-
Notifications
You must be signed in to change notification settings - Fork 0
/
AYA_Codeathon_Visualization_Day4_v02.Rmd
236 lines (198 loc) · 8.04 KB
/
AYA_Codeathon_Visualization_Day4_v02.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
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
---
title: "AYA_Codeathon_Visualization_Day4_v0.2"
author: "Faith Lee and Lesley Chapman"
output: pdf_document
---
## DATA VISUALIZATION FUNCTIONS
```{r setup, include=FALSE}
library(ggplot2)
library(dplyr)
library(usmap)
SEER_Cleaned <- read.csv("codeathon_RECODE_v03.csv")
```
## TOP 10 CANCERS
```{r}
heatmap_data<- SEER_Cleaned %>%
group_by(Year.of.diagnosis, Site.recode.ICD.O.3.WHO.2008) %>%
summarize(cancer_count = n()) %>% arrange(Year.of.diagnosis, desc(cancer_count)) %>%
group_by(Year.of.diagnosis) %>% slice(1:10)
ggplot(heatmap_data, aes(x=factor(Year.of.diagnosis), y=Site.recode.ICD.O.3.WHO.2008, fill= cancer_count)) +
geom_tile() +
xlab("Year of Diagnosis") +
ylab("Type of Cancer") +
ggtitle("Top 10 cancers of each year")
```
## BY AGE GROUP
```{r}
heatmap_data<- SEER_Cleaned %>%
group_by(Year.of.diagnosis, Age.recode.with..1.year.olds) %>%
summarize(cancer_count = n())
ggplot(heatmap_data, aes(x=factor(Year.of.diagnosis), y=Age.recode.with..1.year.olds, fill= cancer_count)) +
geom_tile(color="white") +
xlab("Year of Diagnosis") +
ylab("Age Group") +
ggtitle("AYA Cancer Counts by Age Group") +
scale_fill_gradient(low="pink", high="red")+theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
```
## BY RACE
```{r}
heatmap_data<- SEER_Cleaned %>%
group_by(Year.of.diagnosis, Race.and.origin.recode..NHW..NHB..NHAIAN..NHAPI..Hispanic.) %>%
summarize(cancer_count = n())
ggplot(heatmap_data, aes(x=factor(Year.of.diagnosis), y=Race.and.origin.recode..NHW..NHB..NHAIAN..NHAPI..Hispanic., fill= cancer_count)) +
geom_tile() +
xlab("Year of Diagnosis") +
ylab("Race And Origin") +
ggtitle("AYA Cancer Counts by Race and Origin") +
scale_fill_gradient(low="chartreuse", high="chartreuse4")+theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
```
## IS there a relation between education level and cancer count?
## Distribution of Survival Months BY RACE
```{r}
ggplot(SEER_Cleaned_updated, aes(x=Race.and.origin.recode..NHW..NHB..NHAIAN..NHAPI..Hispanic., y=Survival.months, fill=factor(Decade))) +
geom_boxplot() +
ggtitle("Survival Months by Race") +
xlab("Race and Origin") +ylab("Survival Months") +
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
```
#### Survival Plots
## Survival time between men and women .
```{r}
ggplot(SEER_Cleaned_updated, aes(x=Survival.months, color=Sex)) +
geom_histogram(fill="white", alpha=0.5, position="identity") +
ylab("Frequency") +
xlab("Survival Months") +
ggtitle("Distribution of Survival months by Gender") +
theme_bw()
# map_data <- SEER_Cleaned_updated %>% group_by(State) %>% summarize(count=n())
# names(map_data)[names(map_data) == 'State'] <- 'state'
# plot_usmap(data = map_data, values="count", color="blue") +
# labs(title = "U.S. States", subtitle = "Map of the United States") +
# theme(panel.background=element_blank(), legend.position = "right") +
# scale_fill_continuous(low = "white", high = "red", name = "Cancer Counts \n 1997-2016 in 13 States")
```
### Note: Survival.months.flag is currently coded as 1 not 'complete'
**1997 to 2006**
```{r}
SEER_1997_2006 <- SEER_Cleaned_updated %>%
filter(Year.of.diagnosis >= 1997 & Year.of.diagnosis <= 2006) %>%
filter(Survival.months > 0)
```
```{r}
er <- SEER_1997_2006 %>% distinct(Year.of.diagnosis)
er$Year.of.diagnosis
```
```{r}
ggplot(SEER_1997_2006, aes(x=Survival.months, color=Unemployed_cat)) +
geom_histogram(fill="white", alpha=0.5, position="identity") +
ylab("Frequency") +
xlab("Survival Months") +
ggtitle("1997-2006: Distribution of Survival months by Employment Status") +
theme_bw() +
guides(col=guide_legend("Employment_Status"))
```
```{r}
ggplot(SEER_1997_2006, aes(x=Survival.months, color=Rural.Urban.Continuum.Code.2013)) +
geom_histogram(fill="white", alpha=0.5, position="identity") +
ylab("Frequency") +
xlab("Survival Months") +
ggtitle("1997-2006: Distribution of Survival months by Region : Rural vs Urban") +
theme_bw() +
guides(col=guide_legend("Rural_Urban"))
```
```{r}
ggplot(SEER_1997_2006, aes(x=Survival.months, color=HighSchoolEdCat)) +
geom_histogram(fill="white", alpha=0.5, position="identity") +
ylab("Frequency") +
xlab("Survival Months") +
ggtitle("1997-2006: Distribution of Survival months by High School Education") +
theme_bw() +
guides(col=guide_legend("Education Stauts"))
```
**2007-2016**
```{r}
SEER_2007_2016 <- SEER_Cleaned_updated %>%
filter(Year.of.diagnosis >= 2007 & Year.of.diagnosis <= 2016) %>%
filter(Survival.months > 0)
```
```{r}
er <- SEER_2007_2016 %>% distinct(Year.of.diagnosis)
er$Year.of.diagnosis
```
```{r}
ggplot(SEER_2007_2016, aes(x=Survival.months, color=Unemployed_cat)) +
geom_histogram(fill="white", alpha=0.5, position="identity") +
ylab("Frequency") +
xlab("Survival Months") +
ggtitle("2007-2016: Distribution of Survival months by Employment Status") +
theme_bw() +
guides(col=guide_legend("Employment_Status"))
```
```{r}
ggplot(SEER_2007_2016, aes(x=Survival.months, color=Rural.Urban.Continuum.Code.2013)) +
geom_histogram(fill="white", alpha=0.5, position="identity") +
ylab("Frequency") +
xlab("Survival Months") +
ggtitle("2007-2016: Distribution of Survival months by Region : Rural vs Urban") +
theme_bw() +
guides(col=guide_legend("Rural_Urban"))
```
```{r}
ggplot(SEER_2007_2016, aes(x=Survival.months, color=HighSchoolEdCat)) +
geom_histogram(fill="white", alpha=0.5, position="identity") +
ylab("Frequency") +
xlab("Survival Months") +
ggtitle("2007-2016: Distribution of Survival months by High School Education") +
theme_bw() +
guides(col=guide_legend("Education Stauts"))
```
## MOST COMMON CANCERS TO MEN
## MOST COMMON CANCERS TO WOMEN
## CANCER COUNTS by unemployedment year over year
```{r}
lineplot <- SEER_Cleaned_updated%>% group_by(Year.of.diagnosis, Sex) %>% summarize(count=n())
ggplot(data=lineplot, aes(x=Year.of.diagnosis, y=count, group=Sex)) +
geom_line(aes(linetype=Sex))+ theme_bw() +
geom_point(aes(shape=Sex))+ ggtitle("AYA Counts by Gender") +
ylab("Count") +
xlab("Year")
ggplot(SEER_Cleaned_updated, aes(x=Chemotherapy.recode..yes..no.unk., y=Survival.months, fill=factor(Decade))) +
geom_boxplot() +
ggtitle("Survival Months by Chemotherapy") +
xlab("Chemotherapy (Yes, No| Unknown)") +
ylab("Survival Months") +
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
```
## REMOVAL OF 31307 rows
```{r}
ggplot(SEER_Cleaned_updated, aes(x=factor(median_income_household_group), y=Survival.months, fill=factor(Decade))) +
geom_boxplot() +
ggtitle("Survival Months by Median Income Household Group") +
xlab("Median Income Group") +ylab("Survival Months") +
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
ggplot(SEER_Cleaned_updated, aes(x=factor(Unemployed_cat), y=Survival.months, fill=factor(Decade))) +
geom_boxplot() +
ggtitle("Survival Months by Unemployment in County") +
xlab("Unemployment Level In County") +ylab("Survival Months") +
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
```
## POVERTY, SURVIVAL AND COUNTS
```{r}
SEER_Cleaned_updated$family_poverty<- as.double(SEER_Cleaned_updated$X..Families.below.poverty.ACS.2013.2017)/100
tt<-SEER_Cleaned_updated %>%
group_by(family_poverty, Race.and.origin.recode..NHW..NHB..NHAIAN..NHAPI..Hispanic.)%>%
summarize(count=n(), median_survival_months = median(Survival.months, na.rm=TRUE))
tt$family_poverty_grouped<- cut(tt$family_poverty, breaks = c(0,10,20,30,40,50,100))
tt_count <- tt%>% filter(count>100)
ggplot(tt_count, aes(x=family_poverty,median_survival_months)) +
geom_point(aes(size = count, color=Race.and.origin.recode..NHW..NHB..NHAIAN..NHAPI..Hispanic.)) +
ggtitle("Counts by Median Survival Months and Family Poverty (>200) w Racial component") +
ylab("Median Survival") + xlab("Family Poverty (%) at County Level") +
theme_bw()
```
## TOP 10 Cancer
```{r}
SEER_Cleaned_updated %>%
filter(Survival.months.flag==1) %>%
summarize(median(Survival.months, na.rm=TRUE))
```