# for Core packages
library(tidyverse)## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.4.4 ✔ purrr 1.0.2
## ✔ tibble 3.2.1 ✔ dplyr 1.1.4
## ✔ tidyr 1.3.0 ✔ stringr 1.5.0
## ✔ readr 2.1.3 ✔ forcats 1.0.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()# for financial analysis
library(tidyquant)## Loading required package: lubridate
##
## Attaching package: 'lubridate'
##
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union
##
## 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
##
##
## 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)
# for h2o
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 1.1.1 ──
## ✔ broom 1.0.5 ✔ rsample 1.2.0
## ✔ dials 1.2.0 ✔ tune 1.1.2
## ✔ infer 1.0.6 ✔ workflows 1.1.4
## ✔ modeldata 1.3.0 ✔ workflowsets 1.0.1
## ✔ parsnip 1.2.0 ✔ yardstick 1.2.0
## ✔ recipes 1.0.10
## ── 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()
## • Search for functions across packages at https://www.tidymodels.org/find/library(umap)Goal: Apply Matt Dancho’s tutorial to state unemployment initial claims of New England states.
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)set.seed(1234)
data_split <- initial_split(claims_tbl, 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()) # Initialize h20
h2o.init()## Connection successful!
##
## R is connected to the H2O cluster:
## H2O cluster uptime: 11 days 21 hours
## 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 16 days
## H2O cluster name: H2O_started_from_R_stephenmorris_fhp551
## H2O cluster total nodes: 1
## H2O cluster total memory: 0.91 GB
## H2O cluster total cores: 8
## H2O cluster allowed cores: 8
## H2O cluster healthy: TRUE
## H2O Connection ip: localhost
## H2O Connection port: 54321
## H2O Connection proxy: NA
## H2O Internal Security: FALSE
## R Version: R version 4.2.2 (2022-10-31)## Warning in h2o.clusterInfo():
## Your H2O cluster version is (4 months and 16 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,
nfolds = 5,
seed = 3456
)##
|
| | 0%
|
|== | 3%
## 13:29:45.336: 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.
|
|======= | 10%
|
|============ | 17%
|
|================= | 24%
|
|===================== | 30%
|
|========================== | 37%
|
|=============================== | 44%
|
|=================================== | 51%
|
|======================================== | 57%
|
|============================================= | 64%
|
|================================================== | 71%
|
|====================================================== | 78%
|
|=========================================================== | 85%
|
|================================================================ | 91%
|
|===================================================================== | 98%
|
|======================================================================| 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 XGBoost_grid_1_AutoML_17_20240507_132945_model_4 1911.023 3652009
## 2 StackedEnsemble_BestOfFamily_4_AutoML_17_20240507_132945 1911.285 3653009
## 3 StackedEnsemble_AllModels_3_AutoML_17_20240507_132945 1968.134 3873552
## 4 StackedEnsemble_AllModels_2_AutoML_17_20240507_132945 1998.728 3994914
## 5 StackedEnsemble_BestOfFamily_3_AutoML_17_20240507_132945 2054.125 4219429
## 6 XGBoost_grid_1_AutoML_17_20240507_132945_model_3 2056.233 4228095
## mae rmsle mean_residual_deviance
## 1 797.4975 NaN 3652009
## 2 806.7797 NaN 3653009
## 3 728.6873 NaN 3873552
## 4 727.3975 NaN 3994914
## 5 791.7993 NaN 4219429
## 6 782.6758 NaN 4228095
##
## [33 rows x 6 columns]best_model <- models_h2o@leader
best_model## Model Details:
## ==============
##
## H2ORegressionModel: xgboost
## Model ID: XGBoost_grid_1_AutoML_17_20240507_132945_model_4
## Model Summary:
## number_of_trees
## 1 32
##
##
## H2ORegressionMetrics: xgboost
## ** Reported on training data. **
##
## MSE: 2601961
## RMSE: 1613.059
## MAE: 695.9029
## RMSLE: NaN
## Mean Residual Deviance : 2601961
##
##
## H2ORegressionMetrics: xgboost
## ** Reported on validation data. **
##
## MSE: 4104847
## RMSE: 2026.042
## MAE: 755.4072
## RMSLE: 0.3449595
## Mean Residual Deviance : 4104847
##
##
## H2ORegressionMetrics: xgboost
## ** Reported on cross-validation data. **
## ** 5-fold cross-validation on training data (Metrics computed for combined holdout predictions) **
##
## MSE: 5786876
## RMSE: 2405.593
## MAE: 781.502
## RMSLE: NaN
## Mean Residual Deviance : 5786876
##
##
## Cross-Validation Metrics Summary:
## mean sd cv_1_valid
## mae 781.501950 49.238117 852.659600
## mean_residual_deviance 5786875.500000 6396435.500000 17133578.000000
## mse 5786875.500000 6396435.500000 17133578.000000
## r2 0.762278 0.109697 0.588625
## residual_deviance 5786875.500000 6396435.500000 17133578.000000
## rmse 2188.181200 1117.329100 4139.273000
## rmsle 0.390123 0.000000 NA
## cv_2_valid cv_3_valid cv_4_valid
## mae 809.418640 732.600300 746.296300
## mean_residual_deviance 3689546.200000 2175749.000000 2080075.000000
## mse 3689546.200000 2175749.000000 2080075.000000
## r2 0.837456 0.840175 0.827557
## residual_deviance 3689546.200000 2175749.000000 2080075.000000
## rmse 1920.819200 1475.042100 1442.246500
## rmsle 0.390123 NA NA
## cv_5_valid
## mae 766.534850
## mean_residual_deviance 3855429.200000
## mse 3855429.200000
## r2 0.717579
## residual_deviance 3855429.200000
## rmse 1963.524700
## rmsle NA?h2o.getModel
?h2o.saveModel
?h2o.loadModel
#best_model <- h2o.loadModel(" XGBoost_grid_1_AutoML_15_20240507_132529_model_4")predictions <- h2o.predict(best_model, newdata = test_h2o)##
|
| | 0%
|
|======================================================================| 100%predictions_tbl <- predictions %>%
as_tibble()
predictions_tbl %>%
bind_cols(test_tbl)## # A tibble: 2,766 × 4
## predict symbol date claims
## <dbl> <fct> <date> <int>
## 1 5544. Connecticut 1989-01-14 6503
## 2 4456. Connecticut 1989-01-28 4663
## 3 4030. Connecticut 1989-04-08 3610
## 4 4030. Connecticut 1989-04-29 3191
## 5 4030. Connecticut 1989-05-06 3224
## 6 4847. Connecticut 1989-08-12 3704
## 7 4847. Connecticut 1989-08-26 3373
## 8 4847. Connecticut 1989-09-02 2902
## 9 4847. Connecticut 1989-09-09 2856
## 10 4847. Connecticut 1989-09-16 3025
## # ℹ 2,756 more rows?h2o.performance
performance_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] "XGBoost_grid_1_AutoML_17_20240507_132945_model_4"
##
## $model$type
## [1] "Key<Model>"
##
## $model$URL
## [1] "/3/Models/XGBoost_grid_1_AutoML_17_20240507_132945_model_4"
##
##
## $model_checksum
## [1] "8452636483024181248"
##
## $frame
## $frame$name
## [1] "test_tbl_sid_8a9b_3"
##
##
## $frame_checksum
## [1] "8320518109852287548"
##
## $description
## NULL
##
## $scoring_time
## [1] 1.715103e+12
##
## $predictions
## NULL
##
## $MSE
## [1] 3652009
##
## $RMSE
## [1] 1911.023
##
## $nobs
## [1] 2766
##
## $custom_metric_name
## NULL
##
## $custom_metric_value
## [1] 0
##
## $r2
## [1] 0.8425054
##
## $mean_residual_deviance
## [1] 3652009
##
## $mae
## [1] 797.4975
##
## $rmsle
## [1] "NaN"h2o.auc(performance_h2o)## NULLh2o.confusionMatrix(performance_h2o)## Warning in .local(object, ...): No Confusion Matrices for H2ORegressionMetrics## NULL