##1. Installing packages in CONSOLE
##2. Loading packages: ranger is for random forest algorithm
library(caret)## Warning: package 'caret' was built under R version 4.4.3## Loading required package: ggplot2## Loading required package: latticelibrary(dplyr)## Warning: package 'dplyr' was built under R version 4.4.3##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(ranger)## Warning: package 'ranger' was built under R version 4.4.3##3. Importing data
sleephealth <- read.csv("C:/Users/ajpay/OneDrive/Documents/MSBA/SCH-MGMT 655 - Machine Learning/Exercise Files/Week 9/Sleep Health & Lifestyle Dataset.csv")##4. Exploring data 374 row dataset. Each row corresponds to one person. trying to predict whether person has sleeping disorder (1) or not (0). Small dataset to make code run faster
head(sleephealth)## Is_Male Age Salary Sleep.Duration Quality.of.Sleep Physical.Activity.Level
## 1 1 32 111283 7.2 8 50
## 2 0 35 113170 7.2 8 60
## 3 0 36 123298 7.2 8 60
## 4 0 36 107043 7.1 8 60
## 5 0 36 97889 7.2 8 60
## 6 0 36 121403 7.1 8 60
## Stress.Level BMI.Category Systolic.BP Diastolic.BP Heart.Rate Daily.Steps
## 1 6 1 118 76 68 7000
## 2 4 1 115 75 68 7000
## 3 4 1 115 75 68 7000
## 4 4 1 115 75 68 7000
## 5 4 1 115 75 68 7000
## 6 4 1 115 75 68 7000
## Sleep.Disorder
## 1 0
## 2 0
## 3 1
## 4 0
## 5 0
## 6 0nrow(sleephealth)## [1] 374##5. Setting random seed
set.seed(1234)##6. Pre-process data for binary classification need to set outcome variable to categorical variable to enable classification
sleephealth$Sleep.Disorder <- factor(sleephealth$Sleep.Disorder, levels = c(0, 1))##7. Partition training and validation sets Randomly putting 80% of our data records into a training partition, the rest (20% in validation). Training data will served as a “look up repository” for every data record that we’re trying to make a classification for. So, for every record that we try to classify as Sleep Disorder = 1 or Sleep Disorder = 0, we will look to our training data to ID the k most similar records, and use their Sleep Disorder status to inform our classification.
sample <- sample.int(n = nrow(sleephealth), size = nrow(sleephealth)*0.8, replace = F)sleephealth_training <- sleephealth[sample, ] ##Yields training dataset that is the training percentage % sleephealth_validation <- sleephealth[-sample, ] ##Yields validation dataset##8. Normalizing data partitions for k-nearest neighbors Using all of our data (data before partitioning), identifying minimum and maximum values for each variable. There are then used to normalize the data in both our training + validation partitions. We are running min-max normalization (other…)
preProcValues <- preProcess(sleephealth, method = c("range")) ##Uses column minimums & maximums to normalize values around 0 using original datasleephealth_training_norm <- predict(preProcValues, sleephealth_training) #Using the normalizing object, normalize the rows in the dataframe and save it new to a new onesleephealth_validation_norm <- predict(preProcValues, sleephealth_validation) #Using the normalizing object, normalize the rows in the dataframe and save it new to a new onehead(sleephealth_training_norm)## Is_Male Age Salary Sleep.Duration Quality.of.Sleep
## 284 0 1.0000 0.07532685 0.81481481 1.0
## 336 1 0.2500 0.12841569 0.33333333 0.6
## 101 1 0.1875 0.37024971 0.07407407 0.4
## 111 1 0.2500 0.37262339 0.51851852 0.8
## 133 1 0.5000 0.49893747 0.74074074 0.8
## 98 1 0.1875 0.61298441 0.07407407 0.4
## Physical.Activity.Level Stress.Level BMI.Category Systolic.BP Diastolic.BP
## 284 0.7500000 0.0 0.5 0.9259259 1.00
## 336 0.1666667 0.4 0.5 0.4814815 0.45
## 101 0.0000000 1.0 0.0 0.3703704 0.25
## 111 0.5000000 0.2 0.0 0.3703704 0.25
## 133 1.0000000 0.4 0.0 0.5555556 0.50
## 98 0.0000000 1.0 0.0 0.3703704 0.25
## Heart.Rate Daily.Steps Sleep.Disorder
## 284 0.1428571 0.5714286 1
## 336 0.2380952 0.3714286 0
## 101 0.3333333 0.2857143 0
## 111 0.0000000 0.2857143 0
## 133 0.2380952 0.7142857 0
## 98 0.3333333 0.2857143 0head(sleephealth_validation_norm)## Is_Male Age Salary Sleep.Duration Quality.of.Sleep
## 1 1 0.15625 0.2122873 0.5185185 0.8
## 3 0 0.28125 0.2404689 0.5185185 0.8
## 5 0 0.28125 0.1808712 0.5185185 0.8
## 8 0 0.31250 0.2400655 0.5185185 0.8
## 9 0 0.31250 0.2475384 0.5185185 0.8
## 11 0 0.31250 0.2064352 0.5185185 0.8
## Physical.Activity.Level Stress.Level BMI.Category Systolic.BP Diastolic.BP
## 1 0.3333333 0.6 0 0.1111111 0.05
## 3 0.5000000 0.2 0 0.0000000 0.00
## 5 0.5000000 0.2 0 0.0000000 0.00
## 8 0.5000000 0.2 0 0.0000000 0.00
## 9 0.5000000 0.2 0 0.0000000 0.00
## 11 0.5000000 0.2 0 0.0000000 0.00
## Heart.Rate Daily.Steps Sleep.Disorder
## 1 0.1428571 0.5714286 0
## 3 0.1428571 0.5714286 1
## 5 0.1428571 0.5714286 0
## 8 0.1428571 0.5714286 0
## 9 0.1428571 0.5714286 0
## 11 0.1428571 0.5714286 0