为什么ggplot的geom_density（）峰值与数据帧数不同？

Question

我有以下数据框：

dat <- structure(list(crt = c(0.049, 0.098, 0.06, 0.06, 0.09951, 0.09939, 
0.09963, 0.09939, 0.09926, 0.0996, 0.09938, 0.09933, 0.09946, 
0.09955, 0.09972, 0.09941, 0.09982, 0.09962, 0.09934, 0.0995, 
0.09985, 0.0996, 0.09976, 0.09951, 0.09986, 0.09979, 0.09931, 
0.09983, 0.09959, 0.09972, 0.09897, 0.09991, 0.09931, 0.09959, 
0.09908, 0.09941, 0.09944, 0.09951, 0.09981, 0.09913, 0.0994, 
0.09934, 0.09969, 0.09967, 0.09968, 0.0991, 0.09937, 0.09968, 
0.09968, 0.09947, 0.09911, 0.0994, 0.09986, 0.0991, 0.09969, 
0.09914, 0.09944, 0.0995, 0.10025, 0.09951, 0.09974, 0.09936, 
0.09914, 0.09901, 0.0996, 0.09975, 0.09865, 0.09916, 0.09936, 
0.0994, 0.09949, 0.0995, 0.09902, 0.09961, 0.09955, 0.09932, 
0.09965, 0.09923, 0.09955, 0.09928, 0.09918, 0.09925, 0.09958, 
0.09944, 0.09953, 0.09942, 0.09918, 0.09977, 0.09931, 0.0998, 
0.0995, 0.09924, 0.0997, 0.09902, 0.09925, 0.09957, 0.09941, 
0.09941, 0.09969, 0.09956, 0.09944, 0.09961, 0.09954, 0.09951, 
0.09974, 0.09925, 0.0995, 0.09999, 0.09944, 0.09894, 0.09986, 
0.09906, 0.09986, 0.09986, 0.09915, 0.09929, 0.09983, 0.09938, 
0.09973, 0.09963, 0.09903, 0.09951, 0.09992, 0.09949, 0.09961, 
0.0993, 0.09967, 0.0997, 0.09946, 0.09995, 0.09931, 0.09963, 
0.09942, 0.09944, 0.09988, 0.09977, 0.09981, 0.09942, 0.0996, 
0.09965, 0.09948, 0.09982, 0.09942, 0.09945, 0.09947, 0.09934, 
0.09974, 0.09944, 0.09931, 0.09979, 0.09915, 0.0996, 0.09938, 
0.09984, 0.09936, 0.09957, 0.09943, 0.09954, 0.09928, 0.09966, 
0.09945, 0.09898, 0.0993, 0.09942, 0.0989, 0.09906, 0.09952, 
0.09925, 0.09913, 0.09935, 0.09992, 0.09966, 0.09914, 0.09957, 
0.09912, 0.09947, 0.09933, 0.09967, 0.09921, 0.09952, 0.09935, 
0.09902, 0.09943, 0.0995, 0.09946, 0.09876, 0.09954, 0.09944, 
0.09932, 0.09981, 0.09993, 0.09924, 0.09917, 0.09911, 0.09947, 
0.09938, 0.09912, 0.0987, 0.09941, 0.09933, 0.09945, 0.09938, 
0.09888, 0.09943, 0.09896, 0.09913, 0.09923, 0.09946, 0.09876, 
0.09951, 0.09831, 0.09951, 0.09955, 0.09929, 0.09981, 0.09964, 
0.09892, 0.09948, 0.09966, 0.09953, 0.09984, 0.09957, 0.09925, 
0.09931, 0.09923, 0.09996, 0.09894, 0.09909, 0.09948, 0.0996, 
0.09988, 0.09973, 0.0999, 0.09961, 0.09966, 0.0989, 0.09994, 
0.09975, 0.09948, 0.09912, 0.09951, 0.09948, 0.09938, 0.09988, 
0.0986, 0.09925, 0.09914, 0.09889, 0.09896, 0.09973, 0.09926, 
0.09936, 0.09962, 0.09962, 0.0997, 0.09932, 0.0996, 0.09935, 
0.09898, 0.09942, 0.09994, 0.09902, 0.09938, 0.09901, 0.09903, 
0.09996, 0.09971, 0.09901, 0.09969, 0.09933, 0.09921, 0.09923, 
0.09956, 0.09897, 0.09949, 0.09934, 0.09923, 0.09976, 0.09913, 
0.09978, 0.09963, 0.09942, 0.09891, 0.09965, 0.09935, 0.09956, 
0.09956, 0.09935, 0.09995, 0.09957, 0.09964, 0.09961, 0.09971, 
0.09962, 0.09959, 0.09934, 0.09916, 0.09945, 0.09935, 0.09931, 
0.09983, 0.09959, 0.09941, 0.09993, 0.09978, 0.09936, 0.09978, 
0.09939, 0.09948, 0.09942, 0.09928, 0.09907, 0.09937, 0.09948, 
0.09972, 0.09925, 0.09942, 0.09908, 0.09963, 0.09968, 0.09937, 
0.09933, 0.09961, 0.09936, 0.09862, 0.09935, 0.09893, 0.09984, 
0.09984, 0.09987, 0.09967, 0.09918, 0.0991, 0.09987, 0.09965, 
0.09949, 0.09965, 0.09942, 0.0997, 0.09931, 0.09984, 0.09954, 
0.09949, 0.09952, 0.09949, 0.0995, 0.09912, 0.09922, 0.09965, 
0.09986, 0.0995, 0.09965, 0.09959, 0.09955, 0.09962, 0.09945, 
0.09943, 0.09988, 0.09974, 0.09996, 0.09883, 0.09932, 0.09917, 
0.09946, 0.09975, 0.09901, 0.0995, 0.09937, 0.09943, 0.09979, 
0.09948, 0.0994, 0.09931, 0.09957, 0.0995, 0.09947, 0.09935, 
0.09939, 0.09954, 0.09978, 0.09889, 0.09911, 0.09904, 0.09936, 
0.09955, 0.09954, 0.09943, 0.0995, 0.09945, 0.09969, 0.09951, 
0.09939, 0.09985, 0.09925, 0.09954, 0.09949, 0.09954, 0.09915, 
0.09968, 0.09928, 0.09943, 0.09914, 0.09945, 0.09945, 0.09996, 
0.09988, 0.09957, 0.09973, 0.09969, 0.09935, 0.09921, 0.09936, 
0.0989, 0.0998, 0.09942, 0.09957, 0.09953, 0.09914, 0.09932, 
0.09904, 0.09982, 0.09929, 0.0997, 0.09954, 0.09939, 0.09966, 
0.09941, 0.09933, 0.09918, 0.09936, 0.09973, 0.09928, 0.0997, 
0.09917, 0.09999, 0.09923, 0.09944, 0.10008, 0.09859, 0.09931, 
0.09942, 0.09937, 0.09916, 0.09991, 0.09931, 0.09946, 0.09923, 
0.09943, 0.0994, 0.09972, 0.09977, 0.0988, 0.09967, 0.09944, 
0.09915, 0.0997, 0.09928, 0.09977, 0.09955, 0.0997, 0.09973, 
0.09891, 0.09978, 0.09987, 0.0986, 0.09926, 0.09934, 0.09952, 
0.09987, 0.09956, 0.09958, 0.09878, 0.0989, 0.09957, 0.0994, 
0.0988, 0.09976, 0.09968, 0.09912, 0.09937, 0.09887, 0.09944, 
0.09912, 0.09973, 0.09969, 0.09944, 0.09945, 0.09941, 0.09864, 
0.09956, 0.0996, 0.09958, 0.09919, 0.09962, 0.09969, 0.09961, 
0.09935, 0.09989, 0.09975, 0.09943, 0.09954, 0.09904, 0.09988, 
0.09929, 0.09945, 0.09978, 0.09899, 0.09957, 0.09905, 0.09967, 
0.09999, 0.09938, 0.09962, 0.0995, 0.09974, 0.09967, 0.0994, 
0.09979, 0.09939, 0.09968, 0.09955, 0.09915, 0.09946, 0.09937, 
0.09988, 0.09988, 0.09928, 0.09968, 0.0998, 0.09972, 0.09895, 
0.09964, 0.09992, 0.09954, 0.09909, 0.0993, 0.0994, 0.09887, 
0.09907, 0.09967, 0.09975, 0.09941, 0.09971, 0.09924, 0.0998, 
0.09931, 0.09897, 0.09932, 0.09973, 0.09948, 0.09955, 0.09933, 
0.09952, 0.09955, 0.09982, 0.09964, 0.09995, 0.09987, 0.09984, 
0.09952, 0.09963, 0.09904, 0.09899, 0.09947, 0.09958, 0.09949, 
0.09971, 0.09973, 0.09956, 0.09864, 0.09944, 0.09964, 0.09942, 
0.09895, 0.09978, 0.09946, 0.09921, 0.09983, 0.09891, 0.09953, 
0.09993, 0.09966, 0.09951, 0.09899, 0.09984, 0.0997, 0.0993, 
0.09851, 0.09932, 0.0994, 0.09948, 0.09984, 0.0999, 0.09988, 
0.09916, 0.09986, 0.09934, 0.09987, 0.09973, 0.0996, 0.09956, 
0.09931, 0.09947, 0.09885, 0.09938, 0.0991, 0.09954, 0.09956, 
0.09959, 0.09904, 0.09933, 0.09938, 0.09939, 0.09933, 0.09901, 
0.09949, 0.09936, 0.09953, 0.09955, 0.09996, 0.09908, 0.0992, 
0.09947, 0.09969, 0.09948, 0.09914, 0.09869, 0.09906, 0.09969, 
0.09964, 0.09896, 0.09924, 0.09954, 0.09969, 0.09967, 0.09946, 
0.09959, 0.0989, 0.09956, 0.09868, 0.09954, 0.09948, 0.09926, 
0.09918, 0.09972, 0.09916, 0.09978, 0.09917, 0.1, 0.09914, 0.09934, 
0.09979, 0.09959, 0.09915, 0.09961, 0.09962, 0.09933, 0.09966, 
0.0992, 0.09918, 0.09933, 0.09975, 0.09986, 0.09951, 0.09937, 
0.09956, 0.09955, 0.09944, 0.09923, 0.09926, 0.09944, 0.09963, 
0.0996, 0.09928, 0.09993, 0.09935, 0.09946, 0.09964, 0.09948, 
0.09985, 0.09912, 0.099, 0.09984, 0.09924, 0.0998, 0.09933, 0.09988, 
0.09947, 0.09931, 0.09906, 0.09889, 0.09905, 0.09969, 0.09946, 
0.09936, 0.09939, 0.0995, 0.09969, 0.09925, 0.09967, 0.09951, 
0.09981, 0.09945, 0.09977, 0.0991, 0.09941, 0.09953, 0.0995, 
0.09977, 0.09929, 0.09952, 0.09944, 0.09926, 0.09907, 0.0996, 
0.09941, 0.09957, 0.099, 0.09944, 0.09857, 0.09958, 0.09961, 
0.10008, 0.09973, 0.09978, 0.09968, 0.09946, 0.09927, 0.09977, 
0.09945, 0.09955, 0.09943, 0.09948, 0.0997, 0.09917, 0.0995, 
0.0999, 0.09942, 0.09915, 0.09895, 0.09878, 0.09946, 0.09934, 
0.09881, 0.09872, 0.09948, 0.09968, 0.09908, 0.0999, 0.09939, 
0.09962, 0.09976, 0.0995, 0.09925, 0.09956, 0.09982, 0.09982, 
0.09886, 0.10021, 0.09891, 0.09956, 0.0994, 0.09867, 0.09837, 
0.09972, 0.09936, 0.09935, 0.09952, 0.09927, 0.09995, 0.09935, 
0.09969, 0.0997, 0.09977, 0.1, 0.09936, 0.0998, 0.09946, 0.09897, 
0.09912, 0.09951, 0.09976, 0.0988, 0.0999, 0.09974, 0.09927, 
0.10006, 0.09945, 0.09969, 0.09872, 0.09916, 0.09885, 0.09989, 
0.09916, 0.09881, 0.09979, 0.09976, 0.09933, 0.09967, 0.09956, 
0.09952, 0.09938, 0.09971, 0.09944, 0.09852, 0.09988, 0.0988, 
0.09958, 0.09967, 0.09973, 0.09955, 0.09998, 0.09921, 0.09923, 
0.09957, 0.09956, 0.09892, 0.09919, 0.0991, 0.09943, 0.09958, 
0.09989, 0.09927, 0.09912, 0.10015, 0.09981, 0.0994, 0.0996, 
0.0996, 0.09953, 0.09827, 0.09919, 0.09969, 0.09956, 0.09988, 
0.09949, 0.09957, 0.09902, 0.09917, 0.09912, 0.09932, 0.09965, 
0.09964, 0.09951, 0.09916, 0.09895, 0.09952, 0.0996, 0.10026, 
0.09945, 0.09862, 0.09987, 0.09991, 0.09897, 0.09913, 0.0998, 
0.09955, 0.09883, 0.09982, 0.09985, 0.09976, 0.09895, 0.09874
), category = c("real", "real", "real", "real", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", "sim", 
"sim", "sim")), row.names = c(NA, -863L), class = c("tbl_df", 
"tbl", "data.frame"), vars = character(0), .Names = c("crt", 
"category"))

看起来像这样：

library(tidyverse)
dat <- as.tibble(dat)
dat
#> # A tibble: 863 × 2
#>        crt category
#>      <dbl>    <chr>
#> 1  0.04900     real
#> 2  0.09800     real
#> 3  0.06000     real
#> 4  0.06000     real
#> 5  0.09951      sim
#> 6  0.09939      sim
#> 7  0.09963      sim
#> 8  0.09939      sim
#> 9  0.09926      sim
#> 10 0.09960      sim
#> # ... with 853 more rows

当我试图用此绘图时：

ggplot() +   
geom_density(data=dat, aes(x=crt, group=category, fill=category), alpha=0.5,  size=0.1) +    
scale_y_continuous(trans="log1p", name="density")

我得到这个情节：

我的问题为什么密度图的峰值是> 1000，其中数据计数仅为853 + 10 = 863行？