ampli/R/clusterviz.R

library(reticulate)
library(ggplot2)
library(dplyr)
theme_set(theme_bw())
use_virtualenv("../venv/")

p <- import("pandas")
sns <- import("seaborn")
cbp <- as.character(p$Series(sns$color_palette("colorblind", as.integer(9))$as_hex()))
aggdf <- p$read_pickle("../data/9-clusters.agg.pkl")
aggdf <- as.data.frame(aggdf)
aggdf$cluster <- factor(aggdf$cluster)
str(aggdf)

ggplot(aggdf, aes(y = kwh_tot_mean, x = cluster)) + geom_boxplot()

ggplot(aggdf, aes(x = read_time, y = kwh_tot_mean, color = cluster)) + 
    geom_line() + facet_grid(cluster ~ .) +
    labs(title = "Cluster behaviour over full year", x = "Date and time", y = "kwh") +
    scale_color_manual(values = cbp)

midjan <- filter(aggdf, read_time > as.POSIXct("2017-01-15"), read_time <= as.POSIXct("2017-01-21"))

ggplot(midjan, aes(x = read_time, y = kwh_tot_mean, color = cluster)) + 
    geom_line() + facet_grid(cluster ~ .) +
    labs(title = "Cluster behaviour over third week of January", x = "Date and time", y = "kwh") +
    scale_color_manual(values = cbp)