Public facing -- clean and modify repo to work for public

R/figures/fig1.R

@@ -45,7 +45,6 @@ create_figure_1 <- function(
   raw_ct_2019,
   health_weighted,
   refining_mortality,
-  labor_2019,
   ca_regions,
   raw_pop_income_2021,
   cpi2020,
@@ -1554,11 +1553,6 @@ create_figure_1 <- function(
   ## merge counties to census tracts
   ## -----------------------------------------------------------------
 
-  # ## join with spatial data 2019
-  # census_tract_labor_2019_sp <- raw_ct_2019 |>
-  #   rename(census_tract = GEOID) |>
-  #   left_join(census_tract_labor_2020)
-
   # Create the expanded data
   census_tracts_l_expanded <- expand_grid(
     census_tracts,

R/figures/health_labor_revised_figs.R

@@ -1300,8 +1300,8 @@ plot_npv_health_labor <- function(
       x = "GHG emissions reduction (%, 2045 vs 2019)"
     ) +
     scale_y_continuous(
-      limits = c(0, 50),
-      breaks = seq(0, 50, by = 10)
+      limits = c(0, 40),
+      breaks = seq(0, 40, by = 10)
     ) +
     xlim(0, 80) +
     scale_color_manual(
@@ -1380,8 +1380,8 @@ plot_npv_health_labor <- function(
       x = "GHG emissions reduction (%, 2045 vs 2019)"
     ) +
     scale_y_continuous(
-      limits = c(-50, 0),
-      breaks = seq(-50, 0, by = 10)
+      limits = c(-40, 0),
+      breaks = seq(-40, 0, by = 10)
     ) +
     xlim(0, 80) +
     scale_color_manual(
@@ -1451,8 +1451,8 @@ plot_npv_health_labor <- function(
       x = "GHG emissions reduction (%, 2045 vs 2019)"
     ) +
     scale_y_continuous(
-      limits = c(-50, 0),
-      breaks = seq(-50, 0, by = 10)
+      limits = c(-40, 0),
+      breaks = seq(-40, 0, by = 10)
     ) +
     xlim(0, 80) +
     scale_color_manual(
@@ -1523,8 +1523,8 @@ plot_npv_health_labor <- function(
       x = "GHG emissions reduction (%, 2045 vs 2019)"
     ) +
     scale_y_continuous(
-      limits = c(-50, 0),
-      breaks = seq(-50, 0, by = 10)
+      limits = c(-40, 0),
+      breaks = seq(-40, 0, by = 10)
     ) +
     xlim(0, 80) +
     scale_color_manual(
@@ -1580,7 +1580,7 @@ plot_npv_health_labor <- function(
       y = NULL,
       x = "GHG emissions reduction (%, 2045 vs 2019)"
     ) +
-    ylim(-50, 0) +
+    ylim(-40, 0) +
     xlim(0, 80) +
     scale_color_manual(
       values = refin_colors,
@@ -1655,7 +1655,7 @@ plot_npv_health_labor <- function(
       y = NULL,
       x = "GHG emissions reduction (%, 2045 vs 2019)"
     ) +
-    ylim(-50, 0) +
+    ylim(-40, 0) +
     xlim(0, 80) +
     scale_color_manual(
       values = refin_colors,
@@ -4727,8 +4727,8 @@ plot_npv_health_labor_non_age_vsl <- function(
       x = "GHG emissions reduction (%, 2045 vs 2019)"
     ) +
     scale_y_continuous(
-      limits = c(-50, 0),
-      breaks = seq(-50, 0, by = 10)
+      limits = c(-40, 0),
+      breaks = seq(-40, 0, by = 10)
     ) +
     xlim(0, 80) +
     scale_color_manual(

README.md

@@ -1,48 +1,90 @@
 # Distributional and climate impacts of low-carbon transition pathways for California's oil refining (repo)
 
 ## Setting up
-This repo relies on the R package ``targets`` to maintain the pipeline of the scripts and the reproducibility of the project.
-Install the package if you have not already done so:
 
-```
+This repo relies on the R package `targets` to maintain the pipeline of the scripts and the reproducibility of the project. Install the package if you have not already done so:
+
+```         
 install.packages("targets")
 ```
 
 Load the package:
 
-```
+```         
 library(targets)
 ```
 
-All of the functions for the pipeline are in the ``R/`` folder.
-To open the ``_targets.R`` script (which is where the workflow is built and specified), run:
+All of the functions for the pipeline are in the `R/` folder. To open the `_targets.R` script (which is where the workflow is built and specified), run:
 
-```
+```         
 tar_edit()
 ```
 
-## Changing the file directory
-
-**IMPORTANT**: Before running the pipeline, one thing needs to be changed -- the path to the ``calepa-cn`` folder. 
-Look for the ``user`` target:
-
-```
-tar_target(name = user, "meas"),
-```
-
-And replace the name in the quotations above with a specified user.
+## Changing important user-specific `targets`
+
+**IMPORTANT**: Before running the pipeline, several things should be modified 
+to reflect user-specific specifications. The `setup_data_paths.R` file, which is 
+sources in the main `_targets.R` folder, should auto-configure paths. Make sure
+the data folder has been moved into your main repo (note that this folder is not
+tracked by git and therefore is not pulled into the repo). 
+
+Next, set the `confidential_data_access` target option based on whether or not 
+you have access to the confidential datasets. The code is as follows:
+
+```         
+tar_target(name = confidential_data_access,
+             command = FALSE),
+```
+
+where `FALSE` indicates that the user does not have access and `TRUE` indicates 
+access. Users with access will have a subfolder within the data folder called
+`confidential-data`.
+
+Next, set the following target to reflect which values for `beta` and `cuf`
+you are running:
+
+```
+## set module settings for specific run (cuf and beta)
+  tar_target(name = beta_scenario, command = "main"), ## UPDATE WITH ("main", "high", or "low")
+  tar_target(
+    name = beta,
+    command = ifelse(
+      beta_scenario == "low",
+      0.00422068,
+      ifelse(beta_scenario == "high", 0.00737932, 0.00582)
+    )
+  ), 
+
+  # Coefficient from Krewski et al (2009) for mortality impact
+  tar_target(name = ref_threshold, command = 0.6),
+  ```
+
+  where the target `beta_scenario` can be "main", "low", or "high" and 
+  will be used for file saving name conventions and sets the `beta` target below. 
+
+  Finally, specify the `version` target to determine folder names for saving outputs:
+
+  ```
+  # list save paths (UPDATE VERSION AS NEEDED)
+  tar_target(name = version, command = "test-no-conf-data"),
+
+```
+where in this example will create a folder with `test-no-conf-data` in the name.
+
 
 ## Using the repo to recreate the analysis
 
 ### Debugging the pipeline
+
 In order to check the pipeline is engineered properly, run the following command:
 
-```
+```         
 tar_manifest(fields=command)
 ```
 
 The output should look something like:
-```
+
+```         
 # A tibble: 90 × 2
    name          command                                                                                                             
    <chr>         <chr>                                                                                                               
@@ -59,19 +101,20 @@ The output should look something like:
 # … with 80 more rows
 # ℹ Use `print(n = ...)` to see more rows
 ```
+
 If there are any issues (missing targets, bugs, etc), you should receive an error message.
 
 ### Running the pipeline
 
 To build and run the pipeline (this will execute everything), run:
 
-```
+```         
 tar_make()
 ```
 
 If you are running this for the first time, it should take a few minutes, but the outputs should look something like:
 
-```
+```         
 • start target ei_crude
 • built target ei_crude [0.019 seconds]
 • start target ei_diesel
@@ -87,90 +130,89 @@ If you are running this for the first time, it should take a few minutes, but th
 ...
 ```
 
-Assuming none of the targets change, the next time(s) you run ``tar_make()``, ``targets`` will skip building targets that are already up-to-date. 
+Assuming none of the targets change, the next time(s) you run `tar_make()`, `targets` will skip building targets that are already up-to-date.
 
 ### Viewing and loading targets
 
-If you are new to ``targets`` you might be confused that there are no objects in your environment. That's because the objects are stored locally in a folder called ``_targets`` (in your local repo).
+If you are new to `targets` you might be confused that there are no objects in your environment. That's because the objects are stored locally in a folder called `_targets` (in your local repo).
 
-But let's say you want to inspect a specific object, like ``dt_its``. If you want to just view it in your console, you can enter:
+But let's say you want to inspect a specific object, like `dt_its`. If you want to just view it in your console, you can enter:
 
-```
+```         
 tar_read(dt_its)
 ```
 
-And that should print the ``data.table``.
+And that should print the `data.table`.
 
-If you want to load the ``data.table`` into your environment, you can run the following instead:
+If you want to load the `data.table` into your environment, you can run the following instead:
 
-```
+```         
 tar_load(dt_its)
 ```
 
 You'll notice the object is in your environment.
 
 You can also view plots. Running the following line should either load the plot in your Plots window or open a new window with the plot:
 
-```
+```         
 tar_read(fig_demand)
 ```
 
 ### Visualizing the pipeline
 
 If you want to visualize the pipeline, run:
 
-```
+```         
 tar_visnetwork()
 ```
 
-You'll notice the diagram is very small -- you can use your mouse to zoom in on the objects if you'd like. If you make changes to the targets/pipeline and run ``tar_visnetwork()`` before running ``tar_make``, you can see the colors of the objects change.
+You'll notice the diagram is very small -- you can use your mouse to zoom in on the objects if you'd like. If you make changes to the targets/pipeline and run `tar_visnetwork()` before running `tar_make`, you can see the colors of the objects change.
 
 ## Example of target changes and impacts on the pipeline
 
 Want an example of what happens when a target is changed? Here's an easy one:
 
-1. Find the target ``ei_crude`` in ``_targets.R``:
+1.  Find the target `ei_crude` in `_targets.R`:
 
-```
+```         
 tar_target(name = ei_crude, command = 5.698)
 ```
 
-2. Change the command value to something else, say 10 for example:
+2.  Change the command value to something else, say 10 for example:
 
-```
+```         
 tar_target(name = ei_crude, command = 10)
 ```
 
-3. Save the script. Then run:
+3.  Save the script. Then run:
 
-```
+```         
 tar_visnetwork()
 ```
 
-4. You'll see the diagram now looks different, with a few lines and points assigned a different color, representing "Outdated". These are the targets affected by the updated ``ei_crude``. Run ``tar_make()`` to rerun the pipeline with the new ``ei_crude`` value:
+4.  You'll see the diagram now looks different, with a few lines and points assigned a different color, representing "Outdated". These are the targets affected by the updated `ei_crude`. Run `tar_make()` to rerun the pipeline with the new `ei_crude` value:
 
-```
+```         
 tar_make()
 ```
 
 In the outputs you'll see that the targets that are affected are being updated, while the ones that are unaffected are not being rebuilt.
 
-If you run ``tar_visnetwork()`` everything should be up-to-date now in the diagram.
+If you run `tar_visnetwork()` everything should be up-to-date now in the diagram.
 
 **Remember to change the value of the target back to normal (by ctrl + z for example).**
 
 ## Output Structure and Git Tracking
 
-This repository uses a standardized output structure defined in `structure.md` and `output_structure.csv`.
-The `output_structure.csv` file specifies:
+This repository uses a standardized output structure defined in `structure.md` and `output_structure.csv`. The `output_structure.csv` file specifies:
 
-- `file_name`: The name of each output file
-- `relative_path`: The path where the file should be saved (relative to `save_path`)
-- `tracked`: Whether the file should be tracked in git (`YES` or `NO`)
+-   `file_name`: The name of each output file
+-   `relative_path`: The path where the file should be saved (relative to `save_path`)
+-   `tracked`: Whether the file should be tracked in git (`YES` or `NO`)
 
 ### Directory Structure
 
-```text
+``` text
 outputs/
   version/
     iteration/
@@ -195,14 +237,14 @@ outputs/
 
 Two utility scripts help manage output files and git tracking:
 
-1. `update_gitignore.R`: Updates all `.gitignore` files based on `output_structure.csv`
-2. `verify_file_paths.R`: Verifies that all files in `_targets.R` are saved in the correct locations
+1.  `update_gitignore.R`: Updates all `.gitignore` files based on `output_structure.csv`
+2.  `verify_file_paths.R`: Verifies that all files in `_targets.R` are saved in the correct locations
 
 ### File Saving Conventions
 
 All file-producing targets in `_targets.R` should use the `simple_fwrite_repo` function:
 
-```r
+``` r
 simple_fwrite_repo(
   data = your_data,
   folder_path = NULL,  # Not needed when using save_path and file_type