# for Core packages
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ 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 errors# for financial analysis
library(tidyquant)## Loading required package: PerformanceAnalytics
## Loading required package: xts
## Loading required package: zoo
##
## Attaching package: 'zoo'
##
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
##
##
## ######################### Warning from 'xts' package ##########################
## # #
## # The dplyr lag() function breaks how base R's lag() function is supposed to #
## # work, which breaks lag(my_xts). Calls to lag(my_xts) that you type or #
## # source() into this session won't work correctly. #
## # #
## # Use stats::lag() to make sure you're not using dplyr::lag(), or you can add #
## # conflictRules('dplyr', exclude = 'lag') to your .Rprofile to stop #
## # dplyr from breaking base R's lag() function. #
## # #
## # Code in packages is not affected. It's protected by R's namespace mechanism #
## # Set `options(xts.warn_dplyr_breaks_lag = FALSE)` to suppress this warning. #
## # #
## ###############################################################################
##
## Attaching package: 'xts'
##
## The following objects are masked from 'package:dplyr':
##
## first, last
##
##
## Attaching package: 'PerformanceAnalytics'
##
## The following object is masked from 'package:graphics':
##
## legend
##
## Loading required package: quantmod
## Loading required package: TTR
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo# for times series
library(timetk)
library(h2o)##
## ----------------------------------------------------------------------
##
## 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, trunclibrary(tidymodels)## ── Attaching packages ────────────────────────────────────── tidymodels 1.2.0 ──
## ✔ broom 1.0.5 ✔ rsample 1.2.1
## ✔ dials 1.2.1 ✔ tune 1.2.1
## ✔ infer 1.0.7 ✔ workflows 1.1.4
## ✔ modeldata 1.4.0 ✔ workflowsets 1.1.0
## ✔ parsnip 1.2.1 ✔ yardstick 1.3.1
## ✔ recipes 1.0.10## Warning: package 'modeldata' was built under R version 4.3.3## ── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
## ✖ scales::discard() masks purrr::discard()
## ✖ dplyr::filter() masks stats::filter()
## ✖ xts::first() masks dplyr::first()
## ✖ recipes::fixed() masks stringr::fixed()
## ✖ dplyr::lag() masks stats::lag()
## ✖ xts::last() masks dplyr::last()
## ✖ dials::momentum() masks TTR::momentum()
## ✖ yardstick::spec() masks readr::spec()
## ✖ recipes::step() masks stats::step()
## • Use suppressPackageStartupMessages() to eliminate package startup messagesGoal is to automate building and tuning a classification model to predict state unemployment, using the h2o::h2o.automl.
The following is the replication of Matt Dancho’s tutorial on this page
start_date <- "1989-01-01"
symbols_txt <- c("CTICLAIMS", # Connecticut
"MEICLAIMS", # Maine
"MAICLAIMS", # Massachusetts
"NHICLAIMS", # New Hampshire
"RIICLAIMS", # Rhode Island
"VTICLAIMS") # Vermont
claims_tbl <- tq_get(symbols_txt, get = "economic.data", from = start_date) %>%
mutate(symbol = fct_recode(symbol,
"Connecticut" = "CTICLAIMS",
"Maine" = "MEICLAIMS",
"Massachusetts" = "MAICLAIMS",
"New Hampshire" = "NHICLAIMS",
"Rhode Island" = "RIICLAIMS",
"Vermont" = "VTICLAIMS")) %>%
rename(claims = price)data <- claims_tbl
set.seed(1234)
data_split <- initial_split(data, strata = "claims")
train_tbl <- training(data_split)
test_tbl <- testing(data_split)recipe_obj <- recipe(claims ~ ., data = train_tbl) %>%
# Remove zero variance variables
step_zv(all_predictors()) h2o.init()## Connection successful!
##
## R is connected to the H2O cluster:
## H2O cluster uptime: 2 days 4 hours
## H2O cluster timezone: America/New_York
## H2O data parsing timezone: UTC
## H2O cluster version: 3.44.0.3
## H2O cluster version age: 10 months and 30 days
## H2O cluster name: H2O_started_from_R_kajsabergstrand_fhp551
## H2O cluster total nodes: 1
## H2O cluster total memory: 1.44 GB
## H2O cluster total cores: 4
## H2O cluster allowed cores: 4
## H2O cluster healthy: TRUE
## H2O Connection ip: localhost
## H2O Connection port: 54321
## H2O Connection proxy: NA
## H2O Internal Security: FALSE
## R Version: R version 4.3.2 (2023-10-31)## Warning in h2o.clusterInfo():
## Your H2O cluster version is (10 months and 30 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.htmlsplit.h2o <- h2o.splitFrame(as.h2o(train_tbl), ratios = c(0.85), seed = 2345)##
|
| | 0%
|
|======================================================================| 100%train_h2o <- split.h2o[[1]]
valid_h2o <- split.h2o[[2]]
test_h2o <- as.h2o(test_tbl)##
|
| | 0%
|
|======================================================================| 100%y <- "claims"
x <- setdiff(names(train_tbl), y)
models_h2o <- h2o.automl(
x = x,
y = y,
training_frame = train_h2o,
validation_frame = valid_h2o,
leaderboard_frame = test_h2o,
#max_runtime_secs = 30,
max_models = 10,
exclude_algos = "DeepLearning",
nfolds = 5,
seed = 3456
)##
|
| | 0%
## 19:43:22.79: User specified a validation frame with cross-validation still enabled. Please note that the models will still be validated using cross-validation only, the validation frame will be used to provide purely informative validation metrics on the trained models.
|
|==== | 5%
|
|===== | 7%
|
|===== | 8%
|
|======= | 10%
|
|========= | 13%
|
|=========== | 15%
|
|============ | 17%
|
|============= | 19%
|
|============== | 21%
|
|================== | 25%
|
|====================== | 31%
|
|======================= | 33%
|
|======================================================================| 100%examine the output of h2o.automl
models_h2o %>% typeof()## [1] "S4"models_h2o %>% slotNames()## [1] "project_name" "leader" "leaderboard" "event_log"
## [5] "modeling_steps" "training_info"models_h2o@leaderboard## model_id rmse mse
## 1 StackedEnsemble_AllModels_1_AutoML_18_20241119_194322 1682.939 2832283
## 2 StackedEnsemble_BestOfFamily_1_AutoML_18_20241119_194322 1755.924 3083268
## 3 XGBoost_2_AutoML_18_20241119_194322 1756.180 3084169
## 4 XGBoost_1_AutoML_18_20241119_194322 1775.195 3151319
## 5 XGBoost_3_AutoML_18_20241119_194322 1792.369 3212586
## 6 GBM_1_AutoML_18_20241119_194322 3111.325 9680342
## mae rmsle mean_residual_deviance
## 1 675.6157 NaN 2832283
## 2 682.4564 NaN 3083268
## 3 682.4860 NaN 3084169
## 4 690.5329 NaN 3151319
## 5 754.4323 NaN 3212586
## 6 1101.7994 NaN 9680342
##
## [12 rows x 6 columns]models_h2o@leader## Model Details:
## ==============
##
## H2ORegressionModel: stackedensemble
## Model ID: StackedEnsemble_AllModels_1_AutoML_18_20241119_194322
## Model Summary for Stacked Ensemble:
## key value
## 1 Stacking strategy cross_validation
## 2 Number of base models (used / total) 3/10
## 3 # GBM base models (used / total) 0/4
## 4 # XGBoost base models (used / total) 3/3
## 5 # DRF base models (used / total) 0/2
## 6 # GLM base models (used / total) 0/1
## 7 Metalearner algorithm GLM
## 8 Metalearner fold assignment scheme Random
## 9 Metalearner nfolds 5
## 10 Metalearner fold_column NA
## 11 Custom metalearner hyperparameters None
##
##
## H2ORegressionMetrics: stackedensemble
## ** Reported on training data. **
##
## MSE: 1505490
## RMSE: 1226.984
## MAE: 554.2382
## RMSLE: NaN
## Mean Residual Deviance : 1505490
##
##
## H2ORegressionMetrics: stackedensemble
## ** Reported on validation data. **
##
## MSE: 2212217
## RMSE: 1487.352
## MAE: 630.5789
## RMSLE: NaN
## Mean Residual Deviance : 2212217
##
##
## H2ORegressionMetrics: stackedensemble
## ** Reported on cross-validation data. **
## ** 5-fold cross-validation on training data (Metrics computed for combined holdout predictions) **
##
## MSE: 4246594
## RMSE: 2060.727
## MAE: 693.0651
## RMSLE: NaN
## Mean Residual Deviance : 4246594
##
##
## Cross-Validation Metrics Summary:
## mean sd cv_1_valid
## mae 692.431200 53.515842 751.971070
## mean_residual_deviance 3994871.800000 4437048.000000 11890053.000000
## mse 3994871.800000 4437048.000000 11890053.000000
## null_deviance 34643366000.000000 18328420400.000000 66062455000.000000
## r2 0.858098 0.075267 0.738124
## residual_deviance 5759607300.000000 6479182800.000000 17300027400.000000
## rmse 1818.641800 926.966550 3448.195600
## rmsle NA 0.000000 NA
## cv_2_valid cv_3_valid cv_4_valid
## mae 677.155900 675.368960 619.600200
## mean_residual_deviance 2210457.200000 2146556.800000 1259065.000000
## mse 2210457.200000 2146556.800000 1259065.000000
## null_deviance 35163509000.000000 23613292500.000000 27020349400.000000
## r2 0.909278 0.865259 0.931908
## residual_deviance 3189689860.000000 3181197060.000000 1836975870.000000
## rmse 1486.760700 1465.113200 1122.080700
## rmsle NA NA NA
## cv_5_valid
## mae 738.059900
## mean_residual_deviance 2468226.000000
## mse 2468226.000000
## null_deviance 21357226000.000000
## r2 0.845924
## residual_deviance 3290145280.000000
## rmse 1571.058800
## rmsle NA?h2o.getModel
?h2o.saveModel
?h2o.loadModel
h2o.getModel("StackedEnsemble_BestOfFamily_1_AutoML_15_20241119_192822") %>%
h2o.saveModel("h20_models1/")## [1] "/Users/kajsabergstrand/Desktop/PSU_DAT3100/11_module13/h20_models1/StackedEnsemble_BestOfFamily_1_AutoML_15_20241119_192822"best_model <- h2o.loadModel("h20_models1/StackedEnsemble_BestOfFamily_1_AutoML_15_20241119_192822")predictions <- h2o.predict(best_model, newdata = test_h2o)##
|
| | 0%
|
|======================================================================| 100%predictions_tbl <- predictions %>%
as_tibble()
predictions_tbl %>%
bind_cols(test_tbl)## # A tibble: 2,808 × 4
## predict symbol date claims
## <dbl> <fct> <date> <int>
## 1 5427. Connecticut 1989-01-14 6503
## 2 4685. Connecticut 1989-01-28 4663
## 3 3443. Connecticut 1989-04-08 3610
## 4 3351. Connecticut 1989-04-29 3191
## 5 3351. Connecticut 1989-05-06 3224
## 6 4743. Connecticut 1989-07-01 5232
## 7 4356. Connecticut 1989-08-26 3373
## 8 3789. Connecticut 1989-09-02 2902
## 9 3789. Connecticut 1989-09-09 2856
## 10 3300. Connecticut 1989-09-16 3025
## # ℹ 2,798 more rowsperformance_h2o <- h2o.performance(best_model, newdata = test_h2o)
typeof(performance_h2o)## [1] "S4"slotNames(performance_h2o)## [1] "algorithm" "on_train" "on_valid" "on_xval" "metrics"performance_h2o@metrics## $model
## $model$`__meta`
## $model$`__meta`$schema_version
## [1] 3
##
## $model$`__meta`$schema_name
## [1] "ModelKeyV3"
##
## $model$`__meta`$schema_type
## [1] "Key<Model>"
##
##
## $model$name
## [1] "StackedEnsemble_BestOfFamily_1_AutoML_15_20241119_192822"
##
## $model$type
## [1] "Key<Model>"
##
## $model$URL
## [1] "/3/Models/StackedEnsemble_BestOfFamily_1_AutoML_15_20241119_192822"
##
##
## $model_checksum
## [1] "2488863327570913280"
##
## $frame
## $frame$name
## [1] "test_tbl_sid_8f97_3"
##
##
## $frame_checksum
## [1] "4281387059679466868"
##
## $description
## NULL
##
## $scoring_time
## [1] 1.732063e+12
##
## $predictions
## NULL
##
## $MSE
## [1] 3648706
##
## $RMSE
## [1] 1910.159
##
## $nobs
## [1] 2808
##
## $custom_metric_name
## NULL
##
## $custom_metric_value
## [1] 0
##
## $r2
## [1] 0.837092
##
## $mean_residual_deviance
## [1] 3648706
##
## $mae
## [1] 757.018
##
## $rmsle
## [1] "NaN"
##
## $residual_deviance
## [1] 10245566283
##
## $null_deviance
## [1] 62892676851
##
## $AIC
## [1] 50403.31
##
## $loglikelihood
## [1] 0
##
## $null_degrees_of_freedom
## [1] 2807
##
## $residual_degrees_of_freedom
## [1] 2806h2o.auc(performance_h2o)## NULL#h2o.confusionMatrix(performance_h2o)
#h2o.metric(performance_h2o)