scoreSEND/test_script.R at main · phuse-org/scoreSEND · 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
# (X) Make sure handles interim sacrifices and recovery sacrifices properly and ensure documentation reflects this logic
# Double check BW Scoring
# add argument to calculate scores within SEX
# add argument to filter by organ system (or not)
# add argument to calculate LB as change from baseline (if baseline data is present) -- perhaps make this the default
# Update xpt_dir functionality to enable reading from multiple datasets
# Develop a python implementation of this package

# We will work by reading from database rather than raw XPT files
## Kevin will create a SQLite database (using sendigR) that we can all use
## Kevin will provide training an documentation for how to use sendigR to do this
## leave raw XPT reading
## don't run lot's of SQL queries but rather pull domain data out into data frames

rm(list = ls())

setwd(dirname(this.path::this.path()))

devtools::load_all()

DBflag <- F

Domains <- c('bw', 'lb', 'mi')

if (DBflag == T) {

  study_dirs <- list.files('sample_data', full.names = F)

} else {

  study_dirs <- list.files('sample_data', full.names = T)

  # Scores_all <- list()
  # study_dir <- "sample_data/35449"
  for (study_dir in study_dirs[1:4]) {
    print(study_dir)

    # # Create tibbles for each domain
    # Files <- list.files(study_dir)
    # for (File in Files) {
    #   Domain <- toupper(unlist(strsplit(File, '.', fixed = T))[1])
    #   assign(Domain, haven::read_xpt(paste0(study_dir, '/', File)))
    # }

    if (DBflag == T) {
      ARGs <- list(
        studyid = study_dir,
        path_db = 'path/to/db'
      )
    } else {
      ARGs <- list(
        xpt_dir = study_dir
      )
    }

    # figiure out how to pass these arguments
    ARGs <- list('xpt-dir' = 'XPT_DIR')
    Doses <- get_doses(ARGs)

    Doses <- get_doses(xpt_dir = XPT_DIR)
    treatmentGroups <- get_treatment_group(xpt_dir = study_dir)
    print(treatmentGroups)

    Compiled_Data <- get_compile_data(xpt_dir = study_dir)

    BWscores <- get_bw_score(xpt_dir = study_dir,
                             master_CompileData = Compiled_Data,
                             score_in_list_format = F)
    BWscoresList <- get_bw_score(xpt_dir = study_dir,
                                 master_CompileData = Compiled_Data,
                                 score_in_list_format = T)

    LBscores <- get_lb_score(xpt_dir = study_dir,
                             master_CompileData = Compiled_Data,
                             score_in_list_format = F)
    LBscoresList <- get_lb_score(xpt_dir = study_dir,
                                 master_CompileData = Compiled_Data,
                                 score_in_list_format = T)

    MIscores <- get_mi_score(xpt_dir = study_dir,
                             master_CompileData = Compiled_Data,
                             score_in_list_format = F)
    MIscoresList <- get_mi_score(xpt_dir = study_dir,
                                 master_CompileData = Compiled_Data,
                                 score_in_list_format = T)

    Scores <- get_all_score(xpt_dir = study_dir, domain = Domains, score_in_list_format = F)
    scoresList <- get_all_score(xpt_dir = study_dir, domain = Domains, score_in_list_format = T)

    if (study_dir == study_dirs[1]) {
      Scores_all <- Scores[Domains]
      scoresList_all <- scoresList[Domains]
    }

    for (Domain in Domains) {
      Scores_all[[Domain]] <- rbind(Scores_all[[Domain]], Scores[[Domain]])
    }
  }
}