library(tidyverse)
## Loading tidyverse: ggplot2
## Loading tidyverse: tibble
## Loading tidyverse: tidyr
## Loading tidyverse: readr
## Loading tidyverse: purrr
## Loading tidyverse: dplyr
## Conflicts with tidy packages ----------------------------------------------
## filter(): dplyr, stats
## lag(): dplyr, stats
setwd("~/Documents/Rstudio DataSets ")
library(readr)
Preview data
CRIMEDATA <- read_csv("/Users/robertperez/Documents/Rstudio DataSets /R11456262_SL050.csv", col_names = TRUE)
## Parsed with column specification:
## cols(
## .default = col_double(),
## Geo_FIPS = col_character(),
## Geo_NAME = col_character(),
## Geo_QNAME = col_character(),
## Geo_NATION = col_character(),
## Geo_STATE = col_integer(),
## Geo_COUNTY = col_character(),
## SE_T001_001 = col_integer()
## )
## See spec(...) for full column specifications.
head(CRIMEDATA)
## # A tibble: 6 x 21
## Geo_FIPS Geo_NAME Geo_QNAME Geo_NATION
## <chr> <chr> <chr> <chr>
## 1 36001 Albany County Albany County, New York <NA>
## 2 36003 Allegany County Allegany County, New York <NA>
## 3 36007 Broome County Broome County, New York <NA>
## 4 36009 Cattaraugus County Cattaraugus County, New York <NA>
## 5 36011 Cayuga County Cayuga County, New York <NA>
## 6 36013 Chautauqua County Chautauqua County, New York <NA>
## # ... with 17 more variables: Geo_STATE <int>, Geo_COUNTY <chr>,
## # SE_T001_001 <int>, SE_T003_001 <dbl>, SE_T003_002 <dbl>,
## # SE_T003_003 <dbl>, SE_T005_001 <dbl>, SE_T005_002 <dbl>,
## # SE_T005_003 <dbl>, SE_T005_004 <dbl>, SE_T005_005 <dbl>,
## # SE_T005_006 <dbl>, SE_T007_001 <dbl>, SE_T007_002 <dbl>,
## # SE_T007_003 <dbl>, SE_T007_004 <dbl>, SE_T009_001 <dbl>
tail(CRIMEDATA)
## # A tibble: 6 x 21
## Geo_FIPS Geo_NAME
## <chr> <chr>
## 1 36115 Washington County
## 2 36117 Wayne County
## 3 36121 Wyoming County
## 4 36123 Yates County
## 5 36AAA Suffolk County Police Department
## 6 36AAB Westchester Public Safety
## # ... with 19 more variables: Geo_QNAME <chr>, Geo_NATION <chr>,
## # Geo_STATE <int>, Geo_COUNTY <chr>, SE_T001_001 <int>,
## # SE_T003_001 <dbl>, SE_T003_002 <dbl>, SE_T003_003 <dbl>,
## # SE_T005_001 <dbl>, SE_T005_002 <dbl>, SE_T005_003 <dbl>,
## # SE_T005_004 <dbl>, SE_T005_005 <dbl>, SE_T005_006 <dbl>,
## # SE_T007_001 <dbl>, SE_T007_002 <dbl>, SE_T007_003 <dbl>,
## # SE_T007_004 <dbl>, SE_T009_001 <dbl>
Recoding Variable Names
library(dplyr)
#T007_001: Total Property Crimes Rate:
#T007_002: Burglaries Rate
#T007_003: Larcenies Rate
#T007_004: Motor Vehicle Thefts Rate
Crimedata2 <- rename(CRIMEDATA,
totalpropertycrime_PER_100K = SE_T007_001,
BURGLARIES_PER_100K = SE_T007_002,
LARCENIES_PER_100K = SE_T007_003,
MOTORVEHICLETHEFT_PER_100K = SE_T007_004,
County = Geo_NAME)
Dropping and Selecting Variables
Crimedata2 <- select(Crimedata2, totalpropertycrime_PER_100K, BURGLARIES_PER_100K, LARCENIES_PER_100K, MOTORVEHICLETHEFT_PER_100K, County)
dim(Crimedata2)
## [1] 54 5
print(Crimedata2)
## # A tibble: 54 x 5
## totalpropertycrime_PER_100K BURGLARIES_PER_100K LARCENIES_PER_100K
## <dbl> <dbl> <dbl>
## 1 35.554866 10.989686 23.272276
## 2 4.213897 0.000000 4.213897
## 3 369.848449 56.469295 305.239435
## 4 376.017043 96.250096 263.083596
## 5 226.088289 45.984059 173.717556
## 6 453.436714 133.813533 299.742313
## 7 515.671119 44.791033 458.246718
## 8 628.531652 124.887397 479.076243
## 9 19.692065 3.692262 15.999803
## 10 518.623291 131.688046 377.180575
## # ... with 44 more rows, and 2 more variables:
## # MOTORVEHICLETHEFT_PER_100K <dbl>, County <chr>
Creating New Variable
CRIMEDATA <- mutate(CRIMEDATA,
TOTALPROP_VIOLENTCRIMESREP = SE_T007_001 + SE_T005_001)
head(CRIMEDATA)
## # A tibble: 6 x 22
## Geo_FIPS Geo_NAME Geo_QNAME Geo_NATION
## <chr> <chr> <chr> <chr>
## 1 36001 Albany County Albany County, New York <NA>
## 2 36003 Allegany County Allegany County, New York <NA>
## 3 36007 Broome County Broome County, New York <NA>
## 4 36009 Cattaraugus County Cattaraugus County, New York <NA>
## 5 36011 Cayuga County Cayuga County, New York <NA>
## 6 36013 Chautauqua County Chautauqua County, New York <NA>
## # ... with 18 more variables: Geo_STATE <int>, Geo_COUNTY <chr>,
## # SE_T001_001 <int>, SE_T003_001 <dbl>, SE_T003_002 <dbl>,
## # SE_T003_003 <dbl>, SE_T005_001 <dbl>, SE_T005_002 <dbl>,
## # SE_T005_003 <dbl>, SE_T005_004 <dbl>, SE_T005_005 <dbl>,
## # SE_T005_006 <dbl>, SE_T007_001 <dbl>, SE_T007_002 <dbl>,
## # SE_T007_003 <dbl>, SE_T007_004 <dbl>, SE_T009_001 <dbl>,
## # TOTALPROP_VIOLENTCRIMESREP <dbl>