#------------------------------------
# AAK:  Sun  9 Aug 2014 23:38:09 PDT
# Extracting data from a data frame
#-------------------------------------
# Reading a CSV file
data <- read.csv("mydata.csv")

cat("The data has the names:\n")
print(names(data))

cat("The actual data is:\n")
print(data)

# R has built-in data sets, loading the library
library(datasets)

# airquality is one of them:
data <- airquality

# Getting rid of all NA values:
# First creating a logical index
goods <- complete.cases(data)
# Using logical indexing:
datag <- data[goods,]

cat("Good data is:\n")
print(datag)

# Extracting all NA that occur in first column "Ozone"
datawithbadozone <- data[is.na(data$Ozone),]

cat("Data with NA Ozone is:\n")
print(datawithbadozone)

# Extracting all available Ozone values and ones with higher
# Temperature than 80

datagoodozhigh80 <- data[!is.na(data$Ozone) & data$Temp >80,]

cat("Data with avail Ozone and Temp > 80 is:\n")
print(datagoodozhigh80)

# Finding the mean of Ozone on the Month 8 after eliminating NA vals (na.rm=TRUE)
meanval <- mean(data[data$Month ==8,]$Ozone,na.rm=TRUE)
cat("Mean of Ozone on month 8 after eliminating NA vals is:",meanval)