Homework_11

Home Page

# Batch Processing
# Bio381 notes
# Andrew McCracken
# 4/5/22

########## Build a set of random files ###########
##################################################
# function: file_builder
# create a set of random files for regression
# input: file_n = number of files to create
#       : file_folder = name of folder for random files
#       : file_size = c(min,max) number of rows in file
#       : file_na = number on average of NA values per column
# output: set of random files
#------------------------------------------------- 
file_builder <- function(file_n=10,
                         file_folder="RandomFiles/",
                         file_size=c(15,100),
                         file_na=3){
 
   for (i in seq_len(file_n)) {
    file_length <- sample(file_size[1]:file_size[2],size=1) # get number of rows
    var_x <- runif(file_length) # create random x
    var_y <- runif(file_length) # create randon y
    df <- data.frame(var_x,var_y) # bind into a data frame
    bad_vals <- rpois(n=1,lambda=file_na) # determine NA number
    df[sample(nrow(df),size=bad_vals),1] <- NA # random NA in var_x
    df[sample(nrow(df),size=bad_vals),2] <- NA # random NA in var_y
    
    # create label for file name with padded zeroes
    file_label <- paste(file_folder,
                        "ranFile",
                        formatC(i,
                                width=3,
                                format="d",
                                flag="0"),
                        ".csv",sep="")
    
    # set up data file and incorporate time stamp and minimal metadata
    write.table(cat("# Simulated random data file for batch processing","\n",
                    "# timestamp: ",as.character(Sys.time()),"\n",
                    "# NJG","\n",
                    "# ------------------------", "\n",
                    "\n",
                    file=file_label,
                    row.names="",
                    col.names="",
                    sep=""))
    
    # now add the data frame
    write.table(x=df,
                file=file_label,
                sep=",",
                row.names=FALSE,
                append=TRUE)
    
    
  }
}


#### Run regression model and extract stats
##################################################
# function: reg_stats
# fits linear model, extracts statistics
# input: 2-column data frame (x and y)
# output: slope, p-value, and r2
#------------------------------------------------- 
reg_stats <- function(d=NULL) {
  if(is.null(d)) {
    x_var <- runif(10)
    y_var <- runif(10)
    d <- data.frame(x_var,y_var)
  }
  . <- lm(data=d,d[,2]~d[,1])
  . <- summary(.)
  stats_list <- list(slope=.$coefficients[2,1],
                     p_val=.$coefficients[2,4],
                     r2=.$r.squared)
  return(stats_list)
  
}

#############################################################################
### Body of script for batch processing of regression models

#--------------------------------------------
# Global variables
file_folder <- "RandomFiles/"
n_files <- 100
file_out <- "StatsSummary.csv"
#--------------------------------------------

# Create 100 random data sets
dir.create(file_folder)
file_builder(file_n=n_files)
file_names <- list.files(path=file_folder)

# Create data frame to hold file summary statistics
ID <- seq_along(file_names)
file_name <- file_names
slope <- rep(NA,n_files)
p_val <- rep(NA,n_files)
r2 <- rep(NA,n_files)

stats_out <- data.frame(ID,file_name,slope,p_val,r2)

# batch process by looping through individual files
for (i in seq_along(file_names)) {
  data <- read.table(file=paste(file_folder,file_names[i],sep=""),
                     sep=",",
                     header=TRUE) # read in next data file
  
  d_clean <- data[complete.cases(data),] # get clean cases
  
  . <- reg_stats(d_clean) # pull regression stats from clean file
  stats_out[i,3:5] <- unlist(.) # unlist, copy into last 3 columns
  
}
# set up output file and incorporate time stamp and minimal metadata
write.table(cat("# Summary stats for ",
                "batch processing of regression models","\n",
                "# timestamp: ",as.character(Sys.time()),"\n",
                "# ARM","\n",
                "# ------------------------", "\n",
                "\n",
                file=file_out,
                row.names="",
                col.names="",
                sep=""))

# now add the data frame
write.table(x=stats_out,
            file=file_out,
            row.names=FALSE,
            col.names=TRUE,
            sep=",",
            append=TRUE)


# Plot p-value Distribution as Histogram
hist(stats_out$p_val)

# Plot Slope Distribution as Histogram
hist(stats_out$slope)