Module 13: Apply it to your data 12
Chapter 21 Iteration
Erin McEvoy
Import your data
fires <- readxl::read_xlsx("myData.xlsx")
data <- as_tibble(fires)
fires2 = select(fires, -1, -5)Repeat the same operation over different columns of a data frame
Case of numeric variables
fires2 %>% map_dbl(.x = ., .f = ~mean(x = .x))## NUMBER_FIRES ACRES_BURNED
## 4.970614e+03 1.919903e+05
## DAMAGE_COSTS Damage_Cost_Per_Acre
## 9.126746e+07 4.094571e+02
## Average_Acres_Burned_Per_Fire
## 5.251226e+01fires2 %>% map_dbl(.f = ~mean(x = .x))## NUMBER_FIRES ACRES_BURNED
## 4.970614e+03 1.919903e+05
## DAMAGE_COSTS Damage_Cost_Per_Acre
## 9.126746e+07 4.094571e+02
## Average_Acres_Burned_Per_Fire
## 5.251226e+01fires2 %>% map_dbl(mean)## NUMBER_FIRES ACRES_BURNED
## 4.970614e+03 1.919903e+05
## DAMAGE_COSTS Damage_Cost_Per_Acre
## 9.126746e+07 4.094571e+02
## Average_Acres_Burned_Per_Fire
## 5.251226e+01# Adding an argument
fires2 %>% map_dbl(.x = ., .f = ~mean(x = .x, trim = 0.1))## NUMBER_FIRES ACRES_BURNED
## 4.906881e+03 1.646687e+05
## DAMAGE_COSTS Damage_Cost_Per_Acre
## 2.455526e+07 1.882805e+02
## Average_Acres_Burned_Per_Fire
## 4.027054e+01fires2 %>% map_dbl(mean, trim = 0.1)## NUMBER_FIRES ACRES_BURNED
## 4.906881e+03 1.646687e+05
## DAMAGE_COSTS Damage_Cost_Per_Acre
## 2.455526e+07 1.882805e+02
## Average_Acres_Burned_Per_Fire
## 4.027054e+01data %>% select(.data = ., ACRES_BURNED)## # A tibble: 83 × 1
## ACRES_BURNED
## <dbl>
## 1 129210
## 2 363052
## 3 127262
## 4 756696
## 5 71312
## 6 221061
## 7 513620
## 8 156015
## 9 278599
## 10 573597
## # ℹ 73 more rowsdata %>% select(ACRES_BURNED)## # A tibble: 83 × 1
## ACRES_BURNED
## <dbl>
## 1 129210
## 2 363052
## 3 127262
## 4 756696
## 5 71312
## 6 221061
## 7 513620
## 8 156015
## 9 278599
## 10 573597
## # ℹ 73 more rowsCreate your own function
# Double value in columns
double_by_factor <- function(x, factor) {x * factor}
10 %>% double_by_factor(factor = 2)## [1] 20fires2 %>% map(.x = ., .f = ~double_by_factor(x = .x, factor = 10))## $NUMBER_FIRES
## [1] 19940 23380 14470 38050 29070 41500 24910 44970 54600 52360
## [11] 21630 20340 25940 26430 24730 19730 26080 22640 21590 22630
## [21] 20800 20170 19410 17580 29360 30870 31670 28690 50050 53710
## [31] 46720 62620 58780 76380 45720 56960 58590 51700 60010 61670
## [41] 69840 85090 80290 81320 84960 100380 91590 74970 57090 59690
## [51] 78300 72380 71490 80630 81300 66350 72830 62380 79390 69880
## [61] 72070 66010 72370 68350 52270 75620 51770 62230 57590 59610
## [71] 55740 49080 48050 41110 40520 33910 31530 35550 34200 41520
## [81] 32150 35430 32330
##
## $ACRES_BURNED
## [1] 1292100 3630520 1272620 7566960 713120 2210610 5136200 1560150 2785990
## [10] 5735970 5533280 6488380 5099980 2348790 2564720 1332230 1322530 3033930
## [19] 1483600 1209740 1251500 1400720 1614880 646170 1243160 1461590 1476580
## [28] 1237430 3279510 1300980 372220 2195520 2531380 1193680 1631600 1210390
## [37] 791950 2084790 450080 647140 1176690 938980 939670 1239040 885860
## [46] 2470060 1602910 2098250 691580 707730 1036700 2232820 536310 869450
## [55] 1908350 736010 2121420 231540 1914900 1226060 1407920 1211980 2326240
## [64] 577880 924560 2852720 727180 909850 1228090 4043280 1681340 740040
## [73] 2228960 5302320 4397170 1070310 302340 1513570 1408180 1429240 1675320
## [82] 2976470 2509960
##
## $DAMAGE_COSTS
## [1] 3186360 5637100 1655430 18771470 1515840 4042250
## [7] 8475790 2721780 5157370 14848640 15020270 13651260
## [13] 20859840 6222650 22516050 7175640 6051020 20250790
## [19] 11600980 11204600 6866770 13491580 67329340 7646120
## [25] 5471810 11257310 30120550 26340660 45385140 13470640
## [31] 5709670 64724190 51830490 80425470 64055320 25373300
## [37] 15544370 210324770 54358800 66970330 99587510 85380210
## [43] 108600950 416578010 267995160 304742670 175846330 550703000
## [49] 229395000 279226000 236567000 429811000 197619000 468149990
## [55] 649582200 273653130 957077490 269041930 1707750230 540777260
## [61] 420047810 324576020 1002831720 819194190 274313180 1342585340
## [67] 298768530 872950010 1739768600 9741868570 1267904170 493929430
## [73] 602703820 2541727350 8893083480 339568970 33974420 2545347040
## [79] 282132000 297997530 200341680 30618366660 1482668930
##
## $Damage_Cost_Per_Acre
## [1] 24.66032 15.52698 13.00805 24.80715 21.25645
## [6] 18.28568 16.50206 17.44563 18.51180 25.88689
## [11] 27.14533 21.03955 40.90181 26.49300 87.79145
## [16] 53.86187 45.75337 66.74772 78.19480 92.61990
## [21] 54.86832 96.31889 416.93092 118.32985 44.01533
## [26] 77.02098 203.98861 212.86586 138.39000 103.54225
## [31] 153.39504 294.80119 204.75191 673.76072 392.59206
## [36] 209.62913 196.27969 1008.85351 1207.75862 1034.86618
## [41] 846.33599 909.28678 1155.73499 3362.10300 3025.25410
## [46] 1233.74602 1097.04431 2624.58239 3316.96984 3945.37465
## [51] 2281.92341 1924.96932 3684.79051 5384.43832 3403.89446
## [56] 3718.06266 4511.49461 11619.67392 8918.22147 4410.69165
## [61] 2983.46362 2678.06416 4310.95553 14175.85295 2966.95920
## [66] 4706.33410 4108.59113 9594.43875 14166.45848 24093.97462
## [71] 7541.03376 6674.36125 2703.96876 4793.61364 20224.56143
## [76] 3172.62260 1123.71568 16816.84389 2003.52228 2085.00693
## [81] 1195.84127 102868.05061 5907.14167
##
## $Average_Acres_Burned_Per_Fire
## [1] 647.99398 1552.83148 879.48860 1988.68857 245.31132 532.67711
## [7] 2061.90285 346.93129 510.25458 1095.48701 2558.15072 3189.96067
## [13] 1966.06785 888.68331 1037.08856 675.23061 507.10506 1340.07509
## [19] 687.16999 534.57357 601.68269 694.45711 831.98351 367.55973
## [25] 423.41962 473.46615 466.23934 431.31056 655.24675 242.22305
## [31] 79.67038 350.61003 430.65328 156.28175 356.86789 212.49824
## [37] 135.16812 403.24758 75.00083 104.93595 168.48368 110.35139
## [43] 117.03450 152.36596 104.26789 246.07093 175.00928 279.87862
## [49] 121.13855 118.56760 132.40102 308.48577 75.01888 107.83207
## [55] 234.72940 110.92841 291.28381 37.11767 241.20166 175.45220
## [61] 195.35452 183.60551 321.43706 84.54718 176.88158 377.24412
## [67] 140.46359 146.20762 213.24709 678.28888 301.63976 150.78240
## [73] 463.88345 1289.78837 1085.18509 315.63256 95.88963 425.75809
## [79] 411.74854 344.22929 521.09487 840.09879 776.35633Repeat the same operation over different elements of a list
When you have a grouping variable (factor)
fires2 %>% lm(formula = ACRES_BURNED ~ NUMBER_FIRES, data = .)##
## Call:
## lm(formula = ACRES_BURNED ~ NUMBER_FIRES, data = .)
##
## Coefficients:
## (Intercept) NUMBER_FIRES
## 274461.05 -16.59fires %>% distinct(SEVERITY)## # A tibble: 3 × 1
## SEVERITY
## <chr>
## 1 Moderate
## 2 Severe
## 3 Mildreg_coeff_tbl <- fires %>%
# Split it into a list of data frames
split(.$SEVERITY) %>%
# Repeat regression over each group
map(.x = ., .f = ~lm(formula = ACRES_BURNED ~ NUMBER_FIRES, data = .)) %>%
map(broom::tidy, conf.int = TRUE) %>%
# Convert to tibble
bind_rows(.id = "SEVERITY") %>%
# Filter for
filter(term == "NUMBER_FIRES")reg_coeff_tbl %>%
mutate(estimate = -estimate,
conf.low = -conf.low,
conf.high = -conf.high) %>%
ggplot(aes(x = estimate, y = SEVERITY)) +
geom_point() +
geom_errorbar(aes(xmin = conf.low, xmax = conf.high))
Create your own
Choose either one of the two cases above and apply it to your data
fires2 %>% map_dbl(.x = ., .f = ~mean(x = .x))## NUMBER_FIRES ACRES_BURNED
## 4.970614e+03 1.919903e+05
## DAMAGE_COSTS Damage_Cost_Per_Acre
## 9.126746e+07 4.094571e+02
## Average_Acres_Burned_Per_Fire
## 5.251226e+01fires2 %>% map_dbl(.f = ~mean(x = .x))## NUMBER_FIRES ACRES_BURNED
## 4.970614e+03 1.919903e+05
## DAMAGE_COSTS Damage_Cost_Per_Acre
## 9.126746e+07 4.094571e+02
## Average_Acres_Burned_Per_Fire
## 5.251226e+01fires2 %>% map_dbl(mean)## NUMBER_FIRES ACRES_BURNED
## 4.970614e+03 1.919903e+05
## DAMAGE_COSTS Damage_Cost_Per_Acre
## 9.126746e+07 4.094571e+02
## Average_Acres_Burned_Per_Fire
## 5.251226e+01# Adding an argument
fires2 %>% map_dbl(.x = ., .f = ~mean(x = .x, trim = 0.2))## NUMBER_FIRES ACRES_BURNED
## 4.897882e+03 1.552624e+05
## DAMAGE_COSTS Damage_Cost_Per_Acre
## 1.740754e+07 1.518660e+02
## Average_Acres_Burned_Per_Fire
## 3.645779e+01fires2 %>% map_dbl(mean, trim = 0.2)## NUMBER_FIRES ACRES_BURNED
## 4.897882e+03 1.552624e+05
## DAMAGE_COSTS Damage_Cost_Per_Acre
## 1.740754e+07 1.518660e+02
## Average_Acres_Burned_Per_Fire
## 3.645779e+01fires2 %>% select(.data = ., NUMBER_FIRES)## # A tibble: 83 × 1
## NUMBER_FIRES
## <dbl>
## 1 1994
## 2 2338
## 3 1447
## 4 3805
## 5 2907
## 6 4150
## 7 2491
## 8 4497
## 9 5460
## 10 5236
## # ℹ 73 more rowsfires2 %>% select(NUMBER_FIRES)## # A tibble: 83 × 1
## NUMBER_FIRES
## <dbl>
## 1 1994
## 2 2338
## 3 1447
## 4 3805
## 5 2907
## 6 4150
## 7 2491
## 8 4497
## 9 5460
## 10 5236
## # ℹ 73 more rows