-
Notifications
You must be signed in to change notification settings - Fork 209
/
eda_nobel.Rmd
732 lines (556 loc) · 16.1 KB
/
eda_nobel.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
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
# (PART) 应用篇 {-}
# 探索性数据分析-诺奖获得者 {#eda-nobel}
探索性数据分析(exporatory data analysis)是各种知识的综合运用。本章通过一个案例,讲解探索性数据分析的基本思路,也算是对前面几章内容的一次总结复习。
## 探索性
- 数据准备(对数据要做到心中有数)
- 描述变量
- 数据结构
- 缺失值及其处理
- 数据探索(围绕探索的目标)
- 数据规整
- 可视化
- 建模
## 数据集
这是一个诺贝尔奖获得者的数据集,
```{r eda-nobel-1, out.width = '80%', fig.align='left', echo = FALSE}
knitr::include_graphics(path = "images/nobel_prize_winners_list.jpg")
```
## 导入数据
```{r eda-nobel-2, message=FALSE, warning=FALSE}
library(tidyverse)
library(lubridate)
```
```{r eda-nobel-3, message=FALSE, warning=FALSE}
df <- read_csv("./demo_data/nobel_winners.csv")
df
```
如果是xlsx格式
```{r eda-nobel-410, eval = FALSE}
readxl::read_excel("myfile.xlsx")
```
如果是csv格式
```{r eda-nobel-420, eval = FALSE}
readr::read_csv("myfile.csv")
```
::: {.rmdnote}
这里有个小小的提示:
- 路径(包括文件名), 不要用中文和空格
- 数据框中变量,也不要有中文和空格(可用下划线代替空格)
:::
## 数据结构
一行就是一个诺奖获得者的记录? 确定?
缺失值及其处理
```{r eda-nobel-6}
df %>% map_df(~ sum(is.na(.)))
```
性别缺失怎么造成的?
```{r eda-nobel-7}
df %>% count(laureate_type)
```
## 我们想探索哪些问题?
你想关心哪些问题,可能是
- 每个学科颁过多少次奖?
- 这些大神都是哪个年代的人?
- 性别比例
- 平均年龄和获奖数量
- 最年轻的诺奖获得者是谁?
- 中国诺奖获得者有哪些?
- 得奖的时候多大年龄?
- 获奖者所在国家的经济情况?
- 有大神多次获得诺贝尔奖,而且在不同科学领域获奖?
- 出生地分布?工作地分布?迁移模式?
- GDP经济与诺奖模型?
- 诺奖分享情况?
## 每个学科颁过多少次奖
```{r eda-nobel-8}
df %>% count(category)
```
```{r eda-nobel-9}
df %>%
count(category) %>%
ggplot(aes(x = category, y = n, fill = category)) +
geom_col() +
geom_text(aes(label = n), vjust = -0.25) +
theme(legend.position = "none")
```
```{r eda-nobel-10, fig.width= 6, fig.height= 4}
df %>%
count(category) %>%
ggplot(aes(x = fct_reorder(category, n), y = n, fill = category)) +
geom_col() +
geom_text(aes(label = n), vjust = -0.25) +
labs(title = "Number of Nobel prizes in different disciplines") +
theme(legend.position = "none")
```
也可以使用别人定义好的配色方案
```{r eda-nobel-11, fig.width= 6, fig.height= 4, warning=FALSE, message=FALSE}
library(ggthemr) # install.packages("devtools")
# devtools::install_github('cttobin/ggthemr')
ggthemr("dust")
df %>%
count(category) %>%
ggplot(aes(x = fct_reorder(category, n), y = n, fill = category)) +
geom_col() +
labs(title = "Number of Nobel prizes in different disciplines") +
theme(legend.position = "none")
```
```{r eda-nobel-12, echo=FALSE}
ggthemr_reset()
```
这个配色方案感觉挺好看的呢,比较适合我这种又挑剔又懒惰的人。
当然,也可以自己DIY,或者使用配色网站的主题方案(https://learnui.design/tools/data-color-picker.html#palette)
```{r eda-nobel-13, fig.width= 6, fig.height= 4}
df %>%
count(category) %>%
ggplot(aes(x = fct_reorder(category, n), y = n)) +
geom_col(fill = c("#003f5c", "#444e86", "#955196", "#dd5182", "#ff6e54", "#ffa600")) +
labs(title = "Number of Nobel prizes in different disciplines") +
theme(legend.position = "none")
```
让图骚动起来吧
```{r eda-nobel-14, eval=FALSE}
library(gganimate) # install.packages("gganimate", dependencies = T)
df %>%
count(category) %>%
mutate(category = fct_reorder(category, n)) %>%
ggplot(aes(x = category, y = n)) +
geom_text(aes(label = n), vjust = -0.25) +
geom_col(fill = c("#003f5c", "#444e86", "#955196", "#dd5182", "#ff6e54", "#ffa600")) +
labs(title = "Number of Nobel prizes in different disciplines") +
theme(legend.position = "none") +
transition_states(category) +
shadow_mark(past = TRUE)
```
和ggplot2的分面一样,动态图可以增加数据展示的维度。
## 看看我们伟大的祖国
```{r eda-nobel-15}
df %>%
dplyr::filter(birth_country == "China") %>%
dplyr::select(full_name, prize_year, category)
```
我们发现获奖者有多个地址,就会有重复的情况,比如 Charles Kuen Kao在2009年Physics有两次,为什么重复计数了呢?
下面我们去重吧, 去重可以用`distinct()`函数
```{r eda-nobel-16}
dt <- tibble::tribble(
~x, ~y, ~z,
1, 1, "a",
1, 1, "b",
1, 2, "c",
1, 2, "d"
)
dt
```
```{r eda-nobel-17}
dt %>% distinct_at(vars(x), .keep_all = T)
```
```{r eda-nobel-18}
dt %>% distinct_at(vars(x, y), .keep_all = T)
```
```{r eda-nobel-19}
nobel_winners <- df %>%
mutate_if(is.character, tolower) %>%
distinct_at(vars(full_name, prize_year, category), .keep_all = TRUE) %>%
mutate(
decade = 10 * (prize_year %/% 10),
prize_age = prize_year - year(birth_date)
)
nobel_winners
```
```{block eda-nobel-20, type="danger"}
这是时候,我们才对数据有了一个初步的了解
```
再来看看我的祖国
```{r eda-nobel-21}
nobel_winners %>%
dplyr::filter(birth_country == "china") %>%
dplyr::select(full_name, prize_year, category)
```
## 哪些大神多次获得诺贝尔奖
```{r eda-nobel-22}
nobel_winners %>% count(full_name, sort = T)
```
```{r eda-nobel-23}
nobel_winners %>%
group_by(full_name) %>%
mutate(
number_prize = n(),
number_cateory = n_distinct(category)
) %>%
arrange(desc(number_prize), full_name) %>%
dplyr::filter(number_cateory == 2)
```
## 大神在得奖的时候是多大年龄?
```{r eda-nobel-24}
nobel_winners %>%
count(prize_age) %>%
ggplot(aes(x = prize_age, y = n)) +
geom_col()
```
```{r eda-nobel-25}
nobel_winners %>%
group_by(category) %>%
summarise(mean_prize_age = mean(prize_age, na.rm = T))
```
```{r eda-nobel-26}
nobel_winners %>%
mutate(category = fct_reorder(category, prize_age, median, na.rm = TRUE)) %>%
ggplot(aes(category, prize_age)) +
geom_point() +
geom_boxplot() +
coord_flip()
```
```{r eda-nobel-27}
nobel_winners %>%
dplyr::filter(!is.na(prize_age)) %>%
group_by(decade, category) %>%
summarize(
average_age = mean(prize_age),
median_age = median(prize_age)
) %>%
ggplot(aes(decade, average_age, color = category)) +
geom_line()
```
```{r eda-nobel-28}
library(ggridges)
nobel_winners %>%
ggplot(aes(
x = prize_age,
y = category,
fill = category
)) +
geom_density_ridges()
```
他们60多少岁才得诺奖,大家才23或24岁,还年轻,不用焦虑喔。
```{r eda-nobel-29}
nobel_winners %>%
ggplot(aes(x = prize_age, fill = category, color = category)) +
geom_density() +
facet_wrap(vars(category)) +
theme(legend.position = "none")
```
有同学说要一个个的画,至于`group_split()`函数,下次课在讲
```{r eda-nobel-30}
nobel_winners %>%
group_split(category) %>%
map(
~ ggplot(data = .x, aes(x = prize_age)) +
geom_density() +
ggtitle(.x$category)
)
```
也可以用强大的`group_by() + group_map()`组合,我们会在第 \@ref(tidyverse-dplyr-adv) 章讲到
```{r eda-nobel-31, eval=FALSE}
nobel_winners %>%
group_by(category) %>%
group_map(
~ ggplot(data = .x, aes(x = prize_age)) +
geom_density() +
ggtitle(.y)
)
```
## 性别比例
```{r eda-nobel-32}
nobel_winners %>%
dplyr::filter(laureate_type == "individual") %>%
count(category, gender) %>%
group_by(category) %>%
mutate(prop = n / sum(n))
```
各年代性别比例
```{r eda-nobel-33}
nobel_winners %>%
dplyr::filter(laureate_type == "individual") %>%
# mutate(decade = glue::glue("{round(prize_year - 1, -1)}s")) %>%
count(decade, category, gender) %>%
group_by(decade, category) %>%
mutate(prop = n / sum(n)) %>%
ggplot(aes(decade, category, fill = prop)) +
geom_tile(size = 0.7) +
# geom_text(aes(label = scales::percent(prop, accuracy = .01))) +
geom_text(aes(label = scales::number(prop, accuracy = .01))) +
facet_grid(vars(gender)) +
scale_fill_gradient(low = "#FDF4E9", high = "#834C0D")
```
```{r eda-nobel-34}
library(ggbeeswarm) # install.packages("ggbeeswarm")
nobel_winners %>%
ggplot(aes(
x = category,
y = prize_age,
colour = gender,
alpha = gender
)) +
ggbeeswarm::geom_beeswarm() +
coord_flip() +
scale_color_manual(values = c("#BB1288", "#5867A6")) +
scale_alpha_manual(values = c(1, .4)) +
theme_minimal() +
theme(legend.position = "top") +
labs(
title = "Gender imbalance of Nobel laureates",
subtitle = "data frome 1901-2016",
colour = "Gender",
alpha = "Gender",
y = "age in prize"
)
```
```{r eda-nobel-35}
nobel_winners %>%
count(decade,
category,
gender = coalesce(gender, laureate_type)
) %>%
group_by(decade, category) %>%
mutate(percent = n / sum(n)) %>%
ggplot(aes(decade, n, fill = gender)) +
geom_col() +
facet_wrap(~category) +
labs(
x = "Decade",
y = "# of nobel prize winners",
fill = "Gender",
title = "Nobel Prize gender distribution over time"
)
```
## 这些大神都是哪个年代出生的人?
```{r eda-nobel-36}
nobel_winners %>%
select(category, birth_date) %>%
mutate(year = floor(year(birth_date) / 10) * 10) %>%
count(category, year) %>%
dplyr::filter(!is.na(year)) %>%
ggplot(aes(x = year, y = n)) +
geom_col() +
scale_x_continuous(breaks = seq(1810, 1990, 20)) +
geom_text(aes(label = n), vjust = -0.25) +
facet_wrap(vars(category))
```
课堂练习,哪位同学能把图弄得好看些?
## 最年轻的诺奖获得者?
```{r eda-nobel-37}
nobel_winners %>%
dplyr::filter(prize_age == min(prize_age, na.rm = T))
```
```{r eda-nobel-38}
nobel_winners %>%
dplyr::filter(
rank(prize_year - year(birth_date)) == 1
)
```
```{r eda-nobel-39}
nobel_winners %>%
arrange(
prize_year - year(birth_date)
)
```
```{r eda-nobel-40}
nobel_winners %>%
top_n(1, year(birth_date) - prize_year)
```
## 平均年龄和获奖数量
```{r eda-nobel-41}
df1 <- nobel_winners %>%
group_by(category) %>%
summarise(
mean_prise_age = mean(prize_age, na.rm = T),
total_num = n()
)
df1
```
```{r eda-nobel-42}
df1 %>%
ggplot(aes(mean_prise_age, total_num)) +
geom_point(aes(color = category)) +
geom_smooth(method = lm, se = FALSE)
```
## 出生地与工作地分布
```{r eda-nobel-43}
nobel_winners_clean <- nobel_winners %>%
mutate_at(
vars(birth_country, death_country),
~ ifelse(str_detect(., "\\("), str_extract(., "(?<=\\().*?(?=\\))"), .)
) %>%
mutate_at(
vars(birth_country, death_country),
~ case_when(
. == "scotland" ~ "united kingdom",
. == "northern ireland" ~ "united kingdom",
str_detect(., "czech") ~ "czechia",
str_detect(., "germany") ~ "germany",
TRUE ~ .
)
) %>%
select(full_name, prize_year, category, birth_date, birth_country, gender, organization_name, organization_country, death_country)
```
```{r eda-nobel-44}
nobel_winners_clean %>% count(death_country, sort = TRUE)
```
## 迁移模式
```{r eda-nobel-45, fig.width= 9, fig.height= 8}
nobel_winners_clean %>%
mutate(
colour = case_when(
death_country == "united states of america" ~ "#FF2B4F",
death_country == "germany" ~ "#fcab27",
death_country == "united kingdom" ~ "#3686d3",
death_country == "france" ~ "#88398a",
death_country == "switzerland" ~ "#20d4bc",
TRUE ~ "gray60"
)
) %>%
ggplot(aes(
x = 0,
y = fct_rev(factor(birth_country)),
xend = death_country,
yend = 1,
colour = colour,
alpha = (colour != "gray60")
)) +
geom_curve(
curvature = -0.5,
arrow = arrow(length = unit(0.01, "npc"))
) +
scale_x_discrete() +
scale_y_discrete() +
scale_color_identity() +
scale_alpha_manual(values = c(0.1, 0.2), guide = F) +
scale_size_manual(values = c(0.1, 0.4), guide = F) +
theme_minimal() +
theme(
panel.grid = element_blank(),
plot.background = element_rect(fill = "#F0EFF1", colour = "#F0EFF1"),
legend.position = "none",
axis.text.x = element_text(angle = 40, hjust = 1)
)
```
## 地图
```{r eda-nobel-46}
library(here)
library(sf)
library(countrycode)
# countrycode('Albania', 'country.name', 'iso3c')
nobel_winners_birth_country <- nobel_winners_clean %>%
count(birth_country) %>%
filter(!is.na(birth_country)) %>%
mutate(ISO3 = countrycode(birth_country,
origin = "country.name", destination = "iso3c"
))
global <-
sf::st_read("./demo_data/worldmap/TM_WORLD_BORDERS_SIMPL-0.3.shp") %>%
st_transform(4326)
global %>%
full_join(nobel_winners_birth_country, by = "ISO3") %>%
ggplot() +
geom_sf(aes(fill = n),
color = "white",
size = 0.1
) +
labs(
x = NULL, y = NULL,
title = "Nobel Winners by country",
subtitle = "color of map indicates number of Nobel lauretes",
fill = "num of Nobel lauretes",
caption = "Made: wang_minjie"
) +
scale_fill_gradientn(colors = c("royalblue1", "magenta", "orange", "gold"), na.value = "white") +
# scale_fill_gradient(low = "wheat1", high = "red") +
theme_void() +
theme(
legend.position = c(0.1, 0.3),
plot.background = element_rect(fill = "gray")
)
```
```{r eda-nobel-47}
# Determine to 10 Countries
topCountries <- nobel_winners_clean %>%
count(birth_country, sort = TRUE) %>%
na.omit() %>%
top_n(8)
topCountries
```
```{r eda-nobel-48}
df4 <- nobel_winners_clean %>%
filter(birth_country %in% topCountries$birth_country) %>%
group_by(birth_country, category, prize_year) %>%
summarise(prizes = n()) %>%
mutate(cumPrizes = cumsum(prizes))
df4
```
```{r eda-nobel-49}
library(gganimate)
df4 %>%
mutate(prize_year = as.integer(prize_year)) %>%
ggplot(aes(x = birth_country, y = category, color = birth_country)) +
geom_point(aes(size = cumPrizes), alpha = 0.6) +
# geom_text(aes(label = cumPrizes)) +
scale_size_continuous(range = c(2, 30)) +
transition_reveal(prize_year) +
labs(
title = "Top 10 countries with Nobel Prize winners",
subtitle = "Year: {frame_along}",
y = "Category"
) +
theme_minimal() +
theme(
plot.title = element_text(size = 22),
axis.title = element_blank()
) +
scale_color_brewer(palette = "RdYlBu") +
theme(legend.position = "none") +
theme(plot.margin = margin(5.5, 5.5, 5.5, 5.5))
```
## 出生地和工作地不一样的占比
```{r eda-nobel-50}
nobel_winners_clean %>%
select(category, birth_country, death_country) %>%
mutate(immigration = if_else(birth_country == death_country, 0, 1))
```
## 诺奖分享者
<!-- # https://github.com/gkaramanis/tidytuesday/blob/master/week-20/nobelShared.R -->
```{r eda-nobel-51, eval=FALSE}
nobel_winners %>%
separate(prize_share, into = c("num", "deno"), sep = "/", remove = FALSE)
```
```{r eda-nobel-52}
nobel_winners %>%
filter(category == "medicine") %>%
mutate(
num_a = as.numeric(str_sub(prize_share, 1, 1)),
num_b = as.numeric(str_sub(prize_share, -1)),
share = num_a / num_b,
year = prize_year %% 10,
decade = 10 * (prize_year %/% 10)
) %>%
group_by(prize_year) %>%
mutate(n = row_number()) %>%
ggplot() +
geom_col(aes(x = "", y = share, fill = as.factor(n)),
show.legend = FALSE
) +
coord_polar("y") +
facet_grid(decade ~ year, switch = "both") +
labs(title = "Annual Nobel Prize sharing") +
theme_void() +
theme(
plot.title = element_text(face = "bold", vjust = 8),
strip.text.x = element_text(
size = 7,
margin = margin(t = 5)
),
strip.text.y = element_text(
size = 7,
angle = 180, hjust = 1, margin = margin(r = 10)
)
)
```
## 其它
没有回答的问题,大家自己花时间探索下。
## 延伸阅读
- 有些图可以再美化下
```{r eda-nobel-53, echo = F}
# remove the objects
rm(df, df1, df4, dt, global, nobel_winners, nobel_winners_birth_country, nobel_winners_clean, scale_color_continuous, scale_color_discrete, scale_color_gradient, topCountries)
```
```{r eda-nobel-54, echo = F, message = F, warning = F, results = "hide"}
pacman::p_unload(pacman::p_loaded(), character.only = TRUE)
```