Working with old 1-year dataset

R/clusterviz.R

@@ -27,7 +27,7 @@ fextract <- function(x, y, keep = 1, top = TRUE) {
 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-1617.agg.pkl")
+aggdf <- p$read_pickle("../data/9-clusters.agg.pkl")
 # aggdf <- as.data.frame(aggdf)
 aggdf$cluster <- factor(aggdf$cluster)
 str(aggdf)
@@ -37,7 +37,7 @@ ggplot(aggdf, aes(y = kwh_tot_mean, x = cluster)) + geom_boxplot()
 
 facall <- ggplot(aggdf, aes(x = read_time, y = kwh_tot_mean, color = cluster, fill = cluster)) + 
     geom_line(size = 1.5) + geom_ribbon(aes(ymin = kwh_tot_CI_low, ymax = kwh_tot_CI_high), alpha = 0.2, color = NA) +
-    labs(title = "Cluster behaviour over 2016 and 2017", x = "Date", y = "kwh") +
+    labs(title = "Cluster behaviour over 2017", x = "Date", y = "kwh") +
     scale_color_manual(values = cbp) +
     scale_fill_manual(values = cbp) +
     theme(legend.position = "none") +
@@ -101,16 +101,16 @@ facoct <- ggplot(midoct, aes(x = read_time, y = kwh_tot_mean, color = cluster, f
 octcon <- facoct + facet_grid(cluster ~ .)
 octfre <- facoct + facet_grid(cluster ~ ., scales = "free")
 
-ggsave("all-9-fix-1617.png", allcon, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
-ggsave("all-9-fre-1617.png", allfre, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
-ggsave("jan-9-fix-1617.png", jancon, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
-ggsave("jan-9-fre-1617.png", janfre, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
-ggsave("apr-9-fix-1617.png",  apcon, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
-ggsave("apr-9-fre-1617.png",  apfre, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
-ggsave("jul-9-fix-1617.png", julcon, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
-ggsave("jul-9-fre-1617.png", julfre, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
-ggsave("oct-9-fix-1617.png", octcon, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
-ggsave("oct-9-fre-1617.png", octfre, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
+# ggsave("all-9-fix-1617.png", allcon, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
+# ggsave("all-9-fre-1617.png", allfre, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
+# ggsave("jan-9-fix-1617.png", jancon, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
+# ggsave("jan-9-fre-1617.png", janfre, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
+# ggsave("apr-9-fix-1617.png",  apcon, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
+# ggsave("apr-9-fre-1617.png",  apfre, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
+# ggsave("jul-9-fix-1617.png", julcon, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
+# ggsave("jul-9-fre-1617.png", julfre, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
+# ggsave("oct-9-fix-1617.png", octcon, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
+# ggsave("oct-9-fre-1617.png", octfre, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
 
 
 # ----
@@ -142,8 +142,8 @@ wcorr <- ggplot(acfm, aes(x = day, y = acorr, color = cluster)) + geom_line(size
     theme(legend.position = "none") + coord_cartesian(xlim = c(0, 15), expand = FALSE) +
     labs(title = "Autocorrelation plot (two weeks)", y = "Autocorrelation", x = "lag (days)")
 
-ggsave("full-autocorr-1617.png", fcorr, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
-ggsave("week-autocorr-1617.png", wcorr, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
+# ggsave("full-autocorr-1617.png", fcorr, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
+# ggsave("week-autocorr-1617.png", wcorr, path = "../img/", dpi = "retina", width = 40, height = 25, units = "cm")
 
 perd <- bind_rows(perd)
 
@@ -260,18 +260,19 @@ hist(resid(cmodi), breaks = 100)
 qqnorm(resid(cmodi))
 
 
-clust = "6"
+clust = "9"
 
 cts <- filter(aggdf, cluster == clust)$kwh_tot_mean
 ctsy <- ts(cts, frequency = floor(48 * 365.25))
 ctsw <- ts(cts, frequency = floor(48 * 7))
 ctsd <- ts(cts, frequency = floor(48))
-harm.y <- harmonic(ctsy, 5)
+harm.y <- harmonic(ctsy, 4)
 harm.w <- harmonic(ctsw, 3)
-harm.d <- harmonic(ctsd, 3)
+harm.d <- harmonic(ctsd, 4)
 cmodi <- lm(cts ~ harm.y * harm.w * harm.d)
 summary(cmodi)
+cldf <- data.frame(x = unique(aggdf$read_time), y = cts, f = fitted(cmodi), r = resid(cmodi))
+ggplot(cldf, aes(x = x, y = y)) + geom_line(aes(y = f), color = "blue", size = 2) + geom_point() +
+    geom_point(aes(y = r), color = "darkgreen") +
+    coord_cartesian(xlim = c(as.POSIXct("2017-01-01", tz = "UTC"), as.POSIXct("2017-12-31", tz = "UTC")))
 
-plot(fitted(cmodi))
-plot(cts)
-plot(resid(cmodi))