From 40e76a2114f8cc04e5e2111d93e4b352ded6dbe3 Mon Sep 17 00:00:00 2001
From: Harrison Curtis <harrisoncurtis50@gmail.com>
Date: Fri, 21 Jun 2024 13:33:06 +0100
Subject: [PATCH] all

---
 R/data_anal_vis.r        | 46 +++++++++++++++-------------------------
 R/data_analyis.r         |  0
 data/.~lock.cattle.xlsx# |  1 +
 3 files changed, 18 insertions(+), 29 deletions(-)
 delete mode 100644 R/data_analyis.r
 create mode 100644 data/.~lock.cattle.xlsx#

diff --git a/R/data_anal_vis.r b/R/data_anal_vis.r
index 69ffdea..89b4fff 100644
--- a/R/data_anal_vis.r
+++ b/R/data_anal_vis.r
@@ -1,37 +1,32 @@
+# Import relevant 
 library(ggplot2)
 library(fable)
+library(feasts)
 
 #Import data----
 # Import data from github repo.
-df_og <- read.csv("https://raw.githubusercontent.com/HPCurtis/causalcovidcattle/main/data/cattle_og.csv")
 df_sa <- read.csv("https://raw.githubusercontent.com/HPCurtis/causalcovidcattle/main/data/cattle_sa.csv")
 
 # Convert to date form.
-df_og$Date <- as.Date(df_og$Date) 
 df_sa$Date <- as.Date(df_sa$Date) 
 
+df_sa <- df_sa %>% drop_na() %>% 
+  as_tsibble( index = Date) %>% 
+  mutate(Date = yearquarter(Date)) 
+
 #Pre/Post Covid----
 pre_covid <- df_sa %>%
-  drop_na() %>%
-  filter(Date < ymd("2020-03-01")) %>%
+  filter(Date < yearquarter("2020 Q2")) %>%
   mutate(Date = yearquarter(Date)) %>%
   as_tsibble(index = Date)
 
 post_covid <- df_sa %>%
-  drop_na() %>%
-  filter(Date >=  ymd("2020-03-01") )%>%
+  filter(Date >=   yearquarter("2020 Q2"))%>%
   mutate(Date = yearquarter(Date)) %>%
   as_tsibble(index = Date)
 
 # Visualisations for the project
 
-#Time series Decomposition------
-# Conduct STL decomposition.
-dcmp <- drop_na(df_sa) |>
-  model(stl = STL(NumberSlaughteredCATTLEexclcalvesTotalState))
-
-components(dcmp) |> autoplot()
-
 # Fit linear model for seasonal adjusted data.
 fitlinear <- pre_covid |>
   model(trend_model = TSLM(NumberSlaughteredCATTLEexclcalvesTotalState ~ trend()))
@@ -42,27 +37,20 @@ fc <- fitlinear %>%
   # Get forecast intervals
   hilo()
 
-# Convert Data column to approriate data type.
-fc$Date <- as_date(fc$Date)
-
-plinear <- fc %>% autoplot(drop_na(df_sa)) +
-  labs(y = "Number of Cattle Slaughtered", 
-       title = "Total number of cattle (excl calves) across all Australian States") +
-  theme(
-    plot.title = element_text(size = 10),      # Title font size
-    axis.title = element_text(size = 8),       # Axis titles font size
-    axis.text = element_text(size = 7)         # Axis text font size
-  ) + geom_vline(xintercept = as.Date("2020-03-01"))
-
-# Save plot out
-ggsave(filename = "/home/harrison/Desktop/gitHubRepos/cattlecovidcausal/img/linearforecast.png", plot = plinear, width = 6, height = 4, units = "in", dpi = 300)
+plinear <- ggplot() +
+  geom_line(data = df_sa, aes(x = Date, y = NumberSlaughteredCATTLEexclcalvesTotalState), color = "blue", linetype = "solid") +
+  geom_line(aes(x = fc$Date, y = fc$.mean), color = "blue") +
+  geom_ribbon(aes(x = fc$Date, ymin = fc$`95%`$lower, ymax = fc$`95%`$upper), 
+              fill = "blue", alpha = 0.3) +
+  geom_vline(xintercept = as.Date("2020-03-01"), color = "red", linetype = "dashed") +
+  labs(x = "Date", y = "Number of Cattle Slaughtered ('000)", title = "Total number of cattle (excl calves) across all Australian States") +
 
 #Calculate Causal impact----
 yhat <- fc$.mean
 yhatupper <- fc$`95%`$upper
 yhatlower <- fc$`95%`$lower
 
-# Clauate mean and lower and upper bounds
+# Calculate mean and lower and upper bounds
 Totalslaughteredimpact <- post_covid$NumberSlaughteredCATTLEexclcalvesTotalState - yhat 
 Totalslaughteredimpactupper <- post_covid$NumberSlaughteredCATTLEexclcalvesTotalState - yhatupper 
 Totalslaughteredimpactlower <- post_covid$NumberSlaughteredCATTLEexclcalvesTotalState - yhatlower
@@ -78,7 +66,7 @@ causal_impact_plot <- ggplot() +
   geom_ribbon(data = fc, 
               aes(x = Date, ymin =  post_covid$NumberSlaughteredCATTLEexclcalvesTotalState),
                   ymax = yhat, fill = "blue", alpha = 0.2) +
-  labs(y = "Number of Cattle Slaughtered", 
+  labs(y = "Number of Cattle Slaughtered ('000)", 
        title = "Total number of cattle (excl calves) across all Australian States") +
   theme(
     plot.title = element_text(size = 10),      # Title font size
diff --git a/R/data_analyis.r b/R/data_analyis.r
deleted file mode 100644
index e69de29..0000000
diff --git a/data/.~lock.cattle.xlsx# b/data/.~lock.cattle.xlsx#
new file mode 100644
index 0000000..f3198f0
--- /dev/null
+++ b/data/.~lock.cattle.xlsx#
@@ -0,0 +1 @@
+,harrison,harrison-HP-Laptop-14-cf1xxx,21.06.2024 13:18,file:///home/harrison/.config/libreoffice/4;
\ No newline at end of file