inst/s_data_preprocess_4.R

In smallsets: Visual Documentation for Data Preprocessing

# smallsets snap s_data caption[Remove rows where C2
# is FALSE.]caption
s_data <- s_data[s_data$C2 == TRUE, ]

# smallsets snap 8 s_data caption[Replace missing values in C6 and
# C8 with column means.]caption
s_data$C6[is.na(s_data$C6)] <- mean(s_data$C6, na.rm = TRUE)
s_data$C8[is.na(s_data$C8)] <- mean(s_data$C8, na.rm = TRUE)

# smallsets snap s_data caption[Drop C7 because there are too many
# missing values.]caption
s_data$C7 <- NULL

# smallsets snap +1 s_data caption[Create a new column,
# C9, by summing C3 and C4.]caption
s_data$C9 <- s_data$C3 + s_data$C4