastolicBP Cholesterol BMI Smoker
## 1 1 45 M 125 78 210 24.5 0
## 2 2 52 F 142 88 245 26.8 1
## 3 3 38 M 118 75 195 23.2 0
## 4 4 61 F 148 92 268 28.1 1
## 5 5 42 M 130 82 220 25.1 0
## 6 6 55 F 138 85 235 27.3 0
# Get the structure and data types:
str(patients)
## 'data.frame': 25 obs. of 8 variables:
## $ PatientID : int 1 2 3 4 5 6 7 8 9 10 ...
## $ Age : int 45 52 38 61 42 55 48 35 59 41 ...
## $ Gender : chr "M" "F" "M" "F" ...
## $ SystolicBP : int 125 142 118 148 130 138 145 115 152 128 ...
## $ DiastolicBP: int 78 88 75 92 82 85 90 72 95 80 ...
## $ Cholesterol: int 210 245 195 268 220 235 255 188 278 205 ...
## $ BMI : num 24.5 26.8 23.2 28.1 25.1 27.3 26.9 22.8 29.2 24.6 ...
## $ Smoker : int 0 1 0 1 0 0 1 0 1 0 ...
# Get summary statistics:
summary(patients)
## PatientID Age Gender SystolicBP DiastolicBP
## Min. : 1 Min. :35.00 Length :25 Min. :115.0 Min. :71.0
## 1st Qu.: 7 1st Qu.:41.00 N.unique : 2 1st Qu.:124.0 1st Qu.:78.0
## Median :13 Median :48.00 N.blank : 0 Median :135.0 Median :85.0
## Mean :13 Mean :47.84 Min.nchar: 1 Mean :134.2 Mean :83.8
## 3rd Qu.:19 3rd Qu.:55.00 Max.nchar: 1 3rd Qu.:145.0 3rd Qu.:90.0
## Max. :25 Max. :61.00 Max. :155.0 Max. :97.0
## Cholesterol BMI Smoker
## Min. :185 Min. :22.50 Min. :0.0
## 1st Qu.:205 1st Qu.:24.10 1st Qu.:0.0
## Median :228 Median :26.20 Median :0.0
## Mean :230 Mean :25.87 Mean :0.4
## 3rd Qu.:255 3rd Qu.:27.30 3rd Qu.:1.0
## Max. :285 Max. :29.80 Max. :1.0
# Get column names:
names(patients)
## [1] "PatientID" "Age" "Gender" "SystolicBP" "DiastolicBP"
## [6] "Cholesterol" "BMI" "Smoker"