-
Notifications
You must be signed in to change notification settings - Fork 3
Expand file tree
/
Copy pathDataAdaptation.R
More file actions
456 lines (373 loc) · 26.4 KB
/
DataAdaptation.R
File metadata and controls
456 lines (373 loc) · 26.4 KB
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
library(tidyverse)
library(ggplot2)
library(dplyr)
library(lubridate)
library(data.table)
setwd("~/dataProcessesProject/")
# Load CSVs
madrid_2010 <-read_csv("data/Madrid_pollution_level_dataset/csvs_per_year/madrid_2010.csv")
madrid_2010$only_month <-unlist(lapply(madrid_2010$date, month))
madrid_2010$only_year <-unlist(lapply(madrid_2010$date, year))
means<- madrid_2010 %>%
group_by(only_year,only_month,station) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
meansNoStation<- madrid_2010 %>%
group_by(only_year,only_month) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
for(i in 1:length(madrid_2010$BEN)){
if(is.na(madrid_2010$CO[i])){
madrid_2010$CO[i]<-means$mean_CO[means$only_month==madrid_2010$only_month[i]&means$only_year==madrid_2010$only_year[i]&means$station==madrid_2010$station[i]]}
if(is.na(madrid_2010$NO_2[i])){
madrid_2010$NO_2[i]<-means$mean_NO2[means$only_month==madrid_2010$only_month[i]&means$only_year==madrid_2010$only_year[i]&means$station==madrid_2010$station[i]]}
if(is.na(madrid_2010$O_3[i])){
madrid_2010$O_3[i]<-means$mean_O3[means$only_month==madrid_2010$only_month[i]&means$only_year==madrid_2010$only_year[i]&means$station==madrid_2010$station[i]]}
if(is.na(madrid_2010$SO_2[i])){
madrid_2010$SO_2[i]<-means$mean_SO2[means$only_month==madrid_2010$only_month[i]&means$only_year==madrid_2010$only_year[i]&means$station==madrid_2010$station[i]]}
if(is.na(madrid_2010$PM10[i])){
madrid_2010$PM10[i]<-means$mean_PM10[means$only_month==madrid_2010$only_month[i]&means$only_year==madrid_2010$only_year[i]&means$station==madrid_2010$station[i]]}
}
for(i in 1:length(madrid_2010$BEN)){
if(is.nan(madrid_2010$CO[i])){
madrid_2010$CO[i]<-meansNoStation$mean_CO[meansNoStation$only_month==madrid_2010$only_month[i]&meansNoStation$only_year==madrid_2010$only_year[i]]}
if(is.nan(madrid_2010$NO_2[i])){
madrid_2010$NO_2[i]<-meansNoStation$mean_NO2[meansNoStation$only_month==madrid_2010$only_month[i]&meansNoStation$only_year==madrid_2010$only_year[i]]}
if(is.nan(madrid_2010$O_3[i])){
madrid_2010$O_3[i]<-meansNoStation$mean_O3[meansNoStation$only_month==madrid_2010$only_month[i]&meansNoStation$only_year==madrid_2010$only_year[i]]}
if(is.nan(madrid_2010$SO_2[i])){
madrid_2010$SO_2[i]<-meansNoStation$mean_SO2[meansNoStation$only_month==madrid_2010$only_month[i]&meansNoStation$only_year==madrid_2010$only_year[i]]}
if(is.nan(madrid_2010$PM10[i])){
madrid_2010$PM10[i]<-meansNoStation$mean_PM10[meansNoStation$only_month==madrid_2010$only_month[i]&meansNoStation$only_year==madrid_2010$only_year[i]]}
}
write.csv(madrid_2010,"dataWoNa/madrid_2010.csv", row.names = TRUE)
madrid_2011 <-read_csv("data/Madrid_pollution_level_dataset/csvs_per_year/madrid_2011.csv")
madrid_2011$only_month <-unlist(lapply(madrid_2011$date, month))
madrid_2011$only_year <-unlist(lapply(madrid_2011$date, year))
means<- madrid_2011 %>%
group_by(only_year,only_month,station) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
meansNoStation<- madrid_2011 %>%
group_by(only_year,only_month) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
for(i in 1:length(madrid_2011$BEN)){
if(is.na(madrid_2011$CO[i])){
madrid_2011$CO[i]<-means$mean_CO[means$only_month==madrid_2011$only_month[i]&means$only_year==madrid_2011$only_year[i]&means$station==madrid_2011$station[i]]}
if(is.na(madrid_2011$NO_2[i])){
madrid_2011$NO_2[i]<-means$mean_NO2[means$only_month==madrid_2011$only_month[i]&means$only_year==madrid_2011$only_year[i]&means$station==madrid_2011$station[i]]}
if(is.na(madrid_2011$O_3[i])){
madrid_2011$O_3[i]<-means$mean_O3[means$only_month==madrid_2011$only_month[i]&means$only_year==madrid_2011$only_year[i]&means$station==madrid_2011$station[i]]}
if(is.na(madrid_2011$SO_2[i])){
madrid_2011$SO_2[i]<-means$mean_SO2[means$only_month==madrid_2011$only_month[i]&means$only_year==madrid_2011$only_year[i]&means$station==madrid_2011$station[i]]}
if(is.na(madrid_2011$PM10[i])){
madrid_2011$PM10[i]<-means$mean_PM10[means$only_month==madrid_2011$only_month[i]&means$only_year==madrid_2011$only_year[i]&means$station==madrid_2011$station[i]]}
}
for(i in 1:length(madrid_2011$BEN)){
if(is.nan(madrid_2011$CO[i])){
madrid_2011$CO[i]<-meansNoStation$mean_CO[meansNoStation$only_month==madrid_2011$only_month[i]&meansNoStation$only_year==madrid_2011$only_year[i]]}
if(is.nan(madrid_2011$NO_2[i])){
madrid_2011$NO_2[i]<-meansNoStation$mean_NO2[meansNoStation$only_month==madrid_2011$only_month[i]&meansNoStation$only_year==madrid_2011$only_year[i]]}
if(is.nan(madrid_2011$O_3[i])){
madrid_2011$O_3[i]<-meansNoStation$mean_O3[meansNoStation$only_month==madrid_2011$only_month[i]&meansNoStation$only_year==madrid_2011$only_year[i]]}
if(is.nan(madrid_2011$SO_2[i])){
madrid_2011$SO_2[i]<-meansNoStation$mean_SO2[meansNoStation$only_month==madrid_2011$only_month[i]&meansNoStation$only_year==madrid_2011$only_year[i]]}
if(is.nan(madrid_2011$PM10[i])){
madrid_2011$PM10[i]<-meansNoStation$mean_PM10[meansNoStation$only_month==madrid_2011$only_month[i]&meansNoStation$only_year==madrid_2011$only_year[i]]}
}
write.csv(madrid_2011,"dataWoNa/madrid_2011.csv", row.names = TRUE)
madrid_2012 <-read_csv("data/Madrid_pollution_level_dataset/csvs_per_year/madrid_2012.csv")
madrid_2012$only_month <-unlist(lapply(madrid_2012$date, month))
madrid_2012$only_year <-unlist(lapply(madrid_2012$date, year))
means<- madrid_2012 %>%
group_by(only_year,only_month,station) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
meansNoStation<- madrid_2012 %>%
group_by(only_year,only_month) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
for(i in 1:length(madrid_2012$BEN)){
if(is.na(madrid_2012$CO[i])){
madrid_2012$CO[i]<-means$mean_CO[means$only_month==madrid_2012$only_month[i]&means$only_year==madrid_2012$only_year[i]&means$station==madrid_2012$station[i]]}
if(is.na(madrid_2012$NO_2[i])){
madrid_2012$NO_2[i]<-means$mean_NO2[means$only_month==madrid_2012$only_month[i]&means$only_year==madrid_2012$only_year[i]&means$station==madrid_2012$station[i]]}
if(is.na(madrid_2012$O_3[i])){
madrid_2012$O_3[i]<-means$mean_O3[means$only_month==madrid_2012$only_month[i]&means$only_year==madrid_2012$only_year[i]&means$station==madrid_2012$station[i]]}
if(is.na(madrid_2012$SO_2[i])){
madrid_2012$SO_2[i]<-means$mean_SO2[means$only_month==madrid_2012$only_month[i]&means$only_year==madrid_2012$only_year[i]&means$station==madrid_2012$station[i]]}
if(is.na(madrid_2012$PM10[i])){
madrid_2012$PM10[i]<-means$mean_PM10[means$only_month==madrid_2012$only_month[i]&means$only_year==madrid_2012$only_year[i]&means$station==madrid_2012$station[i]]}
}
for(i in 1:length(madrid_2012$BEN)){
if(is.nan(madrid_2012$CO[i])){
madrid_2012$CO[i]<-meansNoStation$mean_CO[meansNoStation$only_month==madrid_2012$only_month[i]&meansNoStation$only_year==madrid_2012$only_year[i]]}
if(is.nan(madrid_2012$NO_2[i])){
madrid_2012$NO_2[i]<-meansNoStation$mean_NO2[meansNoStation$only_month==madrid_2012$only_month[i]&meansNoStation$only_year==madrid_2012$only_year[i]]}
if(is.nan(madrid_2012$O_3[i])){
madrid_2012$O_3[i]<-meansNoStation$mean_O3[meansNoStation$only_month==madrid_2012$only_month[i]&meansNoStation$only_year==madrid_2012$only_year[i]]}
if(is.nan(madrid_2012$SO_2[i])){
madrid_2012$SO_2[i]<-meansNoStation$mean_SO2[meansNoStation$only_month==madrid_2012$only_month[i]&meansNoStation$only_year==madrid_2012$only_year[i]]}
if(is.nan(madrid_2012$PM10[i])){
madrid_2012$PM10[i]<-meansNoStation$mean_PM10[meansNoStation$only_month==madrid_2012$only_month[i]&meansNoStation$only_year==madrid_2012$only_year[i]]}
}
write.csv(madrid_2012,"dataWoNa/madrid_2012.csv", row.names = TRUE)
madrid_2013 <-read_csv("data/Madrid_pollution_level_dataset/csvs_per_year/madrid_2013.csv")
madrid_2013$only_month <-unlist(lapply(madrid_2013$date, month))
madrid_2013$only_year <-unlist(lapply(madrid_2013$date, year))
means<- madrid_2013 %>%
group_by(only_year,only_month,station) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
meansNoStation<- madrid_2013 %>%
group_by(only_year,only_month) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
for(i in 1:length(madrid_2013$BEN)){
if(is.na(madrid_2013$CO[i])){
madrid_2013$CO[i]<-means$mean_CO[means$only_month==madrid_2013$only_month[i]&means$only_year==madrid_2013$only_year[i]&means$station==madrid_2013$station[i]]}
if(is.na(madrid_2013$NO_2[i])){
madrid_2013$NO_2[i]<-means$mean_NO2[means$only_month==madrid_2013$only_month[i]&means$only_year==madrid_2013$only_year[i]&means$station==madrid_2013$station[i]]}
if(is.na(madrid_2013$O_3[i])){
madrid_2013$O_3[i]<-means$mean_O3[means$only_month==madrid_2013$only_month[i]&means$only_year==madrid_2013$only_year[i]&means$station==madrid_2013$station[i]]}
if(is.na(madrid_2013$SO_2[i])){
madrid_2013$SO_2[i]<-means$mean_SO2[means$only_month==madrid_2013$only_month[i]&means$only_year==madrid_2013$only_year[i]&means$station==madrid_2013$station[i]]}
if(is.na(madrid_2013$PM10[i])){
madrid_2013$PM10[i]<-means$mean_PM10[means$only_month==madrid_2013$only_month[i]&means$only_year==madrid_2013$only_year[i]&means$station==madrid_2013$station[i]]}
}
for(i in 1:length(madrid_2013$BEN)){
if(is.nan(madrid_2013$CO[i])){
madrid_2013$CO[i]<-meansNoStation$mean_CO[meansNoStation$only_month==madrid_2013$only_month[i]&meansNoStation$only_year==madrid_2013$only_year[i]]}
if(is.nan(madrid_2013$NO_2[i])){
madrid_2013$NO_2[i]<-meansNoStation$mean_NO2[meansNoStation$only_month==madrid_2013$only_month[i]&meansNoStation$only_year==madrid_2013$only_year[i]]}
if(is.nan(madrid_2013$O_3[i])){
madrid_2013$O_3[i]<-meansNoStation$mean_O3[meansNoStation$only_month==madrid_2013$only_month[i]&meansNoStation$only_year==madrid_2013$only_year[i]]}
if(is.nan(madrid_2013$SO_2[i])){
madrid_2013$SO_2[i]<-meansNoStation$mean_SO2[meansNoStation$only_month==madrid_2013$only_month[i]&meansNoStation$only_year==madrid_2013$only_year[i]]}
if(is.nan(madrid_2013$PM10[i])){
madrid_2013$PM10[i]<-meansNoStation$mean_PM10[meansNoStation$only_month==madrid_2013$only_month[i]&meansNoStation$only_year==madrid_2013$only_year[i]]}
}
write.csv(madrid_2013,"dataWoNa/madrid_2013.csv", row.names = TRUE)
madrid_2014 <-read_csv("data/Madrid_pollution_level_dataset/csvs_per_year/madrid_2014.csv")
madrid_2014$only_month <-unlist(lapply(madrid_2014$date, month))
madrid_2014$only_year <-unlist(lapply(madrid_2014$date, year))
means<- madrid_2014 %>%
group_by(only_year,only_month,station) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
meansNoStation<- madrid_2014 %>%
group_by(only_year,only_month) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
for(i in 1:length(madrid_2014$BEN)){
if(is.na(madrid_2014$CO[i])){
madrid_2014$CO[i]<-means$mean_CO[means$only_month==madrid_2014$only_month[i]&means$only_year==madrid_2014$only_year[i]&means$station==madrid_2014$station[i]]}
if(is.na(madrid_2014$NO_2[i])){
madrid_2014$NO_2[i]<-means$mean_NO2[means$only_month==madrid_2014$only_month[i]&means$only_year==madrid_2014$only_year[i]&means$station==madrid_2014$station[i]]}
if(is.na(madrid_2014$O_3[i])){
madrid_2014$O_3[i]<-means$mean_O3[means$only_month==madrid_2014$only_month[i]&means$only_year==madrid_2014$only_year[i]&means$station==madrid_2014$station[i]]}
if(is.na(madrid_2014$SO_2[i])){
madrid_2014$SO_2[i]<-means$mean_SO2[means$only_month==madrid_2014$only_month[i]&means$only_year==madrid_2014$only_year[i]&means$station==madrid_2014$station[i]]}
if(is.na(madrid_2014$PM10[i])){
madrid_2014$PM10[i]<-means$mean_PM10[means$only_month==madrid_2014$only_month[i]&means$only_year==madrid_2014$only_year[i]&means$station==madrid_2014$station[i]]}
}
for(i in 1:length(madrid_2014$BEN)){
if(is.nan(madrid_2014$CO[i])){
madrid_2014$CO[i]<-meansNoStation$mean_CO[meansNoStation$only_month==madrid_2014$only_month[i]&meansNoStation$only_year==madrid_2014$only_year[i]]}
if(is.nan(madrid_2014$NO_2[i])){
madrid_2014$NO_2[i]<-meansNoStation$mean_NO2[meansNoStation$only_month==madrid_2014$only_month[i]&meansNoStation$only_year==madrid_2014$only_year[i]]}
if(is.nan(madrid_2014$O_3[i])){
madrid_2014$O_3[i]<-meansNoStation$mean_O3[meansNoStation$only_month==madrid_2014$only_month[i]&meansNoStation$only_year==madrid_2014$only_year[i]]}
if(is.nan(madrid_2014$SO_2[i])){
madrid_2014$SO_2[i]<-meansNoStation$mean_SO2[meansNoStation$only_month==madrid_2014$only_month[i]&meansNoStation$only_year==madrid_2014$only_year[i]]}
if(is.nan(madrid_2014$PM10[i])){
madrid_2014$PM10[i]<-meansNoStation$mean_PM10[meansNoStation$only_month==madrid_2014$only_month[i]&meansNoStation$only_year==madrid_2014$only_year[i]]}
}
write.csv(madrid_2014,"dataWoNa/madrid_2014.csv", row.names = TRUE)
madrid_2015 <-read_csv("data/Madrid_pollution_level_dataset/csvs_per_year/madrid_2015.csv")
madrid_2015$only_month <-unlist(lapply(madrid_2015$date, month))
madrid_2015$only_year <-unlist(lapply(madrid_2015$date, year))
means<- madrid_2015 %>%
group_by(only_year,only_month,station) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
meansNoStation<- madrid_2015 %>%
group_by(only_year,only_month) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
for(i in 1:length(madrid_2015$BEN)){
if(is.na(madrid_2015$CO[i])){
madrid_2015$CO[i]<-means$mean_CO[means$only_month==madrid_2015$only_month[i]&means$only_year==madrid_2015$only_year[i]&means$station==madrid_2015$station[i]]}
if(is.na(madrid_2015$NO_2[i])){
madrid_2015$NO_2[i]<-means$mean_NO2[means$only_month==madrid_2015$only_month[i]&means$only_year==madrid_2015$only_year[i]&means$station==madrid_2015$station[i]]}
if(is.na(madrid_2015$O_3[i])){
madrid_2015$O_3[i]<-means$mean_O3[means$only_month==madrid_2015$only_month[i]&means$only_year==madrid_2015$only_year[i]&means$station==madrid_2015$station[i]]}
if(is.na(madrid_2015$SO_2[i])){
madrid_2015$SO_2[i]<-means$mean_SO2[means$only_month==madrid_2015$only_month[i]&means$only_year==madrid_2015$only_year[i]&means$station==madrid_2015$station[i]]}
if(is.na(madrid_2015$PM10[i])){
madrid_2015$PM10[i]<-means$mean_PM10[means$only_month==madrid_2015$only_month[i]&means$only_year==madrid_2015$only_year[i]&means$station==madrid_2015$station[i]]}
}
for(i in 1:length(madrid_2015$BEN)){
if(is.nan(madrid_2015$CO[i])){
madrid_2015$CO[i]<-meansNoStation$mean_CO[meansNoStation$only_month==madrid_2015$only_month[i]&meansNoStation$only_year==madrid_2015$only_year[i]]}
if(is.nan(madrid_2015$NO_2[i])){
madrid_2015$NO_2[i]<-meansNoStation$mean_NO2[meansNoStation$only_month==madrid_2015$only_month[i]&meansNoStation$only_year==madrid_2015$only_year[i]]}
if(is.nan(madrid_2015$O_3[i])){
madrid_2015$O_3[i]<-meansNoStation$mean_O3[meansNoStation$only_month==madrid_2015$only_month[i]&meansNoStation$only_year==madrid_2015$only_year[i]]}
if(is.nan(madrid_2015$SO_2[i])){
madrid_2015$SO_2[i]<-meansNoStation$mean_SO2[meansNoStation$only_month==madrid_2015$only_month[i]&meansNoStation$only_year==madrid_2015$only_year[i]]}
if(is.nan(madrid_2015$PM10[i])){
madrid_2015$PM10[i]<-meansNoStation$mean_PM10[meansNoStation$only_month==madrid_2015$only_month[i]&meansNoStation$only_year==madrid_2015$only_year[i]]}
}
write.csv(madrid_2015,"dataWoNa/madrid_2015.csv", row.names = TRUE)
madrid_2016 <-read_csv("data/Madrid_pollution_level_dataset/csvs_per_year/madrid_2016.csv")
madrid_2016$only_month <-unlist(lapply(madrid_2016$date, month))
madrid_2016$only_year <-unlist(lapply(madrid_2016$date, year))
means<- madrid_2016 %>%
group_by(only_year,only_month,station) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
meansNoStation<- madrid_2016 %>%
group_by(only_year,only_month) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
for(i in 1:length(madrid_2016$BEN)){
if(is.na(madrid_2016$CO[i])){
madrid_2016$CO[i]<-means$mean_CO[means$only_month==madrid_2016$only_month[i]&means$only_year==madrid_2016$only_year[i]&means$station==madrid_2016$station[i]]}
if(is.na(madrid_2016$NO_2[i])){
madrid_2016$NO_2[i]<-means$mean_NO2[means$only_month==madrid_2016$only_month[i]&means$only_year==madrid_2016$only_year[i]&means$station==madrid_2016$station[i]]}
if(is.na(madrid_2016$O_3[i])){
madrid_2016$O_3[i]<-means$mean_O3[means$only_month==madrid_2016$only_month[i]&means$only_year==madrid_2016$only_year[i]&means$station==madrid_2016$station[i]]}
if(is.na(madrid_2016$SO_2[i])){
madrid_2016$SO_2[i]<-means$mean_SO2[means$only_month==madrid_2016$only_month[i]&means$only_year==madrid_2016$only_year[i]&means$station==madrid_2016$station[i]]}
if(is.na(madrid_2016$PM10[i])){
madrid_2016$PM10[i]<-means$mean_PM10[means$only_month==madrid_2016$only_month[i]&means$only_year==madrid_2016$only_year[i]&means$station==madrid_2016$station[i]]}
}
for(i in 1:length(madrid_2016$BEN)){
if(is.nan(madrid_2016$CO[i])){
madrid_2016$CO[i]<-meansNoStation$mean_CO[meansNoStation$only_month==madrid_2016$only_month[i]&meansNoStation$only_year==madrid_2016$only_year[i]]}
if(is.nan(madrid_2016$NO_2[i])){
madrid_2016$NO_2[i]<-meansNoStation$mean_NO2[meansNoStation$only_month==madrid_2016$only_month[i]&meansNoStation$only_year==madrid_2016$only_year[i]]}
if(is.nan(madrid_2016$O_3[i])){
madrid_2016$O_3[i]<-meansNoStation$mean_O3[meansNoStation$only_month==madrid_2016$only_month[i]&meansNoStation$only_year==madrid_2016$only_year[i]]}
if(is.nan(madrid_2016$SO_2[i])){
madrid_2016$SO_2[i]<-meansNoStation$mean_SO2[meansNoStation$only_month==madrid_2016$only_month[i]&meansNoStation$only_year==madrid_2016$only_year[i]]}
if(is.nan(madrid_2016$PM10[i])){
madrid_2016$PM10[i]<-meansNoStation$mean_PM10[meansNoStation$only_month==madrid_2016$only_month[i]&meansNoStation$only_year==madrid_2016$only_year[i]]}
}
write.csv(madrid_2016,"dataWoNa/madrid_2016.csv", row.names = TRUE)
madrid_2017 <-read_csv("data/Madrid_pollution_level_dataset/csvs_per_year/madrid_2017.csv")
madrid_2017$only_month <-unlist(lapply(madrid_2017$date, month))
madrid_2017$only_year <-unlist(lapply(madrid_2017$date, year))
means<- madrid_2017 %>%
group_by(only_year,only_month,station) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
meansNoStation<- madrid_2017 %>%
group_by(only_year,only_month) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
for(i in 1:length(madrid_2017$BEN)){
if(is.na(madrid_2017$CO[i])){
madrid_2017$CO[i]<-means$mean_CO[means$only_month==madrid_2017$only_month[i]&means$only_year==madrid_2017$only_year[i]&means$station==madrid_2017$station[i]]}
if(is.na(madrid_2017$NO_2[i])){
madrid_2017$NO_2[i]<-means$mean_NO2[means$only_month==madrid_2017$only_month[i]&means$only_year==madrid_2017$only_year[i]&means$station==madrid_2017$station[i]]}
if(is.na(madrid_2017$O_3[i])){
madrid_2017$O_3[i]<-means$mean_O3[means$only_month==madrid_2017$only_month[i]&means$only_year==madrid_2017$only_year[i]&means$station==madrid_2017$station[i]]}
if(is.na(madrid_2017$SO_2[i])){
madrid_2017$SO_2[i]<-means$mean_SO2[means$only_month==madrid_2017$only_month[i]&means$only_year==madrid_2017$only_year[i]&means$station==madrid_2017$station[i]]}
if(is.na(madrid_2017$PM10[i])){
madrid_2017$PM10[i]<-means$mean_PM10[means$only_month==madrid_2017$only_month[i]&means$only_year==madrid_2017$only_year[i]&means$station==madrid_2017$station[i]]}
}
for(i in 1:length(madrid_2017$BEN)){
if(is.nan(madrid_2017$CO[i])){
madrid_2017$CO[i]<-meansNoStation$mean_CO[meansNoStation$only_month==madrid_2017$only_month[i]&meansNoStation$only_year==madrid_2017$only_year[i]]}
if(is.nan(madrid_2017$NO_2[i])){
madrid_2017$NO_2[i]<-meansNoStation$mean_NO2[meansNoStation$only_month==madrid_2017$only_month[i]&meansNoStation$only_year==madrid_2017$only_year[i]]}
if(is.nan(madrid_2017$O_3[i])){
madrid_2017$O_3[i]<-meansNoStation$mean_O3[meansNoStation$only_month==madrid_2017$only_month[i]&meansNoStation$only_year==madrid_2017$only_year[i]]}
if(is.nan(madrid_2017$SO_2[i])){
madrid_2017$SO_2[i]<-meansNoStation$mean_SO2[meansNoStation$only_month==madrid_2017$only_month[i]&meansNoStation$only_year==madrid_2017$only_year[i]]}
if(is.nan(madrid_2017$PM10[i])){
madrid_2017$PM10[i]<-meansNoStation$mean_PM10[meansNoStation$only_month==madrid_2017$only_month[i]&meansNoStation$only_year==madrid_2017$only_year[i]]}
}
write.csv(madrid_2017,"dataWoNa/madrid_2017.csv", row.names = TRUE)
madrid_2018 <-read_csv("data/Madrid_pollution_level_dataset/csvs_per_year/madrid_2018.csv")
madrid_2018$only_month <-unlist(lapply(madrid_2018$date, month))
madrid_2018$only_year <-unlist(lapply(madrid_2018$date, year))
means<- madrid_2018 %>%
group_by(only_year,only_month,station) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
meansNoStation<- madrid_2018 %>%
group_by(only_year,only_month) %>%
summarize(mean_CO = mean(CO, na.rm = TRUE), mean_NO2 = mean(NO_2, na.rm = TRUE),
mean_O3 = mean(O_3, na.rm = TRUE),mean_SO2 = mean(SO_2, na.rm = TRUE),
mean_PM10 = mean(PM10, na.rm = TRUE))
for(i in 1:length(madrid_2018$BEN)){
if(is.na(madrid_2018$CO[i])){
madrid_2018$CO[i]<-means$mean_CO[means$only_month==madrid_2018$only_month[i]&means$only_year==madrid_2018$only_year[i]&means$station==madrid_2018$station[i]]}
if(is.na(madrid_2018$NO_2[i])){
madrid_2018$NO_2[i]<-means$mean_NO2[means$only_month==madrid_2018$only_month[i]&means$only_year==madrid_2018$only_year[i]&means$station==madrid_2018$station[i]]}
if(is.na(madrid_2018$O_3[i])){
madrid_2018$O_3[i]<-means$mean_O3[means$only_month==madrid_2018$only_month[i]&means$only_year==madrid_2018$only_year[i]&means$station==madrid_2018$station[i]]}
if(is.na(madrid_2018$SO_2[i])){
madrid_2018$SO_2[i]<-means$mean_SO2[means$only_month==madrid_2018$only_month[i]&means$only_year==madrid_2018$only_year[i]&means$station==madrid_2018$station[i]]}
if(is.na(madrid_2018$PM10[i])){
madrid_2018$PM10[i]<-means$mean_PM10[means$only_month==madrid_2018$only_month[i]&means$only_year==madrid_2018$only_year[i]&means$station==madrid_2018$station[i]]}
}
for(i in 1:length(madrid_2018$BEN)){
if(is.nan(madrid_2018$CO[i])){
madrid_2018$CO[i]<-meansNoStation$mean_CO[meansNoStation$only_month==madrid_2018$only_month[i]&meansNoStation$only_year==madrid_2018$only_year[i]]}
if(is.nan(madrid_2018$NO_2[i])){
madrid_2018$NO_2[i]<-meansNoStation$mean_NO2[meansNoStation$only_month==madrid_2018$only_month[i]&meansNoStation$only_year==madrid_2018$only_year[i]]}
if(is.nan(madrid_2018$O_3[i])){
madrid_2018$O_3[i]<-meansNoStation$mean_O3[meansNoStation$only_month==madrid_2018$only_month[i]&meansNoStation$only_year==madrid_2018$only_year[i]]}
if(is.nan(madrid_2018$SO_2[i])){
madrid_2018$SO_2[i]<-meansNoStation$mean_SO2[meansNoStation$only_month==madrid_2018$only_month[i]&meansNoStation$only_year==madrid_2018$only_year[i]]}
if(is.nan(madrid_2018$PM10[i])){
madrid_2018$PM10[i]<-meansNoStation$mean_PM10[meansNoStation$only_month==madrid_2018$only_month[i]&meansNoStation$only_year==madrid_2018$only_year[i]]}
}
write.csv(madrid_2018,"dataWoNa/madrid_2018.csv", row.names = TRUE)
station <- read.csv("data/Madrid_pollution_level_dataset/csvs_per_year/stations.csv")
# Group CSVs
madrid_list <- list(madrid_2010, madrid_2011, madrid_2012, madrid_2013,
madrid_2014, madrid_2015, madrid_2016, madrid_2017, madrid_2018)
madrid_18 <- as.data.frame(rbindlist(madrid_list, fill = T))
remove(madrid_2010)
remove(madrid_2011)
remove(madrid_2012)
remove(madrid_2013)
remove(madrid_2014)
remove(madrid_2015)
remove(madrid_2016)
remove(madrid_2017)
remove(madrid_2018)
remove(madrid_list)
# remove(madrid_18)
# Data Wrangling
madrid_final <- madrid_18[with(madrid_18, order(date)),]
madrid_final$only_month <-lapply(madrid_final$date, month)
madrid_final$only_year <-lapply(madrid_final$date, year)
selected_features <- madrid_final %>%
select("CO", "O_3", "PM10", "NO_2", "SO_2")
selected_na <- as.data.frame(selected_features)
gg_miss_var(selected_features, show_pct = T)