EDA-Examples/CovidEDA.Rmd at master · sbbell/EDA-Examples · 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
123
124
---
title: "COVID-19 EDA"
author: "Julia Layne"
date: "3/13/2020"
output: html_document
---

## Read in Files
Change with new COVID file for most up to date info
```{r}
covid_raw = read.csv("05-21-2020.csv",header = TRUE)
#covid_ts_confirmed = read.csv(file.choose(),header = TRUE)
```

## Look at Raw Data

```{r}
summary(covid_raw)
#covid_ts_confirmed
```

# Plot Data

Initial lookinto ploting data points
Note here
```{r}
#install.packages("tidyverse")
library(tidyverse)
library(ggplot2)
library(GGally)
library(plotly)

plot(covid_raw)

byState10 <- covid_raw %>% head(10) %>% ggplot(aes(x=Deaths, y=Confirmed, fill=Province_State)) + geom_point(aes(fill=Province_State)) + ggtitle("Deaths vs Confirmed Cases in First Ten Provinces")

ggplotly(byState10)

byState <- covid_raw %>% ggplot(aes(x=Deaths, y=Confirmed, fill=Province_State)) + geom_point(aes(fill=Province_State)) + ggtitle("Deaths vs Confirmed Cases per Province")
ggplotly(byState)

byStateNoNY <- filter(covid_raw, Province_State != 'New York' & Province_State != 'New Jersey' & Province_State != 'Hubei')  %>% ggplot(aes(x=Deaths, y=Confirmed, fill=Province_State)) + geom_point(aes(fill=Province_State)) + ggtitle("Deaths vs Confirmed Cases per Province")
ggplotly(byStateNoNY)

#covid_raw %>% head(10) %>% ggplot(aes(x=Deaths, y=Confirmed, fill=Province_State) + geom_point(aes(fill=Province_State)) + ggtitle("Deaths vs Confirmed Cases in Top Countries (Minus China)")

```

```{r}
statesAbove700Deaths <- filter(covid_raw, Deaths > 700)  %>% ggplot(aes(x=Deaths, y=Confirmed, fill=Province_State)) + geom_point(aes(fill=Province_State)) + ggtitle("Over 700 Mortality States")
ggplotly(statesAbove700Deaths)

statesAbove700Deaths <- filter(covid_raw, Deaths < 700)  %>% ggplot(aes(x=Deaths, y=Confirmed, fill=Province_State)) + geom_point(aes(fill=Province_State)) + ggtitle("Under 700 Mortality States")
ggplotly(statesAbove700Deaths)
```


# Map data using Fips codes

```{r}
library(e1071)
library(usmap)

UScovid_dataset <- filter(covid_raw, Country_Region == 'US' & FIPS != 'NA')
UScovid_dataset

#UScovid_dataset$fips <- fips(brew_count_by_state$state)
attach(UScovid_dataset)
UScovid_dataset_fips <- UScovid_dataset[order(FIPS),]
detach(UScovid_dataset)


UScovid_dataset_fips$fips = UScovid_dataset_fips$FIPS

plot_usmap(data = UScovid_dataset_fips,  values = "Deaths", color = rgb(.2, .7, 1)) +
    labs(title = "Covid Deaths by State", subtitle = "Count of Covid19 Deaths per state") +
  scale_fill_continuous(low = "white", high = rgb(.2, .7, 1), name = "Deaths per state", label = scales::comma) + theme(legend.position = "right")

plot_usmap(data = filter(UScovid_dataset_fips, Province_State != 'New York'),  values = "Deaths", color = rgb(.2, .7, 1)) +
    labs(title = "Covid Deaths by State (New York Removed)", subtitle = "Count of Covid19 Deaths per state") +
  scale_fill_continuous(low = "white", high = rgb(.2, .7, 1), name = "Deaths per state", label = scales::comma) + theme(legend.position = "right")

plot_usmap(data = filter(UScovid_dataset_fips, Province_State != 'New York' & Province_State != 'New Jersey'),  values = "Deaths", color = rgb(.2, .7, 1)) +
    labs(title = "Covid Deaths by State (New York Removed)", subtitle = "Count of Covid19 Deaths per state") +
  scale_fill_continuous(low = "white", high = rgb(.2, .7, 1), name = "Deaths per state", label = scales::comma) + theme(legend.position = "right")
```

# Previous Work - Finding the top Countries by Confirmed Cases

```{r}
confirmed_by_country <- covid_raw%>% group_by(Country_Region) %>% tally(Confirmed, name = "Confirmed", sort = TRUE)
confirmed_by_country

deaths_by_country <- covid_raw%>% group_by(Country_Region) %>% tally(Deaths, name = "Deaths", sort = TRUE)
deaths_by_country

totals <- merge(confirmed_by_country, deaths_by_country, by="Country_Region")
totals

```

Then reordered by Confirmed
```{r}

top_to_least <- totals[order(totals$Confirmed, decreasing = TRUE),]

top_to_least
```

```{r}

top10Confirmed <- top_to_least %>% head(10) %>% ggplot(aes(x=Deaths, y=Confirmed, fill=Country_Region)) + geom_point(aes(fill=Country_Region)) + ggtitle("Deaths vs Confirmed Cases in Top countries")

ggplotly(top10Confirmed)

# At the time, China was the highest and I wanted to look at the rest, now it is much different
top10ConfirmedMinusChina <- subset(top_to_least, Country_Region != "China")  %>% head(10) %>% ggplot(aes(x=Deaths, y=Confirmed, fill=Country_Region)) + geom_point(aes(fill=Country_Region)) + ggtitle("Deaths vs Confirmed Cases in Top Countries (Minus China)")
ggplotly(top10ConfirmedMinusChina)

# Now removing US instead
top10ConfirmedMinusUS <- subset(top_to_least, Country_Region != "US")  %>% head(10) %>% ggplot(aes(x=Deaths, y=Confirmed, fill=Country_Region)) + geom_point(aes(fill=Country_Region)) + ggtitle("Deaths vs Confirmed Cases in Top Countries (Minus US)")
ggplotly(top10ConfirmedMinusUS)
```