Update transform_data_famd.r

scripts/phase2/transform_data_famd.r

@@ -6,7 +6,6 @@ library("factoextra")
 
 # phase 2 excel
 input <- "C:/Users/its-student/Desktop/Phase2In.xlsx"
-output <- "C:/Users/its-student/Desktop/Phase2OutFAMD.xlsx"
 
 # read in sheets
 data        <- read_excel(input, sheet = "Data")
@@ -133,20 +132,8 @@ data <- data %>%
                          MAX_LIVES >= 1000 & TRUE_GROUP_VOL == "V" & POLICY_DURATION <  4 ~ 1.0000,
                          MAX_LIVES >= 1000 & TRUE_GROUP_VOL == "V" & POLICY_DURATION >= 4 ~ 1.0200))
 
-# calculate needed premium
-#data <- data %>% mutate(NEEDED_PREMIUM = PREM / RTN)
 
-# calculate expected claims
-#data <- data %>% mutate(EXPECTED_CLAIMS = NEEDED_PREMIUM * TLR)
-
-# calcualte actual claims
-#data <- data %>% mutate(ACTUAL_CLAIMS = PAID_CLAIMS + IBNR)
-
-# calculate actual to expected ratio
-#data <- data %>% mutate(ACTUAL_TO_EXPECTED = ACTUAL_CLAIMS / EXPECTED_CLAIMS)
-
-
-# numerics -> pca + factors -> mca
+# famd = pca (numerics) + mca (factors)
 data <- data %>% select("REGION", "INDUSTRY",
   "COVG_CODE", "LTD_INDICATOR", 
   "AVG_SALARY", "AVG_AGE", "PCT_FEMALE",
@@ -156,9 +143,7 @@ data <- data %>% select("REGION", "INDUSTRY",
   "PAID_COMMISSION", "PAID_CLAIMS", "CLAIM_COUNT", "IBNR",
   "PERCENT_COMMISSION", "PREMIUM_TAX", "INTERNAL_EXPENSES", "PERCENT_PEPM")
 
-save(data, file = "C:/Users/its-student/Desktop/phase2.rdata")
-
-# use FactoMineR for PCA
+# use FactoMineR for FAMD
 data.famd <- FAMD(data, graph = FALSE)
 
 summary(data.famd)