I'm trying to calculate the probability distribution of a huge sample.
I'm using prop.table function; it works as expected when I supply a toy data like c(1,2,3), but when I try it on my database, it gives negative outputs half of the time.
Why is that?
Edit:
Here is the code:
dInfo <- d[, props := prop.table(Data, by=.(N, SimulationID, AgentID, Type, AC)]
Here a part of my data:
structure(list(Time = c(0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), AgentID = c(1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), AC = c("a",
"a", "a", "a", "a", "a", "a", "a", "a", "a", "a", "a", "a", "a",
"a", "a", "a", "a", "a", "a", "a", "a", "a", "a", "a", "a", "a",
"a", "a", "a", "a", "a", "a", "a", "a", "a", "a", "a", "a", "a",
"a", "a", "c", "c", "c", "c", "c", "c", "c", "c"), Layer = c(0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L), Type = c("w", "w", "w", "w", "w", "w", "w", "w", "w", "w",
"w", "w", "w", "w", "w", "w", "w", "w", "w", "w", "w", "w", "w",
"w", "w", "b", "b", "b", "b", "b", "w", "w", "w", "w", "w", "w",
"w", "w", "w", "w", "b", "b", "w", "w", "w", "w", "w", "w", "w",
"w"), Data = c(-0.004488192, 0.035931263, 0.000238355, -0.05017679,
-0.038905628, 0.011275043, -0.002179068, -0.004003432, 0.016829431,
-0.023060411, -0.06022472, 0.08615596, 0.0013049663, 0.019211488,
0.010899153, 0.0023098313, 0.027939968, 0.04645505, 0.0007778046,
-0.040082328, 0.039822448, 0.037230257, 0.13616666, 0.024908375,
0.015247015, 0, 0, 0, 0, 0, -0.016074684, 0.040625643, 0.043461435,
-0.030649526, -0.02392821, 0.040948648, -0.02336491, 0.018872455,
-0.00966381, 0.053552378, 0, 0, -0.056943502, -0.018150102, 0.0296274,
-0.06308299, -0.036620624, 0.065056846, -0.02112275, 0.046921805
), N = c(40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L,
40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L,
40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L,
40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L, 40L
), SimulationID = c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L), props = c(9.91097107644817, 6.66241744000629,
9.97337994012272, 4.54102536134095, 6.21473028139476, 9.58510403938687,
9.95876866798959, 9.92372850444168, 9.1287428935349, 8.44652608868229,
3.21071775135845, 0.980489679221862, 9.96825081589951, 8.88708762327722,
9.61010295867649, 9.95694207591156, 7.8145448800769, 5.08116158863253,
9.97167162498901, 6.03681752692042, 6.07611942773214, 6.46746051762461,
0.0303718985404854, 8.21575628567643, 9.27469717542228, 9.97355701003582,
9.97355701003582, 9.97355701003582, 9.97355701003582, 9.97355701003582,
9.19986406711566, 5.95465874208366, 5.52706640720111, 7.43632548490794,
8.33957729555316, 5.90582919664192, 8.40929463364054, 8.92301866654129,
9.68669369035605, 4.07036192254373, 9.97355701003582, 9.97355701003582,
3.62058833244095, 8.99790347833101, 7.5808865889129, 2.87586905369961,
6.55909663072181, 2.65731021303268, 8.67555229815946, 5.01242514582731
), Info = c(9.7341790210304e-156, 9.7341790210304e-156, 9.7341790210304e-156,
9.7341790210304e-156, 9.7341790210304e-156, 9.7341790210304e-156,
9.7341790210304e-156, 9.7341790210304e-156, 9.7341790210304e-156,
9.7341790210304e-156, 9.7341790210304e-156, 9.7341790210304e-156,
9.7341790210304e-156, 9.7341790210304e-156, 9.7341790210304e-156,
9.7341790210304e-156, 9.7341790210304e-156, 9.7341790210304e-156,
9.7341790210304e-156, 9.7341790210304e-156, 9.7341790210304e-156,
9.7341790210304e-156, 9.7341790210304e-156, 9.7341790210304e-156,
9.7341790210304e-156, 0.315970828703403, 0.315970828703403, 0.315970828703403,
0.315970828703403, 0.315970828703403, 9.7341790210304e-156, 9.7341790210304e-156,
9.7341790210304e-156, 9.7341790210304e-156, 9.7341790210304e-156,
9.7341790210304e-156, 9.7341790210304e-156, 9.7341790210304e-156,
9.7341790210304e-156, 9.7341790210304e-156, 0.315970828703403,
0.315970828703403, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN)), row.names = c(NA,
-50L), class = c("data.table", "data.frame"), .internal.selfref = <pointer: 0x55dc142f2a20>)
