-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathInitial-data-preprocessing
183 lines (181 loc) · 5.66 KB
/
Initial-data-preprocessing
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
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
> options(echo=FALSE, encoding="UTF-8")
Loading required package: readstata13
> options(error = expression(q('no')))
> library(Hmisc)
Loading required package: lattice
Loading required package: survival
Loading required package: Formula
Loading required package: ggplot2
Attaching package: ‘Hmisc’
The following objects are masked from ‘package:base’: format.pval, units
> wmean <- function(x, weight)
+ {
+ y <- x[which(!is.na(x))]
+ wgt <- weight[which(!is.na(x))]
+ wmean <- sum(y*wgt/sum(wgt))
+ return(wmean)
+ }
> wNtile <- function(var, wgt, split) {
+ x <- var[order(var)]
+ y <- wgt[order(var)]
+ z <-cumsum(y)/sum(y)
+ cop <- rep(NA,length(split))
+ for (i in 1:length(cop)) {
+ cop[i] <- x[Find(function(h) z[h] > split[i], seq_along(z))]
+ }
+ return(cop)
+ }
> vars <- c('dhi','hifactor','hpub_i', 'hpub_u','hpub_a','hiprivate','hxitsc','hpopwgt','nhhmem','grossnet')
> df <- read.LIS('ru16h', labels=FALSE, vars=vars)
[1] "Loading dataset ru16h..."
> subset <- 'complete.cases(dhi,hifactor,hpub_i,hpub_u,hpub_a,hiprivate,hxitsc)'
> df2 <- read.LIS('ru16h', labels=FALSE, vars=vars, subset=subset)
[1] "Loading dataset ru16h..."
> print(row_total <- nrow(df))
[1] 160008
> print(row_drop <- with(df, length(which((complete.cases(dhi,hifactor,hpub_i,hpub_u,hpub_a,hiprivate,hxitsc) == TRUE)))))
[1] 160008
> print(miss_income<- row_total- row_drop )
[1] 0
> round(((row_total - row_drop) / row_total) * 100, digits = 2)
[1] 0
> print(c(toupper('grossnet')))
[1] "GROSSNET"
> print(table(df$grossnet, useNA = 'ifany'))
120
160008
> print(paste(round(prop.table(table(df$grossnet, useNA = 'ifany')) * 100, digits = 2), "%", sep = ""))
[1] "100%"
> cat(paste(" "), sep = '\n')
> for (x in c('hpopwgt','dhi','hifactor','hpub_i', 'hpub_u','hpub_a','hiprivate','hxitsc')) {
+ df1 <- df[!is.na(df[[x]]), ]
+ print(c(toupper(x)))
+ print(c(nb_obs = sum(!is.na(df1[[x]]))))
+ print(summary(df1[,x], digits = 10))
+ print(c(weighted_mean = round(wmean(df1[[x]], df1$hpopwgt*df1$nhhmem), digits = 2), weighted_median = round(wNtile(df1[[x]], df1$hpopwgt * df1$nhhmem, split = 0.5), digits = 2)))
+ cat(" ", sep = '\n')
+ }
[1] "HPOPWGT"
nb_obs
160008
Min. 1st Qu. Median Mean 3rd Qu. Max.
2.0 111.3 201.9 355.6 379.7 58058.3
weighted_mean weighted_median
1520.91 604.91
[1] "DHI"
nb_obs
160008
Min. 1st Qu. Median Mean 3rd Qu. Max.
1200 241887 394198 497711 624000 11048410
weighted_mean weighted_median
863230.8 717543.2
[1] "HIFACTOR"
nb_obs
160008
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 20158 243678 363652 531349 9454672
weighted_mean weighted_median
750328.2 592810.3
[1] "HPUB_I"
nb_obs
160008
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 110880 122112 198000 1967232
weighted_mean weighted_median
118689.9 6000.0
[1] "HPUB_U"
nb_obs
160008
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 0 19570 7200 1089128
weighted_mean weighted_median
33260.3 0.0
[1] "HPUB_A"
nb_obs
160008
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 5844 19390 24900 3045276
weighted_mean weighted_median
26350.82 6696.00
[1] "HIPRIVATE"
nb_obs
160008
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 0 11916 5000 9301638
weighted_mean weighted_median
16703.18 0.00
[1] "HXITSC"
nb_obs
160008
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 21159 38928 59023 1800000
weighted_mean weighted_median
82101.62 62758.62
> for (x in c('hpopwgt','dhi','hifactor','hpub_i', 'hpub_u','hpub_a','hiprivate','hxitsc'))
+ {
+ print(c(toupper(x)))
+ print(c(nb_obs = sum(!is.na(df2[[x]]))))
+ print(summary(df2[,x], digits = 10))
+ print(c(weighted_mean = round(wmean(df2[[x]], df2$hpopwgt*df2$nhhmem), digits = 2), weighted_median = round(wNtile(df2[[x]], df2$hpopwgt * df2$nhhmem, split = 0.5), digits = 2)))
+ cat(" ", sep = '\n')
+ }
[1] "HPOPWGT"
nb_obs
160008
Min. 1st Qu. Median Mean 3rd Qu. Max.
2.0 111.3 201.9 355.6 379.7 58058.3
weighted_mean weighted_median
1520.91 604.91
[1] "DHI"
nb_obs
160008
Min. 1st Qu. Median Mean 3rd Qu. Max.
1200 241887 394198 497711 624000 11048410
weighted_mean weighted_median
863230.8 717543.2
[1] "HIFACTOR"
nb_obs
160008
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 20158 243678 363652 531349 9454672
weighted_mean weighted_median
750328.2 592810.3
[1] "HPUB_I"
nb_obs
160008
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 110880 122112 198000 1967232
weighted_mean weighted_median
118689.9 6000.0
[1] "HPUB_U"
nb_obs
160008
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 0 19570 7200 1089128
weighted_mean weighted_median
33260.3 0.0
[1] "HPUB_A"
nb_obs
160008
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 5844 19390 24900 3045276
weighted_mean weighted_median
26350.82 6696.00
[1] "HIPRIVATE"
nb_obs
160008
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 0 11916 5000 9301638
weighted_mean weighted_median
16703.18 0.00
[1] "HXITSC"
nb_obs
160008
Min. 1st Qu. Median Mean 3rd Qu. Max.
0 0 21159 38928 59023 1800000
weighted_mean weighted_median
82101.62 62758.62
>
> proc.time()
user system elapsed
8.552 0.397 10.195