library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ 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(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 zoolibrary(timetk)
library(umap)
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 1.1.3
## ✔ modeldata 1.3.0 ✔ workflowsets 1.0.1
## ✔ parsnip 1.1.1 ✔ yardstick 1.3.0
## ✔ recipes 1.0.9
## ── 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 tidymodels_prefer() to resolve common conflicts.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)I have a dataset called claims_tbl that looks like this.
claims_tbl looks like this :
symbol date claims
The goal is to help predict claims by each state.
Please write R code to create a predictive model that predicts the probability of claims for each state.
library(tidyverse)
library(tidymodels)
library(h2o)set.seed(123) # for reproducibility
claims_split <- initial_split(claims_tbl, prop = 0.8)
claims_train <- training(claims_split)
claims_test <- testing(claims_split)claims_recipe <- recipe(claims ~ ., data = claims_train) %>%
step_dummy(all_nominal(), -all_outcomes())claims_prep <- claims_recipe %>%
prep() %>%
bake(new_data = claims_train)h2o.init()## Connection successful!
##
## R is connected to the H2O cluster:
## H2O cluster uptime: 15 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 12 days
## H2O cluster name: H2O_started_from_R_spencer_qns693
## H2O cluster total nodes: 1
## H2O cluster total memory: 2.85 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 12 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.htmlclaims_h2o_train <- as.h2o(claims_prep)##
|
| | 0%
|
|======================================================================| 100%rf_model <- h2o.randomForest(y = "claims", training_frame = claims_h2o_train)##
|
| | 0%
|
|======================================================================| 100%claims_test_prep <- claims_recipe %>%
prep() %>%
bake(new_data = claims_test)claims_h2o_test <- as.h2o(claims_test_prep)##
|
| | 0%
|
|======================================================================| 100%predictions <- h2o.predict(rf_model, newdata = claims_h2o_test)##
|
| | 0%
|
|======================================================================| 100%predictions_df <- as.data.frame(predictions)claims_predictions <- bind_cols(claims_test, predictions_df)claims_predictions %>%
select(symbol, predict) %>%
rename(probability_of_claim = predict)## # A tibble: 2,212 × 2
## symbol probability_of_claim
## <fct> <dbl>
## 1 Connecticut 4749.
## 2 Connecticut 4749.
## 3 Connecticut 4749.
## 4 Connecticut 4749.
## 5 Connecticut 4749.
## 6 Connecticut 4749.
## 7 Connecticut 4749.
## 8 Connecticut 4749.
## 9 Connecticut 4749.
## 10 Connecticut 4749.
## # ℹ 2,202 more rows