-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathcovid_count.Rmd
174 lines (125 loc) · 6.1 KB
/
covid_count.Rmd
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
---
title: "covid_case_by_county"
output: html_document
---
```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```
## R Markdown
# covid cumulative case count (Y)
```{r}
us.counties <- read.csv("covid-project-raw-data/us-counties.txt")
us.counties["id"] <- paste(us.counties$county,us.counties$state, sep="_")
length(unique(us.counties$id))
```
```{r}
nov23count <- us.counties[which(us.counties$date == "2020-11-23"),] # extract data on nov 23th
nov23count <- nov23count[order(nov23count$fips),] # order by county
length(unique(nov23count$id)) # calculate how many data points are left...
```
```{r}
nov23count <- nov23count[nov23count$county != "Unknown",] # some counties are unknown so I removed them...
length(unique(nov23count$id))
# note that 3 counties are missing fips number
Y <- nov23count[,2:6]
```
# covid mask use
```{r}
mask_use <- read.csv("covid-project-raw-data/mask-use-by-county.txt")
colnames(mask_use) <- c("fips", "NEVER", "RARELY", "SOMETIMES", "FREQUENTLY", "ALWAYS")
mask_use["mask_score"] <- mask_use$NEVER*0 + mask_use$RARELY*1 + mask_use$SOMETIMES*2 + mask_use$FREQUENTLY*3 + mask_use$ALWAYS*4
X1 <- mask_use[,c(1,7)]
length(unique(mask_use$fips))
```
```{r}
full_data <- merge(Y, X1, by = "fips", all.x = TRUE, all.y = TRUE) # Keep all rows of both data frames
```
# health data
```{r}
health2019 <- read.csv("covid-project-raw-data/analytic_data2019.csv")
```
```{r}
# these are the data we want to use...
v1=which(colnames(health2019)=="Ratio.of.population.to.primary.care.providers.other.than.physicians." ) # Population to Primary Care Physicians ratio
v2=which(colnames(health2019)=="Unemployment.raw.value" ) #
v3=which(colnames(health2019)=="High.school.graduation.raw.value" )
v4=which(colnames(health2019)=="Flu.vaccinations.raw.value" )
v5=which(colnames(health2019)=="Uninsured.raw.value" )
v6=which(colnames(health2019)=="Median.household.income.raw.value" )
v7=which(colnames(health2019)=="Population.raw.value" )
v8=which(colnames(health2019)=="X..Rural.raw.value" )
v9=which(colnames(health2019)=="Life.expectancy.raw.value" )
```
```{r}
# calculate diversity index
# pull out race proportions
q=which(colnames(health2019)=="X..Non.Hispanic.African.American.raw.value" )
w=which(colnames(health2019)=="X..American.Indian.and.Alaskan.Native.raw.value" )
e=which(colnames(health2019)=="X..Asian.raw.value" )
r=which(colnames(health2019)=="X..Native.Hawaiian.Other.Pacific.Islander.raw.value" )
t=which(colnames(health2019)=="X..Hispanic.raw.value" )
y=which(colnames(health2019)=="X..Non.Hispanic.white.raw.value" )
race_index <- c(q,w,e,r,t,y)
race_data <- health2019[3:nrow(health2019),race_index] # 3rd column is the fips number for each county, 1st row is not data, 2nd row is nation-wide values
race_data[] <- lapply(race_data, as.numeric)
race_data["sim_diversity_index"] <- 1 - race_data[,1]^2 - race_data[,2]^2 - race_data[,3]^2 - race_data[,4]^2 - race_data[,5]^2 - race_data[,6]^2
```
# clean up var names and such...
```{r}
index <- c(v1,v2,v3,v4,v5,v6,v7,v8,v9)
health_data <- health2019[3:nrow(health2019),c(3,index)] # 3rd column is the fips number for each county, 1st row is not data, 2nd row is nation-wide values
health_data <- cbind(health_data, race_data[1:7])
# rename var so more compact...
colnames(health_data) <- c("fips", "ratio_pop_to_physician", "unemploy_rate", "HS_grad_rate", "flu_vacc_%", "uninsured", "median_income", "pop_size", "%_rural", "life_expectancy", "non_hispanic_african_american","american_indian","asian","native_hawaiian","hispanic","non_hispanic_white","sim_diversity_index")
# there is an issue with fips code, in health data numbers < 10000 have a 0 in front (ie: 015034)
health_data[,1] <- as.integer(health_data[,1])
```
```{r}
full_data <- merge(full_data, health_data, by = "fips", all.x = TRUE, all.y = TRUE) # Keep all rows of both data frames
```
# party preferrence
```{r}
county_vote_2016 <- read.csv("covid-project-raw-data/countypres_2000-2016.csv") # read in data
county_vote_2016 <- county_vote_2016[county_vote_2016$year == 2016,] # only used 2016 election
county_vote_2016 <- na.omit(county_vote_2016) # remove na rows
demo <- county_vote_2016[county_vote_2016$party == "democrat", c(5,9)] # take democratic votes
rep <- county_vote_2016[county_vote_2016$party == "republican",c(5,9)] # take republican votes
county_vote_2016 <- merge(demo,rep, by = "FIPS", all.x = TRUE, all.y = TRUE) # merge back into dataframe
colnames(county_vote_2016) <- c("fips", "democratic_votes", "republican_votes")
county_vote_2016[] <- lapply(county_vote_2016, as.integer)
county_vote_2016["%_democrat"] <- county_vote_2016$democratic_votes / (county_vote_2016$democratic_votes+ county_vote_2016$republican_votes)
full_data <- merge(full_data, county_vote_2016[,c(1,4)], by = "fips", all.x = TRUE, all.y = TRUE)
```
# population density
```{r}
popdense <- read.csv("covid-project-raw-data/census-population-landarea.csv")
popdense <- na.omit(popdense)
merged_pop <- popdense[,-c(2:5)]
colnames(merged_pop) <- c("fips", "area", "pop_density")
```
```{r}
full_data <- merge(full_data, merged_pop, by = "fips", all.x = TRUE, all.y = TRUE) # Keep all rows of both data frames
```
# remove rows with na....
```{r}
full_data_no_na = na.omit(full_data)
nrow(full_data_no_na)
full_data
full_data_no_na
full_data_no_na[which(rowSums(is.na(full_data_no_na)) > 0),]
write.csv(full_data_no_na, file = "covid-project-raw-data/full_data_no_na.csv")
```
```{r}
data = read.csv('covid-project-raw-data/full_data_no_na.csv')
final_data = data[-which(rowSums(is.na(data)) > 0),]
data
final_data
write.csv(final_data, file = "covid-project-raw-data/full_data_no_na.csv")
```
##############################################
# plot %rural %democrat
```{r}
#full_data_no_na[,4:ncol(full_data_no_na)] <- lapply(full_data_no_na[,4:ncol(full_data_no_na)], as.numeric)
#plot(full_data_no_na$`%_rural`,full_data_no_na$`%_democrat`)
#cor(full_data_no_na$`%_rural`,full_data_no_na$`%_democrat`)
```