FishGlob_data/summary/table_1_script.Rmd at main · fishglob/FishGlob_data · 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
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
---
title: "Table 1"
author: "Juliano Palacios Abrantes"
output: html_document
date: "2022-08-22"
---

```{r setup, include=FALSE}


# Function that loads multiple packages
# NOTE; It will install those you do not have
load_all <- function (pkg_list){
  new.pkg <- pkg_list[!(pkg_list %in% installed.packages()[,
                                                           "Package"])]
  if (length(new.pkg))
    install.packages(new.pkg, dependencies = TRUE, repos = "http://cran.us.r-project.org")
  sapply(pkg_list, require, character.only = TRUE)
}


# Load packages
load_all(
  c(
    "googledrive",
    "tidyverse",
    "here"
  )
)


```

# Create function for table one

```{r table one function, eval = R}

table_one_fun <- function(region, datras){

  # Get data from google drive

  # Deal with DATRAS dataset containing all surveys
  if(region %in% datras){

    file_name <- "DATRAS_v2_clean.csv"

    drive_download(file = file_name,
                   overwrite = TRUE)

    df <- read.csv(here("./summary/",file_name)) %>%
      filter(survey == region)

  }else{
    # If not a DATRAS survey
    file_name <- paste0(region,"_clean.csv")

    drive_download(file = file_name,
                   overwrite = TRUE)

    df <- read.csv(here("./summary/",file_name))

  }

  # Attach df for ease typing
  suppressMessages(
    attach(df)
  )
  # Create df
  clean_df <- tibble(
    # survey
    survey = unique(region),
    # year
    year = paste(min(year),max(year),sep = "-"),
    # months
    months = paste(sort(unique(month)),collapse = " "),
    # number of hauls
    `number of hauls` = length(unique(haul_id)),
    # gear_type
    # you can just write "multiple gears" unless there's like 2 or 3 max
    `gear type` = ifelse(
      length(unique(gear)) > 3,
      "multiple gears",
      paste(unique(gear),collapse =", ")
    )
  )

  # Detach df
  detach(df)

  # remove df from computer
  file.remove(here("./summary/",file_name))

  # Return function
  return(clean_df)
}

```

## Test function

```{r fun_test}

# Single survey
# table_one_fun("EVHOE", c("EVHOE")) #OK! *tested with AI, NZ, ZAF and EVHOE

# Binding rows
# bind_rows(c(table_one_fun("AI"),table_one("AI"))) #OK!

# In lapply mode
# bind_rows(lapply(c("AI","AI"), table_one_fun)) # OK!

```

## Run function

```{r}

# List of surveys for Table 1
surveys <- c(
  # Datras surveys
  "BITS", "EVHOE","FR-CGFS", "IE-IGFS", "NIGFS","NS-IBTS", 'PT-IBTS', 'ROCKALL',"SWC-IBTS",
  # Rest of surveys
  "AI",
  "HS",
  "QCS",
  "SOG",
  "WCHG",
  'WCVI',
  "EBS",
  "GMEX",
  "GOA",
  "GSL-N",
  "GSL-S",
  "NEUS",
  "NorBTS", # NorBTS
  'SEUS',
  'SCS',
  "WCANN",
  "WCTRI"
)

# DATRAS surveys need to be identified because they are all joined in one single dataset datras_v2_clean.csv
datras <- c("BITS", "EVHOE","FR-CGFS", "IE-IGFS", "NIGFS","NS-IBTS", 'PT-IBTS', 'ROCKALL',"SWC-IBTS")


# Routine
suppressMessages(
  table_one <-
    bind_rows(
      lapply(datras,
             table_one_fun,
             datras = datras)
    )
)


```