Update finalproject

finalproject

@@ -18,39 +18,45 @@ names(data)
 
 # predictor data cleaning
 data <- na.omit(data)
-data$X30.5drinks <- as.numeric(str_remove_all(data$X30.5drinks, " days"))
-data$X30.5drinks <- as.numeric(str_remove_all(data$X30.5drinks, " day"))
-data$X30.5drinks <- as.numeric(str_remove_all(data$X30.5drinks, " or more"))
+data$X30.5drinks <- str_remove_all(data$X30.5drinks, " days")
+data$X30.5drinks <- str_remove_all(data$X30.5drinks, " day")
+data$X30.5drinks <- str_remove_all(data$X30.5drinks, " or more")
 data$X30.5drinks[data$X30.5drinks == "3 to 5"] <- 4
 data$X30.5drinks[data$X30.5drinks == "6 to 9"] <- 7.5
 data$X30.5drinks[data$X30.5drinks == "10 to 19"] <- 14.5
-mean(data$X30.5drinks)
-
-data$X30.cig <- as.numeric(str_remove_all(data$X30.cig, " days"))
-data$X30.cig <- as.numeric(str_remove_all(data$X30.cig, " day"))
-data$X30.cig <- as.numeric(str_remove_all(data$X30.cig, " or more"))
-data$X30.cig[data$X30.cig == "3 to 5"] <- 4
-data$X30.cig[data$X30.cig == "6 to 9"] <- 7.5
-data$X30.cig[data$X30.cig == "10 to 19"] <- 14.5
-mean(data$X30.cig)
-
-data$X30drink <- as.numeric(str_remove_all(data$X30drink, " days"))
-data$X30drink <- as.numeric(str_remove_all(data$X30drink, " day"))
-data$X30drink <- as.numeric(str_remove_all(data$X30drink, " or more"))
-data$X30drink[data$X30drink == "3 to 5"] <- 4
-data$X30drink[data$X30drink == "6 to 9"] <- 7.5
-data$X30drink[data$X30drink == "10 to 19"] <- 14.5
-data <- na.omit(data)
-mean(data$X30drink)
-
-data$X30marijuana <- as.numeric(str_remove_all(data$X30marijuana, " days"))
-data$X30marijuana <- as.numeric(str_remove_all(data$X30marijuana, " day"))
-data$X30marijuana <- as.numeric(str_remove_all(data$X30marijuana, " or more"))
-data$X30marijuana[data$X30marijuana == "3 to 5"] <- 4
-data$X30marijuana[data$X30marijuana == "6 to 9"] <- 7.5
-data$X30marijuana[data$X30marijuana == "10 to 19"] <- 14.5
-data <- na.omit(data)
-mean(data$X30marijuana)
+mean(as.numeric(data$X30.5drinks))
+
+data$X30.cig <- str_remove_all(data$X30.cig, " days")
+data$X30.cig <- str_remove_all(data$X30.cig, " day")
+data$X30.cig <- str_remove_all(data$X30.cig, " or more")
+data$X30.cig[data$X30.cig == "1-2"] <- 1.5
+data$X30.cig[data$X30.cig == "3-5"] <- 4
+data$X30.cig[data$X30.cig == "6-9"] <- 7.5
+data$X30.cig[data$X30.cig == "10-19"] <- 14.5
+data$X30.cig[data$X30.cig == "20-29"] <- 24.5
+mean(as.numeric(data$X30.cig))
+
+data$X30drink <- str_remove_all(data$X30drink, " days")
+data$X30drink <- str_remove_all(data$X30drink, " day")
+data$X30drink <- str_remove_all(data$X30drink, " or more")
+data$X30drink[data$X30drink == "1-2"] <- 1.5
+data$X30drink[data$X30drink == "3-5"] <- 4
+data$X30drink[data$X30drink == "6-9"] <- 7.5
+data$X30drink[data$X30drink == "10-19"] <- 14.5
+data$X30drink[data$X30drink == "20-29"] <- 24.5
+data <- na.omit(data)
+mean(as.numeric(data$X30drink))
+
+data$X30marijuana <- str_remove_all(data$X30marijuana, " days")
+data$X30marijuana <- str_remove_all(data$X30marijuana, " day")
+data$X30marijuana <- str_remove_all(data$X30marijuana, " or more")
+data$X30marijuana[data$X30marijuana == "1-2"] <- 1.5
+data$X30marijuana[data$X30marijuana == "3-5"] <- 4
+data$X30marijuana[data$X30marijuana == "6-9"] <- 7.5
+data$X30marijuana[data$X30marijuana == "10-19"] <- 14.5
+data$X30marijuana[data$X30marijuana == "20-29"] <- 24.5
+data <- na.omit(data)
+mean(as.numeric(data$X30marijuana))
 
 # response data cleaning
 data$times.moved[data$times.moved == "None"] <- 0
@@ -138,17 +144,19 @@ data$talk.adult[data$talk.adult == "Strongly disagree"] <- 1
 data <- na.omit(data)
 mean(as.numeric(data$talk.adult))
 
-data$grades[data$grades == "Strongly agree"] <- 4
-data$grades[data$grades == "Agree"] <- 3
-data$grades[data$grades == "Disagree"] <- 2
-data$grades[data$grades == "Strongly disagree"] <- 1
+data$grades[data$grades == "Excellent"] <- 4
+data$grades[data$grades == "Above average"] <- 3
+data$grades[data$grades == "Average"] <- 2
+data$grades[data$grades == "Below average"] <- 1
+data$grades[data$grades == "Failing"] <- 0
 data <- na.omit(data)
 mean(as.numeric(data$grades))
 
-data$Wpdrink[data$Wpdrink == "Strongly agree"] <- 4
-data$Wpdrink[data$Wpdrink == "Agree"] <- 3
-data$Wpdrink[data$Wpdrink == "Disagree"] <- 2
-data$Wpdrink[data$Wpdrink == "Strongly disagree"] <- 1
+data$Wpdrink[data$Wpdrink == "Very wrong"] <- 4
+data$Wpdrink[data$Wpdrink == "Wrong"] <- 3
+data$Wpdrink[data$Wpdrink == "Dont know"] <- 2.5
+data$Wpdrink[data$Wpdrink == "A little wrong"] <- 2
+data$Wpdrink[data$Wpdrink == "Not wrong at all"] <- 1
 data <- na.omit(data)
 mean(as.numeric(data$Wpdrink))
 
@@ -160,3 +168,15 @@ data <- na.omit(data)
 mean(as.numeric(data$N.safe))
 
 ```
+
+```{r}
+# new response binary variable
+
+data$substance <- 
+
+
+```
+
+
+
+