Assignment6
Shreejit
1/14/2018
Research Question
The purpose the research is understanding robberies in different communities in the United States. The focus is on knowing which states or communities have more robberies (above or below the national average) and what are the factors driving robbery in different regions.
# Recoding Missing Values
library(readr)
crimedata <- read_csv("~/Downloads/crimedata.csv")## Parsed with column specification:
## cols(
## .default = col_double(),
## Ecommunityname = col_character(),
## state = col_character(),
## countyCode = col_character(),
## communityCode = col_character(),
## fold = col_integer(),
## population = col_integer(),
## numbUrban = col_integer(),
## medIncome = col_integer(),
## medFamInc = col_integer(),
## perCapInc = col_integer(),
## whitePerCap = col_integer(),
## blackPerCap = col_integer(),
## indianPerCap = col_integer(),
## AsianPerCap = col_integer(),
## OtherPerCap = col_integer(),
## HispPerCap = col_integer(),
## NumUnderPov = col_integer(),
## NumKidsBornNeverMar = col_integer(),
## NumImmig = col_integer(),
## MedNumBR = col_integer()
## # ... with 51 more columns
## )## See spec(...) for full column specifications.## Warning in rbind(names(probs), probs_f): number of columns of result is not
## a multiple of vector length (arg 1)## Warning: 7 parsing failures.
## row # A tibble: 5 x 5 col row col expected actual file expected <int> <chr> <chr> <chr> <chr> actual 1 1427 autoTheft an integer ? '~/Downloads/crimedata.csv' file 2 1427 autoTheftPerPop a double ? '~/Downloads/crimedata.csv' row 3 1610 autoTheft an integer ? '~/Downloads/crimedata.csv' col 4 1610 autoTheftPerPop a double ? '~/Downloads/crimedata.csv' expected 5 1783 autoTheft an integer ? '~/Downloads/crimedata.csv'
## ... ................. ... ..................................................................... ........ ..................................................................... ...... ..................................................................... .... ..................................................................... ... ..................................................................... ... ..................................................................... ........ .....................................................................
## See problems(...) for more details.cd <- crimedata
sapply(cd,class)## Ecommunityname state countyCode
## "character" "character" "character"
## communityCode fold population
## "character" "integer" "integer"
## householdsize racepctblack racePctWhite
## "numeric" "numeric" "numeric"
## racePctAsian racePctHisp agePct12t21
## "numeric" "numeric" "numeric"
## agePct12t29 agePct16t24 agePct65up
## "numeric" "numeric" "numeric"
## numbUrban pctUrban medIncome
## "integer" "numeric" "integer"
## pctWWage pctWFarmSelf pctWInvInc
## "numeric" "numeric" "numeric"
## pctWSocSec pctWPubAsst pctWRetire
## "numeric" "numeric" "numeric"
## medFamInc perCapInc whitePerCap
## "integer" "integer" "integer"
## blackPerCap indianPerCap AsianPerCap
## "integer" "integer" "integer"
## OtherPerCap HispPerCap NumUnderPov
## "integer" "integer" "integer"
## PctPopUnderPov PctLess9thGrade PctNotHSGrad
## "numeric" "numeric" "numeric"
## PctBSorMore PctUnemployed PctEmploy
## "numeric" "numeric" "numeric"
## PctEmplManu PctEmplProfServ PctOccupManu
## "numeric" "numeric" "numeric"
## PctOccupMgmtProf MalePctDivorce MalePctNevMarr
## "numeric" "numeric" "numeric"
## FemalePctDiv TotalPctDiv PersPerFam
## "numeric" "numeric" "numeric"
## PctFam2Par PctKids2Par PctYoungKids2Par
## "numeric" "numeric" "numeric"
## PctTeen2Par PctWorkMomYoungKids PctWorkMom
## "numeric" "numeric" "numeric"
## NumKidsBornNeverMar PctKidsBornNeverMar NumImmig
## "integer" "numeric" "integer"
## PctImmigRecent PctImmigRec5 PctImmigRec8
## "numeric" "numeric" "numeric"
## PctImmigRec10 PctRecentImmig PctRecImmig5
## "numeric" "numeric" "numeric"
## PctRecImmig8 PctRecImmig10 PctSpeakEnglOnly
## "numeric" "numeric" "numeric"
## PctNotSpeakEnglWell PctLargHouseFam PctLargHouseOccup
## "numeric" "numeric" "numeric"
## PersPerOccupHous PersPerOwnOccHous PersPerRentOccHous
## "numeric" "numeric" "numeric"
## PctPersOwnOccup PctPersDenseHous PctHousLess3BR
## "numeric" "numeric" "numeric"
## MedNumBR HousVacant PctHousOccup
## "integer" "integer" "numeric"
## PctHousOwnOcc PctVacantBoarded PctVacMore6Mos
## "numeric" "numeric" "numeric"
## MedYrHousBuilt PctHousNoPhone PctWOFullPlumb
## "integer" "numeric" "numeric"
## OwnOccLowQuart OwnOccMedVal OwnOccHiQuart
## "integer" "integer" "integer"
## OwnOccQrange RentLowQ RentMedian
## "integer" "integer" "integer"
## RentHighQ RentQrange MedRent
## "integer" "integer" "integer"
## MedRentPctHousInc MedOwnCostPctInc MedOwnCostPctIncNoMtg
## "numeric" "numeric" "numeric"
## NumInShelters NumStreet PctForeignBorn
## "integer" "integer" "numeric"
## PctBornSameState PctSameHouse85 PctSameCity85
## "numeric" "numeric" "numeric"
## PctSameState85 LemasSwornFT LemasSwFTPerPop
## "numeric" "character" "character"
## LemasSwFTFieldOps LemasSwFTFieldPerPop LemasTotalReq
## "character" "character" "character"
## LemasTotReqPerPop PolicReqPerOffic PolicPerPop
## "character" "character" "character"
## RacialMatchCommPol PctPolicWhite PctPolicBlack
## "character" "character" "character"
## PctPolicHisp PctPolicAsian PctPolicMinor
## "character" "character" "character"
## OfficAssgnDrugUnits NumKindsDrugsSeiz PolicAveOTWorked
## "character" "character" "character"
## LandArea PopDens PctUsePubTrans
## "numeric" "numeric" "numeric"
## PolicCars PolicOperBudg LemasPctPolicOnPatr
## "character" "character" "character"
## LemasGangUnitDeploy LemasPctOfficDrugUn PolicBudgPerPop
## "character" "numeric" "character"
## murders murdPerPop rapes
## "integer" "numeric" "character"
## rapesPerPop robberies robbbPerPop
## "character" "character" "character"
## assaults assaultPerPop burglaries
## "character" "character" "character"
## burglPerPop larcenies larcPerPop
## "character" "character" "character"
## autoTheft autoTheftPerPop arsons
## "integer" "numeric" "character"
## arsonsPerPop ViolentCrimesPerPop nonViolPerPop
## "character" "character" "character"#cd$countyCode[cd$countyCode=="?"] <- NA
# Recoding all mising values in the dataset
cd[cd=="?"] <- NA
#The output for str() duplicates some information that we already have, like the number of rows and columns.
str(cd)## Classes 'tbl_df', 'tbl' and 'data.frame': 2215 obs. of 147 variables:
## $ Ecommunityname : chr "BerkeleyHeightstownship" "Marpletownship" "Tigardcity" "Gloversvillecity" ...
## $ state : chr "NJ" "PA" "OR" "NY" ...
## $ countyCode : chr "39" "45" NA "35" ...
## $ communityCode : chr "5320" "47616" NA "29443" ...
## $ fold : int 1 1 1 1 1 1 1 1 1 1 ...
## $ population : int 11980 23123 29344 16656 11245 140494 28700 59459 74111 103590 ...
## $ householdsize : num 3.1 2.82 2.43 2.4 2.76 2.45 2.6 2.45 2.46 2.62 ...
## $ racepctblack : num 1.37 0.8 0.74 1.7 0.53 ...
## $ racePctWhite : num 91.8 95.6 94.3 97.3 89.2 ...
## $ racePctAsian : num 6.5 3.44 3.43 0.5 1.17 0.9 1.47 0.4 1.25 0.92 ...
## $ racePctHisp : num 1.88 0.85 2.35 0.7 0.52 ...
## $ agePct12t21 : num 12.5 11 11.4 12.6 24.5 ...
## $ agePct12t29 : num 21.4 21.3 25.9 25.2 40.5 ...
## $ agePct16t24 : num 10.9 10.5 11 12.2 28.7 ...
## $ agePct65up : num 11.3 17.2 10.3 17.6 12.7 ...
## $ numbUrban : int 11980 23123 29344 0 0 140494 28700 59449 74115 103590 ...
## $ pctUrban : num 100 100 100 0 0 100 100 100 100 100 ...
## $ medIncome : int 75122 47917 35669 20580 17390 21577 42805 23221 25326 17852 ...
## $ pctWWage : num 89.2 79 82 68.2 69.3 ...
## $ pctWFarmSelf : num 1.55 1.11 1.15 0.24 0.55 1 0.39 0.67 2.93 0.86 ...
## $ pctWInvInc : num 70.2 64.1 55.7 39 42.8 ...
## $ pctWSocSec : num 23.6 35.5 22.2 39.5 32.2 ...
## $ pctWPubAsst : num 1.03 2.75 2.94 11.71 11.21 ...
## $ pctWRetire : num 18.4 22.9 14.6 18.3 14.4 ...
## $ medFamInc : int 79584 55323 42112 26501 24018 27705 50394 28901 34269 24058 ...
## $ perCapInc : int 29711 20148 16946 10810 8483 11878 18193 12161 13554 10195 ...
## $ whitePerCap : int 30233 20191 17103 10909 9009 12029 18276 12599 13727 12126 ...
## $ blackPerCap : int 13600 18137 16644 9984 887 7382 17342 9820 8852 5715 ...
## $ indianPerCap : int 5725 0 21606 4941 4425 10264 21482 6634 5344 11313 ...
## $ AsianPerCap : int 27101 20074 15528 3541 3352 10753 12639 8802 8011 5770 ...
## $ OtherPerCap : int 5115 5250 5954 2451 3000 7192 21852 7428 5332 7320 ...
## $ HispPerCap : int 22838 12222 8405 4391 1328 8104 22594 6187 5174 6984 ...
## $ NumUnderPov : int 227 885 1389 2831 2855 23223 1126 10320 9603 27767 ...
## $ PctPopUnderPov : num 1.96 3.98 4.75 17.23 29.99 ...
## $ PctLess9thGrade : num 5.81 5.61 2.8 11.05 12.15 ...
## $ PctNotHSGrad : num 9.9 13.72 9.09 33.68 23.06 ...
## $ PctBSorMore : num 48.2 29.9 30.1 10.8 25.3 ...
## $ PctUnemployed : num 2.7 2.43 4.01 9.86 9.08 5.72 4.85 8.19 4.18 8.39 ...
## $ PctEmploy : num 64.5 62 69.8 54.7 52.4 ...
## $ PctEmplManu : num 14.65 12.26 15.95 31.22 6.89 ...
## $ PctEmplProfServ : num 28.8 29.3 21.5 27.4 36.5 ...
## $ PctOccupManu : num 5.49 6.39 8.79 26.76 10.94 ...
## $ PctOccupMgmtProf : num 50.7 37.6 32.5 22.7 27.8 ...
## $ MalePctDivorce : num 3.67 4.23 10.1 10.98 7.51 ...
## $ MalePctNevMarr : num 26.4 28 25.8 28.1 50.7 ...
## $ FemalePctDiv : num 5.22 6.45 14.76 14.47 11.64 ...
## $ TotalPctDiv : num 4.47 5.42 12.55 12.91 9.73 ...
## $ PersPerFam : num 3.22 3.11 2.95 2.98 2.98 2.89 3.14 2.95 3 3.11 ...
## $ PctFam2Par : num 91.4 86.9 78.5 64 58.6 ...
## $ PctKids2Par : num 90.2 85.3 78.8 62.4 55.2 ...
## $ PctYoungKids2Par : num 95.8 96.8 92.4 65.4 66.5 ...
## $ PctTeen2Par : num 95.8 86.5 75.7 67.4 79.2 ...
## $ PctWorkMomYoungKids : num 44.6 51.1 66.1 59.6 61.2 ...
## $ PctWorkMom : num 58.9 62.4 74.2 70.3 68.9 ...
## $ NumKidsBornNeverMar : int 31 43 164 561 402 1511 263 2368 751 3537 ...
## $ PctKidsBornNeverMar : num 0.36 0.24 0.88 3.84 4.7 1.58 1.18 4.66 1.64 4.71 ...
## $ NumImmig : int 1277 1920 1468 339 196 2091 2637 517 1474 4793 ...
## $ PctImmigRecent : num 8.69 5.21 16.42 13.86 46.94 ...
## $ PctImmigRec5 : num 13 8.65 23.98 13.86 56.12 ...
## $ PctImmigRec8 : num 21 13.3 32.1 15.3 67.9 ...
## $ PctImmigRec10 : num 30.9 22.5 35.6 15.3 69.9 ...
## $ PctRecentImmig : num 0.93 0.43 0.82 0.28 0.82 0.32 1.05 0.11 0.47 0.72 ...
## $ PctRecImmig5 : num 1.39 0.72 1.2 0.28 0.98 0.45 1.49 0.2 0.67 1.07 ...
## $ PctRecImmig8 : num 2.24 1.11 1.61 0.31 1.18 0.57 2.2 0.25 0.93 1.63 ...
## $ PctRecImmig10 : num 3.3 1.87 1.78 0.31 1.22 0.68 2.55 0.29 1.07 2.31 ...
## $ PctSpeakEnglOnly : num 85.7 87.8 93.1 95 94.6 ...
## $ PctNotSpeakEnglWell : num 1.37 1.81 1.14 0.56 0.39 0.6 0.6 0.28 0.43 2.51 ...
## $ PctLargHouseFam : num 4.81 4.25 2.97 3.93 5.23 3.08 5.08 3.85 2.59 6.7 ...
## $ PctLargHouseOccup : num 4.17 3.34 2.05 2.56 3.11 1.92 3.46 2.55 1.54 4.1 ...
## $ PersPerOccupHous : num 2.99 2.7 2.42 2.37 2.35 2.28 2.55 2.36 2.32 2.45 ...
## $ PersPerOwnOccHous : num 3 2.83 2.69 2.51 2.55 2.37 2.89 2.42 2.77 2.47 ...
## $ PersPerRentOccHous : num 2.84 1.96 2.06 2.2 2.12 2.16 2.09 2.27 1.91 2.44 ...
## $ PctPersOwnOccup : num 91.5 89 64.2 58.2 58.1 ...
## $ PctPersDenseHous : num 0.39 1.01 2.03 1.21 2.94 2.11 1.47 1.9 1.67 6.14 ...
## $ PctHousLess3BR : num 11.1 23.6 47.5 45.7 55.6 ...
## $ MedNumBR : int 3 3 3 3 2 2 3 2 2 2 ...
## $ HousVacant : int 64 240 544 669 333 5119 566 2051 1562 5606 ...
## $ PctHousOccup : num 98.4 97.2 95.7 91.2 92.5 ...
## $ PctHousOwnOcc : num 91 84.9 57.8 54.9 53.6 ...
## $ PctVacantBoarded : num 3.12 0 0.92 2.54 3.9 2.09 1.41 6.39 0.45 5.64 ...
## $ PctVacMore6Mos : num 37.5 18.33 7.54 57.85 42.64 ...
## $ MedYrHousBuilt : int 1959 1958 1976 1939 1958 1966 1956 1954 1971 1960 ...
## $ PctHousNoPhone : num 0 0.31 1.55 7 7.45 ...
## $ PctWOFullPlumb : num 0.28 0.14 0.12 0.87 0.82 0.31 0.28 0.49 0.19 0.33 ...
## $ OwnOccLowQuart : int 215900 136300 74700 36400 30600 37700 155100 26300 54500 28600 ...
## $ OwnOccMedVal : int 262600 164200 90400 49600 43200 53900 179000 37000 70300 43100 ...
## $ OwnOccHiQuart : int 326900 199900 112000 66500 59500 73100 215500 52400 93700 67400 ...
## $ OwnOccQrange : int 111000 63600 37300 30100 28900 35400 60400 26100 39200 38800 ...
## $ RentLowQ : int 685 467 370 195 202 215 463 186 241 192 ...
## $ RentMedian : int 1001 560 428 250 283 280 669 253 321 281 ...
## $ RentHighQ : int 1001 672 520 309 362 349 824 325 387 369 ...
## $ RentQrange : int 316 205 150 114 160 134 361 139 146 177 ...
## $ MedRent : int 1001 627 484 333 332 340 736 338 355 353 ...
## $ MedRentPctHousInc : num 23.8 27.6 24.1 28.7 32.2 26.4 24.4 26.3 25.2 29.6 ...
## $ MedOwnCostPctInc : num 21.1 20.7 21.7 20.6 23.2 17.3 20.8 15.1 20.7 19.4 ...
## $ MedOwnCostPctIncNoMtg: num 14 12.5 11.6 14.5 12.9 11.7 12.5 12.2 12.8 13 ...
## $ NumInShelters : int 11 0 16 0 2 327 0 21 125 43 ...
## $ NumStreet : int 0 0 0 0 0 4 0 0 15 4 ...
## $ PctForeignBorn : num 10.66 8.3 5 2.04 1.74 ...
## [list output truncated]
## - attr(*, "problems")=Classes 'tbl_df', 'tbl' and 'data.frame': 7 obs. of 5 variables:
## ..$ row : int 1427 1427 1610 1610 1783 1783 2006
## ..$ col : chr "autoTheft" "autoTheftPerPop" "autoTheft" "autoTheftPerPop" ...
## ..$ expected: chr "an integer" "a double" "an integer" "a double" ...
## ..$ actual : chr "?" "?" "?" "?" ...
## ..$ file : chr "'~/Downloads/crimedata.csv'" "'~/Downloads/crimedata.csv'" "'~/Downloads/crimedata.csv'" "'~/Downloads/crimedata.csv'" ...
## - attr(*, "spec")=List of 2
## ..$ cols :List of 147
## .. ..$ Ecommunityname : list()
## .. .. ..- attr(*, "class")= chr "collector_character" "collector"
## .. ..$ state : list()
## .. .. ..- attr(*, "class")= chr "collector_character" "collector"
## .. ..$ countyCode : list()
## .. .. ..- attr(*, "class")= chr "collector_character" "collector"
## .. ..$ communityCode : list()
## .. .. ..- attr(*, "class")= chr "collector_character" "collector"
## .. ..$ fold : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ population : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ householdsize : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ racepctblack : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ racePctWhite : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ racePctAsian : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ racePctHisp : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ agePct12t21 : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ agePct12t29 : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ agePct16t24 : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ agePct65up : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ numbUrban : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ pctUrban : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ medIncome : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ pctWWage : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ pctWFarmSelf : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ pctWInvInc : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ pctWSocSec : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ pctWPubAsst : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ pctWRetire : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ medFamInc : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ perCapInc : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ whitePerCap : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ blackPerCap : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ indianPerCap : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ AsianPerCap : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ OtherPerCap : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ HispPerCap : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ NumUnderPov : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ PctPopUnderPov : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctLess9thGrade : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctNotHSGrad : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctBSorMore : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctUnemployed : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctEmploy : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctEmplManu : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctEmplProfServ : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctOccupManu : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctOccupMgmtProf : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ MalePctDivorce : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ MalePctNevMarr : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ FemalePctDiv : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ TotalPctDiv : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PersPerFam : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctFam2Par : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctKids2Par : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctYoungKids2Par : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctTeen2Par : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctWorkMomYoungKids : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctWorkMom : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ NumKidsBornNeverMar : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ PctKidsBornNeverMar : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ NumImmig : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ PctImmigRecent : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctImmigRec5 : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctImmigRec8 : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctImmigRec10 : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctRecentImmig : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctRecImmig5 : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctRecImmig8 : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctRecImmig10 : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctSpeakEnglOnly : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctNotSpeakEnglWell : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctLargHouseFam : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctLargHouseOccup : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PersPerOccupHous : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PersPerOwnOccHous : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PersPerRentOccHous : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctPersOwnOccup : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctPersDenseHous : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctHousLess3BR : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ MedNumBR : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ HousVacant : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ PctHousOccup : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctHousOwnOcc : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctVacantBoarded : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctVacMore6Mos : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ MedYrHousBuilt : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ PctHousNoPhone : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ PctWOFullPlumb : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ OwnOccLowQuart : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ OwnOccMedVal : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ OwnOccHiQuart : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ OwnOccQrange : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ RentLowQ : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ RentMedian : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ RentHighQ : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ RentQrange : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ MedRent : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ MedRentPctHousInc : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ MedOwnCostPctInc : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ MedOwnCostPctIncNoMtg: list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ NumInShelters : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ NumStreet : list()
## .. .. ..- attr(*, "class")= chr "collector_integer" "collector"
## .. ..$ PctForeignBorn : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. .. [list output truncated]
## ..$ default: list()
## .. ..- attr(*, "class")= chr "collector_guess" "collector"
## ..- attr(*, "class")= chr "col_spec"##You can peek at the top and bottom of the data with the head() and tail() functions
head(cd[, c(6:7, 10)])## # A tibble: 6 x 3
## population householdsize racePctAsian
## <int> <dbl> <dbl>
## 1 11980 3.10 6.50
## 2 23123 2.82 3.44
## 3 29344 2.43 3.43
## 4 16656 2.40 0.50
## 5 11245 2.76 1.17
## 6 140494 2.45 0.90tail(cd[, c(6:7, 10)])## # A tibble: 6 x 3
## population householdsize racePctAsian
## <int> <dbl> <dbl>
## 1 10567 2.57 0.84
## 2 56216 3.07 15.23
## 3 12251 2.68 1.52
## 4 32824 2.46 0.98
## 5 13547 2.89 0.90
## 6 28898 2.61 9.09unique(cd$state)## [1] "NJ" "PA" "OR" "NY" "MN" "MO" "MA" "IN" "ND" "TX" "CA" "KY" "AR" "CT"
## [15] "OH" "NH" "FL" "WA" "LA" "ME" "WY" "NC" "MS" "MI" "VA" "SC" "IL" "WI"
## [29] "TN" "UT" "OK" "AZ" "CO" "GA" "WV" "RI" "AL" "SD" "ID" "NV" "KS" "IA"
## [43] "MD" "NM" "DE" "VT" "AK" "DC"table(cd$state)##
## AK AL AR AZ CA CO CT DC DE FL GA IA ID IL IN KS KY LA
## 3 43 25 20 279 25 71 1 1 90 37 20 7 40 48 1 26 22
## MA MD ME MI MN MO MS NC ND NH NJ NM NV NY OH OK OR PA
## 123 12 17 108 66 42 20 46 8 21 211 10 5 46 111 36 31 101
## RI SC SD TN TX UT VA VT WA WI WV WY
## 26 28 9 35 162 24 33 4 40 60 14 7table(cd$countyCode)##
## 1 101 103 105 107 109 11 111 113 115 117 119 121 123 125 127 129 13
## 40 6 3 3 2 2 23 3 5 2 1 8 5 8 17 1 3 32
## 131 133 135 137 139 141 143 145 147 149 15 151 153 155 157 161 163 165
## 4 11 1 2 8 3 1 5 3 1 15 3 5 2 2 3 34 2
## 167 169 17 173 181 187 19 193 21 215 23 25 27 29 3 31 33 35
## 1 2 63 2 1 1 10 1 34 1 29 27 37 22 78 17 4 27
## 37 39 41 43 45 47 49 5 510 53 55 550 57 570 59 590 61 63
## 11 17 7 5 12 1 14 37 2 17 4 1 2 1 2 1 8 5
## 630 65 650 660 67 670 680 683 69 690 7 700 71 710 73 730 735 740
## 1 5 1 1 2 1 1 1 4 1 40 1 15 1 3 1 1 1
## 75 750 760 77 770 775 79 790 800 81 810 820 83 830 840 85 87 89
## 6 1 1 10 1 1 15 1 1 8 1 1 1 1 1 3 3 5
## 9 91 93 95 97 99
## 45 9 7 5 2 11table(cd$communityCode) ##Confirms that data is at the community level ##
## 100 1000 10000 10025 10030 10375 10460 10464 10472 10675 10750 10824
## 1 3 1 1 1 1 1 1 1 1 1 1
## 10846 10918 10972 11000 11200 11220 11272 11315 11800 1185 11950 12000
## 1 1 1 2 1 1 1 1 1 1 1 1
## 12016 12060 12144 12160 1220 12280 12320 12700 12900 12940 13045 13135
## 1 1 1 1 1 1 1 1 1 1 1 1
## 13150 13208 13456 13570 13690 1380 14000 14140 14158 14160 1420 14200
## 1 1 1 1 1 1 1 1 1 1 1 1
## 14260 14395 14575 1465 14712 1486 14875 15000 15060 15340 15350 15384
## 1 1 1 1 1 1 1 1 1 1 1 1
## 15640 16000 16014 1605 16160 16250 16425 16495 16520 16749 16775 16920
## 1 2 1 1 1 1 1 1 1 1 1 1
## 17000 1720 17288 1740 17440 17475 17650 17710 17720 17800 17940 17975
## 1 1 1 1 1 1 1 1 1 1 1 1
## 1798 18000 18070 18080 18116 18130 18188 18256 18350 18388 18400 18448
## 1 1 1 1 1 1 1 1 1 1 1 1
## 18455 18500 18640 18674 18820 18850 1900 19000 19180 19390 19550 1960
## 1 1 1 1 1 1 1 1 1 1 1 1
## 19620 19645 19700 19775 19780 19792 19840 2000 20080 20100 20230 20290
## 1 1 1 1 1 1 1 1 1 1 1 1
## 20330 20352 20546 2060 2066 2080 20906 2100 21000 21020 21105 2130
## 1 1 1 2 1 1 1 1 3 1 1 1
## 21300 21344 21480 21504 21600 2184 21990 22000 22110 22140 22185 22240
## 1 2 1 1 1 1 1 1 1 1 1 1
## 22300 22456 22470 22490 22560 22630 22814 22960 23000 23584 2375 23832
## 1 1 1 1 1 1 1 1 1 1 1 1
## 23850 23875 23980 24000 24120 24308 24420 24740 2480 24820 24925 25065
## 1 1 1 1 1 1 1 1 1 1 1 1
## 25112 25200 25230 25380 25485 25560 2568 25700 25770 25950 25990 26150
## 1 1 1 1 1 1 1 1 1 2 1 1
## 26275 26340 26430 26620 26640 26675 26760 26820 27025 27380 27530 27600
## 1 1 1 1 1 1 1 1 1 1 1 1
## 27706 27815 27880 2795 28240 28640 28680 28740 28770 28790 28826 28875
## 1 1 1 1 1 1 1 1 1 1 1 1
## 28950 29000 29020 2908 29333 29400 29405 29428 29430 29443 29550 29553
## 1 1 2 1 1 1 1 1 1 1 1 1
## 29744 29860 3000 30075 30140 30210 30367 30420 30455 3050 30570 30644
## 1 1 1 1 1 2 1 2 1 1 1 1
## 30690 30700 3078 31000 31010 31076 31125 31240 31420 31470 31540 31645
## 1 1 1 1 1 1 1 1 1 1 1 1
## 31800 31890 31980 32060 32250 32296 32310 32328 32448 32640 32800 32910
## 1 1 1 1 1 1 1 1 1 1 1 1
## 33012 33144 33180 33340 3336 33408 33620 34000 34160 3425 34450 34550
## 1 1 1 1 1 1 1 1 1 1 1 1
## 34680 34795 34950 34952 34980 35000 35060 35075 35180 35215 35520 35580
## 1 1 1 1 1 1 1 1 1 1 1 1
## 35624 35650 3580 36000 36100 36280 36300 3635 36480 36510 36610 36700
## 1 1 1 1 1 1 1 1 1 1 1 1
## 37000 37070 37175 37380 37420 37490 37720 37772 37825 37875 37940 38077
## 1 1 1 1 1 1 1 1 1 1 1 1
## 38180 3828 38288 38400 38424 38550 38640 38715 38740 38800 38855 39225
## 1 1 1 1 1 1 1 1 1 1 1 1
## 39300 39510 39625 39727 39765 39784 39835 39878 4000 40040 40115 40166
## 1 1 1 1 1 1 1 1 1 2 1 1
## 40180 40189 40290 40350 40382 40440 40560 40580 40620 40675 40688 40775
## 1 1 1 1 1 1 1 1 1 1 1 1
## 40890 4105 41100 41165 41216 41224 41300 41310 41420 41440 41500 41610
## 1 1 1 1 1 1 1 1 1 1 1 1
## 41664 41690 41720 42090 42160 42168 42180 42364 42510 42750 42820 42990
## 1 1 1 1 1 1 1 1 1 1 1 1
## 4300 43000 43082 43100 43140 43220 43252 43335 43344 43440 43554 43620
## 1 1 1 1 1 1 1 1 1 1 1 1
## 43740 43800 43864 43895 440 44070 44105 44328 44530 44700 44832 44856
## 1 1 1 1 1 1 1 1 1 1 1 1
## 44968 4500 45000 45008 45056 45096 45120 45140 45430 45460 45560 45628
## 1 1 1 1 1 1 1 1 1 1 1 1
## 45690 45810 45900 45990 46000 46042 4615 46225 46365 46380 46410 46520
## 1 1 1 1 1 1 1 1 1 1 1 1
## 46680 46820 46896 46924 46925 4695 47042 47068 47138 4720 47360 4750
## 1 1 1 1 1 1 1 1 1 1 1 1
## 47500 47535 47540 47600 47616 47628 47670 47672 47680 47800 47880 4792
## 1 1 1 1 1 1 1 1 1 1 1 1
## 48000 48020 48090 48244 4825 48300 48340 48342 48500 4860 48620 48900
## 1 1 1 1 1 1 1 1 1 1 1 1
## 48952 48955 49000 49020 49056 49080 49120 49121 4920 4930 49300 49322
## 1 1 1 1 1 1 1 1 1 1 2 1
## 49600 49675 49784 49840 49890 49950 49960 49970 50000 50034 50250 50260
## 1 1 1 1 1 1 1 1 1 1 1 1
## 50440 50580 50640 5068 5070 50784 50825 5100 51000 51025 51055 51150
## 1 1 1 1 1 1 1 1 2 1 1 1
## 51210 5140 51575 51660 5170 51730 51760 51810 51825 51900 52070 52140
## 1 2 1 1 1 1 1 1 1 1 1 1
## 52200 52320 52350 52470 52480 52490 52560 52584 52594 52630 52805 52940
## 1 1 1 1 1 1 1 1 1 1 1 1
## 52980 5300 53000 53026 53104 5320 53224 53280 53368 53380 53620 53680
## 2 1 1 1 1 1 1 1 1 1 1 1
## 53682 53750 53780 53850 53890 53960 54040 54214 54270 54310 54360 54485
## 1 1 1 1 1 1 1 1 1 1 1 1
## 54640 54688 54705 54716 54808 54837 54870 54875 54880 54881 55000 55020
## 1 1 1 1 1 1 1 1 1 1 1 1
## 55128 55216 55275 55540 55574 5560 55745 55750 55770 55820 55852 5595
## 1 1 1 1 1 1 1 1 1 1 1 1
## 55950 55955 55980 56000 56020 56060 56130 5616 56160 56270 56320 56340
## 1 1 1 1 1 1 1 1 1 1 1 1
## 56360 56375 56456 56460 56550 56966 56979 57000 57260 57302 57386 57510
## 1 1 1 1 1 1 1 2 1 1 1 1
## 57600 57660 57760 57780 57870 57880 58110 58200 58350 58730 58800 5888
## 1 1 1 1 1 1 1 1 1 1 1 1
## 58880 58980 5900 59000 59020 5910 59105 59140 59190 5920 59250 59280
## 1 1 1 2 1 1 1 1 1 1 1 1
## 59350 59440 59608 59640 59641 59735 59880 59920 59925 59980 59998 60000
## 1 1 1 1 1 1 1 1 1 1 1 1
## 60015 60090 60120 6020 60330 60500 60545 6064 60750 60785 60825 6088
## 1 1 2 1 1 1 1 1 1 1 1 1
## 60900 60915 6096 61000 61120 61225 61530 61680 61714 61798 61800 61832
## 1 1 1 1 1 1 1 1 1 1 1 1
## 61890 61920 61940 62148 62250 62430 62432 62535 6260 6278 62824 62900
## 1 1 1 1 1 2 1 1 1 1 1 1
## 62940 63000 63150 63264 63360 63418 63624 63768 6382 63968 64000 64080
## 1 2 1 1 1 1 1 1 1 1 1 1
## 64145 64304 64309 64544 64560 64620 64650 64675 64980 6500 65080 65255
## 1 1 1 1 1 1 1 1 1 1 1 1
## 65280 65340 65370 65392 65440 65508 65560 65732 65760 65790 65820 66000
## 1 1 1 1 1 1 1 1 1 1 1 1
## 66060 6607 66145 6616 66175 66200 66376 66460 66570 66660 66700 67000
## 1 1 1 1 1 1 1 1 1 1 1 2
## 6740 67460 67610 67945 68000 68170 68260 68388 68430 68460 68645 68750
## 1 1 1 1 1 1 1 1 1 1 1 1
## 68760 68790 68880 68940 69000 69170 69274 69300 69390 694 69420 69584
## 1 1 1 1 1 1 1 1 1 1 2 1
## 69690 69800 69940 69970 70 7000 70000 70020 70040 70320 70380 70420
## 1 1 1 1 1 1 1 1 1 1 1 1
## 70520 70540 70550 70880 71032 71390 71416 71428 71430 71620 71682 7175
## 1 1 1 1 1 1 1 1 1 1 1 1
## 7180 71892 71990 7200 72215 72360 72420 72495 72600 72632 72820 72824
## 1 1 1 1 1 1 1 1 1 1 1 1
## 72928 72975 7300 73000 73020 73060 73070 7310 73140 73168 73405 73725
## 1 1 1 1 1 1 1 1 1 1 1 1
## 73760 73770 73895 74000 74104 74118 74119 74190 7420 74300 74480 74540
## 1 1 1 1 1 1 1 1 1 1 1 1
## 74608 74630 74880 74900 74944 74960 75015 75098 75125 7520 75216 75620
## 1 1 1 1 1 1 1 1 1 1 1 1
## 75672 75740 7580 75815 75816 7600 76025 76030 76070 76106 76135 76220
## 1 1 1 1 1 1 1 1 1 1 1 1
## 76432 76460 76490 76540 76570 7660 7665 76778 76940 76960 77000 77152
## 1 2 1 1 1 1 1 1 1 1 2 1
## 7720 77200 77255 77344 77360 77570 77630 77840 77850 77930 7810 78250
## 1 3 1 1 1 1 1 1 1 1 1 1
## 78510 78600 78650 78690 78736 78740 78776 78800 78865 78932 79000 79002
## 1 1 1 1 1 1 1 1 1 1 3 1
## 79040 79056 79460 7948 79492 79520 79610 7966 79740 79800 79820 80070
## 1 1 1 1 1 1 1 1 1 1 1 1
## 80230 80240 80270 80280 80340 80420 80490 80510 8070 80700 80740 80780
## 1 1 1 1 1 1 1 1 1 1 1 1
## 8085 80990 81035 81048 81168 81325 81440 81660 81677 81740 82000 82105
## 1 1 1 1 1 1 1 1 1 1 3 1
## 82120 82525 82590 82704 82870 8300 83050 83080 83152 83342 83432 83500
## 1 1 1 1 1 1 1 1 1 1 1 1
## 83512 83622 8364 83680 83975 84000 84077 8416 84192 84250 8430 84475
## 1 1 1 1 1 1 1 1 1 1 1 1
## 84512 84528 84675 84780 8490 84900 84940 85036 85188 85300 85312 85350
## 1 1 1 1 1 1 1 1 1 1 1 1
## 85480 86000 86025 86160 86220 86370 8640 86548 86700 86720 86772 86860
## 1 1 1 1 1 1 1 1 1 1 1 1
## 86925 86968 87000 87056 87070 87560 8760 8794 88000 88084 88200 88380
## 1 1 1 1 1 1 1 1 1 1 1 1
## 88900 88940 89140 8950 8980 9000 90672 90741 91085 9110 91370 9175
## 1 1 1 1 1 1 1 1 1 1 1 1
## 92036 9246 9280 92890 93170 93218 93480 93926 93955 94597 980
## 1 1 1 1 1 1 1 1 1 1 1# Distribution of number of communities by states
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, uniontable(cd$state) %>% barplot(col = "wheat")
# Understanding Distribution through Histogram
library(ggplot2)
hist(cd$medIncome,col="grey",main="Histogram of Median Income",xlab="Median Income")
hist(cd$PctPopUnderPov,col="grey",main="Histogram of Population Under Poverty",xlab="Percentage Under Poverty")
hist(cd$PctUnemployed,col="grey",main="Histogram of Percentage Unemployed",xlab="Percentage Unemployed")
hist(cd$PctHousOccup,col="grey",main="Histogram of Percentage of House Occupied",xlab="Percentage House Occupied")
# Population Density in Persons per Square Mile
hist(cd$PopDens,col="grey",breaks=20,main="Histogram of Population Density",xlab="Population Density")
hist(as.numeric(cd$PolicBudgPerPop),col="grey",main="Histogram of Police Budged Per Population",xlab="Police Budged Per Population")
# Measures of Central Tendancy // Mean Median
summary(cd$medIncome)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 8866 23817 31441 33985 41480 123625summary(cd$PctPopUnderPov)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.64 4.51 9.33 11.62 16.91 58.00summary(cd$PctUnemployed)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.320 4.045 5.450 6.045 7.440 31.230summary(cd$PctHousOccup)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 37.47 91.29 94.21 92.93 96.02 99.00summary(cd$PolicBudgPerPop)## Length Class Mode
## 2215 character charactersummary(cd$PopDens)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 10 1182 2027 2784 3322 44230#Measuring Skewness and Kurtosis
#Skewness is a measure of asymmetry. Kurtosis is a more subtle measure of peakedness compared to a Gaussian distribution.
library(moments)
skewness(cd$medIncome)## [1] 1.347235kurtosis(cd$medIncome)## [1] 6.243133skewness(cd$PctPopUnderPov)## [1] 1.114628kurtosis(cd$PctPopUnderPov)## [1] 4.161799skewness(cd$PctUnemployed)## [1] 1.749989kurtosis(cd$PctUnemployed)## [1] 9.619677# plots
plot(as.numeric(robberies)~as.numeric(medIncome),data=cd, main="Robberies Vs Median Income",xlab="Median Income", ylab="Robberies per population")
plot(as.numeric(robbbPerPop)~as.numeric(PctUnemployed),data=cd, main="Robberies Vs Percentage Unemplyed",xlab="PercentageUnemployed", ylab="Robberies per population")
plot(as.numeric(robbbPerPop)~as.numeric(PctPopUnderPov),data=cd, main="Robberies Vs Population Under Poverty",xlab="Population Under Poverty", ylab="Robberies per population")
boxplot(as.numeric(robbbPerPop)~state,data=cd, main="Robberies By States",xlab="States", ylab="Robberies By States")