From 3e1edf46e6afc5a69e9fd3e81942d6f7069484e4 Mon Sep 17 00:00:00 2001
From: "louis.heraut" <louis.heraut@inrae.fr>
Date: Tue, 30 Nov 2021 11:22:06 +0100
Subject: [PATCH] Name change and new extraction all from BH
---
plotting/layout.R | 7 +-
processing/{extractBH.R => extract.R} | 101 +++++++++++++++++------
script.R | 113 +++++++++++++++-----------
3 files changed, 147 insertions(+), 74 deletions(-)
rename processing/{extractBH.R => extract.R} (80%)
diff --git a/plotting/layout.R b/plotting/layout.R
index f2e27d0..b3631f9 100644
--- a/plotting/layout.R
+++ b/plotting/layout.R
@@ -98,7 +98,7 @@ panels_layout = function (df_data, df_meta, layout_matrix, figdir='', filedir_op
for (code in Code) {
# Print code of the station for the current plotting
- print(paste("Plotting for sation :", code))
+ print(paste("Plotting for station :", code))
nbh = as.numeric(info_header) + as.numeric(!is.null(time_header))
nbg = nbp + nbh
@@ -111,8 +111,9 @@ panels_layout = function (df_data, df_meta, layout_matrix, figdir='', filedir_op
}
if (!is.null(time_header)) {
- time_header_code = time_header[time_header$code == code,]
+ time_header_code = time_header[time_header$code == code,]
+
Htime = time_panel(time_header_code, df_trend_code=NULL,
period=period, missRect=TRUE,
unit2day=365.25, type='Q')
@@ -129,7 +130,7 @@ panels_layout = function (df_data, df_meta, layout_matrix, figdir='', filedir_op
unit2day = list_df2plot[[i]]$unit2day
missRect = list_df2plot[[i]]$missRect
type = list_df2plot[[i]]$type
-
+
df_data_code = df_data[df_data$code == code,]
df_trend_code = df_trend[df_trend$code == code,]
diff --git a/processing/extractBH.R b/processing/extract.R
similarity index 80%
rename from processing/extractBH.R
rename to processing/extract.R
index 2ce4f4b..606877d 100644
--- a/processing/extractBH.R
+++ b/processing/extract.R
@@ -83,10 +83,40 @@ iRegHydro = c('D'='Affluents du Rhin',
'4'='Réunion')
+create_selection = function (computer_data_path, filedir, outname) {
+
+ outfile = file.path(computer_data_path, outname)
+ codelist = c()
+ dir_path = file.path(computer_data_path, filedir)
+ filelist_tmp = list.files(dir_path)
+
+ for (f in filelist_tmp) {
+ if (file_ext(f) == 'txt') {
+ codelist = c(codelist, gsub('.txt', '', f))
+ }
+ }
+
+ df_file = tibble(code=codelist,
+ filename=paste(codelist,
+ '_HYDRO_QJM.txt', sep=''),
+ ok=TRUE)
+
+ write.table(df_file, outfile, sep=";", col.names=TRUE, quote=FALSE)
+
+ return (NULL)
+}
+
+# Example
+# create_selection(
+# "/home/louis/Documents/bouleau/INRAE/CDD_stationnarite/data",
+# "France207",
+# "nival_selection.txt")
+
+
# 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'),
- c_num=c('BV_km2', 'longueur_serie')) {
+get_selection_AG = function (computer_data_path, listdir, listname,
+ cnames=c('code','station', 'BV_km2', 'axe_principal_concerne', 'longueur_serie', 'commentaires', 'choix'),
+ c_num=c('BV_km2', 'longueur_serie')) {
# Get the file path to the data
list_path = file.path(computer_data_path, listdir, listname)
@@ -123,22 +153,46 @@ get_selection = function (computer_data_path, listdir, listname,
}
# Example
-# df_selec = get_selection(
-# "/home/louis/Documents/bouleau/INRAE/CDD_stationnarite/data",
-# "",
-# "Liste-station_RRSE.docx",
-# cnames=c('code','station',
-# 'BV_km2',
-# 'axe_principal_concerne',
-# 'longueur_serie',
-# 'commentaires',
-# 'choix'),
-# c_num=c('BV_km2',
-# 'longueur_serie'))
+df_selec_AG = get_selection_AG(
+ "/home/louis/Documents/bouleau/INRAE/CDD_stationnarite/data",
+ "",
+ "Liste-station_RRSE.docx",
+ cnames=c('code','station',
+ 'BV_km2',
+ 'axe_principal_concerne',
+ 'longueur_serie',
+ 'commentaires',
+ 'choix'),
+ c_num=c('BV_km2',
+ 'longueur_serie'))
+
+
+get_selection_NV = function (computer_data_path, listdir, listname) {
+
+ # Get the file path to the data
+ list_path = file.path(computer_data_path, listdir, listname)
+
+ # Extract the data as a data frame
+ df_selec = read.table(list_path,
+ header=TRUE,
+ encoding='UTF-8',
+ sep=';',
+ )
+ df_selec = tibble(code=as.character(df_selec$code),
+ filename=as.character(df_selec$filename),
+ ok=df_selec$ok)
+
+ return (df_selec)
+}
+# Example
+# df_selec_NV = get_selection_NV(
+ # "/home/louis/Documents/bouleau/INRAE/CDD_stationnarite/data",
+ # "",
+ # "nival_selection.txt")
# Extraction of metadata
-extractBH_meta = function (computer_data_path, filedir, filename, verbose=TRUE) {
+extract_meta = function (computer_data_path, filedir, filename, verbose=TRUE) {
# Convert the filename in vector
filename = c(filename)
@@ -177,7 +231,7 @@ extractBH_meta = function (computer_data_path, filedir, filename, verbose=TRUE)
# Concatenate by raw data frames created by this function when filename correspond to only one filename
df_meta = rbind(df_meta,
- extractBH_meta(computer_data_path,
+ extract_meta(computer_data_path,
filedir,
f))
}
@@ -192,7 +246,7 @@ extractBH_meta = function (computer_data_path, filedir, filename, verbose=TRUE)
# Print metadata if asked
if (verbose) {
- print(paste("extraction of BH info for file :", filename))
+ print(paste("extraction of BH meta for file :", filename))
}
# Get the file path to the data
@@ -221,7 +275,6 @@ extractBH_meta = function (computer_data_path, filedir, filename, verbose=TRUE)
QME=iQME[trimws(substr(metatxt[26], 74, 74))],
QHE=iQHE[trimws(substr(metatxt[26], 76, 76))],
file_path=file_path,
- source='BH'
)
df_meta$region_hydro = iRegHydro[substr(df_meta$code, 1, 1)]
@@ -235,14 +288,14 @@ extractBH_meta = function (computer_data_path, filedir, filename, verbose=TRUE)
}
# Example
-# df_meta = extractBH_meta(
+# df_meta = extract_meta(
# "/home/louis/Documents/bouleau/INRAE/CDD_stationnarite/data",
# '',
# c('H5920011_HYDRO_QJM.txt', 'K4470010_HYDRO_QJM.txt'))
# Extraction of data
-extractBH_data = function (computer_data_path, filedir, filename, verbose=TRUE) {
+extract_data = function (computer_data_path, filedir, filename, verbose=TRUE) {
# Convert the filename in vector
filename = c(filename)
@@ -280,7 +333,7 @@ extractBH_data = function (computer_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,
- extractBH_data(computer_data_path,
+ extract_data(computer_data_path,
filedir,
f))
}
@@ -311,7 +364,7 @@ extractBH_data = function (computer_data_path, filedir, filename, verbose=TRUE)
skip=41)
# Extract all the metadata for the station
- df_meta = extractBH_meta(computer_data_path, filedir, filename, verbose=FALSE)
+ df_meta = extract_meta(computer_data_path, filedir, filename, verbose=FALSE)
# Get the code of the station
code = df_meta$code
# Create a tibble with the date as Date class and the code of the station
@@ -330,7 +383,7 @@ extractBH_data = function (computer_data_path, filedir, filename, verbose=TRUE)
}
# Example
-# df_data = extractBH_data(
+# df_data = extract_data(
# "/home/louis/Documents/bouleau/INRAE/CDD_stationnarite/data",
# '',
# c('H5920011_HYDRO_QJM.txt', 'K4470010_HYDRO_QJM.txt'))
diff --git a/script.R b/script.R
index d45154a..d7763d0 100644
--- a/script.R
+++ b/script.R
@@ -15,57 +15,53 @@ computer_work_path =
### BANQUE HYDRO ###
# Path to the directory where BH data is stored
-BHfiledir =
- ""
- # "BanqueHydro_Export2021"
+filedir =
+ # ""
+ "BanqueHydro_Export2021"
+
+
+### MANUAL SELECTION ###
+# Name of the file that will be analysed from the AG directory
+filename =
+ # ""
-## Manual selection ##
-# Name of the file that will be analysed from the BH directory
-BHfilename =
- ""
# c(
# "S2235610_HYDRO_QJM.txt",
# "P1712910_HYDRO_QJM.txt",
# "P0885010_HYDRO_QJM.txt",
- # "A1000030_HYDRO_QJM.txt",
+ # "O5055010_HYDRO_QJM.txt",
# "A2250310_HYDRO_QJM.txt"
# )
-## Or list selection ##
-# Path to the list file of BH data that will be analysed
-BHlistdir =
+ c("O3035210_HYDRO_QJM.txt",
+ "O3011010_HYDRO_QJM.txt",
+ "O1442910_HYDRO_QJM.txt")
+
+
+### AGENCE ADOUR GARONNE SELECTION ###
+# Path to the list file of AG data that will be analysed
+AGlistdir =
""
-BHlistname =
+AGlistname =
""
# "Liste-station_RRSE.docx"
-
-
-### NIVALE ###
-# Path to the directory where NV data is stored
-NVfiledir =
- # ""
- "France207"
-
-# Name of the file that will be analysed from the NV directory
-NVfilename =
- # ""
- "all"
+### NIVALE SELECTION ###
# Path to the list file of metadata about station that will be analysed
NVlistdir =
""
NVlistname =
- # ""
- "liste_bv_principaux_global.txt"
+ ""
+ # "nival_selection.txt"
### TREND ANALYSIS ###
# Time period to analyse
period_all = c("1800-01-01", "2019-12-31")
-period2 = c("1980-01-01", "2019-12-31")
+period2 = c("1968-01-01", "2019-12-31")
########################
@@ -76,8 +72,7 @@ period2 = c("1980-01-01", "2019-12-31")
setwd(computer_work_path)
# Sourcing R file
-source('processing/extractBH.R', encoding='latin1')
-source('processing/extractNV.R', encoding='latin1')
+source('processing/extract.R', encoding='latin1')
source('processing/format.R', encoding='latin1')
source('processing/analyse.R', encoding='latin1')
source('plotting/panel.R', encoding='latin1')
@@ -101,12 +96,19 @@ if (!(file.exists(figdir))) {
print(paste('figdir :', figdir))
-# BANQUE HYDRO #
-# Get only the selected station from a list station file
-if (BHlistname != ""){
- df_selec = get_selection(computer_data_path,
- BHlistdir,
- BHlistname,
+df_data_AG = NULL
+df_data_NV = NULL
+df_meta_AG = NULL
+df_meta_NV = NULL
+
+
+# AGENCE ADOUR GARONNE SELECTION #
+if (AGlistname != ""){
+
+ # Get only the selected station from a list station file
+ df_selec_AG = get_selection_AG(computer_data_path,
+ AGlistdir,
+ AGlistname,
cnames=c('code',
'station',
'BV_km2',
@@ -117,28 +119,45 @@ if (BHlistname != ""){
c_num=c('BV_km2',
'longueur_serie'))
- BHfilename = df_selec[df_selec$ok,]$filename
+ filename = df_selec_AG[df_selec_AG$ok,]$filename
+
+ # Extract metadata about selected stations
+ df_meta_AG = extract_meta(computer_data_path, filedir, filename)
+
+ # Extract data about selected stations
+ df_data_AG = extract_data(computer_data_path, filedir, filename)
}
+# NIVALE SELECTION #
+if (NVlistname != ""){
+
+ # Get only the selected station from a list station file
+ df_selec_NV = get_selection_NV(computer_data_path,
+ NVlistdir,
+ NVlistname)
-# Extract metadata about selected stations
-df_meta_BH = extractBH_meta(computer_data_path, BHfiledir, BHfilename)
+ filename = df_selec_NV[df_selec_NV$ok,]$filename
-# Extract data about selected stations
-df_data_BH = extractBH_data(computer_data_path, BHfiledir, BHfilename)
+ # Extract metadata about selected stations
+ df_meta_NV = extract_meta(computer_data_path, filedir, filename)
+ # Extract data about selected stations
+ df_data_NV = extract_data(computer_data_path, filedir, filename)
+}
-# NIVALE #
-# Extract metadata about selected stations
-df_meta_NV = extractNVlist_meta(computer_data_path, NVfiledir, NVlistdir, NVlistname)
-### /!\ missing station info ###
+# MANUAL SELECTION #
+if (AGlistname == "" & NVlistname == "") {
+
+ # Extract metadata about selected stations
+ df_meta_AG = extract_meta(computer_data_path, filedir, filename)
-# Extract data about selected stations
-df_data_NV = extractNV_data(computer_data_path, NVfiledir, NVfilename)
+ # Extract data about selected stations
+ df_data_AG = extract_data(computer_data_path, filedir, filename)
+}
# JOIN #
-df_join = join(df_data_BH, df_data_NV, df_meta_BH, df_meta_NV)
+df_join = join(df_data_AG, df_data_NV, df_meta_AG, df_meta_NV)
df_data = df_join$data
df_meta = df_join$meta
--
GitLab