checkop

giocoal · Jan 5, 2023 · f2e6f4e · f2e6f4e
1 parent f045807
commit f2e6f4e
Show file tree

Hide file tree

Showing 14 changed files with 19 additions and 17 deletions.
diff --git a/Analisi predittive/Images/CV_Covid_MAE.png b/Analisi predittive/Images/CV_Covid_MAE.png
diff --git a/Analisi predittive/Images/CV_Covid_MAPE.png b/Analisi predittive/Images/CV_Covid_MAPE.png
diff --git a/Analisi predittive/Images/CV_Precovid_MAE.png b/Analisi predittive/Images/CV_Precovid_MAE.png
diff --git a/Analisi predittive/Images/CV_Precovid_MAPE.png b/Analisi predittive/Images/CV_Precovid_MAPE.png
diff --git a/Analisi predittive/Images/CV_Precovid_RMSE.png b/Analisi predittive/Images/CV_Precovid_RMSE.png
diff --git a/Analisi predittive/Images/CV_Precovid_RMdSE.png b/Analisi predittive/Images/CV_Precovid_RMdSE.png
diff --git a/Analisi predittive/Images/cut/CV_Precovid_MAE_cut.png b/Analisi predittive/Images/cut/CV_Precovid_MAE_cut.png
diff --git a/Analisi predittive/Images/cut/CV_Precovid_MAPE_cut.png b/Analisi predittive/Images/cut/CV_Precovid_MAPE_cut.png
diff --git a/Analisi predittive/Images/cut/CV_Precovid_RMSE_cut.png b/Analisi predittive/Images/cut/CV_Precovid_RMSE_cut.png
diff --git a/Analisi predittive/Images/cut/CV_Precovid_RMdSE_cut.png b/Analisi predittive/Images/cut/CV_Precovid_RMdSE_cut.png
diff --git a/Analisi predittive/Images/cut/CV_Precovid_legend_cut.png b/Analisi predittive/Images/cut/CV_Precovid_legend_cut.png
diff --git a/Analisi predittive/My-TSCrossValidation-Functions.R b/Analisi predittive/My-TSCrossValidation-Functions.R
@@ -326,7 +326,7 @@ pre_covid_accuracy_plot <- function(i_x, f_x, by_x, i_y, f_y, by_y, ylab, model_
   par(mai=c(0.8, 0.8, 0.1, 2.7)) #oma=c(0, 0, 0, 8) mar=c(5, 4, 1, 20) asp=1, 
 
   plot(x = NULL, y = NULL, type = "n", xlim = c(i_x, f_x), ylim = c(i_y, f_y),
-       xlab="Forecast Horizon", ylab=ylab,
+       xlab="Orizzonte di Previsione (h)", ylab=ylab,
        xaxt = "n",
        yaxt = "n", grid = TRUE)
 

diff --git a/Analisi predittive/Ristorante1_RandomForest_Covid.Rmd b/Analisi predittive/Ristorante1_RandomForest_Covid.Rmd
@@ -132,14 +132,16 @@ r1_post <- xts(postcovid1[, "lordototale"], as.Date(as.character(postcovid1$data
 ```
 
 ```{r}
-train_test_split <- nrow(r1_post)*0.8
+#train_test_split <- nrow(r1_post)*0.8
+#train_test_split <- 662
 ```
 
 ```{r}
 train1_post <- r1_post[1:train_test_split, ]
 test1_post <- r1_post[-c(1:train_test_split), ]
 ```
 
+
 ```{r}
 # Matrice dei ritardi
 

diff --git a/Analisi predittive/TSCrossValidation-Summary.Rmd b/Analisi predittive/TSCrossValidation-Summary.Rmd
@@ -214,16 +214,16 @@ for (df_name in names(error_df_list_precovid)) {
 
 ```{r, dpi=1000, fig.height = 4.5, fig.width = 9} 
 color_map <- list(
-    alpha("red", 0.8),
-    alpha("red", 0.8),
+    alpha("red", 0.5),
+    alpha("red", 0.5),
     alpha("red", 1),
-    alpha("red", 0.8),
-    alpha("blue", 0.8),
+    alpha("red", 0.5),
+    alpha("blue", 0.5),
     alpha("blue", 1),
     alpha("blue", 1),
-    alpha("green", 0.8),
-    alpha("green", 0.8),
-    alpha("green", 0.8)
+    alpha("green", 1),
+    alpha("green", 1),
+    alpha("green", 1)
   )
 
 
@@ -237,7 +237,7 @@ by_y = 1000
 
 lwd = 1.4
 
-ylab = "RMSE"
+ylab = "Root Mean Squared Error (RMSE)"
 accuracy_metrics = RMSE_PreCovid
 nome_file = "CV_Precovid_RMSE.png"
 
@@ -308,7 +308,7 @@ by_y = 200
 
 lwd = 1.4
 
-ylab = "RMdSE"
+ylab = "Root Median Squared Error (RMdSE)"
 accuracy_metrics = RMdSE_PreCovid
 nome_file = "CV_Precovid_RMdSE.png"
 
@@ -360,13 +360,13 @@ i_x = 0
 f_x = 73
 by_x = 10
 
-i_y = 1800
-f_y = 4800
-by_y = 200
+i_y = 1900
+f_y = 4400
+by_y = 500
 
 lwd = 1.4
 
-ylab = "MAE"
+ylab = "Mean Absolute Error (MAE)"
 accuracy_metrics = MAE_PreCovid
 nome_file = "CV_Precovid_MAE.png"
 
@@ -435,11 +435,11 @@ by_x = 10
 
 i_y = 10
 f_y = 25
-by_y = 5
+by_y = 3
 
 lwd = 1.4
 
-ylab = "MAPE"
+ylab = "Mean Absolute Percentage Error (MAPE)"
 accuracy_metrics = MAPE_PreCovid
 nome_file = "CV_Precovid_MAPE.png"