嗨，这是this one的后续问题。基本上，我有以下数据框：
> dput(foo)
structure(list(Local.Y = c(50.71994, 60.37412, 69.99005, 78.60745
), Un = c(9.48762, 9.93521, 8.9674, 8.33772), PrecVehLocalY = c(70.19624,
78.50749, 86.49717, 93.4731), Ln = c(3.9019, 3.9019, 3.9019,
3.9019), sn_minus_Ln = c(15.5744, 14.23147, 12.60522, 10.96375
), Vehicle.ID2 = c("1-2", "1-2", "1-2", "1-2")), .Names = c("Local.Y",
"Un", "PrecVehLocalY", "Ln", "sn_minus_Ln", "Vehicle.ID2"), row.names = c(NA,
4L), class = "data.frame")
这些是示例数据。原始数据框具有数百个变量Vehicle.ID2的唯一值。它代表车辆对，即＃34;主题车辆＃-front vehicle＃＆＃34;。
我想使用现有变量估计5个新变量。由于新变量既依赖于现有变量又依赖于它们本身，因此使用了for-loop。示例数据（foo）仅包含1个唯一Vehicle.ID2。如果以下for-loop直接应用于foo，则会显示预期结果：
# for loop
for( i in ( seq_len( nrow(foo)-1 ) + 1 ) ) {
if( i <= 2L ) {
foo$Un_dt_1[i] <- foo$Un[i-1] * 3.6 +
3.6 * ( 1.765 + ( 1.765 - 1.04 ) *
foo$Un[1] * 3.6 / 80 ) * 1
foo$Un_dt_2[i] <- 3.6 * ( foo$sn_minus_Ln[i-1] - 4.4 ) / 1
} else {
foo$Un_dt_1[i] <- foo$Un_dt[i-1] +
3.6 * ( 1.765 + ( 1.765 - 1.04 ) *
foo$Un_dt[i-1] / 80 ) * 1
foo$Un_dt_2[i] <- 3.6 * ( foo$pred_sn_minus_Ln[i-1] - 4.4 ) / 1
}
foo$Un_dt[i] <- pmin( foo$Un_dt_1[i], foo$Un_dt_2[i] )
if( i <= 2 ) {
foo$pred_Local.Y[i] <- foo$Local.Y[i-1] +
0.5 * ( ( foo$Un_dt[i] + foo$Un[i-1] ) / 3.6 ) * 1
} else {
foo$pred_Local.Y[i] <- foo$pred_Local.Y[i-1] +
0.5 * ( ( foo$Un_dt[i] + foo$Un_dt[i-1] ) / 3.6 ) * 1
}
foo$pred_sn_minus_Ln[i] <- foo$PrecVehLocalY[i] - foo$pred_Local.Y[i] - foo$Ln[i]
}
# results
structure(list(Local.Y = c(50.71994, 60.37412, 69.99005, 78.60745
), Un = c(9.48762, 9.93521, 8.9674, 8.33772), PrecVehLocalY = c(70.19624,
78.50749, 86.49717, 93.4731), Ln = c(3.9019, 3.9019, 3.9019,
3.9019), sn_minus_Ln = c(15.5744, 14.23147, 12.60522, 10.96375
), Vehicle.ID2 = c("1-2", "1-2", "1-2", "1-2"), Un_dt_1 = c(NA,
41.623752969, 47.89427328, 53.12221615125), Un_dt_2 = c(NA, 40.22784,
45.29061, 31.294233), Un_dt = c(NA, 40.22784, 45.29061, 31.294233
), pred_Local.Y = c(NA, 57.624865, 69.5024275, 80.13921125),
pred_sn_minus_Ln = c(NA, 16.980725, 13.0928425, 9.43198875
)), .Names = c("Local.Y", "Un", "PrecVehLocalY", "Ln", "sn_minus_Ln",
"Vehicle.ID2", "Un_dt_1", "Un_dt_2", "Un_dt", "pred_Local.Y",
"pred_sn_minus_Ln"), row.names = c(NA, 4L), class = "data.frame")
由于原始数据框有很多Vehicle.ID2 s，我想在函数内部使用此for-loop，然后将该函数应用于由Vehicle.ID2分割的所有数据组。
我尝试使用purrr包。
f1 <- function(df){
for( i in ( seq_len( nrow(df)-1 ) + 1 ) ) {
if( i <= 2L ) {
df$Un_dt_1[i] <- df$Un[i-1] * 3.6 +
3.6 * ( 1.765 + ( 1.765 - 1.04 ) *
df$Un[1] * 3.6 / 80 ) * 1
df$Un_dt_2[i] <- 3.6 * ( df$sn_minus_Ln[i-1] - 4.4 ) / 1
} else {
df$Un_dt_1[i] <- df$Un_dt[i-1] +
3.6 * ( 1.765 + ( 1.765 - 1.04 ) *
df$Un_dt[i-1] / 80 ) * 1
df$Un_dt_2[i] <- 3.6 * ( df$pred_sn_minus_Ln[i-1] - 4.4 ) / 1
}
df$Un_dt[i] <- pmin( df$Un_dt_1[i], df$Un_dt_2[i] )
if( i <= 2 ) {
df$pred_Local.Y[i] <- df$Local.Y[i-1] +
0.5 * ( ( df$Un_dt[i] + df$Un[i-1] ) / 3.6 ) * 1
} else {
df$pred_Local.Y[i] <- df$pred_Local.Y[i-1] +
0.5 * ( ( df$Un_dt[i] + df$Un_dt[i-1] ) / 3.6 ) * 1
}
df$pred_sn_minus_Ln[i] <- df$PrecVehLocalY[i] - df$pred_Local.Y[i] - df$Ln[i]
}
}
library(purrr)
foor <- split(foo, foo$Vehicle.ID2)
> map(foor, f1)
$`1-2`
NULL
为什么导致NULL？这是完全相同的功能。