GSSData/Data_Preprocessing.Rmd at main · artofstat/GSSData · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
---
title: "project_BK"
author: "Deniz KB"
date: "2022-10-21"
output:
  pdf_document: default
  html_document: default
---

**Reading Data from dta file**

```{r}
#"https://gss.norc.org/get-the-data/stata"
library(haven)
data_dta_all <- read_dta("./gss7221_r2.dta")
```


**Sample of Data**

I will need to work with small datasets. I will get last 2 years data and data from 2000; some numeric and categorical variables.

```{r}
library(tidyverse)
sample_dta <- subset(data_dta_all,
                     year %in% c(2018,2021, 2000),
                     select = c("year", #categorical 1
                                "id", #num 2
                                "wrkstat", #categorical 3
                                "commute", #NAs 4
                                "marital", #categorical 5
                                "martype", #categorical 6
                                "degree", #categorical 7
                                "income", #categorical 8
                                "life", #categorical 9
                                "fair", #categorical 10
                                "trust", #categorical 11
                                "prestige", # NAs 12
                                "news", #categorical 13
                                "fear", #categorical 14
                                "age", #numeric 15
                                "agewed", # NAs 16
                                "educ", #numeric 17
                                "paeduc", #num 18
                                "maeduc", #num 19
                                "hompop", #num 20
                                "childs", #num 21
                                "sibs", #num 22
                                "babies", #num 23
                                "preteen", #num 24
                                "teens", #num 25
                                "adults" #num 26
                                )
                     )

#View(sample_dta)
```


**Write/Read Subset of Data as dta file**

```{r}
#write_dta(sample_dta,"finaldata.dta")

df_dta <- read_dta("finaldata.dta")
```


**Original Filtered Data**

**Converting Data Types**

```{r}
library(labelled)
copy_df_dta <- df_dta
```


**DataSet for Summaries**

```{r}
# I might need to come back for "year" variable. #col =1

#For categorical variables
catCols <- c(3, 5, 6, 7, 8, 9, 10, 11, 13, 14)

for( i in catCols) {
  copy_df_dta[,i ] <- unlist(to_factor(copy_df_dta[,i ], levels = "l"))
}

#For numeric Variables
numCols <- c(1, 2, 4, 12, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26)

for( i in numCols) {
  copy_df_dta[,i ] <- as.numeric(unlist(to_factor(copy_df_dta[,i ], levels = "v")))
}

#View(copy_df_dta)

#All NAs for the selected years but they are numeric.
NAs <- c(4, 12, 16)
```


**DataSet for DT**

```{r}
#Convert all variables into factors to have goodlooking table instead of slides to filter, drop-down to filter

#Does not work here! I will convert all in server.
copy_df_dta2 <- df_dta
for( i in 1:ncol(copy_df_dta2)) {
  copy_df_dta2[,i ] <- unlist(to_factor(copy_df_dta2[,i ], levels = "l"))
}
```


**Converting Data from dta file to CSV**
```{r}
#write.csv(copy_df_dta,"./finaldata.csv", row.names = FALSE)
```