Weather including rolling maximum

R/combmodels.R

@@ -19,7 +19,8 @@ clusters <- levels(aggdf$cluster)
 str(aggdf)
 mtempdf <- read.csv("../data/weatherharm.csv", stringsAsFactors = FALSE) %>% 
     mutate(x = as.POSIXct(x, tz = "UTC")) %>%
-    rename(read_time = x, rollingmin = y, fitmin = f, resmin = r)
+    rename(read_time = x, rollingmin = y.min, fitmin = f.min, resmin = r.min,
+           rollingmax = y.max, fitmax = f.max, resmax = r.max)
 str(mtempdf)
 sns <- import("seaborn")
 cbp <- as.character(p$Series(sns$color_palette("colorblind", as.integer(9))$as_hex()))
@@ -50,10 +51,13 @@ ycols <- paste(colnames(harm.y), collapse = " + ")
 wcols <- paste(colnames(harm.w), collapse = " + ") 
 dcols <- paste(colnames(harm.d), collapse = " + ") 
 
-nform.full <- sprintf("kwh ~ %s + %s + %s + (%s):(%s) + (%s):(%s) + (%s):(%s) + resmin + resmin:(%s) + resmin:(%s) + resmin:(%s)", 
-        ycols, wcols, dcols, ycols, wcols, ycols, dcols, wcols, dcols, ycols, wcols, dcols) %>% formula()
-nform.comp <- sprintf("kwh ~ %s + %s + %s + (%s):(%s) + (%s):(%s) + resmin + resmin:(%s) + resmin:(%s) + resmin:(%s)", 
-        ycols, wcols, dcols, ycols, dcols, wcols, dcols, ycols, wcols, dcols) %>% formula()
+nform.full <- sprintf(paste0("kwh ~ %s + %s + %s + (%s):(%s) + (%s):(%s) + (%s):(%s) + resmin",
+                             " + resmin:(%s) + resmin:(%s) + resmin:(%s)",
+                             " + resmax + resmax:(%s) + resmax:(%s) + resmax:(%s)"), 
+        ycols, wcols, dcols, ycols, wcols, ycols, dcols, wcols, dcols, ycols, wcols, dcols, ycols, wcols, dcols) %>% formula()
+nform.comp <- sprintf(paste0("kwh ~ %s + %s + %s + (%s):(%s) + (%s):(%s) + resmin + resmin:(%s) + resmin:(%s) + resmin:(%s)",
+                             " + resmax + resmax:(%s) + resmax:(%s) + resmax:(%s)"), 
+        ycols, wcols, dcols, ycols, dcols, wcols, dcols, ycols, wcols, dcols, ycols, wcols, dcols) %>% formula()
 nform.now <- sprintf("kwh ~ %s + %s + %s + (%s):(%s) + (%s):(%s)", 
         ycols, wcols, dcols, ycols, dcols, wcols, dcols) %>% formula()
 nform.min <- formula("kwh ~ 1")
@@ -116,3 +120,6 @@ predplot <-ggplot(predf, aes(x = x, y = y)) + geom_line(aes(y = f), color = "blu
 predplot
 
 predplot + coord_cartesian(xlim = c(as.POSIXct("2018-03-01", tz = "UTC"), as.POSIXct("2018-04-01", tz = "UTC")))
+
+mean(abs(predf$r))
+sd(predf$r)

R/weathmod.R

@@ -38,15 +38,18 @@ for (coln in names(fulltemp)[3:7]) {
 }
 sum(is.na(fulltemp$tmin_c))
 fulltemp$runmin <- runmin(fulltemp$tmin_c, 48, endrule = "min", align = "right")
+fulltemp$runmax <- runmax(fulltemp$tmax_c, 48, endrule = "max", align = "right")
 str(fulltemp)
 
 # Temperature plots
 tplot <- ggplot(fulltemp, aes(x = temp_timestamp, y = tmin_c)) + geom_line() +
-    geom_line(aes(y = runmin), color = "blue")
+    geom_line(aes(y = tmax_c), color = "magenta") +
+    geom_line(aes(y = runmin), color = "blue") +
+    geom_line(aes(y = runmax), color = "red")
 
 tplot
 
-tplot + coord_cartesian(xlim = c(as.POSIXct("2017-05-01"), as.POSIXct("2017-06-01")))
+tplot + coord_cartesian(xlim = c(as.POSIXct("2016-12-01"), as.POSIXct("2017-03-01")))
 
 # Create a harmonic (sine wave) model for minimum temperature
 yharm <- harmonic(ts(1:nrow(fulltemp), frequency = floor(365.25 * 48)), 2)
@@ -62,4 +65,28 @@ tmplot
 
 tmplot + coord_cartesian(xlim = c(as.POSIXct("2017-05-01", tz = "UTC"), as.POSIXct("2017-06-01", tz = "UTC")))
 
-write.csv(hmdf, "../data/weatherharm.csv", row.names = FALSE)
+
+
+maxhmod <- lm(fulltemp$runmax ~ yharm)
+summary(maxhmod)
+mhmdf <- data.frame(x = fulltemp$temp_timestamp, y = fulltemp$runmax, f = fitted(maxhmod), r = resid(maxhmod))
+
+mtmplot <- ggplot(mhmdf, aes(x = x, y = y)) + geom_line(aes(y = f), color = "blue", size = 2) + geom_point() +
+    geom_point(aes(y = r), color = "darkgreen")
+
+mtmplot
+
+mtmplot + coord_cartesian(xlim = c(as.POSIXct("2017-05-01", tz = "UTC"), as.POSIXct("2017-06-01", tz = "UTC")))
+
+hmdf.comb <- left_join(hmdf, mhmdf, by = "x", suffix = c(".min", ".max"))
+
+ctmplot <- ggplot(hmdf.comb, aes(x = x, y = f.min)) + geom_line(color = "blue", size = 2) +
+    geom_line(aes(y = f.max), color = "red", size = 2) +
+    geom_point(aes(y = y.max), color = "magenta") +
+    geom_point(aes(y = y.min), color = "lightblue")
+
+ctmplot
+
+ctmplot + coord_cartesian(xlim = c(as.POSIXct("2017-05-01", tz = "UTC"), as.POSIXct("2017-06-01", tz = "UTC")))
+
+write.csv(hmdf.comb, "../data/weatherharm.csv", row.names = FALSE)