Replace the cloud with a smoother.
Harold Nelson
10/4/2018
This little presentation looks at weather for the Olympia area. If you’re new, what should you expect over the next few months?
I thought that last July was unusually hot. Was it different?
Look at the data and see what we have.
## Classes 'tbl_df', 'tbl' and 'data.frame': 53034 obs. of 6 variables:
## $ STATION_NAME: chr "OLYMPIA PRIEST PT PA WA US" "OLYMPIA PRIEST PT PA WA US" "OLYMPIA PRIEST PT PA WA US" "OLYMPIA PRIEST PT PA WA US" ...
## $ DATE : chr "18770701" "18770702" "18770703" "18770704" ...
## $ PRCP : num 0 0 0 0 0 0 0 0 0 0 ...
## $ SNOW : num -9999 -9999 -9999 -9999 -9999 ...
## $ TMAX : num 63 63 67 67 71 74 80 88 81 70 ...
## $ TMIN : num 48 53 45 45 43 49 49 50 57 57 ...
## - attr(*, "spec")=List of 2
## ..$ cols :List of 6
## .. ..$ STATION_NAME: list()
## .. .. ..- attr(*, "class")= chr "collector_character" "collector"
## .. ..$ DATE : list()
## .. .. ..- attr(*, "class")= chr "collector_character" "collector"
## .. ..$ PRCP : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ SNOW : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ TMAX : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## .. ..$ TMIN : list()
## .. .. ..- attr(*, "class")= chr "collector_double" "collector"
## ..$ default: list()
## .. ..- attr(*, "class")= chr "collector_guess" "collector"
## ..- attr(*, "class")= chr "col_spec"## STATION_NAME DATE PRCP
## Length:53034 Length:53034 Min. :-9999.00
## Class :character Class :character 1st Qu.: 0.00
## Mode :character Mode :character Median : 0.00
## Mean : -126.37
## 3rd Qu.: 0.14
## Max. : 4.82
##
## SNOW TMAX TMIN
## Min. :-9999.0 Min. :-9999.000 Min. :-9999.000
## 1st Qu.:-9999.0 1st Qu.: 50.000 1st Qu.: 34.000
## Median : 0.0 Median : 59.000 Median : 41.000
## Mean :-4119.4 Mean : 6.775 Mean : -6.512
## 3rd Qu.: 0.0 3rd Qu.: 71.000 3rd Qu.: 47.000
## Max. : 14.2 Max. : 104.000 Max. : 76.000
## NA's :7Fix the dates
Fix the rest of the problems.
olyw1018 %>% mutate(TMAX = ifelse(TMAX == -9999,NA,TMAX),
TMIN = ifelse(TMIN == -9999,NA,TMIN),
SNOW = ifelse(SNOW == -9999,0,SNOW),
PRCP = ifelse(PRCP == -9999,0,PRCP),
yr = year(DATE),
mo = month(DATE),
dy = day(DATE)) %>%
filter(complete.cases(olyw1018)) %>%
filter(yr >= 1948) -> olyw1018
save(olyw1018,file="olyw1018.rdata")The dataset contains daily observations of weather from July 1948 forward.
## STATION_NAME DATE PRCP
## Length:28705 Min. :1948-01-01 Min. :0.0000
## Class :character 1st Qu.:1959-10-04 1st Qu.:0.0000
## Mode :character Median :1979-05-28 Median :0.0000
## Mean :1980-03-14 Mean :0.1404
## 3rd Qu.:1999-01-21 3rd Qu.:0.1400
## Max. :2018-09-21 Max. :4.8200
##
## SNOW TMAX TMIN yr
## Min. : 0.00000 Min. : 18.00 Min. :-8.00 Min. :1948
## 1st Qu.: 0.00000 1st Qu.: 50.00 1st Qu.:33.00 1st Qu.:1959
## Median : 0.00000 Median : 59.00 Median :40.00 Median :1979
## Mean : 0.03357 Mean : 60.45 Mean :39.85 Mean :1980
## 3rd Qu.: 0.00000 3rd Qu.: 71.00 3rd Qu.:47.00 3rd Qu.:1999
## Max. :14.20000 Max. :104.00 Max. :69.00 Max. :2018
## NA's :13 NA's :14
## mo dy
## Min. : 1.000 Min. : 1.00
## 1st Qu.: 4.000 1st Qu.: 8.00
## Median : 7.000 Median :16.00
## Mean : 6.501 Mean :15.72
## 3rd Qu.: 9.000 3rd Qu.:23.00
## Max. :12.000 Max. :31.00
## Let’s create a permanent weather prediction for any future year based on average historical values for each day.
Here’s a graph showing all of the historical values.
Here’s the same graph with 2018 values enhanced.