agroforestrySampling/targets_preprocessing.R at main · GeospatialCentroid/agroforestrySampling · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
# _targets.R

library(targets)
library(tarchetypes)
library(geotargets)

# Load packages required by your functions
tar_option_set(
  packages = c("sf", "dplyr", "tigris", "targets")
)

# Source the functions (which we will also rename)
source("functions/preprocessingFunction.R")

# Define the pipeline
list(

  # State and County Processing ---------------------------------------------
  # Target 1: Download the raw data as an R object
  tar_target(
    name = rawStatesData,
    command = downloadRawStates()
  ),

  # Target 2: Process the raw data to get an R object for the lower 48
  # This target depends on the `rawStatesData` target
  tar_target(
    name = lower48Data,
    command = processLower48(rawStatesData)
  ),

  # Target 3: Save the raw data object to a file
  # This depends on `rawStatesData`
  tar_target(
    name = rawStatesFile,
    command = saveGeopackageSF(rawStatesData, "data/raw/us/allStates.gpkg"),
    format = "file"
  ),?

  # Target 4: Save the processed data object to a file
  # This depends on `lower48Data`
  tar_target(
    name = lower48File,
    command = saveGeopackageSF(lower48Data, "data/derived/us/lower48.gpkg"),
    format = "file"
  ),
  # 5. Download all US counties from tigris
  tar_target(
    name = tigrisCountiesData, # Renamed for clarity
    command = downloadTigrisCounties() # Changed function call
  ),

  # 6. Filter counties to only those in the lower 48
  tar_target(
    name = lower48CountiesData,
    command = filterCountiesToLower48(tigrisCountiesData, lower48Data) # Uses new tigris data
  ),

  # 7. Save the filtered counties to a file
  tar_target(
    name = lower48CountiesFile,
    command = saveGeopackageSF(lower48CountiesData, "data/derived/us/lower48_counties.gpkg"),
    format = "file"
  ),

  #8. bounding box of the lower 48
  tar_target(
    name = extent48,
    command = lower48Extent(lower48Data),

  ),
  #9. export the extent
  tar_target(
    name = extent48File,
    command = saveGeopackageSF(extent48, "data/derived/us/extent48.gpkg"),
    format = "file"
  ),

  # MLRA processing ---------------------------------------------------------
  # process MLRA data
  tar_target(
    name = mlraPath,
    command = {"data/raw/mlra/MLRA_52_2022/MLRA_52.shp"},
    format = "file"
  ),

  tar_target(
    name = lower48MLRA,
    command = processMLRA(mlraPath, extent48)
  ),

  # # 7. Save the filtered counties to a file
  tar_target(
    name = lower48MLRAFile,
    command = saveGeopackageSF(lower48MLRA, "data/derived/mlra/lower48MLRA.gpkg"),
    format = "file"
  ),

  # 8. generate the lrr
  tar_target(
    name =lrr48,
    command = generateLRR(lower48MLRA = lower48MLRA)
  ),

  # 9. export the dataset
  tar_target(
    name = lower48LRRFile,
    command = saveGeopackageSF(lrr48, "data/derived/mlra/lower48LRR.gpkg"),
    format = "file"
  ),
  # developing sample grids  ---------------------------------------------------------
  # 10. 100km grid in AEA
  tar_target(
    name = grid100ARA,
    command = buildAGrid(extent_object = extent48, cell_size = 100000)
  ),
  # 11. export the 100km AEA dataset
  tar_target(
    name = grid100ARAFile,
    command = saveGeopackageSF(grid100ARA, "data/derived/grids/grid100km_aea.gpkg"),
    format = "file"
  )
)