New install file, comment, compute gap

README.txt

-
-
-tools
-
-install_github("https://github.com/benRenard/BFunk")
-
-install.packages("ggplot2")
+ASH package

plotting/panel.R

+# Usefull library
 library(ggplot2)
 
+width = 30
+height = 14
+dpi = 100
+
 # Time panel
 panel = function (df_data, df_info, figdir, filedir, span=Inf) {
-        
+    
     # If there is not a dedicated figure directory it creats one
     # outdir = file.path(figdir, filedir, paste('span_', as.character(span), '_years', sep=''))
-    outdir = file.path(figdir, filedir, '_years', sep='')
+    outdir = file.path(figdir, filedir, sep='')
     if (!(file.exists(outdir))) {
         dir.create(outdir)
     }
     
-    # Create name for the figure file
-    outfile = paste('Panel_', df_info$code, '.png', sep='')
-    
-    plot = 
-        ggplot(df_data, aes(x=Date, y=Qls)) +
-        geom_line()
+    # Get all different stations code
+    Code = levels(factor(df_info$code))
 
+    for (code in Code) {
+        # Create name for the figure file
+        outfile = paste('Panel_', code, '.pdf', sep='')
+        print(paste("Plotting for sation :", code))
+        
+        df_data_code = df_data[df_data$code==code,] 
+        
+        # Plot
+        plot = 
+            ggplot(df_data_code, aes(x=Date, y=Qls)) +
+            geom_line()
+        
+        # Save the plot
+        ggsave(path=outdir, 
+               filename=outfile,
+               plot=plot,
+               width=width,
+               height=height, 
+               dpi=dpi,
+               units='cm')
+    }
     
- 
-    return (plot)
 } 
 
 

processing/analyse.R

+# Usefull library
+# library(StatsAnalysisTrend)
+library(dplyr)
+
+
+# Compute the time gap by station
+get_lacune = function (df_data, df_info) {
+    
+    # Get all different stations code
+    Code = levels(factor(df_info$code))
+    
+    # Create new vector to stock results for cumulative time gap by station
+    tLac = c()
+    # Create new vector to stock results for mean time gap by station
+    meanLac = c()
+
+    # Get rows where there is no NA
+    NoNA = complete.cases(df_data)
+    # Get data where there is no NA
+    df_data_NoNA = df_data[NoNA,]
+
+    # For every station
+    for (code in Code) {
+        
+        # Get only the data rows for the selected station
+        df_data_code = df_data[df_data$code==code,]
+        # Get date for the selected station
+        Date = df_data_code$Date
+        # Get time span for the selection station
+        span = as.numeric(Date[length(Date)] - Date[1])
+        
+        # Get only the data rows with no NA for the selected station
+        df_data_NoNA_code = df_data_NoNA[df_data_NoNA$code==code,]
+        # Get date for the selected station
+        Date_NoNA = df_data_NoNA_code$Date
+        
+        # Compute the time gap
+        lac = as.numeric(diff(Date_NoNA) - 1)
+
+        # Compute the cumulative gap
+        lac_sum = sum(lac)
+        # Store the cumulative gap rate
+        tLac = c(tLac, lac_sum/span)
+
+        # Compute the mean gap
+        lac_mean = mean(lac[lac != 0])
+        # Store the mean gap
+        meanLac = c(meanLac, lac_mean)
+        
+    }
+    
+    # Compute the cumulative gap rate in pourcent
+    tLac100 = tLac * 100
+    
+    # Create a tibble
+    df_lac = tibble(code=Code, tLac100=tLac100, meanLac=meanLac)
+    
+    return (df_lac)
+}

processing/extract.R

+# Usefull library
 library(tools)
 library(dplyr)
-# library(readr)
+
 
 # General information on station
 iStatut = c('0'='inconnu', 
@@ -48,40 +49,70 @@ iQHE = c('0'='qualité hautes eaux inconnue',
 
 
 # Extraction of information
-extract_info = function (data_path, filedir, filename) {
-
+extract_info = function (data_path, filedir, filename, verbose=TRUE) {
+    
+    # Convert the filename in vector
     filename = c(filename)
     
+    # If the filename is 'all' or regroup more than one filename
     if (all(filename == 'all') | length(filename) > 1) {
+
+        # If the filename is 'all'
         if (all(filename == 'all')) {
+            # 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,
                                                 filedir))
+            
+            # For all the filename in the directory selected
             for (f in filelist_tmp) {
+                # If the filename extention is 'txt'
                 if (file_ext(f) == 'txt') {
+                    # Store the filename in the filelist
                     filelist = c(filelist, f) 
                 }
             }
+
+            # If the filename regroup more than one filename
         } else if (length(filename > 1)) {
+            # The filelist correspond to the filename
             filelist = filename
-        } 
+        }
+        
+        # Create a blank data frame
         df_info = 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,
                             extract_info(data_path, 
                                          filedir, 
-                                         f)
-                            )
+                                         f))
         }
+        
+        # Set the rownames by default (to avoid strange numbering)
         rownames(df_info) = NULL
         return (df_info)
     }
 
-    filename = filename[1]    
+    # Get the filename from the vector
+    filename = filename[1]
+    
+    # Print information if asked
+    if (verbose) {
+        print(paste("extraction of info for file :", filename))
+    }
 
+    # Get the file path to the data
     file_path = file.path(data_path, filedir, filename)
+
+    # Extract all the header
     infotxt = 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]))),
@@ -103,6 +134,7 @@ extract_info = function (data_path, filedir, filename) {
     return (df_info)
 }
 
+# Example
 # df_info = extract_info(
     # "/home/louis/Documents/bouleau/INRAE/CDD_stationnarite/data",
     # '',
@@ -110,37 +142,63 @@ extract_info = function (data_path, filedir, filename) {
 
 
 # Extraction of data
-extract_data = function (data_path, filedir, filename) {
+extract_data = function (data_path, filedir, filename, verbose=TRUE) {
     
+    # Convert the filename in vector
     filename = c(filename)
 
+    # If the filename is 'all' or regroup more than one filename
     if (all(filename == 'all') | length(filename) > 1) {
+
+        # If the filename is 'all'
         if (all(filename == 'all')) {
+            # 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,
                                                 filedir))
+
+            # For all the filename in the directory selected
             for (f in filelist_tmp) {
+                # If the filename extention is 'txt'
                 if (file_ext(f) == 'txt') {
+                    # Store the filename in the filelist
                     filelist = c(filelist, f) 
                 }
             }
+            # If the filename regroup more than one filename
         } else if (length(filename > 1)) {
+             # The filelist correspond to the filename
             filelist = filename
         } 
+
+        # Create a blank data frame
         df_data = 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_data = rbind(df_data,
                             extract_data(data_path, 
                                          filedir, 
-                                         f)
-                            )
+                                         f))
         }
+
+        # Set the rownames by default (to avoid strange numbering)
         rownames(df_data) = NULL
         return (df_data)
     }
 
+    # Get the filename from the vector
     filename = filename[1]
+    
+    # Print information if asked
+    if (verbose) {
+        print(paste("extraction of data for file :", filename))
+    }
 
+    # Get the file path to the data
     file_path = file.path(data_path, filedir, filename)
     
     df_data = read.table(file_path,
@@ -149,9 +207,11 @@ extract_data = function (data_path, filedir, filename) {
                          sep=';',
                          skip=41)[,1:2]    
 
-    df_info = extract_info(data_path, filedir, filename)
+    # Extract all the information for the station
+    df_info = extract_info(data_path, filedir, filename, verbose=FALSE)
+    # Get the code of the station
     code = df_info$code
-    
+    # Create a tibble with the date as Date class and the code of the station
     df_data = tibble(Date=as.Date(as.character(df_data$Date),
                                   format="%Y%m%d"),
                      df_data[-1],
@@ -160,6 +220,7 @@ extract_data = function (data_path, filedir, filename) {
     return (df_data)
 }
 
+# Example
 # df_data = extract_data(
 #     "/home/louis/Documents/bouleau/INRAE/CDD_stationnarite/data",
 #     '',

script.R

@@ -9,7 +9,8 @@ computer_work_path = "/home/louis/Documents/bouleau/INRAE/CDD_stationnarite/ASH"
 
 filedir = ""
 
-filename = "H5920011_HYDRO_QJM.txt"
+filename = c("H5920011_HYDRO_QJM.txt", "K4470010_HYDRO_QJM.txt")
+# filename = "all"
 
 ##################
 
@@ -19,6 +20,7 @@ setwd(computer_work_path)
 
 # Sourcing R file
 source('processing/extract.R')
+source('processing/analyse.R')
 source('plotting/panel.R')
 
 # Usefull library
@@ -33,9 +35,14 @@ figdir = file.path(computer_work_path, 'figures')
 print(paste('figdir :', figdir))
 
 
+# Extract information about selected stations
 df_info = extract_info(computer_data_path, filedir, filename)
+
+# Extract data about selected stations
 df_data = extract_data(computer_data_path, filedir, filename)
 
+# Plot time panel of debit by stations
 panel(df_data, df_info, figdir, filedir)
 
-
+# Compute gap parameters for stations
+df_lac = get_lacune(df_data, df_info)

script_install.R

+
+
+install.packages("tools")
+install.packages("devtools")
+install.packages("dplyr")
+install.packages("ggplot2")
+
+library(devtools)
+install_github("https://github.com/benRenard/BFunk")
+# install_git("git@gitlab-ssh.irstea.fr:valentin.mansanarez/statistical-analysis-of-trends.git") # SSH
+install_git("https://gitlab.irstea.fr/valentin.mansanarez/statistical-analysis-of-trends.git")
+
+
+
+ 
+
+