In this lab you can use the interactive console to explore but please record your commands here. Remember anything you type here can be “sent” to the console with Cmd-Enter (OS-X) or Cntr-Enter (Windows/Linux) (But only in side the {r} areas).
library(tidyverse)read_csv, call it ufo_slice_5.ufo_slice_5 <- read_csv("https://sisbid.github.io/Data-Wrangling/data/ufo/ufo_slice_5.csv")## Rows: 20 Columns: 11
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: ","
## chr (8): datetime, city, state, country, shape, duration (hours/min), commen...
## dbl (3): duration (seconds), latitude, longitude
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.head(), glimpse(), str() etc.). Do results look different if you had used read_delim above?str(ufo_slice_5)## spc_tbl_ [20 × 11] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
## $ datetime : chr [1:20] "8/2/2012 21:00" "10/6/1995 19:00" "4/17/2005 23:00" "12/31/2013 23:10" ...
## $ city : chr [1:20] "kennewick" "puyallup" "grovetown" "corvallis" ...
## $ state : chr [1:20] "wa" "wa" "ga" "or" ...
## $ country : chr [1:20] "us" "us" "us" "us" ...
## $ shape : chr [1:20] "triangle" NA "circle" "circle" ...
## $ duration (seconds) : num [1:20] 600 900 2700 60 1200 120 60 2 7200 1680 ...
## $ duration (hours/min): chr [1:20] "5-10 minutes" "15 min." "45 minutes" "1 minute" ...
## $ comments : chr [1:20] "Saw three triangle shaped craft with red and white lights and moving in slow formation.." "Man witnesses "small whitish, blue-green ball" pass overhead, flying to east." "Object appeared to be a star at first glance sitting low on the horizon ((NUFORC Note: Possibly Sirius. PD))" "2 amber lights dimming as ascending into sky. Moving then stopping." ...
## $ date posted : chr [1:20] "8/19/2012" "11/2/1999" "5/11/2005" "1/10/2014" ...
## $ latitude : num [1:20] 46.2 47.2 33.5 44.6 33.4 ...
## $ longitude : num [1:20] -119.1 -122.3 -82.2 -123.3 -111.5 ...
## - attr(*, "spec")=
## .. cols(
## .. datetime = col_character(),
## .. city = col_character(),
## .. state = col_character(),
## .. country = col_character(),
## .. shape = col_character(),
## .. `duration (seconds)` = col_double(),
## .. `duration (hours/min)` = col_character(),
## .. comments = col_character(),
## .. `date posted` = col_character(),
## .. latitude = col_double(),
## .. longitude = col_double()
## .. )
## - attr(*, "problems")=<pointer: 0x6000022c2250>head(ufo_slice_5)## # A tibble: 6 × 11
## datetime city state country shape `duration (seconds)` `duration (hours/min)`
## <chr> <chr> <chr> <chr> <chr> <dbl> <chr>
## 1 8/2/201… kenn… wa us tria… 600 5-10 minutes
## 2 10/6/19… puya… wa us <NA> 900 15 min.
## 3 4/17/20… grov… ga us circ… 2700 45 minutes
## 4 12/31/2… corv… or us circ… 60 1 minute
## 5 3/30/20… apac… az us light 1200 20 minutes
## 6 6/22/20… pitt… nj us light 120 a few minutes
## # ℹ 4 more variables: comments <chr>, `date posted` <chr>, latitude <dbl>,
## # longitude <dbl>glimpse(ufo_slice_5)## Rows: 20
## Columns: 11
## $ datetime <chr> "8/2/2012 21:00", "10/6/1995 19:00", "4/17/2005…
## $ city <chr> "kennewick", "puyallup", "grovetown", "corvalli…
## $ state <chr> "wa", "wa", "ga", "or", "az", "nj", "tx", "ca",…
## $ country <chr> "us", "us", "us", "us", "us", "us", NA, "us", "…
## $ shape <chr> "triangle", NA, "circle", "circle", "light", "l…
## $ `duration (seconds)` <dbl> 600, 900, 2700, 60, 1200, 120, 60, 2, 7200, 168…
## $ `duration (hours/min)` <chr> "5-10 minutes", "15 min.", "45 minutes", "1 min…
## $ comments <chr> "Saw three triangle shaped craft with red and w…
## $ `date posted` <chr> "8/19/2012", "11/2/1999", "5/11/2005", "1/10/20…
## $ latitude <dbl> 46.21139, 47.18556, 33.45028, 44.56472, 33.4150…
## $ longitude <dbl> -119.13611, -122.29167, -82.19833, -123.26083, …nrow(ufo_slice_5)## [1] 20read_delim, call it ufo_slice_6. Should any additional arguments be used?ufo_slice_6 <- read_delim("https://sisbid.github.io/Data-Wrangling/data/ufo/ufo_slice_6.txt")## Rows: 20 Columns: 11
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: ":"
## chr (8): datetime, city, state, country, shape, duration (hours/min), commen...
## dbl (3): duration (seconds), latitude, longitude
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.ufo_slice_6## # A tibble: 20 × 11
## datetime city state country shape `duration (seconds)`
## <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 " 6/30/1973 24:00" "los alamos" nm us <NA> 0
## 2 "5/16/2005 19:15" "oklahoma c… ok us tria… 480
## 3 " 9/24/2009 00:00" "cambridge" nh <NA> form… 1200
## 4 "6/15/1981 19:00" "foxton (ne… <NA> <NA> oval 1200
## 5 " 8/20/2013 03:00" "springfiel… va us cigar 3600
## 6 "11/16/2012 23:50" " alto" mi us light 120
## 7 "11/8/2007 23:30" "aztec" nm us fire… 3600
## 8 "2/23/1996 21:29" "madison" tn us <NA> 60
## 9 "3/3/2012 22:15" "greensboro" nc us light 900
## 10 "9/8/2005 05:43" "gainesvill… ga us other 120
## 11 "11/11/1978 18:00" "st. albert… ab ca unkn… 1200
## 12 "6/15/2006 21:45" "tampa" fl us light 20
## 13 "7/13/2012 22:00" "wapakoneta" oh us fire… 120
## 14 "8/9/2008 22:50" "buchholz (… <NA> de light 60
## 15 "12/16/2012 18:25" "bakersfiel… ca us light 120
## 16 "7/21/2006 23:35" "erie" pa us light 15
## 17 "12/8/2012 06:00" "chetek" wi us light 900
## 18 "9/30/2011 21:50" "searcy" ar us diam… 120
## 19 "8/7/2006 00:26" "nanaimo (c… bc ca tria… 0
## 20 "7/10/2009 23:00" "bear creek" al us circ… 4
## # ℹ 5 more variables: `duration (hours/min)` <chr>, comments <chr>,
## # `date posted` <chr>, latitude <dbl>, longitude <dbl>ufo_slice_6 <- read_delim("https://sisbid.github.io/Data-Wrangling/data/ufo/ufo_slice_6.txt", trim_ws = TRUE)## Rows: 20 Columns: 11
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: ":"
## chr (8): datetime, city, state, country, shape, duration (hours/min), commen...
## dbl (3): duration (seconds), latitude, longitude
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.ufo_slice_6## # A tibble: 20 × 11
## datetime city state country shape `duration (seconds)`
## <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 6/30/1973 24:00 los alamos nm us <NA> 0
## 2 5/16/2005 19:15 oklahoma city ok us tria… 480
## 3 9/24/2009 00:00 cambridge nh <NA> form… 1200
## 4 6/15/1981 19:00 foxton (new zealan… <NA> <NA> oval 1200
## 5 8/20/2013 03:00 springfield va us cigar 3600
## 6 11/16/2012 23:50 alto mi us light 120
## 7 11/8/2007 23:30 aztec nm us fire… 3600
## 8 2/23/1996 21:29 madison tn us <NA> 60
## 9 3/3/2012 22:15 greensboro nc us light 900
## 10 9/8/2005 05:43 gainesville ga us other 120
## 11 11/11/1978 18:00 st. albert (canada) ab ca unkn… 1200
## 12 6/15/2006 21:45 tampa fl us light 20
## 13 7/13/2012 22:00 wapakoneta oh us fire… 120
## 14 8/9/2008 22:50 buchholz (germany) <NA> de light 60
## 15 12/16/2012 18:25 bakersfield ca us light 120
## 16 7/21/2006 23:35 erie pa us light 15
## 17 12/8/2012 06:00 chetek wi us light 900
## 18 9/30/2011 21:50 searcy ar us diam… 120
## 19 8/7/2006 00:26 nanaimo (canada) bc ca tria… 0
## 20 7/10/2009 23:00 bear creek al us circ… 4
## # ℹ 5 more variables: `duration (hours/min)` <chr>, comments <chr>,
## # `date posted` <chr>, latitude <dbl>, longitude <dbl>read_table and read_delim on “https://sisbid.github.io/Data-Wrangling/data/ufo/ufo_slice_7.txt”. Which one is more appropriate?# read_delim! read_table interprets all whitespace as delimiting - spaces in our data interfere with this function reading the data.
ufo_slice_7_table <- read_table("https://sisbid.github.io/Data-Wrangling/data/ufo/ufo_slice_7.txt")## Warning: Duplicated column names deduplicated: '"duration' => '"duration_1' [8]##
## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## cols(
## datetime = col_character(),
## city = col_character(),
## state = col_character(),
## country = col_character(),
## shape = col_character(),
## `"duration` = col_character(),
## `(seconds)"` = col_character(),
## `"duration_1` = col_character(),
## `(hours/min)"` = col_character(),
## comments = col_character(),
## `"date` = col_character(),
## `posted"` = col_character(),
## latitude = col_character(),
## longitude = col_character()
## )## Warning: 20 parsing failures.
## row col expected actual file
## 1 -- 14 columns 25 columns 'https://sisbid.github.io/Data-Wrangling/data/ufo/ufo_slice_7.txt'
## 2 -- 14 columns 29 columns 'https://sisbid.github.io/Data-Wrangling/data/ufo/ufo_slice_7.txt'
## 3 -- 14 columns 19 columns 'https://sisbid.github.io/Data-Wrangling/data/ufo/ufo_slice_7.txt'
## 4 -- 14 columns 19 columns 'https://sisbid.github.io/Data-Wrangling/data/ufo/ufo_slice_7.txt'
## 5 -- 14 columns 21 columns 'https://sisbid.github.io/Data-Wrangling/data/ufo/ufo_slice_7.txt'
## ... ... .......... .......... ..................................................................
## See problems(...) for more details.ufo_slice_7_delim <- read_delim("https://sisbid.github.io/Data-Wrangling/data/ufo/ufo_slice_7.txt")## Rows: 20 Columns: 11## ── Column specification ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
## Delimiter: " "
## chr (8): datetime, city, state, country, shape, duration (hours/min), commen...
## dbl (3): duration (seconds), latitude, longitude
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.