olm hard code paths

.Rhistory

@@ -1,357 +1,3 @@
-g1
-tar_visnetwork(targets_only = T)
-tar_make()
-tar_make()
-tar_visnetwork(targets_only = T)
-library(parsnip)
-?fit
-sf_outcomes
-pest_data <- data.frame(
-y1 = rnorm(100),  # Example response variable 1
-y2 = rnorm(100),  # Example response variable 2
-x1 = rnorm(100),  # Example predictor variable 1
-x2 = rnorm(100)   # Example predictor variable 2
-)
-# Fit using the linear_model function in Parsnip
-lasso <- linear_reg() %>%
-set_engine("glmnet", family = "mgaussian") %>%
-set_mode("regression") %>%
-fit(cbind(y1, y2) ~ ., data = pest_data)
-pest_data <- data.frame(
-y1 = rnorm(100),  # Example response variable 1
-y2 = rnorm(100),  # Example response variable 2
-x1 = rnorm(100),  # Example predictor variable 1
-x2 = rnorm(100)   # Example predictor variable 2
-)
-pest_data
-a <- cbind(y1, y2)
-y1 = rnorm(100),  # Example response variable 1
-y1 = rnorm(100)
-y2 = rnorm(100)
-a <- cbind(y1, y2)
-dim(a)
-a
-?glmnet
-df
-pest_data <- df |>
-select(c("cncntrt","Year","left_cns"))
-df
-df
-pest_data <- df |>
-select(c("cncntrt","Year","lft_cns"))
-pest_data
-# Fit using the linear_model function in Parsnip
-lasso <- linear_reg() %>%
-set_engine("glmnet", family = "gaussian") %>%
-set_mode("regression") %>%
-fit(cncntrt ~ ., data = pest_data)
-pest_data <- data.frame(
-y1 = rnorm(100),  # Example response variable 1
-y2 = rnorm(100),  # Example response variable 2
-x1 = rnorm(100),  # Example predictor variable 1
-x2 = rnorm(100)   # Example predictor variable 2
-)
-# Fit using the linear_model function in Parsnip
-lasso <- linear_reg() %>%
-set_engine("glmnet", family = "mgaussian") %>%
-set_mode("regression") %>%
-fit(cbind(y1, y2) ~ ., data = pest_data)
-# Fit using the linear_model function in Parsnip
-lasso <- linear_reg(penalty = 1) %>%
-set_engine("glmnet", family = "mgaussian") %>%
-set_mode("regression") %>%
-fit(cbind(y1, y2) ~ ., data = pest_data)
-lasso
-lasso$fit
-lasso$fit$beta
-data_partitioned <- tar_read(sf_pesticide_partition_cleaned)
-data_partitioned[[1]]
-data_partitioned[[2]]
-data_partitioned[[2]][,l10n_info()]
-data_partitioned[[2]][,1:10]
-data_partitioned[[2]][,1:5]
-data_partitioned[[1]]
-data_outcome <- data_partitioned[[1]] |>
-st_drop_geometry()
-data_outcome
-data_model <- left_join(data_outcome, data_covariates, by = "id")
-data_covariates <- data_partitioned[[2]] |>
-st_drop_geometry()
-data_model <- left_join(data_outcome, data_covariates, by = "id")
-data_model
-data_model[,1:5]
-data_model[,1:10]
-data <- left_join(data_outcome, data_covariates, by = "id")
-data
-data_covariates
-colnames(data_covariates)
-colnames(data_covariates)[1:20]
-data_outcome
-data_outcome_to_join <- data_outcome |>
-st_drop_geometry() |>
-filter("cncntrt","id") |>
-as.data.frame() |>
-mutate(id = row_number())
-data_outcome_to_join <- data_outcome |>
-st_drop_geometry() |>
-select(c("cncntrt","id")) |>
-as.data.frame() |>
-mutate(id = row_number())
-data_outcome_to_join
-data_outcome_to_join |> head()
-data_covariates
-colnames(data_covariates)[1:10]
-colnames(data_covariates)[1790:1803]
-data_covariates_to_join <- data_covariates |>
-st_drop_geometry() |>
-select(-"geometry") |>
-as.data.frame() |>
-mutate(id = row_number())
-data_covariates <- sf_pesticide_partition_cleaned[[2]]
-data_covariates_to_join <- data_covariates |>
-st_drop_geometry() |>
-select(-"geometry") |>
-as.data.frame() |>
-mutate(id = row_number())
-data_covariates_to_join <- data_covariates |>
-st_drop_geometry() |>
-as.data.frame() |>
-mutate(id = row_number())
-View(data_covariates_to_join)
-data_fit <- left_join(data_outcome_to_join, data_covariates_to_join, by = "id")
-View(data_fit)
-data_fit <- left_join(data_outcome_to_join, data_covariates_to_join, by = "id") |>
-select(-"id")
-View(data_fit)
-hist(data_fit$cncntrt)
-summary(data_fit$cncntrt)
-data_outcome
-data_outcome[data_outcome$cncntrt==0,]
-d1 <- tar_read(readQS)
-d1
-d1[d1$cncntrt==0,]
-p1<-d1[d1$cncntrt==0,]
-p1$X
-p1$Y
-p1[c("X","Y")]
-p1
-azo <- st_read("/Volumes/SET/Projects/PrestoGP_Pesticides/input/data_process/data_AZO_watershed_huc_join.shp")
-azo
-azo.idx <- azo[azo$cncntrt==0,]
-azo.idx
-azo.initial <- load("/Volumes/SET/Projects/PrestoGP_Pesticides/input/data_process/data_AZO_year_avg.RData")
-azo.initial
-azo.initial[[1]]
-load("/Volumes/SET/Projects/PrestoGP_Pesticides/input/data_process/data_AZO_year_avg.RData")
-data.AZO.year.avg
-data.AZO.year.avg[data.AZO.year.avg$concentration==0,]
-sf_pesticide_partition_cleaned[[3]]
-sf_pesticide_partition_cleaned[[3]]$wll_dpt
-knitr::opts_chunk$set(echo = TRUE)
-library(dataRetrieval)
-install.packages("dataRetrieval")
-library(dataRetrieval)
-library(dplyr)
-library(beepr)
-install.packages("beepr")
-library(dataRetrieval)
-library(dplyr)
-library(beepr)
-library(lubridate)
-library(tidyverse)
-library(data.table)
-param.chlorotriazines <- c("39632", "04040", "04038", "04039", "38535", "04035")
-startDate <- "2000-01-01"
-endDate <- "2022-12-31"
-state.list <- state.abb[c(-2, -11)]
-state.fun.AZO <- function(x) {
-print(x)
-temp <- whatWQPdata(
-statecode = state.list[x],
-parameterCd = param.chlorotriazines
-)
-temp <- temp[temp$MonitoringLocationTypeName == "Well", ]
-if (nrow(temp) > 0) {
-site.info <- str_subset(temp$MonitoringLocationIdentifier, "(?<=USGS-)\\d+") %>%
-str_extract("(?<=USGS-)\\d+") %>%
-readNWISsite() %>%
-select(c(site_no, well_depth_va))
-site.info$MonitoringLocationIdentifier <- paste0("USGS-", site.info$site_no)
-data.chlorotriazines <- readWQPqw(temp$MonitoringLocationIdentifier, param.chlorotriazines,
-startDate = startDate, endDate = endDate
-)
-result <- left_join(data.chlorotriazines, temp, by = "MonitoringLocationIdentifier") %>%
-left_join(site.info, by = "MonitoringLocationIdentifier")
-return(result)
-}
-}
-data.AZO <- lapply(1:48, state.fun.AZO)
-sum(is.na(sf_pesticide_partition_cleaned[[3]]$wll_dpt))
-dim(d1)
-dim(d1,1)
-dim(d1)[1]
-dim(d1)[1]-6
-tar_make()
-p1 <- tar_read(plot_pesticide_maps_57fe39ed)
-p1
-sf_pesticide_partition_cleaned <- tar_read(sf_pesticide_partition_cleaned)
-sf_pesticide_partition_cleaned[[1]]
-ggplot(sf_pesticide_partition_cleaned,aes(cncntrt)) + geom_density()
-ggplot(sf_pesticide_partition_cleaned |> as.data.frame(),aes(cncntrt)) + geom_density()
-ggplot(sf_pesticide_partition_cleaned |> as.data.frame(),aes(cncntrt)) + geom_density() + scale_x_log10()
-library(PrestoGP)
-?VecchiaModel
-?check_input
-?PrestoGP::check_input
-?PrestoGP::prestogp_fit
-?MultivariateVecchiaModel
-tar_make()
-tar_make()
-sf_pesticide_dummies_cv <- tar_read(sf_pesticide_dummies_cv)
-sf_pesticide_dummies_cv[[1]]
-sf_pesticide_dummies_cv
-length(sf_pesticide_dummies_cv)
-sf_pesticide_dummies_cv[[1]]
-tar_make()
-sf_pesticide_dummies_cv[[1]]
-sf_pesticide_dummies_cv[[1]]$kfolds
-?tar_group_by
-tar_make()
-tar_make()
-sf_pesticide_for_fit <- tar_read(sf_pesticide_for_fit)
-sf_pesticide_for_fit
-sf_pesticide_for_fit[,1:10]
-head(sf_pesticide_for_fit)
-View(sf_pesticide_for_fit)
-tar_make()
-lasso.fit <- tar_read(lasso_fit_by_chem_4eeee620)
-lasso.fit$censor_probs
-?glmnet
-lasso.fit$fit$beta
-plot(lasso.fit$fit)
-plot(lasso.fit$fit$beta)
-plot(lasso.fit$fit)
-lasso.fit$lvl
-glmnet::plot(lasso.fit$fit)
-tar_visnetwork(targets_only = T)
-tar_make()
-lasso.fit <- tar_read(lasso_fit_by_chem_4eeee620)
-autoplot(lasso.fit)
-autoplot(lasso.fit$fit)
-lasso.fit
-autoplot(lasso.fit)
-autoplot(lasso.fit$spec)
-lasso.fit$fit
-tar_make()
-f2 <- tar_read(lasso_fit_by_kfold_2808dfa1)
-f2
-f2[[1]]
-f2[[2]]
-f2[[3]]
-f2[[4]]
-plot(f2)
-plot(f2[[2]])
-f2
-autoplot(f2)
-autoplot(f2$fit)
-tar_make()
-f1 <- tar_read(lasso_fit_by_kfold_68b90cee)
-f1
-autoplot(f1)
-autoplot(f1$fit)
-plot(f1$fit)
-tar_visnetwork(targets_only = T)
-?tar_visnetwork
-tar_mermaid(targets_only = T)
-tm <- tar_mermaid(targets_only = T)
-tm
-tar_visnetwork(targets_only = T)
-tar_visnetwork()
-tar_make()
-m1 <- tar_read(plot_covariate_maps_97adc691)
-m1
-1259*24
-1259*24/2
-=======
-group_by(ChmclNm) |>
-nest() |>
-mutate(data = map(data, ~ ifelse(.x$lft_cns == 0, .x$cncntrt, 1e-9))) |>
-pull(data)
-# 2) A list of LOD, each element is a vector of the limit of detection
-# use dplyr to create a separate list by each ChmlNm and create an LOD. The
-# LOD should be the cnctrnt
-pesticide_lod <- data_analysis |>
-group_by(ChmclNm) |>
-nest() |>
-mutate(data = map(data, ~ .x$cnctrnt)) |>
-pull(data)
-# 2) A list of LOD, each element is a vector of the limit of detection
-# use dplyr to create a separate list by each ChmlNm and create an LOD. The
-# LOD should be the cnctrnt
-pesticide_lod <- data_analysis |>
-group_by(ChmclNm) |>
-nest() |>
-mutate(data = map(data, ~ .x$cncntrt)) |>
-pull(data)
-pesticide_outcomes[[1]][1:10]
-pesticide_lod[[1]][1:10]
-#2a) Create a list of the of the lft_cns variable by ChmclNm
-pesticide_lft_cns <- data_analysis |>
-group_by(ChmclNm) |>
-nest() |>
-mutate(data = map(data, ~ .x$lft_cns)) |>
-pull(data)
-pesticide_lft_cns[[1]][1:10]
-cbind(pesticide_lft_cns[[1]][1:10],pesticide_outcomes[[1]][1:10],pesticide_lod[[1]][1:10])
-# 4) A list of X's, each element is a matrix of the covariates
-# For now, we will use the covariates in the data_analysis
-pesticide_covariates <- data_analysis |>
-group_by(ChmclNm) |>
-nest() |>
-mutate(data = map(data, ~ .x %>% select(-cncntrt, -lft_cns))) |>
-pull(data)
-pesticide_covariates[[1]]
-pesticide_covariates[[2]]
-pesticide_covariates[[3]]
-pesticide_covariates[[4]]
-ls
-pesticide_covariates[[3]]
-data_analysis
-data_analysis[[1]][,1:20]
-data_analysis[[1]][,1:10]
-data_analysis[,1:10]
-# 5) A list of locs, each element is a matrix of the locations
-# For now, we will use the locations in the data_analysis - it includes x, y, and time
-# Because the locations are from the sf geometry object we need to use the original data
-# We get the geometry from the sf object and then add the time (column name is Year)
-pesticide_locs <- data_analysis |>
-group_by(ChmclNm) |>
-nest() |>
-mutate(data = map(data, ~ st_coordinates(.x |> select(geometry)))) |>
-pull(data)
-# 5) A list of locs, each element is a matrix of the locations
-# For now, we will use the locations in the data_analysis - it includes x, y, and time
-# Because the locations are from the sf geometry object we need to use the original data
-# We get the geometry from the sf object and then add the time (column name is Year)
-data_analysis <- splits |>
-analysis() |>
-group_by(ChmclNm) |>
-nest() |>
-mutate(geometry = st_as_text(geometry)) |>
-sf::st_drop_geometry()
-# 5) A list of locs, each element is a matrix of the locations
-# For now, we will use the locations in the data_analysis - it includes x, y, and time
-# Because the locations are from the sf geometry object we need to use the original data
-# We get the geometry from the sf object and then add the time (column name is Year)
-data_analysis <- splits |>
-analysis() |>
-group_by(ChmclNm) |>
-nest() |>
-mutate(data = map(data, st_coordinates())) |>
-sf::st_drop_geometry()
-data_analysis <- splits |>
-analysis() |>
-group_by(ChmclNm)
 data_analysis <- splits |>
 analysis()
 data_analysis
@@ -863,3 +509,4 @@ library(yardstick)
 library(data.table)
 tar_visnetwork(targets_only = T)
 getwd()
+getwd()