Summarize Data for Matrices/Dataframes Results, R

Summarize Data for Matrices/Dataframes Results

Language: Layout:

options(width=150)

set.seed(7132019)
alpha <- c(LETTERS, letters, c(0:9))
data_tools <- c("sas", "stata", "spss", "python", "r", "julia")

#################
### DATA BUILD
#################
random_df <- data.frame(
  group = sample(data_tools, 500, replace=TRUE),
  year = sample(2010:2019, 500, replace=TRUE),
  var1 = runif(500),
  var2 = rnorm(500),
  var3 = rgamma(500, 0.75)
)

cat("\nSAPPLY SINGLE AGGREGATE\n")
sapply(random_df[c("var1", "var2", "var3")], mean)
    
cat("\nSAPPLY MULTIPLE AGGREGATES\n")
sapply(random_df[c("var1", "var2", "var3")], function(x) c(sum=sum(x), mean=mean(x), min=min(x), q1=quantile(x)[2], median=median(x),  q3=quantile(x)[4], max=max(x), sd=sd(x)))
    
cat("\nAGGREGATE SINGLE FUNC\n")
aggregate(cbind(var1, var2, var3) ~ group, random_df, mean)

cat("\nAGGREGATE MULTIPLE FUNCs\n")
aggregate(cbind(var1, var2, var3) ~ group, random_df, function(x) c(sum=sum(x), mean=mean(x), min=min(x), q1=quantile(x)[2], median=median(x),  q3=quantile(x)[4], max=max(x), sd=sd(x)))

[ + ] Show input
Absolute running time: 0.38 sec, cpu time: 0.68 sec, memory peak: 33 Mb, absolute service time: 0,39 sec

SAPPLY SINGLE AGGREGATE var1 var2 var3 0.49278880 -0.07354253 0.81653513 SAPPLY MULTIPLE AGGREGATES var1 var2 var3 sum 2.463944e+02 -36.77126649 4.082676e+02 mean 4.927888e-01 -0.07354253 8.165351e-01 min 8.014957e-04 -3.32555226 4.421362e-06 q1.25% 2.405156e-01 -0.73246513 1.613800e-01 median 4.899179e-01 -0.03591260 5.506604e-01 q3.75% 7.258722e-01 0.59926765 1.145058e+00 max 9.994167e-01 2.69842955 6.138613e+00 sd 2.860351e-01 1.03284330 8.798103e-01 AGGREGATE SINGLE FUNC group var1 var2 var3 1 julia 0.4376963 -0.29245506 0.8245299 2 python 0.4834428 0.02120193 0.8733324 3 r 0.5050477 -0.10625986 0.8220693 4 sas 0.5473456 -0.17142677 0.8234295 5 spss 0.5094733 0.03886740 0.9284450 6 stata 0.4666691 0.01999630 0.6324121 AGGREGATE MULTIPLE FUNCs group var1.sum var1.mean var1.min var1.q1.25% var1.median var1.q3.75% var1.max var1.sd var2.sum var2.mean 1 julia 3.107643e+01 4.376963e-01 3.039399e-03 2.235550e-01 4.364901e-01 6.571541e-01 9.703487e-01 2.653389e-01 -20.764308997 -0.292455056 2 python 4.109264e+01 4.834428e-01 8.014957e-04 2.271314e-01 5.247033e-01 7.038840e-01 9.963282e-01 2.934828e-01 1.802163635 0.021201925 3 r 4.191896e+01 5.050477e-01 3.915853e-03 3.452389e-01 5.045798e-01 7.068593e-01 9.862924e-01 2.759782e-01 -8.819568508 -0.106259862 4 sas 4.542968e+01 5.473456e-01 2.886394e-02 3.120615e-01 5.902397e-01 7.863649e-01 9.994167e-01 2.829303e-01 -14.228422033 -0.171426771 5 spss 4.534312e+01 5.094733e-01 5.578085e-02 2.548768e-01 5.098657e-01 7.673425e-01 9.826217e-01 2.786200e-01 3.459198713 0.038867401 6 stata 4.153355e+01 4.666691e-01 5.822764e-03 1.707117e-01 4.634947e-01 7.192619e-01 9.918951e-01 3.099486e-01 1.779670702 0.019996300 var2.min var2.q1.25% var2.median var2.q3.75% var2.max var2.sd var3.sum var3.mean var3.min var3.q1.25% 1 -3.325552262 -1.099162118 -0.158257303 0.404294597 2.062768884 1.014865620 5.854162e+01 8.245299e-01 4.421362e-06 1.108153e-01 2 -2.790201158 -0.698363658 -0.084499845 0.796072082 1.886823033 0.986448179 7.423326e+01 8.733324e-01 5.181204e-03 1.450949e-01 3 -2.742473841 -0.916552574 0.055653072 0.666392994 1.785740261 1.053131137 6.823175e+01 8.220693e-01 2.421360e-04 2.297271e-01 4 -2.486995621 -0.897282773 -0.213568930 0.444213481 2.698429548 1.025259525 6.834465e+01 8.234295e-01 2.170648e-03 1.140533e-01 5 -2.202455172 -0.699109459 0.004878545 0.909582903 2.668273212 1.132830841 8.263161e+01 9.284450e-01 5.804070e-03 2.686339e-01 6 -2.959961375 -0.505855312 0.039508693 0.574543686 2.089854412 0.962104738 5.628468e+01 6.324121e-01 4.918626e-03 1.738537e-01 var3.median var3.q3.75% var3.max var3.sd 1 4.427998e-01 1.113309e+00 4.249317e+00 9.800600e-01 2 6.389867e-01 1.294346e+00 4.606581e+00 9.098180e-01 3 6.352142e-01 1.198870e+00 6.138613e+00 8.842292e-01 4 5.820043e-01 1.227659e+00 5.331560e+00 9.286314e-01 5 6.970385e-01 1.393692e+00 3.821311e+00 8.503074e-01 6 4.187489e-01 8.198077e-01 3.760204e+00 7.278648e-01