# Installing libraries
# KKNN
library(kknn)
# GG Plot
library(ggplot2)
# Read Excel
library(readxl)
# CorrPlot
library(corrplot)
## corrplot 0.92 loaded
spotify_songs <- read_excel("spotify/spotify_songs.xlsx")
## New names:
## • `` -> `...7`
summary(spotify_songs)
## track_id track_name track_artist track_popularity
## Length:32833 Length:32833 Length:32833 Min. : 0.00
## Class :character Class :character Class :character 1st Qu.: 24.00
## Mode :character Mode :character Mode :character Median : 45.00
## Mean : 42.48
## 3rd Qu.: 62.00
## Max. :100.00
##
## track_album_id track_album_name ...7 playlist_name
## Length:32833 Length:32833 Mode:logical Length:32833
## Class :character Class :character NA's:32833 Class :character
## Mode :character Mode :character Mode :character
##
##
##
##
## playlist_id playlist_genre playlist_subgenre danceability
## Length:32833 Length:32833 Length:32833 Min. :0.0000
## Class :character Class :character Class :character 1st Qu.:0.5630
## Mode :character Mode :character Mode :character Median :0.6720
## Mean :0.6548
## 3rd Qu.:0.7610
## Max. :0.9830
##
## energy key loudness mode
## Min. :0.000175 Min. : 0.000 Min. :-46.448 Min. :0.0000
## 1st Qu.:0.581000 1st Qu.: 2.000 1st Qu.: -8.171 1st Qu.:0.0000
## Median :0.721000 Median : 6.000 Median : -6.166 Median :1.0000
## Mean :0.698619 Mean : 5.374 Mean : -6.720 Mean :0.5657
## 3rd Qu.:0.840000 3rd Qu.: 9.000 3rd Qu.: -4.645 3rd Qu.:1.0000
## Max. :1.000000 Max. :11.000 Max. : 1.275 Max. :1.0000
##
## speechiness acousticness instrumentalness liveness
## Min. :0.0000 Min. :0.0000 Min. :0.0000000 Min. :0.0000
## 1st Qu.:0.0410 1st Qu.:0.0151 1st Qu.:0.0000000 1st Qu.:0.0927
## Median :0.0625 Median :0.0804 Median :0.0000161 Median :0.1270
## Mean :0.1071 Mean :0.1753 Mean :0.0847472 Mean :0.1902
## 3rd Qu.:0.1320 3rd Qu.:0.2550 3rd Qu.:0.0048300 3rd Qu.:0.2480
## Max. :0.9180 Max. :0.9940 Max. :0.9940000 Max. :0.9960
##
## valence tempo duration_ms track_album_release_date
## Min. :0.0000 Min. : 0.00 Min. : 4000 Min. : 1960
## 1st Qu.:0.3310 1st Qu.: 99.96 1st Qu.:187819 1st Qu.:39448
## Median :0.5120 Median :121.98 Median :216000 Median :42608
## Mean :0.5106 Mean :120.88 Mean :225800 Mean :38946
## 3rd Qu.:0.6930 3rd Qu.:133.92 3rd Qu.:253585 3rd Qu.:43574
## Max. :0.9910 Max. :239.44 Max. :517810 Max. :43859
## NA's :31
ggplot(spotify_songs, aes(x=track_popularity)) +
geom_histogram(binwidth=5, fill="blue", alpha=0.7) +
ggtitle("Dsitribution of Track Popularity") +
xlab("Rating") +
ylab("Frequency")
# Check for missing values
colSums(is.na(spotify_songs))
## track_id track_name track_artist
## 0 1 0
## track_popularity track_album_id track_album_name
## 0 0 1
## ...7 playlist_name playlist_id
## 32833 0 0
## playlist_genre playlist_subgenre danceability
## 0 0 0
## energy key loudness
## 0 0 0
## mode speechiness acousticness
## 0 0 0
## instrumentalness liveness valence
## 0 0 0
## tempo duration_ms track_album_release_date
## 0 0 31
# Energy Outlier Cleaner
lower_bound_energy <- quantile(spotify_songs$energy, 0.10, na.rm = TRUE)
upper_bound_energy <- quantile(spotify_songs$energy, 0.90, na.rm = TRUE)
spotify_songs$energy[spotify_songs$energy < lower_bound_energy] <- lower_bound_energy
spotify_songs$energy[spotify_songs$energy > upper_bound_energy] <- upper_bound_energy
# Loudness Outlier Cleaner
lower_bound_loudness <- quantile(spotify_songs$loudness, 0.05, na.rm = TRUE)
upper_bound_loudness <- quantile(spotify_songs$loudness, 0.99, na.rm = TRUE)
spotify_songs$loudness[spotify_songs$loudness < lower_bound_loudness] <- lower_bound_loudness
spotify_songs$loudness[spotify_songs$loudness > upper_bound_loudness] <- upper_bound_loudness
# Spilting Data
set.seed(2023)
train_indices <- sample(1:NROW(spotify_songs),NROW(spotify_songs)*0.70)
# Create the training set
train_data <- spotify_songs[train_indices, ]
# Create the testing set
test_data <- spotify_songs[-train_indices, ]
# Creating the model
lm_model <- lm(track_popularity ~ loudness + valence, data = spotify_songs)
# Summary stats
summary(lm_model)
##
## Call:
## lm(formula = track_popularity ~ loudness + valence, data = spotify_songs)
##
## Residuals:
## Min 1Q Median 3Q Max
## -46.497 -18.386 3.028 19.490 58.765
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 44.61767 0.48794 91.440 <2e-16 ***
## loudness 0.57656 0.05219 11.047 <2e-16 ***
## valence 3.27328 0.59058 5.543 3e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 24.92 on 32830 degrees of freedom
## Multiple R-squared: 0.004803, Adjusted R-squared: 0.004743
## F-statistic: 79.23 on 2 and 32830 DF, p-value: < 2.2e-16
# Coefficient stats
coefficients <- coef(lm_model)
print(coefficients)
## (Intercept) loudness valence
## 44.6176721 0.5765613 3.2732823
Testing the MSE
lm_track_popularity <- mean((lm_model$fitted.values - spotify_songs$track_popularity)^2)
print(paste("Training MSE for Linear Model:", round(lm_track_popularity, 2)))
## [1] "Training MSE for Linear Model: 621.19"
# KNN modeling wtih k values 5, 10, and 15
knn_model_5 <- kknn(track_popularity ~ loudness + valence, train = train_data, test = train_data, k = 5)
summary(knn_model_5)
##
## Call:
## kknn(formula = track_popularity ~ loudness + valence, train = train_data, test = train_data, k = 5)
##
## Response: "continuous"
knn_model_10 <- kknn(track_popularity ~ loudness + valence, train = train_data, test = train_data, k = 10)
summary(knn_model_10)
##
## Call:
## kknn(formula = track_popularity ~ loudness + valence, train = train_data, test = train_data, k = 10)
##
## Response: "continuous"
knn_model_15 <- kknn(track_popularity ~ loudness + valence, train = train_data, test = train_data, k = 15)
summary(knn_model_15)
##
## Call:
## kknn(formula = track_popularity ~ loudness + valence, train = train_data, test = train_data, k = 15)
##
## Response: "continuous"
Testing the MSE
knn_model_5 <- mean((knn_model_5$fitted.values - train_data$track_popularity)^2)
print(paste("Training MSE for KNN 5:", round(knn_model_5, 2)))
## [1] "Training MSE for KNN 5: 282.96"
knn_model_10 <- mean((knn_model_10$fitted.values - train_data$track_popularity)^2)
print(paste("Training MSE for KNN 10:", round(knn_model_10, 2)))
## [1] "Training MSE for KNN 10: 412.26"
knn_model_15 <- mean((knn_model_15$fitted.values - train_data$track_popularity)^2)
print(paste("Training MSE for KNN 15:", round(knn_model_15, 2)))
## [1] "Training MSE for KNN 15: 468.3"
KNN MSE
print(paste("Training MSE for KNN 10:", round(knn_model_10, 2)))
## [1] "Training MSE for KNN 10: 412.26"
LM MSE
print(paste("Training MSE for Linear Model:", round(lm_track_popularity, 2)))
## [1] "Training MSE for Linear Model: 621.19"
The KNN model had a better MSE score. The MSE is still not great in terms of correlation, but KNN was still better
The linear model is easier to interpret and is an easier fit for data. But knn has a more flexible approach. The disadvantages are that linear regression will be a poor fit if the data does not form a correlation. KNN is a bit more complex to interpret.
I would recommend KNN since there doesn’t seem to be a correlation between variables.
What variables are most strongly correlated with target? Instrumentalness
How does the value of k in KNN affect the model’s performance (in terms of training MSE and testing MSE)? The MSE seemed to go down the higher the k value went (though not by much).
What assumptions are being made when we use linear regression? Are they met in this dataset? Just describe what you observe from the diagnostic plots. Linear assumptions are: relationship between x and y is linear, variance of residual is the same for any value of x, observations are independent of each other, and for any fixed value of X, Y is normally distributed.
We can tell if the residuals are normally dsitributed through this plot
plot(lm_model, 2)
The plot should ideally have the residuals following in a straight line. In this case, they are not.
lm_model_interation <- lm(track_popularity ~ speechiness * danceability, data = train_data)
summary(lm_model_interation)
##
## Call:
## lm(formula = track_popularity ~ speechiness * danceability, data = train_data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -47.614 -18.329 3.049 19.576 57.080
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 37.072 1.106 33.505 < 2e-16 ***
## speechiness -19.821 7.866 -2.520 0.0117 *
## danceability 8.336 1.693 4.924 8.52e-07 ***
## speechiness:danceability 28.344 11.415 2.483 0.0130 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 24.89 on 22979 degrees of freedom
## Multiple R-squared: 0.004637, Adjusted R-squared: 0.004507
## F-statistic: 35.69 on 3 and 22979 DF, p-value: < 2.2e-16
There is less variance explained in the interaction model than the no interaction. I would say this model is less reliable and a worse fit for my data.
# Track_popularity does not have outliers
# Danceability
lower_bound_danceability <- quantile(spotify_songs$danceability, 0.01, na.rm = TRUE)
upper_bound_danceability <- quantile(spotify_songs$danceability, 0.99, na.rm = TRUE)
spotify_songs$danceability[spotify_songs$danceability < lower_bound_danceability] <- lower_bound_danceability
spotify_songs$danceability[spotify_songs$danceability > upper_bound_danceability] <- upper_bound_danceability
# Energy
lower_bound_energy <- quantile(spotify_songs$energy, 0.10, na.rm = TRUE)
upper_bound_energy <- quantile(spotify_songs$energy, 0.90, na.rm = TRUE)
spotify_songs$energy[spotify_songs$energy < lower_bound_energy] <- lower_bound_energy
spotify_songs$energy[spotify_songs$energy > upper_bound_energy] <- upper_bound_energy
# Loudness
lower_bound_loudness <- quantile(spotify_songs$loudness, 0.05, na.rm = TRUE)
upper_bound_loudness <- quantile(spotify_songs$loudness, 0.99, na.rm = TRUE)
spotify_songs$loudness[spotify_songs$loudness < lower_bound_loudness] <- lower_bound_loudness
spotify_songs$loudness[spotify_songs$loudness > upper_bound_loudness] <- upper_bound_loudness
# Mode does not have outliers
# Speechiness
lower_bound_speechiness <- quantile(spotify_songs$speechiness, 0.01, na.rm = TRUE)
upper_bound_speechiness <- quantile(spotify_songs$speechiness, 0.90, na.rm = TRUE)
spotify_songs$speechiness[spotify_songs$speechiness < lower_bound_speechiness] <- lower_bound_speechiness
spotify_songs$speechiness[spotify_songs$speechiness > upper_bound_speechiness] <- upper_bound_speechiness
# Acousticness
lower_bound_acousticness <- quantile(spotify_songs$acousticness, 0.01, na.rm = TRUE)
upper_bound_acousticness <- quantile(spotify_songs$acousticness, 0.90, na.rm = TRUE)
spotify_songs$acousticness[spotify_songs$acousticness < lower_bound_acousticness] <- lower_bound_acousticness
spotify_songs$acousticness[spotify_songs$acousticness > upper_bound_acousticness] <- upper_bound_acousticness
# Instrumentalness
lower_bound_instrumentalness <- quantile(spotify_songs$instrumentalness, 0.01, na.rm = TRUE)
upper_bound_instrumentalness <- quantile(spotify_songs$instrumentalness, 0.75, na.rm = TRUE)
spotify_songs$instrumentalness[spotify_songs$instrumentalness < lower_bound_instrumentalness] <- lower_bound_instrumentalness
spotify_songs$instrumentalness[spotify_songs$instrumentalness > upper_bound_instrumentalness] <- upper_bound_instrumentalness
# Liveness
lower_bound_liveness <- quantile(spotify_songs$liveness, 0.01, na.rm = TRUE)
upper_bound_liveness <- quantile(spotify_songs$liveness, 0.90, na.rm = TRUE)
spotify_songs$liveness[spotify_songs$liveness < lower_bound_liveness] <- lower_bound_liveness
spotify_songs$liveness[spotify_songs$liveness > upper_bound_liveness] <- upper_bound_liveness
# Valence does not have outliers
# Tempo
lower_bound_tempo <- quantile(spotify_songs$tempo, 0.05, na.rm = TRUE)
upper_bound_tempo <- quantile(spotify_songs$tempo, 0.90, na.rm = TRUE)
spotify_songs$tempo[spotify_songs$tempo < lower_bound_tempo] <- lower_bound_tempo
spotify_songs$tempo[spotify_songs$tempo > upper_bound_tempo] <- upper_bound_tempo
# Duration_ms
lower_bound_duration_ms <- quantile(spotify_songs$duration_ms, 0.01, na.rm = TRUE)
upper_bound_duration_ms <- quantile(spotify_songs$duration_ms, 0.95, na.rm = TRUE)
spotify_songs$duration_ms[spotify_songs$duration_ms < lower_bound_duration_ms] <- lower_bound_duration_ms
spotify_songs$duration_ms[spotify_songs$duration_ms > upper_bound_duration_ms] <- upper_bound_duration_ms
lm_model_win <- lm(track_popularity ~ danceability, data = spotify_songs)
summary(lm_model_win)
##
## Call:
## lm(formula = track_popularity ~ danceability, data = spotify_songs)
##
## Residuals:
## Min 1Q Median 3Q Max
## -45.549 -18.410 2.944 19.475 57.135
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 35.0478 0.6438 54.44 <2e-16 ***
## danceability 11.3403 0.9600 11.81 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 24.93 on 32831 degrees of freedom
## Multiple R-squared: 0.004233, Adjusted R-squared: 0.004202
## F-statistic: 139.6 on 1 and 32831 DF, p-value: < 2.2e-16
There is slightly more variance explained as indicated by R^2
How could feature scaling (standardization) affect the KNN model? Feature scaling helps prevent dominant numbers from having a greater influence in the KNN model.
What insights can you derive from comparing the linear regression and KNN models? Which model would you recommend the most and Why? I would recommend KNN models for this dataset, since linear regression doesn’t seem to be a true fit. The assumptions are not met.