###
###
###  Superconductor - Prelim  ver 0.0.4
###
###
####################################################


#-------------------------------------------------
###--- 0. Preliminary
library(tidyverse)
Super <- read_csv("https://nmimoto.github.io/datasets/superconduct.csv")
Super          # see the data

dim(Super)
names(Super)   # list of column names

Super                    # only first 10 rows will print
print(Super, n=100)      # if you want to see more rows
print(Super, width=1000) # if you want to see more cols


# Histogram of the respoonse variable
plot(Super$critical_temp)
hist(Super$critical_temp)


# Rename "critial_temp" column as "resp" and move "resp" columnm to 1st
Super2 = Super %>% rename(resp=critical_temp) %>% relocate(resp)
Super2

# Take random sample of 1000 rows b/c Super2 will take too long to analyze.
set.seed(5563)
Super3 <- Super2[sample(nrow(Super2), 1000), ]

#-------------------------------------------------
###--- 1. Routine Exploratory Analysis (class of resp should be "dbl")
Orig <- Super3        # "resp" column needed

  #- Check for N/A in data. Remove if there's any.
  summary(Orig)
  sum(is.na(Orig))
  # If there is na in the data, run below
  dim(Orig)
  Orig <- Orig %>% na.omit()
  dim(Orig)


  ##----------
  ##- Correlation Check

  # Pick columns that are numeric
  library(corrplot)    # install.packages("corrplot")
    Orig_num <- Orig %>% select_if(is.numeric)
    # cor(Orig_num)
    corrplot::corrplot(cor(Orig_num))
    # corrplot::corrplot(cor(Orig_num), method="number")


  ##----------
  ##- Visualization

  # pairs(Orig) equivalent
  library(GGally)      # install.packages("GGally")
    #GGally::ggpairs(Orig[, c(2:7, 1)], aes(alpha=1))
    #GGally::ggpairs(Orig[, c(8:14, 1)], aes(alpha=1))

    # Too many columns to plot


  ###----------
  ###- Chi-sq test of association for each column

  # Pick columns that has more than 1 unique value
  list_cols <- Orig %>% summarise_all(function(x) length(unique(x))) %>%
        gather() %>% filter(value>1) %>% pull(key)

  # Apply chisq.test to those columns
  ChiSq.pval <- Orig %>% select(list_cols) %>%
        summarise_all(funs(chisq.test(., Orig$resp)$p.value))

  ChiSq.pval <- Orig %>% summarise_all(funs(chisq.test(., Orig$resp)$p.value))
  ChiSq.pval
  barplot(t(t(as.matrix(ChiSq.pval))), las=2, cex.names=1,
      main="p-values from Chi-sq test of association")
  abline(h=.05, col='red')

  which(ChiSq.pval < .05)             # Col num of variables w <.05 p-value
  list_cols[which(ChiSq.pval < .05)]  # Top list of 'important' variables

  which(ChiSq.pval > .6)              # Col num of variables w >.6 p-value
  list_cols[which(ChiSq.pval > .6)]   # Top list of 'unimportatnt' variables

### End of Routine Exploratory Analysis.
### Try repeating with Super3.