diff --git a/processing/analyse.R b/processing/analyse.R
index 5977ded39318d64477ed4fb5a3799142611132f6..604116b2b5fc61bf2f159944cef091d488607fc8 100644
--- a/processing/analyse.R
+++ b/processing/analyse.R
@@ -157,11 +157,11 @@ get_QMNAtrend = function (df_data, period) {
}
-get_VCN10trend = function (df_data, df_info, period) {
+get_VCN10trend = function (df_data, df_meta, period) {
# MINIMUM 10 DAY AVERAGE FLOW OVER THE YEAR : VCN10 #
# Get all different stations code
- Code = levels(factor(df_info$code))
+ Code = levels(factor(df_meta$code))
df_data_roll = tibble()
diff --git a/processing/extractBH.R b/processing/extractBH.R
index 09ea390447fabbe5d2efc24fd513c338ce601981..a55d9f89c5ebfe95756a257e36608650e745702f 100644
--- a/processing/extractBH.R
+++ b/processing/extractBH.R
@@ -4,7 +4,7 @@ library(dplyr)
library(officer)
-# General information on station
+# General metadata on station
iStatut = c('0'='inconnu',
'1'='station avec signification hydrologique',
'2'='station sans signification hydrologique',
@@ -102,8 +102,8 @@ get_selection = function (computer_data_path, listdir, listname,
# 'longueur_serie'))
-# Extraction of information
-extractBH_info = function (computer_data_path, filedir, filename, verbose=TRUE) {
+# Extraction of metadata
+extractBH_meta = function (computer_data_path, filedir, filename, verbose=TRUE) {
# Convert the filename in vector
filename = c(filename)
@@ -135,27 +135,27 @@ extractBH_info = function (computer_data_path, filedir, filename, verbose=TRUE)
}
# Create a blank data frame
- df_info = data.frame()
+ df_meta = data.frame()
# For all the file in the filelist
for (f in filelist) {
# Concatenate by raw data frames created by this function when filename correspond to only one filename
- df_info = rbind(df_info,
- extractBH_info(computer_data_path,
+ df_meta = rbind(df_meta,
+ extractBH_meta(computer_data_path,
filedir,
f))
}
# Set the rownames by default (to avoid strange numbering)
- rownames(df_info) = NULL
- return (df_info)
+ rownames(df_meta) = NULL
+ return (df_meta)
}
# Get the filename from the vector
filename = filename[1]
- # Print information if asked
+ # Print metadata if asked
if (verbose) {
print(paste("extraction of BH info for file :", filename))
}
@@ -167,29 +167,29 @@ extractBH_info = function (computer_data_path, filedir, filename, verbose=TRUE)
if (file.exists(file_path) & substr(file_path, nchar(file_path), nchar(file_path)) != '/') {
# Extract all the header
- infotxt = c(readLines(file_path, n=41))
+ metatxt = c(readLines(file_path, n=41))
- # Create a tibble with all the information needed
- df_info =
- tibble(code=trimws(substr(infotxt[11], 38, nchar(infotxt[11]))),
- nom=trimws(substr(infotxt[12], 39, nchar(infotxt[12]))),
- territoire=trimws(substr(infotxt[13], 39, nchar(infotxt[13]))),
- L93X=as.numeric(substr(infotxt[16], 38, 50)),
- L93Y=as.numeric(substr(infotxt[16], 52, 63)),
- surface_km2=as.numeric(substr(infotxt[19], 38, 50)),
- statut=iStatut[trimws(substr(infotxt[26], 38, 50))],
- finalite=iFinalite[trimws(substr(infotxt[26], 52, 56))],
- type=iType[trimws(substr(infotxt[26], 58, 58))],
- influence=iInfluence[trimws(substr(infotxt[26], 60, 60))],
- debit=iDebit[trimws(substr(infotxt[26], 62, 62))],
- QBE=iQBE[trimws(substr(infotxt[26], 72, 72))],
- QME=iQME[trimws(substr(infotxt[26], 74, 74))],
- QHE=iQHE[trimws(substr(infotxt[26], 76, 76))],
+ # Create a tibble with all the metadata needed
+ df_meta =
+ tibble(code=trimws(substr(metatxt[11], 38, nchar(metatxt[11]))),
+ nom=trimws(substr(metatxt[12], 39, nchar(metatxt[12]))),
+ territoire=trimws(substr(metatxt[13], 39, nchar(metatxt[13]))),
+ L93X=as.numeric(substr(metatxt[16], 38, 50)),
+ L93Y=as.numeric(substr(metatxt[16], 52, 63)),
+ surface_km2=as.numeric(substr(metatxt[19], 38, 50)),
+ statut=iStatut[trimws(substr(metatxt[26], 38, 50))],
+ finalite=iFinalite[trimws(substr(metatxt[26], 52, 56))],
+ type=iType[trimws(substr(metatxt[26], 58, 58))],
+ influence=iInfluence[trimws(substr(metatxt[26], 60, 60))],
+ debit=iDebit[trimws(substr(metatxt[26], 62, 62))],
+ QBE=iQBE[trimws(substr(metatxt[26], 72, 72))],
+ QME=iQME[trimws(substr(metatxt[26], 74, 74))],
+ QHE=iQHE[trimws(substr(metatxt[26], 76, 76))],
file_path=file_path,
source='BH'
)
- return (df_info)
+ return (df_meta)
} else {
print(paste('filename', file_path, 'do not exist'))
@@ -198,7 +198,7 @@ extractBH_info = function (computer_data_path, filedir, filename, verbose=TRUE)
}
# Example
-# df_info = extractBH_info(
+# df_meta = extractBH_meta(
# "/home/louis/Documents/bouleau/INRAE/CDD_stationnarite/data",
# '',
# c('H5920011_HYDRO_QJM.txt', 'K4470010_HYDRO_QJM.txt'))
@@ -256,7 +256,7 @@ extractBH_data = function (computer_data_path, filedir, filename, verbose=TRUE)
# Get the filename from the vector
filename = filename[1]
- # Print information if asked
+ # Print metadata if asked
if (verbose) {
print(paste("extraction of BH data for file :", filename))
}
@@ -273,10 +273,10 @@ extractBH_data = function (computer_data_path, filedir, filename, verbose=TRUE)
sep=';',
skip=41)
- # Extract all the information for the station
- df_info = extractBH_info(computer_data_path, filedir, filename, verbose=FALSE)
+ # Extract all the metadata for the station
+ df_meta = extractBH_meta(computer_data_path, filedir, filename, verbose=FALSE)
# Get the code of the station
- code = df_info$code
+ code = df_meta$code
# Create a tibble with the date as Date class and the code of the station
df_data = tibble(Date=as.Date(as.character(df_data$Date),
format="%Y%m%d"),
diff --git a/processing/extractNV.R b/processing/extractNV.R
index babdf908a572eb9f45e37e72305976738ea07c04..3f9ffe9af3d75d1bf652cb4d21f77318905fe728 100644
--- a/processing/extractNV.R
+++ b/processing/extractNV.R
@@ -3,12 +3,12 @@ library(tools)
library(dplyr)
-# Extraction of information
-extractNVlist_info = function (computer_data_path, filedir, listdir, listname, verbose=TRUE) {
+# Extraction of metadata
+extractNVlist_meta = function (computer_data_path, filedir, listdir, listname, verbose=TRUE) {
- # Print information if asked
+ # Print metadata if asked
if (verbose) {
- print(paste("extraction of NV info for file :", listname))
+ print(paste("extraction of NV meta for file :", listname))
}
# Get the file path to the list of station
@@ -17,7 +17,7 @@ extractNVlist_info = function (computer_data_path, filedir, listdir, listname, v
if (file.exists(list_path) & substr(list_path, nchar(list_path), nchar(list_path)) != '/') {
# Extract the data as a data frame
- df_info = read.table(list_path,
+ df_meta = read.table(list_path,
header=TRUE)
# Create a filelist to store all the filename
@@ -37,44 +37,44 @@ extractNVlist_info = function (computer_data_path, filedir, listdir, listname, v
}
}
- exist = df_info$CODE %in% codelist
- missing = codelist[!(codelist %in% df_info$CODE)]
- print(paste('missing station info for :', missing))
+ exist = df_meta$CODE %in% codelist
+ missing = codelist[!(codelist %in% df_meta$CODE)]
+ print(paste('missing station meta for :', missing))
- df_info = df_info[exist,]
-
- # Create a tibble with all the information needed
- df_info =
- tibble(code=as.character(df_info$CODE),
- nom=as.character(df_info$NOM),
- L93X=df_info$X_L2E,
- L93Y=df_info$Y_L2E,
- surface_km2=df_info$S_km2,
- altitude_m=df_info$Alt,
+ df_meta = df_meta[exist,]
+
+ # Create a tibble with all the metadata needed
+ df_meta =
+ tibble(code=as.character(df_meta$CODE),
+ nom=as.character(df_meta$NOM),
+ L93X=df_meta$X_L2E,
+ L93Y=df_meta$Y_L2E,
+ surface_km2=df_meta$S_km2,
+ altitude_m=df_meta$Alt,
file_path=file.path(dir_path,
- paste(df_info$CODE, '.txt', sep='')),
+ paste(df_meta$CODE, '.txt', sep='')),
source='NV'
)
- df_info = bind_rows(df_info,
+ df_meta = bind_rows(df_meta,
data.frame(code=missing,
file_path=file.path(dir_path,
paste(missing,
'.txt',
sep=''))))
- df_info = df_info[order(df_info$code),]
+ df_meta = df_meta[order(df_meta$code),]
} else {
print(paste('filename', list_path, 'do not exist'))
return (NULL)
}
- return (df_info)
+ return (df_meta)
}
# Example
-# df_info = extractNVlist_info(
+# df_meta = extractNVlist_meta(
# "/home/louis/Documents/bouleau/INRAE/CDD_stationnarite/data",
# 'France207',
# '',
@@ -133,7 +133,7 @@ extractNV_data = function (computer_data_path, filedir, filename, verbose=TRUE)
# Get the filename from the vector
filename = filename[1]
- # Print information if asked
+ # Print metadata if asked
if (verbose) {
print(paste("extraction of NV data for file :", filename))
}
diff --git a/processing/format.R b/processing/format.R
index 28f9c7ee1559188d301f60da7292aab255012e40..d5ddb597bbc57defd69b6f285fd73774eff0f36f 100644
--- a/processing/format.R
+++ b/processing/format.R
@@ -1,35 +1,35 @@
library(dplyr)
-join = function (df_data_BH, df_data_NV, df_info_BH, df_info_NV) {
+join = function (df_data_BH, df_data_NV, df_meta_BH, df_meta_NV) {
if (!is.null(df_data_NV) & !is.null(df_data_BH)) {
# Get the station in common
- common = levels(factor(df_info_NV[df_info_NV$code %in% df_info_BH$code,]$code))
+ common = levels(factor(df_meta_NV[df_meta_NV$code %in% df_meta_BH$code,]$code))
# Get the Nv station to add
- NVadd = levels(factor(df_info_NV[!(df_info_NV$code %in% df_info_BH$code),]$code))
+ NVadd = levels(factor(df_meta_NV[!(df_meta_NV$code %in% df_meta_BH$code),]$code))
- # Select only the NV info to add
- df_info_NVadd = df_info_NV[df_info_NV$code %in% NVadd,]
+ # Select only the NV meta to add
+ df_meta_NVadd = df_meta_NV[df_meta_NV$code %in% NVadd,]
# Join NV data to BH data
- df_info = full_join(df_info_BH, df_info_NVadd, by=c("code", "nom", "L93X", "L93Y", "surface_km2", "file_path"))
+ df_meta = full_join(df_meta_BH, df_meta_NVadd, by=c("code", "nom", "L93X", "L93Y", "surface_km2", "file_path"))
# Select only the NV data to add
df_data_NVadd = df_data_NV[df_data_NV$code %in% NVadd,]
- # Join NV info to BH info
+ # Join NV meta to BH meta
df_data = full_join(df_data_BH, df_data_NVadd, by=c("Date", "Qm3s", "code"))
} else if (is.null(df_data_NV) & !is.null(df_data_BH)) {
- df_info = df_info_BH
+ df_meta = df_meta_BH
df_data = df_data_BH
} else if (!is.null(df_data_NV) & is.null(df_data_BH)) {
- df_info = df_info_NV
+ df_meta = df_meta_NV
df_data = df_data_NV
} else {
stop('No data')
}
- return (list(data=df_data, info=df_info))
+ return (list(data=df_data, meta=df_meta))
}
diff --git a/script.R b/script.R
index 1ff1e56a7e90409833f7f1f4286ef0d267b26ea0..386ec84aa7da64e46a696a815d96ebedf18cf2a1 100644
--- a/script.R
+++ b/script.R
@@ -48,7 +48,7 @@ NVfilename =
# "all"
-# Path to the list file of information about station that will be analysed
+# Path to the list file of metadata about station that will be analysed
NVlistdir =
""
@@ -115,16 +115,16 @@ if (BHlistname != ""){
BHfilename = df_selec[df_selec$ok,]$filename
}
-# Extract information about selected stations
-df_info_BH = extractBH_info(computer_data_path, BHfiledir, BHfilename)
+# Extract metadata about selected stations
+df_meta_BH = extractBH_meta(computer_data_path, BHfiledir, BHfilename)
# Extract data about selected stations
df_data_BH = extractBH_data(computer_data_path, BHfiledir, BHfilename)
# NIVALE #
-# Extract information about selected stations
-df_info_NV = extractNVlist_info(computer_data_path, NVfiledir, NVlistdir, NVlistname)
+# Extract metadata about selected stations
+df_meta_NV = extractNVlist_meta(computer_data_path, NVfiledir, NVlistdir, NVlistname)
### /!\ missing station info ###
# Extract data about selected stations
@@ -132,21 +132,21 @@ df_data_NV = extractNV_data(computer_data_path, NVfiledir, NVfilename)
# JOIN #
-df_join = join(df_data_BH, df_data_NV, df_info_BH, df_info_NV)
+df_join = join(df_data_BH, df_data_NV, df_meta_BH, df_meta_NV)
df_data = df_join$data
-df_info = df_join$info
+df_meta = df_join$meta
# TIME PANEL #
# Plot time panel of debit by stations
-# panel(df_data, df_info, figdir, "")
-# panel(df_data, df_info, figdir, "", is_sqrt=TRUE)
+# panel(df_data, df_meta, figdir, "")
+# panel(df_data, df_meta, figdir, "", is_sqrt=TRUE)
### /!\ Removed 185 row(s) containing missing values (geom_path) -> remove NA ###
# ANALYSE #
# Compute gap parameters for stations
-# df_lac = get_lacune(df_data, df_info)
+# df_lac = get_lacune(df_data, df_meta)
# QA TREND #
@@ -156,4 +156,4 @@ res_QAtrend = get_QAtrend(df_data, period)
# res_QMNAtrend = get_QMNAtrend(df_data, period)
# VCN10 TREND #
-# res_VCN10trend = get_VCN10trend(df_data, df_info, period)
+res_VCN10trend = get_VCN10trend(df_data, df_meta, period)