679hwk2
Dingxian Cao
September 27, 2016
import data
a<-read.csv("Emergency_Response_Incidents.csv")#resource : https://nycopendata.socrata.com/
head(a,n = 3)## Incident.Type
## 1 LawEnforcement-Suspicious Package
## 2 LawEnforcement-Suspicious Package
## 3 Medical-EMS MCI (Multiple Casualty Incident)
## Location Borough Creation.Date
## 1 East 84th Street & Madison Avenue Manhattan 05/14/2012 03:09:10 PM
## 2 West St & Albany St Manhattan 05/15/2012 04:53:14 PM
## 3 Longfellow Avenue & Oak Point Avenue Bronx 05/17/2012 08:10:00 PM
## Closed.Date Latitude Longitude
## 1 05/14/2012 04:05:19 PM 40.779540434387258 -73.959772521534646
## 2 05/15/2012 05:37:55 PM 40.709824372194177 -74.014824702464466
## 3 05/17/2012 09:09:00 PM 40.810608382153468 -73.883549173641953This dataset is collected by NYC which shows the details of each emergency response incidents. It contains the incident type, the accurate location of the incident and happening time. This dataset aroused my interest, because NYC is a dangerous city and it will be useful to find out which part of the city is safer and what time on which part of the city is dangerous. With the geological information, it will be very explicit and direct to show the information on a heat map.
5.2.4 Exercises
suppressMessages(library(dplyr))## Warning: package 'dplyr' was built under R version 3.2.5library(nycflights13)## Warning: package 'nycflights13' was built under R version 3.2.5filter(flights,arr_delay >= 120 )## # A tibble: 10,200 × 19
## year month day dep_time sched_dep_time dep_delay arr_time
## <int> <int> <int> <int> <int> <dbl> <int>
## 1 2013 1 1 811 630 101 1047
## 2 2013 1 1 848 1835 853 1001
## 3 2013 1 1 957 733 144 1056
## 4 2013 1 1 1114 900 134 1447
## 5 2013 1 1 1505 1310 115 1638
## 6 2013 1 1 1525 1340 105 1831
## 7 2013 1 1 1549 1445 64 1912
## 8 2013 1 1 1558 1359 119 1718
## 9 2013 1 1 1732 1630 62 2028
## 10 2013 1 1 1803 1620 103 2008
## # ... with 10,190 more rows, and 12 more variables: sched_arr_time <int>,
## # arr_delay <dbl>, carrier <chr>, flight <int>, tailnum <chr>,
## # origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>,
## # minute <dbl>, time_hour <dttm>filter(flights,dest=='IAH'|dest== 'HOU' )## # A tibble: 9,313 × 19
## year month day dep_time sched_dep_time dep_delay arr_time
## <int> <int> <int> <int> <int> <dbl> <int>
## 1 2013 1 1 517 515 2 830
## 2 2013 1 1 533 529 4 850
## 3 2013 1 1 623 627 -4 933
## 4 2013 1 1 728 732 -4 1041
## 5 2013 1 1 739 739 0 1104
## 6 2013 1 1 908 908 0 1228
## 7 2013 1 1 1028 1026 2 1350
## 8 2013 1 1 1044 1045 -1 1352
## 9 2013 1 1 1114 900 134 1447
## 10 2013 1 1 1205 1200 5 1503
## # ... with 9,303 more rows, and 12 more variables: sched_arr_time <int>,
## # arr_delay <dbl>, carrier <chr>, flight <int>, tailnum <chr>,
## # origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>,
## # minute <dbl>, time_hour <dttm>filter(flights,carrier =='UA'|carrier =='AA'|carrier =='DL')## # A tibble: 139,504 × 19
## year month day dep_time sched_dep_time dep_delay arr_time
## <int> <int> <int> <int> <int> <dbl> <int>
## 1 2013 1 1 517 515 2 830
## 2 2013 1 1 533 529 4 850
## 3 2013 1 1 542 540 2 923
## 4 2013 1 1 554 600 -6 812
## 5 2013 1 1 554 558 -4 740
## 6 2013 1 1 558 600 -2 753
## 7 2013 1 1 558 600 -2 924
## 8 2013 1 1 558 600 -2 923
## 9 2013 1 1 559 600 -1 941
## 10 2013 1 1 559 600 -1 854
## # ... with 139,494 more rows, and 12 more variables: sched_arr_time <int>,
## # arr_delay <dbl>, carrier <chr>, flight <int>, tailnum <chr>,
## # origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>,
## # minute <dbl>, time_hour <dttm>filter(flights,month == 7|month == 8|month ==9 )## # A tibble: 86,326 × 19
## year month day dep_time sched_dep_time dep_delay arr_time
## <int> <int> <int> <int> <int> <dbl> <int>
## 1 2013 7 1 1 2029 212 236
## 2 2013 7 1 2 2359 3 344
## 3 2013 7 1 29 2245 104 151
## 4 2013 7 1 43 2130 193 322
## 5 2013 7 1 44 2150 174 300
## 6 2013 7 1 46 2051 235 304
## 7 2013 7 1 48 2001 287 308
## 8 2013 7 1 58 2155 183 335
## 9 2013 7 1 100 2146 194 327
## 10 2013 7 1 100 2245 135 337
## # ... with 86,316 more rows, and 12 more variables: sched_arr_time <int>,
## # arr_delay <dbl>, carrier <chr>, flight <int>, tailnum <chr>,
## # origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>,
## # minute <dbl>, time_hour <dttm>filter(flights,arr_delay >= 120 & dep_delay <=0 )## # A tibble: 29 × 19
## year month day dep_time sched_dep_time dep_delay arr_time
## <int> <int> <int> <int> <int> <dbl> <int>
## 1 2013 1 27 1419 1420 -1 1754
## 2 2013 10 7 1350 1350 0 1736
## 3 2013 10 7 1357 1359 -2 1858
## 4 2013 10 16 657 700 -3 1258
## 5 2013 11 1 658 700 -2 1329
## 6 2013 3 18 1844 1847 -3 39
## 7 2013 4 17 1635 1640 -5 2049
## 8 2013 4 18 558 600 -2 1149
## 9 2013 4 18 655 700 -5 1213
## 10 2013 5 22 1827 1830 -3 2217
## # ... with 19 more rows, and 12 more variables: sched_arr_time <int>,
## # arr_delay <dbl>, carrier <chr>, flight <int>, tailnum <chr>,
## # origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>,
## # minute <dbl>, time_hour <dttm>filter(flights,dep_delay >= 60 & (dep_delay-arr_delay)>30 )## # A tibble: 1,844 × 19
## year month day dep_time sched_dep_time dep_delay arr_time
## <int> <int> <int> <int> <int> <dbl> <int>
## 1 2013 1 1 2205 1720 285 46
## 2 2013 1 1 2326 2130 116 131
## 3 2013 1 3 1503 1221 162 1803
## 4 2013 1 3 1839 1700 99 2056
## 5 2013 1 3 1850 1745 65 2148
## 6 2013 1 3 1941 1759 102 2246
## 7 2013 1 3 1950 1845 65 2228
## 8 2013 1 3 2015 1915 60 2135
## 9 2013 1 3 2257 2000 177 45
## 10 2013 1 4 1917 1700 137 2135
## # ... with 1,834 more rows, and 12 more variables: sched_arr_time <int>,
## # arr_delay <dbl>, carrier <chr>, flight <int>, tailnum <chr>,
## # origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>,
## # minute <dbl>, time_hour <dttm>filter(flights, dep_time<=600)## # A tibble: 9,344 × 19
## year month day dep_time sched_dep_time dep_delay arr_time
## <int> <int> <int> <int> <int> <dbl> <int>
## 1 2013 1 1 517 515 2 830
## 2 2013 1 1 533 529 4 850
## 3 2013 1 1 542 540 2 923
## 4 2013 1 1 544 545 -1 1004
## 5 2013 1 1 554 600 -6 812
## 6 2013 1 1 554 558 -4 740
## 7 2013 1 1 555 600 -5 913
## 8 2013 1 1 557 600 -3 709
## 9 2013 1 1 557 600 -3 838
## 10 2013 1 1 558 600 -2 753
## # ... with 9,334 more rows, and 12 more variables: sched_arr_time <int>,
## # arr_delay <dbl>, carrier <chr>, flight <int>, tailnum <chr>,
## # origin <chr>, dest <chr>, air_time <dbl>, distance <dbl>, hour <dbl>,
## # minute <dbl>, time_hour <dttm>sum(is.na(flights$dep_time))## [1] 8255flights %>% sapply(function(x) sum(is.na(x)))## year month day dep_time sched_dep_time
## 0 0 0 8255 0
## dep_delay arr_time sched_arr_time arr_delay carrier
## 8255 8713 0 9430 0
## flight tailnum origin dest air_time
## 0 2512 0 0 9430
## distance hour minute time_hour
## 0 0 0 0plot: The least/most punctual flights
d <- flights %>% select(carrier)
dd<- flights %>% filter(dep_delay >= 60) %>% select( carrier)
delay_rate <- table(dd) / table(d)
barplot(sort(delay_rate,decreasing = T)[1:10],main = 'department delay rate top10' )
barplot(sort(delay_rate,decreasing = F)[1:10],main = 'department delay rate tail10' )