Add of selection file

processing/extract.R

 # Usefull library
 library(tools)
 library(dplyr)
+library(officer)
 
 
 # General information on station
@@ -48,8 +49,76 @@ iQHE = c('0'='qualité hautes eaux inconnue',
          '2'='qualité hautes eaux douteuse')
 
 
+# Get the selection of data from the 'Liste-station_RRSE' file and the BanqueHydro directory
+get_selection = function (computer_data_path, listdir, listname,
+                          cnames=c('code','station', 'BV_km2', 'axe_principal_concerne', 'longueur_serie', 'commentaires', 'choix'), 
+                          cisnum=c('BV_km2', 'longueur_serie')) {
+    
+    # Get the file path to the data
+    list_path = file.path(computer_data_path, listdir, listname)
+    
+    # Extract the data as a data frame
+    # df_list = read.table(list_path,
+    #                      header=TRUE,
+    #                      sep=';',
+    #                      dec=',',
+    #                      quote='',
+    #                      skip=0,
+    #                      nrows=3,
+    #                      strip.white=TRUE,
+    #                      comment.char="",
+    #                      colClasses=c("character", 
+    #                                   "character",
+    #                                   "numeric",
+    #                                   "character",
+    #                                   "numeric",
+    #                                   "character",
+    #                                   "character"))
+
+    sample_data = read_docx(list_path)
+    content = docx_summary(sample_data)
+    table_cells <- content %>% filter(content_type == "table cell")
+    table_data <- table_cells %>% filter(!is_header) %>% select(row_id, cell_id, text)
+    # Split data into individual columns
+    splits <- split(table_data, table_data$cell_id)
+    splits <- lapply(splits, function(x) x$text)
+    
+    # Combine columns back together in wide format
+    df_list <- bind_cols(splits)
+    
+    df_list = df_list[-1,]
+    
+    names(df_list) = cnames
+
+    for (c in cisnum) {
+        df_list$c = as.numeric(sub(",", ".",
+                                   pull(df_list, c)))
+    }
+    
+    df_selec = df_list[df_list$choix == 'A garder' | df_list$choix == 'Ajout',]
+    
+    df_selec = bind_cols(df_selec, 
+                         filename=paste(df_selec$code, '_HYDRO_QJM.txt', sep=''))
+    return (df_selec)
+}
+
+# Example
+# df_selec = get_selection(
+#     "/home/louis/Documents/bouleau/INRAE/CDD_stationnarite/data",
+#     "liste_station",
+#     "Liste-station_RRSE.docx",
+#     cnames=c('code','station', 
+#              'BV_km2',
+#              'axe_principal_concerne',
+#              'longueur_serie',
+#              'commentaires',
+#              'choix'), 
+#     cisnum=c('BV_km2',
+#              'longueur_serie'))
+
+
 # Extraction of information
-extract_info = function (data_path, filedir, filename, verbose=TRUE) {
+extract_info = function (computer_data_path, filedir, filename, verbose=TRUE) {
     
     # Convert the filename in vector
     filename = c(filename)
@@ -62,7 +131,7 @@ extract_info = function (data_path, filedir, filename, verbose=TRUE) {
             # Create a filelist to store all the filename
             filelist = c()
             # Get all the filename in the data directory selected
-            filelist_tmp = list.files(file.path(data_path,
+            filelist_tmp = list.files(file.path(computer_data_path,
                                                 filedir))
             
             # For all the filename in the directory selected
@@ -88,7 +157,7 @@ extract_info = function (data_path, filedir, filename, verbose=TRUE) {
             
             # Concatenate by raw data frames created by this function when filename correspond to only one filename
             df_info = rbind(df_info,
-                            extract_info(data_path, 
+                            extract_info(computer_data_path, 
                                          filedir, 
                                          f))
         }
@@ -107,7 +176,7 @@ extract_info = function (data_path, filedir, filename, verbose=TRUE) {
     }
 
     # Get the file path to the data
-    file_path = file.path(data_path, filedir, filename)
+    file_path = file.path(computer_data_path, filedir, filename)
 
     # Extract all the header
     infotxt = c(readLines(file_path, n=41))
@@ -142,7 +211,7 @@ extract_info = function (data_path, filedir, filename, verbose=TRUE) {
 
 
 # Extraction of data
-extract_data = function (data_path, filedir, filename, verbose=TRUE) {
+extract_data = function (computer_data_path, filedir, filename, verbose=TRUE) {
     
     # Convert the filename in vector
     filename = c(filename)
@@ -155,7 +224,7 @@ extract_data = function (data_path, filedir, filename, verbose=TRUE) {
             # Create a filelist to store all the filename
             filelist = c()
              # Get all the filename in the data directory selected
-            filelist_tmp = list.files(file.path(data_path,
+            filelist_tmp = list.files(file.path(computer_data_path,
                                                 filedir))
 
             # For all the filename in the directory selected
@@ -180,7 +249,7 @@ extract_data = function (data_path, filedir, filename, verbose=TRUE) {
 
             # Concatenate by raw data frames created by this function when filename correspond to only one filename
             df_data = rbind(df_data,
-                            extract_data(data_path, 
+                            extract_data(computer_data_path, 
                                          filedir, 
                                          f))
         }
@@ -199,8 +268,9 @@ extract_data = function (data_path, filedir, filename, verbose=TRUE) {
     }
 
     # Get the file path to the data
-    file_path = file.path(data_path, filedir, filename)
+    file_path = file.path(computer_data_path, filedir, filename)
     
+    # Extract the data as a data frame
     df_data = read.table(file_path,
                          header=TRUE,
                          na.strings=c('     -99', ' -99.000'),
@@ -208,7 +278,7 @@ extract_data = function (data_path, filedir, filename, verbose=TRUE) {
                          skip=41)[,1:2]    
 
     # Extract all the information for the station
-    df_info = extract_info(data_path, filedir, filename, verbose=FALSE)
+    df_info = extract_info(computer_data_path, filedir, filename, verbose=FALSE)
     # Get the code of the station
     code = df_info$code
     # Create a tibble with the date as Date class and the code of the station

script.R

@@ -2,18 +2,39 @@
 ### A MODIFIER ###
 
 # Path to the data
-computer_data_path = #"/home/louis/Documents/bouleau/INRAE/CDD_stationnarite/data"
-                     "C:\\Users\\louis.heraut\\Documents\\CDD_stationnarite\\data"
+computer_data_path = 
+    "/home/louis/Documents/bouleau/INRAE/CDD_stationnarite/data"
+    # "C:\\Users\\louis.heraut\\Documents\\CDD_stationnarite\\data"
   
 # Work path
-computer_work_path = #"/home/louis/Documents/bouleau/INRAE/CDD_stationnarite/ASH"
-                     "C:\\Users\\louis.heraut\\Documents\\CDD_stationnarite\\ASH"
+computer_work_path = 
+    "/home/louis/Documents/bouleau/INRAE/CDD_stationnarite/ASH"
+    # "C:\\Users\\louis.heraut\\Documents\\CDD_stationnarite\\ASH"
 
+# Manual selection
 # Path to data that will be analysed
-filedir = "test"
-
-filename = #c("H5920011_HYDRO_QJM.txt", "K4470010_HYDRO_QJM.txt")
-           "all"
+filedir = 
+    FALSE
+    # "test"
+    # "BanqueHydro_Export2021"
+filename =
+    FALSE
+    # c("H5920011_HYDRO_QJM.txt", "K4470010_HYDRO_QJM.txt")
+    # "all"
+
+# Or list selection
+# Path to the list file of station that will be analysed
+listdir = 
+    # FALSE
+    ""
+listname = 
+    "Liste-station_RRSE.docx"
+    # FALSE
+BHdir = 
+    "BanqueHydro_Export2021"
+    # FALSE
+    
+# selecdir = "RRSE_selection"
 
 ##################
 
@@ -44,6 +65,24 @@ if (!(file.exists(figdir))) {
 print(paste('figdir :', figdir))
 
 
+# Get only the selected station from a list station file
+if (is.character(listdir) & is.character(listname) & is.character(BHdir)){
+    df_selec = get_selection(computer_data_path, 
+                             listdir,
+                             listname,
+                             cnames=c('code',
+                                      'station', 
+                                      'BV_km2',
+                                      'axe_principal_concerne',
+                                      'longueur_serie',
+                                      'commentaires',
+                                      'choix'), 
+                             cisnum=c('BV_km2',
+                                      'longueur_serie'))
+    filedir = BHdir
+    filename = df_selec$filename
+}
+
 # Extract information about selected stations
 df_info = extract_info(computer_data_path, filedir, filename)