---
title:  'Tutorial 9: Classification'
output: html_notebook
editor_options: 
  chunk_output_type: inline
---

This file is part of the lecture Business Intelligence & Analytics (EESYS-BIA-M), Information Systems and Energy Efficient Systems, University of Bamberg.


```{r Load libraries}
library(FSelector) #for feature selection
library(party) #for classification algorithm decision trees
library(class) #for classification algorithm kNN
library(e1071) #for classification algorithm SVM
library(randomForest) #further random forest
```



```{r Load and prepare data}
# Load data
load("../data/classification.RData")

# Derive and investigate the dependent variable "number of residents"
adults <- as.integer(ifelse(customers$residents.numAdult=="5 oder mehr",
                            "5",customers$residents.numAdult))
children <- as.integer(ifelse(customers$residents.numChildren=="5 oder mehr",
                              "5",customers$residents.numChildren))

table(ifelse(is.na(children), adults, adults+children))
# think in classes. we have some very rare classes of number of residents (>5)

customers$pNumResidents <- sapply(ifelse(is.na(children), adults, adults+children), 
                                       function(a) {
  if(a==0 || is.na(a)){
    return(NA)
  } else if(a==1){
    return("1 person")
  } else if(a==2){
    return("2 persons")
  } else if(a<=5){
    return("3-5 persons")
  } else {
    return(">5 persons")
  }
})

customers$pNumResidents <- ordered(customers$pNumResidents, 
                                      levels=c("1 person", "2 persons", 
                                               "3-5 persons", ">5 persons"))
table(customers$pNumResidents)
```

```{r Detailed analysis of the independent variables}
# Descriptive analysis of load traces -------------------------------------
# Plot some load curves from households to get familiar with the data

household <- 8

#plot the weekly trace of one household (ts creates a time series object)
plot(ts(smd[household,], frequency = 4*24), 
     main="Weekly load curve")

#plot the monday
plot(ts(smd[household,1:(24*4)], frequency = 4*24), 
     main="Load curve of monday")

#add the other days to the same plot
cols <- heat.colors(8)
for(i in 1:6){
  lines(ts(smd[household,(i*24*4):((i+1)*24*4)], frequency = 4*24), 
        col=cols[i])  
}
legend("topleft",legend = c("Mon", "Tue", "Wed", "Thu", "Fri","Sat","Sun"), 
       col = c("black",cols), lty = 1)
```


```{r Feature extraction}
# Define and implement 10 features from SMD (e.g. mean consumption, mean 
# consumption in the evening)

calcFeatures.smd <- function(SMD){
  #SMD: the load trace for one week (vector with 672 elements)
  
  #create a matrix with 7 columns for each day
  dm15=matrix(as.numeric(SMD),ncol=7)

  # define some times
  weekday <-   1:(5*4*24)
  weekend <-   (5*4*24+1):672
  night <-       ( 1*4+1):( 6*4)
  morning <-     ( 6*4+1):(10*4)
  noon <-        (10*4+1):(14*4)
  afternoon <-   (14*4+1):(18*4)
  evening <-     (18*4+1):(22*4)
  
  #data.frame for the results
  D=data.frame(c_week=mean(dm15, na.rm = T))
  
  #calculate consumption features
  D$c_night <-     mean(dm15[night,     1:7], na.rm = T)
  D$c_morning <-   mean(dm15[morning,   1:7], na.rm = T)
  D$c_noon <-      mean(dm15[noon,      1:7], na.rm = T)
  D$c_afternoon <- mean(dm15[afternoon, 1:7], na.rm = T)
  D$c_evening <-   mean(dm15[evening,   1:7], na.rm = T)
  
  #calculate statistical features
  D$s_we_max <- max(dm15[weekend], na.rm = T)
  D$s_we_min <- min(dm15[weekend], na.rm = T)
  D$s_wd_max <- max(dm15[weekday], na.rm = T)
  D$s_wd_min <- min(dm15[weekday], na.rm = T)
  
  #calculate relations
  D$r_min_wd_we <- D$s_wd_min / D$s_we_min #division by 0 leads to NaN!
  D$r_min_wd_we <- ifelse(is.na(D$r_min_wd_we), 0, D$r_min_wd_we)
  D$r_max_wd_we <- D$s_wd_max / D$s_we_max
  D$r_max_wd_we <- ifelse(is.na(D$r_max_wd_we), 0, D$r_max_wd_we)
  
  return(D)
}

#calculate the features for one household
calcFeatures.smd(smd[2,])

features <- calcFeatures.smd(smd[1,])
for(i in 2:nrow(smd)){
  features <- rbind(features, calcFeatures.smd(smd[i,]))
}
```