randomforests.r

# Training a Random Forest in R - used in blog post:
# https://towardsdatascience.com/data-science-tutorials-training-a-random-forest-in-r-a883cc1bacd1

library(dplyr)
library(randomForest) 
library(ranger)
library(Metrics)

# Load london bike csv
london_bike <- read.csv('./london_merged.csv')

# Using a function to split into train and test
train_test_split <- function(data, percentage) {
  
  data_with_row_id <- data %>% 
    mutate(id = row_number())
  
  set.seed(1234)
  training_data <- data_with_row_id %>%
    sample_frac(percentage)
  test_data <- anti_join(
    data_with_row_id,
    training_data,
    by='id'
  )
  
  training_data$id <- NULL
  test_data$id <- NULL
  
  return (list(training_data, test_data))
}

# Keeping 80% for the training set
training_data <- train_test_split(london_bike, 0.8)[[1]]
test_data <- train_test_split(london_bike, 0.8)[[2]]

# Subsetting only target and features
training_data <- training_data[,c('t1','t2','hum',
                                  'wind_speed','weather_code',
                                  'is_holiday','is_weekend',
                                  'season', 'cnt')]
test_data <- test_data[,c('t1','t2','hum',
                          'wind_speed','weather_code',
                          'is_holiday','is_weekend',
                          'season', 'cnt')]

# Fitting Random Forest

set.seed(1234)
rf <- randomForest(formula = cnt ~ ., 
                   data = training_data,
                   ntree = 100)

# Timing the execution
system.time(
  randomForest(cnt ~ ., data = training_data,
                         ntree = 100))

# Adding a new hyperparameter
rf_2 <- randomForest(formula = cnt ~ ., 
                     data = training_data,
                     ntree = 100, 
                     nodesize = 10)

# Assessing performance
rmse(test_data$cnt, predict(rf, test_data))

# Implementation with Ranger

set.seed(1234)
rf_ranger <- ranger(
  formula = cnt ~ ., 
  data = training_data, 
  num.trees=100)

# Let's check the execution time
system.time(rf_ranger <- ranger(
              formula = cnt ~ ., 
              data = training_data, 
              num.trees=100))

# Adding hyperparameters
rf_ranger_2 <- ranger(formula = cnt ~ ., 
                      data = training_data, 
                      num.trees=100,
                      min.node.size = 10)

# Assessing performance
rmse(
  test_data$cnt, 
  predict(rf_ranger, test_data)$predictions
  )