EcoPlate解析 (1)

##########スクリプト全体へのコメント###########

########必要なライブラリを全部読み込む（ライブラリ・ブロック）##########

library(library_name1)

library(library_name2)

...

########必要な関数をすべて定義する（関数ブロック）#############

func1<-function(...)

{

}

func2<-function(...)

{

}

...

########関数などを読み出して計算を実行する（解析ブロック）#######

#####解析の種類ごとにブロックを作る##############

####Analysis01#######

a<-func1(...)

####Analysis02#######

....

#######関数をつくるまでにやった予備計算のスクリプトなどを最後に残しておいてもよい####

おわり

#1)解析1に必要なライブラリを読み込む（もしあれば）

#2)解析に必要な関数を定義する前に予備的計算を行う

#3)関数を定義する

#4)定義した関数を使って解析を行う

#1)解析2に必要なライブラリを読み込む

（以下2)以降に戻って、解析の種類だけ繰り返す）

####Preparation#####

####use the function "paste" to generate the sequence of relative path to efficiently access to multiple files of ecoplate data

#example 01

paste("ACGCTT", "AGCCTTC", "data01-023", sep="_")

place_name<-"osaka"

file_name<-"sample01.csv"

file_path<-paste("./data", place_name, file_names, sep="/")

file_path

############Simple trial to load three files at the same time and stock the data into list##############

path_file<-"../data_merged/"   #folder name

data_name<-"20150512-1500higashihori"   #data name

time_m<-c(24,48,72)  #sequence of time_point

#check the type

time_m[1]

#check the type

class(time_m[1])  #--> this should be converted into character to be used in the part of file path

#To generate file path "../higashi_hori_bashi_rain/20150512-1500higashihori_24.csv""

j<-1

file_ph<-paste(path_file, data_name, "_", as.character(time_m[j]), ".csv", sep="")

file_ph

#generate empy list ecoplate data are saved as a list

data_box<-list()

#the first several lines in csv file include metadata, but should be skipped

no_skip<-7

#read the text file and saved into the item of the list

data_box[[j]] <- read.csv(file_ph, skip=no_skip, header=FALSE)  

View(data_box[[j]])

#Deleve the first column (A,B,...H)

data_box[[j]] <-data_box[[j]][,-1]  

#set names

rownames(data_box[[j]])<-c("A", "B", "C", "D", "E", "F", "H", "G")   

colnames(data_box[[j]])<-c("V1","V2","V3", "V4","V5","V6","V7","V8", "V9", "V10", "V11", "V12") 

#If you like to load three files ***24.csv, ***48.csv, ***72.csv at the same time, you can use the loop function

for(j in 1:3) {

  #file path

  file_ph<-paste(path_file, data_name, "_", as.character(time_m[j]), ".csv", sep="")

  data_box[[j]] <- read.csv(file_ph, skip=no_skip, header=FALSE)  

  #Deleve the first column (A,B,...H)

  data_box[[j]] <-data_box[[j]][,-1]  

  #set names

  rownames(data_box[[j]])<-c("A", "B", "C", "D", "E", "F", "G", "H")   

  colnames(data_box[[j]])<-c("V1","V2","V3", "V4","V5","V6","V7","V8", "V9", "V10", "V11", "V12") 

}

#Add one more complexity to avoid the error

#Skip the index j if the file does not exist

time_m2<-c(24,28, 48,72)  #sequence of time_point, noting that the data (file) at 28 does not exist

#check what happens without or with error by class(e)

#without error

j<-1

file_ph<-paste(path_file, data_name, "_", as.character(time_m2[j]), ".csv", sep="")

e<-try(read.csv(file_ph, skip=no_skip, header=T), silent=FALSE)   #error management

class(e) 

e

#with error

j<-2

file_ph<-paste(path_file, data_name, "_", as.character(time_m2[j]), ".csv", sep="")

e<-try(read.csv(file_ph, skip=no_skip, header=T), silent=FALSE)   #error management

class(e)  

#funtion version 1 using file name

###############list of parameters#######################

#relative_path & folder_name: need to specify the folder position of data 

#date_time_sample: the string to specify the sample date and time, which should have the correspondance with thte file name

#place_sample: the name of sample place, which is the part of file name

#measured_time: the vector of the measured time

#no_skip_line: The first some lines of the raw output from microplate reader represent metadata, which should be excluded

##################Output is a list; each element of the list is the data frame to have ecoplate 96 values

load_ecoplate_data_osaka <-  function(relative_path="../", folder_name="data_merged", date_time_sample="20150115-0700", place_sample ="higashihori", measured_time=c(24,48,72), no_skip_line=7)    #The parameters that already have values in the functional definition are recognized as default setting.

{  

  data_list <-list() #generate empty list, ecoplate data are saved as a list

  loop_length=length(measured_time)  #count the length of loop by the number of files 

  for(i in 1:loop_length) {

    file_name <- paste(relative_path,folder_name,"/", date_time_sample, place_sample, "_", as.character(measured_time[i]),".csv", sep="")   #the function paste is used to combine multiple character sequences. 

    e <-try(read.csv(file_name, skip=no_skip_line, header=T), silent=FALSE)   #error management

    if(class(e) == "try-error") next  #if the file doesn't exist, skip the index; it could happen because the measurement dates may not continuous

    else {

      data_list[[i]] <- read.csv(file_name, skip=no_skip_line, header=FALSE)  #read the text file and saved into the item of the list

      data_list[[i]] <-data_list[[i]][,-1]  #Deleve the first column (A,B,...H)

      rownames(data_list[[i]])<-c("A", "B", "C", "D", "E", "F", "G", "H")   #set names

      colnames(data_list[[i]])<-c("V1","V2","V3", "V4","V5","V6","V7","V8", "V9", "V10", "V11", "V12") #set names

    }

  }

  data_list  #output (return value) of this function

}

#example, you can see the second element of the result list is empty

time_m3<-c(24,34,48,72,120,168)

#call the function and save the result into "ecoplate_data01"

ecoplate_data01<-load_ecoplate_data_osaka(folder_name="data_merged", date_time_sample="20150114-2300", place_sample ="higashihori", measured_time=time_m3, no_skip_line=7)

> ecoplate_data01[[2]]

NULL

#load the metadata

meta_test<-read.csv("../meta_data/meta_sample.csv", header=TRUE)

View(meta_test)

nrow(meta_test)  #sample size in metadata

> class(meta_test$date_time_sample[2])

[1] "factor"

> as.numeric(meta_test$date_time_sample[2])

[1] 9

> as.character(meta_test$date_time_sample[2])

[1] "20150114-2300"

#We can generate file path

i<-2

folder_name<-"data_merged"

file_ph<- paste("../" ,folder_name,"/", as.character(meta_test$date_time_sample[i]), as.character(meta_test$place_sample[i]), "_", as.character(meta_test$measured_time[i]), ".csv", sep="") 

file_ph

#funciton version 2 using metadata file, which stock the the metadata of results from multiple samples 

#data in the metadata file can be used to generate file path, instead of manually specifying as in the function above

###############list of parameters#######################

#relative_path & folder_name_data: need to specify the folder position of data 

#metadata: dataframe that includes the sampling date, time, and measured time information

#no_skip_line: The first some lines of the raw output from microplate reader represent metadata, which should be excluded

##################Output is a list; each element of the list is the data frame to have ecoplate 96 values

load_ecoplate_data_osaka2 <-  function(relative_path="../", folder_name_data="data_merged", metadata=meta_test, no_skip_line=7)    

{

  data_list <-list() #generate empty list, ecoplate data are saved as a list

  loop_length=nrow(metadata)  #decide the loop length based on the sample size

  cat("The number of sample to be loaded is:", loop_length, "\n")  #output basic information

  cat("The levels of sample places are:", levels(metadata$place_sample), "\n")  #output basic information

  #file_name

  for(i in 1:loop_length) {

    file_name <- paste(relative_path,folder_name_data,"/", as.character(metadata$date_time_sample[i]), as.character(metadata$place_sample[i]), "_", as.character(metadata$measured_time[i]), ".csv", sep="")   #the function paste is used to combine multiple character sequences. 

    e <-try(read.csv(file_name, skip=no_skip_line), silent=FALSE)   #error management

    if(class(e) == "try-error") next  #if the file doesn't exist, skip the index; it could happen because the measurement dates may not continuous

    else {

      data_list[[i]] <- read.csv(file_name, skip=no_skip_line, header=FALSE)  #read the text file and saved into the item of the list

      data_list[[i]] <-data_list[[i]][,-1]  #Deleve the first column (A,B,...H)

      rownames(data_list[[i]])<-c("A", "B", "C", "D", "E", "F", "G", "H")   #set names

      colnames(data_list[[i]])<-c("V1","V2","V3", "V4","V5","V6","V7","V8", "V9", "V10", "V11", "V12") #set names

    }

  }

  data_list  #output (return value) of this function

}

#load metadata

meta_test<-read.csv("../meta_data/meta_sample.csv", header=TRUE)  

#example

osaka_data<-load_ecoplate_data_osaka2(folder_name_data="data_merged", metadata=meta_test, no_skip_line=7)  

> osaka_data<-load_ecoplate_data_osaka2(folder_name_data="data_merged", metadata=meta_test, no_skip_line=7)

The number of sample to be loaded is: 145 

The levels of sample places are: higashihori honmachi 

#Check the information of metadata & list of data (osaka_data)

meta_test[133,]

osaka_data[[133]]

> meta_test[133,]

    date_time_sample place_sample measured_time

133    20150717-1100     honmachi           168

> osaka_data[[133]]

   V1       V2       V3      V4      V5      V6       V7      V8      V9       V10   V11    V12

A 0.543 2.306 1.745 2.993 0.165 2.636 1.232 2.907 0.174 1.808 1.793 2.531

B 2.674 2.927 2.010 2.844 2.625 3.194 2.285 2.771 2.036 2.615 2.237 3.201

C 2.884 0.574 0.211 2.664 2.673 1.600 0.054 2.679 2.892 2.497 0.093 2.183

D 2.804 1.974 2.548 2.648 2.533 2.469 2.542 2.042 2.901 2.070 2.165 2.622

E 1.997 2.222 0.994 2.742 2.449 2.261 1.074 2.587 2.500 2.196 1.002 2.021

F 2.466 2.060 2.656 2.161 1.803 1.781 2.655 2.279 2.468 2.635 2.564 1.907

H 1.977 1.782 2.187 2.829 1.754 2.000 2.082 2.790 1.923 2.030 1.968 1.835

G 2.308 1.122 0.756 2.607 1.965 1.633 2.687 1.615 2.323 1.033 2.157 1.860