R Notebook
c(-1,0,1)/0[1] -Inf NaN Inf#Describe the Data
bike <- read.csv("bike_sharing_data.csv")
str(bike)'data.frame': 17379 obs. of 13 variables:
$ datetime : chr "1/1/2011 0:00" "1/1/2011 1:00" "1/1/2011 2:00" "1/1/2011 3:00" ...
$ season : int 1 1 1 1 1 1 1 1 1 1 ...
$ holiday : int 0 0 0 0 0 0 0 0 0 0 ...
$ workingday: int 0 0 0 0 0 0 0 0 0 0 ...
$ weather : int 1 1 1 1 1 2 1 1 1 1 ...
$ temp : num 9.84 9.02 9.02 9.84 9.84 ...
$ atemp : num 14.4 13.6 13.6 14.4 14.4 ...
$ humidity : chr "81" "80" "80" "75" ...
$ windspeed : num 0 0 0 0 0 ...
$ casual : int 3 8 5 3 0 0 2 1 1 8 ...
$ registered: int 13 32 27 10 1 1 0 2 7 6 ...
$ count : int 16 40 32 13 1 1 2 3 8 14 ...
$ sources : chr "ad campaign" "www.yahoo.com" "www.google.fi" "AD campaign" ...# 1. humidity: chr -> int
# 2. seaon, holiday, workingday, weather: int -> factor
# 3. datetime: chr -> POSIXctRecode data type
# Approach one
table(bike$humidity)
0 10 100 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31
22 1 270 1 1 2 4 10 10 10 16 17 26 27 46 56 59 78 71 97 106 113 118
32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54
99 162 133 163 187 224 186 209 224 290 235 270 244 248 316 247 240 327 266 262 312 267 287
55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77
352 310 231 258 272 267 335 325 163 219 387 388 161 172 359 430 193 191 317 341 222 219 336
78 79 8 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 96 97 x61
327 238 1 107 275 299 630 124 5 76 488 657 239 7 1 2 331 560 3 1 1 which(bike$humidity == "x61")[1] 14177bike[14177, "humidity"] <- 61
#Alternatively,
bike[which(bike$humidity == "x61"), "humidity"] <- 61
#Approach two
pacman::p_load(stringr)
str_subset(bike$humidity, "[a-z, A-Z]")character(0)str_replace_all(bike$humidity, "x61", "61") [1] "81" "80" "80" "75" "75" "75" "80" "86" "75" "76" "76" "81" "77" "72"
[15] "72" "77" "82" "82" "88" "88" "87" "87" "94" "88" "88" "94" "100" "94"
[29] "94" "77" "76" "71" "76" "81" "71" "66" "66" "76" "81" "71" "57" "46"
[43] "42" "39" "44" "44" "47" "44" "44" "47" "47" "50" "50" "50" "43" "43"
[57] "40" "35" "35" "30" "30" "30" "30" "32" "47" "47" "64" "69" "55" "55"
[71] "59" "63" "63" "68" "74" "74" "69" "64" "69" "51" "51" "56" "52" "52"
[85] "49" "48" "48" "48" "48" "64" "64" "69" "64" "74" "74" "48" "47" "47"
[99] "43" "40" "37" "37" "33" "33" "30" "28" "28" "28" "38" "38" "38" "47"
[113] "51" "55" "47" "55" "64" "64" "64" "69" "63" "59" "59" "51" "47" "44"
[127] "35" "35" "36" "36" "38" "51" "51" "55" "51" "55" "51" "59" "64" "69"
[141] "69" "69" "55" "69" "69" "51" "47" "37" "40" "37" "37" "40" "37" "37"
[155] "37" "40" "55" "47" "47" "43" "51" "51" "55" "55" "55" "55" "74" "74"
[169] "74" "93" "93" "80" "69" "59" "44" "32" "32" "29" "37" "39" "36" "36"
[183] "39" "36" "39" "42" "42" "46" "46" "53" "53" "49" "53" "49" "46" "43"
[197] "40" "37" "34" "32" "35" "34" "37" "40" "43" "46" "46" "46" "50" "50"
[211] "50" "50" "50" "54" "54" "50" "50" "50" "50" "50" "47" "40" "40" "40"
[225] "40" "40" "40" "40" "47" "50" "59" "59" "59" "59" "59" "55" "55" "55"
[239] "55" "51" "51" "51" "47" "51" "59" "59" "80" "86" "86" "93" "93" "93"
[253] "86" "93" "93" "86" "86" "86" "86" "93" "69" "59" "59" "55" "51" "47"
[267] "44" "47" "47" "44" "47" "47" "47" "50" "55" "55" "59" "59" "50" "50"
[281] "50" "50" "50" "54" "54" "50" "50" "50" "44" "44" "41" "41" "38" "38"
[295] "40" "40" "47" "47" "46" "46" "50" "50" "54" "54" "54" "54" "54" "74"
[309] "68" "69" "55" "51" "44" "37" "41" "38" "41" "41" "47" "59" "59" "69"
[323] "69" "55" "55" "59" "59" "59" "59" "59" "63" "63" "63" "64" "59" "55"
[337] "48" "38" "39" "36" "34" "36" "45" "39" "39" "39" "42" "45" "56" "56"
[351] "56" "69" "56" "56" "56" "56" "55" "51" "51" "44" "41" "35" "36" "38"
[365] "38" "37" "40" "47" "47" "51" "49" "40" "47" "44" "43" "43" "43" "43"
[379] "43" "50" "47" "47" "50" "55" "47" "47" "43" "47" "47" "51" "55" "59"
[393] "80" "80" "93" "86" "86" "86" "80" "87" "87" "82" "80" "80" "87" "93"
[407] "93" "93" "93" "93" "93" "93" "93" "93" "92" "93" "93" "93" "87" "81"
[421] "62" "58" "54" "58" "57" "61" "57" "49" "49" "52" "52" "56" "56" "56"
[435] "56" "56" "60" "60" "55" "55" "52" "48" "45" "42" "45" "45" "45" "49"
[449] "49" "56" "56" "60" "60" "65" "65" "70" "70" "75" "80" "87" "60" "55"
[463] "51" "47" "51" "47" "41" "27" "21" "25" "26" "26" "28" "30" "30" "33"
[477] "38" "41" "38" "45" "41" "41" "41" "48" "44" "44" "44" "41" "41" "38"
[491] "38" "35" "33" "28" "28" "28" "35" "35" "45" "41" "49" "57" "57" "57"
[505] "62" "62" "57" "57" "58" "62" "54" "46" "43" "37" "33" "28" "28" "26"
[519] "26" "30" "30" "36" "36" "38" "41" "41" "45" "45" "48" "48" "48" "48"
[533] "49" "41" "42" "46" "42" "43" "46" "40" "47" "50" "59" "54" "59" "63"
[547] "63" "64" "69" "69" "69" "74" "74" "74" "74" "74" "64" "60" "60" "56"
[561] "56" "45" "42" "42" "45" "49" "65" "65" "65" "64" "64" "69" "65" "69"
[575] "86" "86" "87" "87" "87" "93" "93" "93" "93" "93" "93" "93" "93" "55"
[589] "55" "69" "69" "74" "74" "74" "80" "75" "75" "75" "75" "80" "80" "86"
[603] "86" "86" "86" "93" "93" "93" "80" "86" "80" "75" "75" "75" "70" "75"
[617] "65" "60" "64" "64" "64" "64" "69" "64" "59" "55" "59" "64" "64" "59"
[631] "55" "60" "69" "60" "60" "69" "69" "74" "74" "80" "80" "80" "80" "80"
[645] "93" "93" "86" "86" "86" "80" "80" "75" "52" "61" "61" "56" "56" "56"
[659] "65" "65" "65" "70" "70" "65" "65" "64" "64" "64" "59" "64" "69" "64"
[673] "59" "59" "59" "59" "55" "59" "55" "59" "56" "59" "55" "61" "59" "59"
[687] "59" "64" "64" "69" "69" "69" "93" "93" "93" "93" "93" "93" "86" "86"
[701] "86" "80" "75" "75" "75" "81" "81" "87" "87" "87" "93" "93" "93" "93"
[715] "93" "93" "93" "93" "93" "93" "93" "100" "93" "93" "93" "82" "76" "71"
[729] "53" "42" "45" "48" "47" "44" "44" "40" "44" "43" "43" "50" "43" "50"
[743] "50" "47" "43" "43" "40" "40" "37" "37" "37" "40" "40" "40" "47" "55"
[757] "51" "47" "44" "59" "63" "63" "63" "55" "59" "74" "80" "51" "51" "48"
[771] "50" "45" "48" "42" "56" "60" "65" "65" "70" "65" "70" "70" "65" "75"
[785] "75" "93" "100" "100" "93" "100" "100" "100" "100" "100" "100" "100" "100" "100"
[799] "100" "93" "93" "87" "100" "93" "93" "70" "65" "60" "60" "60" "60" "60"
[813] "65" "65" "56" "52" "49" "46" "46" "46" "46" "49" "46" "56" "61" "61"
[827] "60" "60" "65" "65" "75" "80" "86" "86" "86" "93" "86" "100" "80" "75"
[841] "65" "62" "57" "57" "54" "57" "70" "66" "70" "70" "70" "81" "81" "87"
[855] "87" "93" "93" "93" "81" "70" "65" "56" "52" "47" "47" "38" "32" "37"
[869] "35" "35" "32" "32" "40" "40" "33" "33" "33" "36" "36" "38" "45" "45"
[883] "45" "49" "42" "39" "36" "43" "40" "40" "34" "34" "37" "34" "47" "86"
[897] "86" "86" "80" "80" "86" "80" "80" "59" "50" "54" "50" "49" "42" "42"
[911] "39" "34" "29" "27" "25" "27" "26" "28" "28" "31" "39" "39" "42" "49"
[925] "54" "54" "63" "68" "73" "74" "74" "69" "47" "47" "35" "26" "21" "28"
[939] "24" "28" "33" "55" "59" "64" "69" "69" "86" "80" "80" "74" "74" "93"
[953] "80" "86" "64" "41" "28" "39" "39" "31" "29" "29" "31" "38" "38" "41"
[967] "41" "44" "51" "64" "59" "75" "69" "69" "69" "55" "64" "60" "45" "39"
[981] "32" "29" "30" "30" "28" "28" "32" "35" "35" "35" "35" "35" "37" "37"
[995] "40" "46" "53" "53" "46" "46"
[ reached getOption("max.print") -- omitted 16379 entries ]bike$humidity <- as.integer(bike$humidity)
class(bike$humidity)[1] "integer"hist(bike$humidity)
NA
NAstr(bike$season) int [1:17379] 1 1 1 1 1 1 1 1 1 1 ...bike$season <- as.factor(bike$season)
bike$season <- factor(bike$season, levels = c(1,2,3,4),
labels= c("spring" , "summer" , "fall", "winter"))
summary(bike) datetime season holiday workingday weather
Length:17379 spring:4242 Min. :0.00000 Min. :0.0000 Min. :1.000
Class :character summer:4409 1st Qu.:0.00000 1st Qu.:0.0000 1st Qu.:1.000
Mode :character fall :4496 Median :0.00000 Median :1.0000 Median :1.000
winter:4232 Mean :0.02877 Mean :0.6827 Mean :1.425
3rd Qu.:0.00000 3rd Qu.:1.0000 3rd Qu.:2.000
Max. :1.00000 Max. :1.0000 Max. :4.000
temp atemp humidity windspeed casual
Min. : 0.82 Min. : 0.00 Min. : 0.00 Min. : 0.000 Min. : 0.00
1st Qu.:13.94 1st Qu.:16.66 1st Qu.: 48.00 1st Qu.: 7.002 1st Qu.: 4.00
Median :20.50 Median :24.24 Median : 63.00 Median :12.998 Median : 16.00
Mean :20.38 Mean :23.79 Mean : 62.72 Mean :12.737 Mean : 34.48
3rd Qu.:27.06 3rd Qu.:31.06 3rd Qu.: 78.00 3rd Qu.:16.998 3rd Qu.: 46.00
Max. :41.00 Max. :50.00 Max. :100.00 Max. :56.997 Max. :367.00
registered count sources
Min. : 0.0 Min. : 1 Length:17379
1st Qu.: 36.0 1st Qu.: 42 Class :character
Median :116.0 Median :141 Mode :character
Mean :152.5 Mean :187
3rd Qu.:217.0 3rd Qu.:277
Max. :886.0 Max. :977 pacman::p_load(lubridate)
str(bike$datetime) chr [1:17379] "1/1/2011 0:00" "1/1/2011 1:00" "1/1/2011 2:00" "1/1/2011 3:00" ...bike$datetime <- mdy_hm(bike$datetime)
#Deal with missing values
sum(is.na(bike))[1] 554apply(is.na(bike), 2, sum) datetime season holiday workingday weather temp atemp humidity
0 0 0 0 0 0 0 0
windspeed casual registered count sources
0 0 0 0 554 str_detect(bike, "NA")Warning: argument is not an atomic vector; coercing [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE TRUEbike_complete <- bike[which(is.na(bike$sources)),]
bike_complete2 <- bike[complete.cases(bike),]
bike_complete3 <-na.omit(bike)
complete.cases(bike) [1] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[15] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE
[29] TRUE TRUE TRUE TRUE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE
[43] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[57] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[71] FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE
[85] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[99] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[113] TRUE TRUE FALSE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[127] TRUE TRUE TRUE TRUE FALSE TRUE FALSE TRUE TRUE TRUE TRUE FALSE TRUE FALSE
[141] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[155] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[169] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[183] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[197] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[211] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[225] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[239] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[253] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[267] TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[281] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[295] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[309] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[323] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE
[337] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[351] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[365] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[379] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[393] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[407] TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[421] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[435] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[449] TRUE FALSE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE FALSE TRUE
[463] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[477] TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[491] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[505] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[519] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
[533] TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[547] FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE
[561] TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[575] TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[589] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE
[603] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE
[617] TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE
[631] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
[645] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[659] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[673] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[687] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[701] FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[715] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[729] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[743] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[757] TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[771] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[785] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[799] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[813] TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE FALSE TRUE FALSE TRUE
[827] TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE
[841] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[855] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[869] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE
[883] TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE
[897] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[911] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[925] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[939] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE
[953] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[967] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[981] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE
[995] TRUE TRUE TRUE TRUE TRUE TRUE
[ reached getOption("max.print") -- omitted 16379 entries ]Deal with strings/character data
- Normalize characters: same case
- Extra blank spaces
- Mathcing characters
table(bike$sources)
ad campaign Ad Campaign AD campaign blog direct
3472 851 894 494 1610
facebook page Twitter Twitter www.bing.com www.google.co.uk
1551 890 855 1595 1553
www.google.com www.google.fi www.yahoo.com
527 828 1705 #Normalize characters
bike$sources <- tolower(bike$sources)
table(bike$sources)
ad campaign blog direct facebook page twitter
5217 494 1610 1551 890
twitter www.bing.com www.google.co.uk www.google.com www.google.fi
855 1595 1553 527 828
www.yahoo.com
1705 #Remove unneeded spaces
library(stringr)
bike$sources <- str_trim(bike$sources, "both")
table(bike$sourcse)< table of extent 0 >#Pattern matching
goog_indices <- grep("google", bike$sources)
goog_indices [1] 3 13 15 16 19 22 28 31 35 37 47 58 64 67 80 83 89
[18] 94 99 105 109 119 120 134 146 148 151 156 159 160 165 170 178 208
[35] 219 222 234 244 246 247 253 254 257 259 262 272 282 294 296 306 315
[52] 319 324 329 334 338 347 350 364 365 386 396 397 401 412 419 423 425
[69] 430 436 442 448 451 459 471 475 476 477 482 494 499 505 519 526 532
[86] 537 540 544 550 556 562 569 583 590 591 603 604 607 611 631 632 645
[103] 650 652 657 659 669 670 672 673 675 678 680 686 688 690 696 697 700
[120] 704 711 712 713 719 722 724 738 740 741 747 757 769 775 780 782 796
[137] 816 826 828 829 831 848 855 860 878 883 885 886 904 905 910 912 923
[154] 935 936 937 943 946 950 959 960 963 967 970 971 978 987 988 992 994
[171] 1004 1008 1015 1018 1019 1022 1032 1034 1036 1037 1040 1047 1053 1057 1058 1061 1063
[188] 1070 1084 1086 1091 1098 1103 1107 1110 1118 1129 1132 1138 1142 1155 1157 1162 1163
[205] 1175 1180 1185 1188 1193 1196 1197 1199 1203 1215 1217 1224 1230 1248 1252 1260 1262
[222] 1268 1271 1276 1293 1298 1302 1305 1308 1309 1315 1317 1324 1330 1336 1337 1340 1344
[239] 1353 1358 1360 1362 1367 1368 1377 1380 1386 1390 1393 1395 1400 1402 1407 1414 1426
[256] 1428 1438 1442 1443 1445 1446 1455 1459 1476 1480 1490 1494 1495 1503 1516 1524 1525
[273] 1526 1529 1533 1534 1541 1563 1573 1578 1583 1602 1607 1610 1612 1613 1617 1620 1632
[290] 1639 1641 1643 1670 1671 1678 1684 1693 1696 1698 1701 1704 1707 1709 1728 1733 1751
[307] 1755 1756 1758 1761 1766 1770 1776 1789 1790 1792 1794 1795 1799 1808 1810 1819 1824
[324] 1825 1832 1833 1855 1865 1877 1881 1882 1884 1891 1905 1907 1914 1919 1923 1936 1939
[341] 1941 1944 1946 1948 1951 1953 1957 1958 1961 1968 1974 1997 1998 2004 2009 2022 2034
[358] 2035 2053 2066 2072 2077 2081 2084 2086 2090 2094 2123 2132 2137 2166 2167 2183 2184
[375] 2187 2188 2200 2203 2204 2205 2207 2216 2218 2227 2242 2247 2250 2251 2252 2268 2286
[392] 2301 2303 2311 2322 2324 2327 2344 2352 2354 2355 2360 2365 2375 2377 2380 2391 2404
[409] 2407 2409 2413 2417 2434 2435 2438 2447 2450 2456 2481 2498 2503 2510 2514 2517 2518
[426] 2519 2534 2539 2553 2555 2578 2580 2588 2591 2601 2607 2615 2624 2627 2631 2635 2636
[443] 2641 2643 2655 2660 2661 2675 2694 2702 2707 2709 2710 2717 2719 2722 2723 2727 2732
[460] 2743 2744 2746 2751 2755 2757 2765 2772 2777 2782 2789 2791 2792 2799 2810 2814 2820
[477] 2821 2823 2827 2831 2840 2842 2847 2849 2854 2859 2860 2862 2863 2881 2887 2901 2903
[494] 2916 2922 2926 2939 2940 2942 2950 2972 2978 2987 2991 3003 3011 3012 3018 3041 3043
[511] 3053 3057 3065 3066 3076 3078 3080 3081 3082 3089 3097 3109 3114 3119 3157 3159 3161
[528] 3169 3181 3187 3190 3193 3195 3201 3203 3223 3224 3229 3234 3237 3238 3260 3264 3280
[545] 3286 3289 3294 3299 3303 3304 3312 3319 3322 3333 3335 3358 3359 3362 3368 3375 3376
[562] 3383 3399 3405 3417 3424 3430 3432 3439 3443 3450 3461 3464 3467 3474 3476 3480 3482
[579] 3487 3489 3520 3534 3537 3540 3545 3547 3554 3560 3562 3563 3568 3570 3571 3580 3587
[596] 3591 3592 3593 3599 3611 3631 3634 3635 3674 3681 3683 3693 3694 3708 3714 3716 3719
[613] 3725 3731 3735 3742 3756 3772 3780 3797 3810 3812 3813 3814 3821 3830 3831 3839 3844
[630] 3846 3858 3862 3863 3868 3871 3885 3886 3888 3896 3899 3902 3905 3907 3913 3916 3918
[647] 3922 3924 3925 3926 3934 3935 3942 3943 3966 3967 3971 3974 3994 3998 4002 4004 4005
[664] 4006 4012 4027 4030 4043 4047 4070 4078 4085 4109 4111 4122 4128 4131 4146 4156 4160
[681] 4162 4167 4170 4172 4175 4178 4181 4184 4187 4196 4201 4205 4218 4220 4221 4238 4246
[698] 4261 4265 4268 4269 4271 4279 4288 4299 4302 4323 4336 4346 4347 4350 4352 4362 4365
[715] 4367 4371 4377 4381 4388 4421 4434 4438 4439 4446 4452 4456 4463 4465 4466 4468 4471
[732] 4482 4490 4494 4495 4496 4519 4525 4526 4528 4556 4562 4563 4575 4594 4596 4597 4601
[749] 4605 4622 4625 4635 4637 4645 4655 4663 4665 4669 4676 4677 4685 4687 4692 4697 4701
[766] 4711 4722 4727 4731 4732 4753 4755 4758 4760 4766 4768 4772 4799 4815 4823 4842 4846
[783] 4861 4873 4874 4878 4887 4890 4904 4908 4915 4926 4930 4933 4942 4943 4946 4960 4964
[800] 4967 4973 4974 4978 4979 5003 5010 5011 5021 5026 5029 5041 5053 5060 5065 5073 5077
[817] 5086 5094 5111 5112 5119 5128 5132 5133 5137 5151 5152 5156 5159 5162 5165 5171 5176
[834] 5184 5185 5186 5191 5193 5195 5196 5198 5199 5215 5219 5225 5231 5250 5251 5255 5264
[851] 5266 5271 5279 5285 5293 5299 5303 5306 5307 5308 5315 5316 5319 5325 5336 5338 5339
[868] 5345 5348 5352 5357 5365 5368 5373 5374 5375 5377 5379 5381 5385 5387 5388 5392 5400
[885] 5402 5406 5411 5412 5416 5417 5426 5427 5430 5435 5450 5455 5458 5465 5474 5485 5488
[902] 5490 5494 5501 5513 5516 5517 5518 5525 5526 5527 5529 5532 5533 5552 5553 5555 5559
[919] 5591 5594 5597 5604 5612 5613 5626 5631 5633 5647 5654 5670 5672 5679 5694 5698 5702
[936] 5709 5711 5717 5740 5743 5746 5759 5761 5768 5771 5779 5781 5790 5794 5795 5796 5798
[953] 5832 5836 5840 5841 5843 5844 5846 5853 5854 5856 5857 5858 5860 5862 5866 5875 5879
[970] 5881 5885 5890 5893 5896 5906 5908 5912 5919 5928 5938 5941 5950 5954 5955 5959 5963
[987] 5969 5970 5992 6000 6009 6010 6017 6021 6022 6023 6025 6028 6040 6044
[ reached getOption("max.print") -- omitted 1908 entries ]bike$sources[goog_indices] <- "google"
table(bike$sources)
ad campaign blog direct facebook page google twitter
5217 494 1610 1551 2908 1745
www.bing.com www.yahoo.com
1595 1705 bad_data <- str_subset(bike_complete$humidity, "[a-z A-Z]")
bike_complete$humidity <- str_replace_all(bike_complete$humidity,bad_data,"61")Error in `str_replace_all()`:
! Can't recycle `string` (size 554) to match `pattern` (size 0).
Backtrace:
1. stringr::str_replace_all(bike_complete$humidity, bad_data, "61")str(cast)
'data.frame': 1298 obs. of 3 variables:
$ X : int 1 2 3 4 5 6 7 8 9 10 ...
$ Name.1: chr "Angela Bassett" "Peter Krause" "Oliver Stark" "Aisha Hinds" ...
$ Name.2: chr "Athena Grant\n 87 episodes, 2018-2022" "Bobby Nash\n 87 episodes, 2018-2022" "Evan 'Buck' Buckley\n 87 episodes, 2018-2022" "Henrietta 'Hen' Wilson\n 87 episodes, 2018-2022" ...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