Oscars/dataheattable2 at master · apalbright/Oscars · 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
**Import oscars info**
clear all
set more off

cd "raw_data"
import excel "oscars3", firstrow clear

drop if Speech==""

gen wordcount=wordcount(Speech)

replace Award="Makeup/Makeup and Hairstyling" if Award=="Makeup"
replace Award="Art Direction/Production Design" if Award=="Art Direction"

egen words1=sum(wordcount), by(Award)
gen words2=words1/5
replace words2=words1/6 if Award=="Sound Editing" //two teams were given award in 2012

**avgs of length, I, we across groups**
gen I=length(Speech)-length(subinstr(Speech, "I ", " ",.))
gen I2=length(Speech)-length(subinstr(Speech, "me ", "  ",.))
gen I3=length(Speech)-length(subinstr(Speech, "my ", "  ",.))
gen I4=length(Speech)-length(subinstr(Speech, "My ", "  ",.))
gen I5=length(Speech)-length(subinstr(Speech, "Me ", "  ",.))
gen I6=length(Speech)-length(subinstr(Speech, "I'", " ",.))
gen I7=length(Speech)-length(subinstr(Speech, "myself", "     ",.))
gen I1=I+I2+I3+I4+I5+I6+I7
drop I I2 I3 I4 I5 I6 I7

gen We1=length(Speech)-length(subinstr(Speech, "we ", "  ",.))
gen We2=length(Speech)-length(subinstr(Speech, "We ", "  ",.))
gen We3=length(Speech)-length(subinstr(Speech, "our ", "   ",.))
gen We4=length(Speech)-length(subinstr(Speech, "Our ", "   ",.))
gen We5=length(Speech)-length(subinstr(Speech, "us ", "  ",.))
gen We6=length(Speech)-length(subinstr(Speech, "we'", "  ",.))
gen We7=length(Speech)-length(subinstr(Speech, "We'", "  ",.))
gen We8=length(Speech)-length(subinstr(Speech, "ourselves", "        ",.))
gen We10=We1+We2+We3+We4+We5+We6+We7+We8
drop We1 We2 We3 We4 We5 We6 We7 We8

rename wordcount words
rename I1 I
rename We1 We

gen GenderActor="Female Actor" if Gender==1 & Actors==1
replace GenderActor="Male Actor" if Gender==0 & Actors==1
replace GenderActor="Female Non-Actor" if Gender==1 & Actors==0
replace GenderActor="Male Non-Actor" if Gender==0 & Actors==0

*calc avg length by category*
egen words4=mean(words), by(GenderActor)

*calc avg wepercent by category*
egen words3=sum(words), by(GenderActor)
egen We1=sum(We), by(GenderActor)
gen Wepercent=(We1/words3)*100

*calc avg Ipercent by category*
egen I1=sum(I), by(GenderActor)
gen Ipercent=(I1/words3)*100

*calc avg selfrat by category*
gen self=I1/We1

sort GenderActor
by GenderActor: gen i=_n
keep if i<2

keep GenderActor words4 Ipercent Wepercent self
order GenderActor words4 Ipercent Wepercent self

cd "tld-oscars/generated_data"
outsheet GenderActor words4 Ipercent Wepercent self using genderactor.csv , comma nolabel replace