mirror of
https://github.com/saymrwulf/prophet.git
synced 2026-11-18 08:53:42 +00:00
Improved execution time of rolling_mean_by_h (#2142)
This commit is contained in:
parent
a2c102cbae
commit
e665430adc
2 changed files with 58 additions and 51 deletions
|
|
@ -347,38 +347,45 @@ rolling_mean_by_h <- function(x, h, w, name) {
|
||||||
df <- data.frame(x=x, h=h)
|
df <- data.frame(x=x, h=h)
|
||||||
df2 <- df %>%
|
df2 <- df %>%
|
||||||
dplyr::group_by(h) %>%
|
dplyr::group_by(h) %>%
|
||||||
dplyr::summarise(mean = mean(x), n = dplyr::n())
|
dplyr::summarise(sum = sum(x), n = dplyr::n())
|
||||||
|
|
||||||
xm <- df2$mean
|
xs <- df2$sum
|
||||||
ns <- df2$n
|
ns <- df2$n
|
||||||
hs <- df2$h
|
hs <- df2$h
|
||||||
|
|
||||||
res <- data.frame(horizon=c())
|
trailing_i <- length(hs)
|
||||||
res[[name]] <- c()
|
x_sum <- 0
|
||||||
|
n_sum <- 0
|
||||||
|
# We don't know output size but it is bounded by length(hs)
|
||||||
|
res_x <- vector("double", length=length(hs))
|
||||||
|
|
||||||
# Start from the right and work backwards
|
# Start from the right and work backwards
|
||||||
i <- length(hs)
|
for(i in length(hs):1) {
|
||||||
while (i > 0) {
|
x_sum <- x_sum + xs[i]
|
||||||
# Construct a mean of at least w samples
|
n_sum <- n_sum + ns[i]
|
||||||
n <- ns[i]
|
while (n_sum >= w) {
|
||||||
xbar <- xm[i]
|
# Include points from the previous horizon. All of them if still
|
||||||
j <- i - 1
|
# less than w, otherwise weight the mean by the difference
|
||||||
while ((n < w) & (j > 0)) {
|
excess_n <- n_sum - w
|
||||||
# Include points from the previous horizon. All of them if still less
|
excess_x <- excess_n * xs[i]/ ns[i]
|
||||||
# than w, otherwise just enough to get to w.
|
res_x[trailing_i] <- (x_sum - excess_x) / w
|
||||||
n2 <- min(w - n, ns[j])
|
x_sum <- x_sum - xs[trailing_i]
|
||||||
xbar <- xbar * (n / (n + n2)) + xm[j] * (n2 / (n + n2))
|
n_sum <- n_sum - ns[trailing_i]
|
||||||
n <- n + n2
|
trailing_i <- trailing_i - 1
|
||||||
j <- j - 1
|
|
||||||
}
|
}
|
||||||
if (n < w) {
|
|
||||||
# Ran out of horizons before enough points.
|
|
||||||
break
|
|
||||||
}
|
|
||||||
res.i <- data.frame(horizon=hs[i])
|
|
||||||
res.i[[name]] <- xbar
|
|
||||||
res <- rbind(res.i, res)
|
|
||||||
i <- i - 1
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
# R handles subsetting weirdly
|
||||||
|
if(trailing_i == 0) {
|
||||||
|
res_h <- hs
|
||||||
|
} else {
|
||||||
|
res_h <- hs[-(1:trailing_i)]
|
||||||
|
res_x <- res_x[-(1:trailing_i)]
|
||||||
|
}
|
||||||
|
|
||||||
|
res <- data.frame(horizon=res_h)
|
||||||
|
res[[name]] <- res_x
|
||||||
|
|
||||||
return(res)
|
return(res)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -420,39 +420,39 @@ def rolling_mean_by_h(x, h, w, name):
|
||||||
# Aggregate over h
|
# Aggregate over h
|
||||||
df = pd.DataFrame({'x': x, 'h': h})
|
df = pd.DataFrame({'x': x, 'h': h})
|
||||||
df2 = (
|
df2 = (
|
||||||
df.groupby('h').agg(['mean', 'count']).reset_index().sort_values('h')
|
df.groupby('h').agg(['sum', 'count']).reset_index().sort_values('h')
|
||||||
)
|
)
|
||||||
xm = df2['x']['mean'].values
|
xs = df2['x']['sum'].values
|
||||||
ns = df2['x']['count'].values
|
ns = df2['x']['count'].values
|
||||||
hs = df2['h'].values
|
hs = df2.h.values
|
||||||
|
|
||||||
|
trailing_i = len(df2) - 1
|
||||||
|
x_sum = 0
|
||||||
|
n_sum = 0
|
||||||
|
# We don't know output size but it is bounded by len(df2)
|
||||||
|
res_x = np.empty(len(df2))
|
||||||
|
|
||||||
res_h = []
|
|
||||||
res_x = []
|
|
||||||
# Start from the right and work backwards
|
# Start from the right and work backwards
|
||||||
i = len(hs) - 1
|
for i in range(len(df2) - 1, -1, -1):
|
||||||
while i >= 0:
|
x_sum += xs[i]
|
||||||
# Construct a mean of at least w samples.
|
n_sum += ns[i]
|
||||||
n = int(ns[i])
|
while n_sum >= w:
|
||||||
xbar = float(xm[i])
|
|
||||||
j = i - 1
|
|
||||||
while ((n < w) and j >= 0):
|
|
||||||
# Include points from the previous horizon. All of them if still
|
# Include points from the previous horizon. All of them if still
|
||||||
# less than w, otherwise just enough to get to w.
|
# less than w, otherwise weight the mean by the difference
|
||||||
n2 = min(w - n, ns[j])
|
excess_n = n_sum - w
|
||||||
xbar = xbar * (n / (n + n2)) + xm[j] * (n2 / (n + n2))
|
excess_x = excess_n * xs[i] / ns[i]
|
||||||
n += n2
|
res_x[trailing_i] = (x_sum - excess_x)/ w
|
||||||
j -= 1
|
x_sum -= xs[trailing_i]
|
||||||
if n < w:
|
n_sum -= ns[trailing_i]
|
||||||
# Ran out of horizons before enough points.
|
trailing_i -= 1
|
||||||
break
|
|
||||||
res_h.append(hs[i])
|
res_h = hs[(trailing_i + 1):]
|
||||||
res_x.append(xbar)
|
res_x = res_x[(trailing_i + 1):]
|
||||||
i -= 1
|
|
||||||
res_h.reverse()
|
|
||||||
res_x.reverse()
|
|
||||||
return pd.DataFrame({'horizon': res_h, name: res_x})
|
return pd.DataFrame({'horizon': res_h, name: res_x})
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
def rolling_median_by_h(x, h, w, name):
|
def rolling_median_by_h(x, h, w, name):
|
||||||
"""Compute a rolling median of x, after first aggregating by h.
|
"""Compute a rolling median of x, after first aggregating by h.
|
||||||
|
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue