library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.3 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.3 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(tidymodels)## ── Attaching packages ────────────────────────────────────── tidymodels 1.1.1 ──
## ✔ broom 1.0.5 ✔ rsample 1.2.0
## ✔ dials 1.2.0 ✔ tune 1.1.2
## ✔ infer 1.0.5 ✔ workflows 1.1.3
## ✔ modeldata 1.2.0 ✔ workflowsets 1.0.1
## ✔ parsnip 1.1.1 ✔ yardstick 1.2.0
## ✔ recipes 1.0.8
## ── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
## ✖ scales::discard() masks purrr::discard()
## ✖ dplyr::filter() masks stats::filter()
## ✖ recipes::fixed() masks stringr::fixed()
## ✖ dplyr::lag() masks stats::lag()
## ✖ yardstick::spec() masks readr::spec()
## ✖ recipes::step() masks stats::step()
## • Use tidymodels_prefer() to resolve common conflicts.library(h2o)## Warning: package 'h2o' was built under R version 4.3.3##
## ----------------------------------------------------------------------
##
## Your next step is to start H2O:
## > h2o.init()
##
## For H2O package documentation, ask for help:
## > ??h2o
##
## After starting H2O, you can use the Web UI at http://localhost:54321
## For more information visit https://docs.h2o.ai
##
## ----------------------------------------------------------------------
##
##
## Attaching package: 'h2o'
##
## The following objects are masked from 'package:lubridate':
##
## day, hour, month, week, year
##
## The following objects are masked from 'package:stats':
##
## cor, sd, var
##
## The following objects are masked from 'package:base':
##
## %*%, %in%, &&, ||, apply, as.factor, as.numeric, colnames,
## colnames<-, ifelse, is.character, is.factor, is.numeric, log,
## log10, log1p, log2, round, signif, truncPrompt 1: I have a dataset called climbers_data that looks like this
climbers_data <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2020/2020-09-22/members.csv')## Rows: 76519 Columns: 21
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (10): expedition_id, member_id, peak_id, peak_name, season, sex, citizen...
## dbl (5): year, age, highpoint_metres, death_height_metres, injury_height_me...
## lgl (6): hired, success, solo, oxygen_used, died, injured
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.climbers_data %>% glimpse() ## Rows: 76,519
## Columns: 21
## $ expedition_id <chr> "AMAD78301", "AMAD78301", "AMAD78301", "AMAD78301…
## $ member_id <chr> "AMAD78301-01", "AMAD78301-02", "AMAD78301-03", "…
## $ peak_id <chr> "AMAD", "AMAD", "AMAD", "AMAD", "AMAD", "AMAD", "…
## $ peak_name <chr> "Ama Dablam", "Ama Dablam", "Ama Dablam", "Ama Da…
## $ year <dbl> 1978, 1978, 1978, 1978, 1978, 1978, 1978, 1978, 1…
## $ season <chr> "Autumn", "Autumn", "Autumn", "Autumn", "Autumn",…
## $ sex <chr> "M", "M", "M", "M", "M", "M", "M", "M", "M", "M",…
## $ age <dbl> 40, 41, 27, 40, 34, 25, 41, 29, 35, 37, 23, 44, 2…
## $ citizenship <chr> "France", "France", "France", "France", "France",…
## $ expedition_role <chr> "Leader", "Deputy Leader", "Climber", "Exp Doctor…
## $ hired <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, …
## $ highpoint_metres <dbl> NA, 6000, NA, 6000, NA, 6000, 6000, 6000, NA, 681…
## $ success <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, …
## $ solo <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, …
## $ oxygen_used <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, …
## $ died <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, …
## $ death_cause <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ death_height_metres <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ injured <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, …
## $ injury_type <chr> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…
## $ injury_height_metres <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, N…The goal is to help predict died for members.
Please write R code to create a classification model that predicts the probability of died.
# Load data
climbers_data_clean <- climbers_data
# Preprocess data
climbers_data_processed <- climbers_data %>%
select(-expedition_id, -member_id, -peak_id, -peak_name) %>% # Remove unnecessary columns
mutate(success = as.factor(success), # Convert success to factor
solo = as.factor(solo), # Convert solo to factor
oxygen_used = as.factor(oxygen_used), # Convert oxygen_used to factor
died = as.factor(died), # Convert died to factor
injured = as.factor(injured)) # Convert injured to factor
# Set seed for reproducibility
set.seed(123)
# Split data into training (80%) and testing (20%) sets
data_split <- initial_split(climbers_data_processed, prop = 0.8, strata = died)
train_data <- training(data_split)
test_data <- testing(data_split)
# Initialize h2o
h2o.init()## Connection successful!
##
## R is connected to the H2O cluster:
## H2O cluster uptime: 4 hours 21 minutes
## H2O cluster timezone: America/New_York
## H2O data parsing timezone: UTC
## H2O cluster version: 3.44.0.3
## H2O cluster version age: 4 months and 18 days
## H2O cluster name: H2O_started_from_R_OPend_eji420
## H2O cluster total nodes: 1
## H2O cluster total memory: 3.61 GB
## H2O cluster total cores: 12
## H2O cluster allowed cores: 12
## H2O cluster healthy: TRUE
## H2O Connection ip: localhost
## H2O Connection port: 54321
## H2O Connection proxy: NA
## H2O Internal Security: FALSE
## R Version: R version 4.3.1 (2023-06-16 ucrt)## Warning in h2o.clusterInfo():
## Your H2O cluster version is (4 months and 18 days) old. There may be a newer version available.
## Please download and install the latest version from: https://h2o-release.s3.amazonaws.com/h2o/latest_stable.html# Convert data to h2o format
train_h2o <- as.h2o(train_data)##
|
| | 0%
|
|======================================================================| 100%test_h2o <- as.h2o(test_data)##
|
| | 0%
|
|======================================================================| 100%# Define predictors and response variable
predictors <- setdiff(colnames(train_h2o), c("died"))
response <- "died"
# Train AutoML model
aml <- h2o.automl(x = predictors,
y = response,
training_frame = train_h2o,
leaderboard_frame = test_h2o,
max_runtime_secs = 30, # Set maximum runtime
seed = 123)##
|
| | 0%
|
|== | 3%
## 16:18:58.126: AutoML: XGBoost is not available; skipping it.
## 16:18:58.126: _train param, Dropping bad and constant columns: [expedition_role, season, death_cause, sex, citizenship, injury_type]
## 16:18:58.557: _train param, Dropping bad and constant columns: [expedition_role, season, death_cause, sex, citizenship, injury_type]
## 16:18:59.809: _train param, Dropping unused columns: [expedition_role, season, death_cause, sex, citizenship, injury_type]
|
|======= | 10%
## 16:19:00.625: _train param, Dropping bad and constant columns: [expedition_role, season, death_cause, sex, citizenship, injury_type]
## 16:19:01.276: _train param, Dropping bad and constant columns: [expedition_role, season, death_cause, sex, citizenship, injury_type]
|
|============ | 17%
## 16:19:02.323: _train param, Dropping bad and constant columns: [expedition_role, season, death_cause, sex, citizenship, injury_type]
## 16:19:03.341: _train param, Dropping bad and constant columns: [expedition_role, season, death_cause, sex, citizenship, injury_type]
|
|================= | 24%
## 16:19:05.59: _train param, Dropping unused columns: [expedition_role, season, death_cause, sex, citizenship, injury_type]
## 16:19:06.3: _train param, Dropping unused columns: [expedition_role, season, death_cause, sex, citizenship, injury_type]
|
|====================== | 31%
## 16:19:07.142: _train param, Dropping bad and constant columns: [expedition_role, season, death_cause, sex, citizenship, injury_type]
## 16:19:07.631: _train param, Dropping bad and constant columns: [expedition_role, season, death_cause, sex, citizenship, injury_type]
## 16:19:08.213: _train param, Dropping bad and constant columns: [expedition_role, season, death_cause, sex, citizenship, injury_type]
|
|=========================== | 38%
## 16:19:09.26: _train param, Dropping unused columns: [expedition_role, season, death_cause, sex, citizenship, injury_type]
## 16:19:09.741: _train param, Dropping unused columns: [expedition_role, season, death_cause, sex, citizenship, injury_type]
|
|================================ | 45%
|
|==================================== | 52%
|
|========================================= | 59%
|
|============================================== | 66%
|
|=================================================== | 73%
|
|======================================================== | 80%
|
|============================================================== | 88%
|
|=================================================================== | 95%
## 16:19:25.776: _train param, Dropping unused columns: [expedition_role, season, death_cause, sex, citizenship, injury_type]
## 16:19:26.341: _train param, Dropping unused columns: [expedition_role, season, death_cause, sex, citizenship, injury_type]
|
|======================================================================| 100%# View AutoML leaderboard
print(aml@leaderboard)## model_id auc logloss aucpr
## 1 GBM_5_AutoML_10_20240509_161858 0.9991879 0.002078241 0.9921059
## 2 GBM_grid_1_AutoML_10_20240509_161858_model_9 0.9991712 0.001838259 0.9913093
## 3 GBM_grid_1_AutoML_10_20240509_161858_model_4 0.9991279 0.009240130 0.9297628
## 4 GBM_4_AutoML_10_20240509_161858 0.9989083 0.001733668 0.9920909
## 5 GBM_grid_1_AutoML_10_20240509_161858_model_3 0.9987784 0.019474249 0.8867014
## 6 GBM_1_AutoML_10_20240509_161858 0.9987706 0.001942950 0.9908809
## mean_per_class_error rmse mse
## 1 0.012254902 0.01878381 0.0003528315
## 2 0.007352941 0.01548552 0.0002398015
## 3 0.007518504 0.02477269 0.0006136862
## 4 0.007386054 0.01592136 0.0002534897
## 5 0.015070121 0.03925796 0.0015411871
## 6 0.007386054 0.01695634 0.0002875174
##
## [29 rows x 7 columns]# Get best model from AutoML
best_model <- aml@leader
# Make predictions on test data
predictions <- h2o.predict(best_model, test_h2o)##
|
| | 0%
|
|======================================================================| 100%# View predictions
head(predictions)## predict FALSE TRUE
## 1 FALSE 0.9996404 0.0003596237
## 2 FALSE 0.9992763 0.0007237478
## 3 FALSE 0.9992132 0.0007868431
## 4 FALSE 0.9992132 0.0007868431
## 5 FALSE 0.9996660 0.0003339674
## 6 FALSE 0.9997021 0.0002979313