Homework_11

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="Homework11Files/",
                         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)
    var_x <- rnorm(n=file_length, mean=0.7, sd=0.5) # create random x
    var_y <- runif(file_length) # create random y
    df <- data.frame(var_x,var_y) # bind into a dataframe
    file_label <- paste(file_folder,
                        "ranFile",
                        formatC(i,
                                width=3,
                                format="d",
                                flag="0"),
                                ".csv",sep="")
    # set up dta file and incorporate time stamp and minimal metadata
    write.table(cat("# Simulated random data file for batch processing homework 11","\n",
                    "# timestamp: ",as.character(Sys.time()),"\n",
                    "# GLS","\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 a regression model

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)
}

#——————————————– # Global variables

file_folder <- "Homework11Files/"
n_files <- 100
file_out <- "StatsSummary_Homework11.csv"

create 100 random data sets

dir.create(file_folder)
file_builder(file_n=n_files)
file_names <- list.files(path=file_folder)
head(file_names)

create dataframe to hold file summary stats

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 inidividual 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 file
  d_clean <- data[complete.cases(data),]
  . <- reg_stats(d_clean) #regression stats from clean file
  stats_out[i,3:5] <- unlist(.)
}

set up output file and incorporate time stamp and minimal metadata

write.table(cat("# Summary stats for ",
                "batch processing of regression models homework 11","\n",
                "# timestamp: ",as.character(Sys.time()),"\n",
                "# GLS","\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)

hist(stats_out$p_val)