我在从Google托管的存储桶中读取数据时遇到问题。 我有一个桶,包含我需要访问的~1000个文件,保存在(例如) gs:// my-bucket / data
使用命令行或其他Google Python客户端中的gsutil,我可以访问存储桶中的数据,但默认情况下,google-cloud-ml-engine不支持导入这些API。
我需要一种方法来访问数据和文件的名称,使用默认的python库(即os)或使用tensorflow。我知道tensorflow在某个地方内置了这个功能,我很难找到
理想情况下,我正在寻找一个命令的替换,例如os.listdir()和另一个命令,用于open()
#install.packages("dismo")
library(dismo)
#install.packages("scales")
library(scales)
#install.packages("rgdal")
library(rgdal)
#install.packages("rgeos")
library(rgeos)
#install.packages("rJava")
library(rJava)
#install.packages("foreach")
library(foreach)
#install.packages("doParallel")
library(doParallel)
#Colors to use in the plots
MyRbw2<-c('#f4f4f4','#3288bd','#66c2a5','#e6f598','#fee08b','#f46d43','#9e0142')
colfunc_myrbw2<-colorRampPalette(MyRbw2)
#Create empty lists to recieve outputs
xm_list<-list()
xm_spc_list<-list()
e_spc_list<-list()
px_spc_list<-list()
tr_spc_list<-list()
spc_pol1<-list()
spc_pol5<-list()
tr<-list()
#Create empty data frame to recieve treshold values for each species
tr_df<-data.frame(matrix(NA, nrow=92, ncol=7))
tr_df[,1]<-as.character(tree_list)
names(tr_df)<- c('spp',"kappa","spec_sens","no_omission","prevalence","equal_sens_spec","sensitivity")
# Assigning objects to run Maxent
data_points <- tree_cd_points # this is a list with SpatialPoints for 92 species
data_list <- tree_list # list with the species names
counts_data<- counts_tree_cd # number of points for each species
predictors2<-predictors_low # rasterStack of Bioclim layers (climatic variables), low resolution
#Stablishing extent for Maxent predictions
xmin=-120; xmax=-35; ymin2=-40; ymax=35
limits2 <- c(xmin, xmax, ymin2, ymax)
# Making the cluster for doParallel
cores<-detectCores() # I have 16
cl <- makeCluster(cores[1]-1) #not to overload your computer
registerDoParallel(cl)
#Just to keep track of time
ptime1 <- proc.time()
pdf("C:/Users/thai/Desktop/Ecologicos/w2/SpDistModel/SEM9/spp/treesp_maxent_20170823.pdf",
paper = "letter", height = 11, width=8,5, pointsize=12,pagecentre = TRUE)
#I have 92 species, but I'll run just the first 4 to test
foreach(i=1:4, .packages=c("dismo","scales","rgdal","rgeos","rJava")) %dopar% { #Runs only species with 5 or more points to avoid maxent problems
if (counts_data$n[i]>4) { #If the species has more than 4 occurrence points, run maxent
tryCatch({ #makes the loop go on despite errors
#Sets train, test and total points for Maxent
group <- kfold(x=data_points[[i]], 5)
pres_train<- data_points[[i]][group != 1, ]
pres_test <- data_points[[i]][group == 1, ]
spoints<- data_points[[i]]
#Sets background points for Maxent
backg <- randomPoints(predictors2, n=20000, ext=limits2, extf = 1.25)
colnames(backg) = c('lon', 'lat')
group <- kfold(backg, 5)
backg_train <- backg[group != 1, ]
backg_test <- backg[group == 1, ]
#The maxent itself (put the xm in the empty list that I created earlier to store all xms)
xm_spc_list[[i]] <- maxent(x=predictors2, p=spoints, a=backg ,
factors='ecoreg',
args=c('visible=true',
'betamultiplier=1',
'randomtestpoints=20',
'randomseed=true',
'linear=true',
'quadratic=true',
'product=true',
'hinge=true',
'threads=4',
'responsecurves=true',
'jackknife=true',
'removeduplicates=false',
'extrapolate=true',
'pictures=true',
'cache=true',
'maximumiterations=5000',
'askoverwrite=false'),
path=paste0("C:/Users/thai/Desktop/Ecologicos/w2/SpDistModel/SEM9/spp/xm/",data_list[i]), overwrite=TRUE)
par(mfrow=c(1,1),mar = c(2,2, 2, 2))
plot(xm_spc_list[[i]], main=paste(data_list[i]))
response(xm_spc_list[[i]])
#Evaluating how good is the model and putting the evaluation values in a list
e_spc_list[[i]] <- evaluate(pres_test, backg_test, xm_spc_list[[i]], predictors2)
#Predicting the climatic envelopes and Sending to a list os predictions
px_spc_list[[i]] <- predict(predictors2, xm_spc_list[[i]], ext=limits2, progress='text',
filename=paste0("C:/Users/thai/Desktop/Ecologicos/w2/SpDistModel/SEM9/spp/xm/",data_list[i],"/",gsub('\\s+', '_', data_list[i]),"_pred.grd"), overwrite=TRUE)
tr_df[i,2:7]<-threshold(e_spc_list[[i]])
tr[[i]]<-threshold(e_spc_list[[i]], 'spec_sens')
#Pol 1 will be the regular polygon, default treshold
spc_pol1[[i]] <- rasterToPolygons(px_spc_list[[i]]>tr[[i]],function(x) x == 1,dissolve=T)
writeOGR(obj = spc_pol1[[i]], dsn = paste0("C:/Users/thai/Desktop/Ecologicos/w2/SpDistModel/SEM9/spp/xm1/",data_list[i]), driver = "ESRI Shapefile",
layer = paste0(gsub('\\s+', '_', data_list[i]),"_pol"), overwrite_layer = TRUE )
#Pol 5 will be a 100km^2 circle around the occurrence points
circ <- circles(spoints, d=5642,lonlat=TRUE)
circ <- circ@polygons
crs(circ)<-crs(wrld_cropped)
circ <- gIntersection(wrld_cropped, circ, byid = TRUE, drop_lower_td = TRUE)
#To write de polygon to a file, the function writeOGR needs an object SPDF, so...
#Getting Polygon IDs
circ_df<- as.data.frame(sapply(slot(circ, "polygons"), function(x) slot(x, "ID")))
#Making the IDs row names
row.names(circ_df) <- sapply(slot(circ, "polygons"), function(x) slot(x, "ID"))
# Make spatial polygon data frame
circ_SPDF <- SpatialPolygonsDataFrame(circ, data =circ_df)
#Save the polygon, finally
writeOGR(obj = circ_SPDF, dsn = paste0("C:/Users/thai/Desktop/Ecologicos/w2/SpDistModel/SEM9/spp/xm5/",data_list[i]), driver = "ESRI Shapefile",
layer = paste0(gsub('\\s+', '_', data_list[i]),"_pol"), overwrite_layer = TRUE )
spc_pol5[[i]]<-circ_SPDF
#Now the plots
par(mfrow=c(2,3),mar = c(2,1, 1, 1))
plot(px_spc_list[[i]], axes=FALSE, legend=TRUE, legend.shrink=1, col=colfunc_myrbw2(20), main=paste((data_list[i]),' - Maxent'))
plot(wrld_cropped,add=TRUE, border='dark grey',axes=FALSE)
points(data_points[[i]], pch=21,col="white", bg='hotpink', lwd=0.5, cex=0.7)
plot(wrld_cropped, border='dark grey', col="#f9f9f9",axes=FALSE, main='px>tr')
plot(spc_pol1[[i]] , main=paste((data_list[i]),' - Range'), add=TRUE, col=alpha("green3",0.8),border=alpha("green3",0.8),axes=FALSE)
points(data_points[[i]], pch="°",col="black", cex=0.7)
plot(wrld_cropped, border='dark grey', col="#f9f9f9",axes=FALSE, main=paste(data_list[i],"circles"))
plot(circ, add=TRUE, col=alpha("green3",0.8),border=alpha("green3",0.8) )
}, error=function(e){cat("Warning message:",conditionMessage(e), "\n")})
#But sometimes, even with >4 occurrence points, Maxent fails...
#So I'll make sure that if I have >4 points but maxent didn't work, I get the circles anyway
f<-paste("C:/Users/thai/Desktop/Ecologicos/w2/SpDistModel/SEM9/spp/xm/",data_list[i],"/",gsub('\\s+', '_', data_list[i]),"_pred.grd", sep="")
gc() #Just collecting garbage to speed up the process
if (!file.exists(f)){ # then, if f (maxent output) doesn't exist, create the circles at least
spoints<- data_points[[i]]
circ <- circles(spoints, d=5642,lonlat=TRUE)
circ <- circ@polygons
crs(circ)<-crs(wrld_cropped)
circ <- gIntersection(wrld_cropped, circ, byid = TRUE, drop_lower_td = TRUE)
#To write de polygon to a file, the function writeOGR needs an object SPDF, so...
#Getting Polygon IDs
circ_df<- as.data.frame(sapply(slot(circ, "polygons"), function(x) slot(x, "ID")))
#Making the IDs row names
row.names(circ_df) <- sapply(slot(circ, "polygons"), function(x) slot(x, "ID"))
# Make spatial polygon data frame
circ_SPDF <- SpatialPolygonsDataFrame(circ, data =circ_df)
#Save the polygon, finally
#dir.create(paste("C:/Users/thai/Desktop/Ecologicos/w2/SpDistModel/SEM9/spp/xm5/",data_list[i],sep=""))
writeOGR(obj = circ_SPDF, dsn = paste0("C:/Users/thai/Desktop/Ecologicos/w2/SpDistModel/SEM9/spp/xm5/",data_list[i],sep=""), driver = "ESRI Shapefile",
layer = paste0(gsub('\\s+', '_', data_list[i]),"_pol"), overwrite_layer = TRUE )
spc_pol5[[i]]<-circ_SPDF
plot(wrld_cropped, border='dark grey', col="#f9f9f9",axes=FALSE, main=data_list[i])
plot(circ, add=TRUE, col=alpha("green3",0.8),border=alpha("green3",0.8) )
#plot(spoints,pch=21,col="white", bg='hotpink', lwd=0.1, cex=0.5, add=TRUE)
}
} else { #If the species does not have more than 4 points,
#do not run maxent, but create a circles polygon
spoints<- data_points[[i]]
#For the circle to have 100km2, d should be 5641.9 ...
circ <- circles(spoints, d=5642,lonlat=TRUE)
circ <- circ@polygons
crs(circ)<-crs(wrld_cropped)
circ <- gIntersection(wrld_cropped, circ, byid = TRUE, drop_lower_td = TRUE)
circ_df<- as.data.frame(sapply(slot(circ, "polygons"), function(x) slot(x, "ID")))
row.names(circ_df) <- sapply(slot(circ, "polygons"), function(x) slot(x, "ID"))
circ_SPDF <- SpatialPolygonsDataFrame(circ, data =circ_df)
writeOGR(obj = circ_SPDF, dsn = paste0("C:/Users/thai/Desktop/Ecologicos/w2/SpDistModel/SEM9/spp/xm5/",data_list[i],sep=""), driver = "ESRI Shapefile",
layer = paste0(gsub('\\s+', '_', data_list[i]),"_pol"), overwrite_layer = TRUE )
par(mfrow=c(1,1),mar = c(2,2, 2, 2))
plot(wrld_cropped, border='dark grey', col="#f9f9f9",axes=FALSE, main=data_list[i])
plot(circ, add=TRUE, col=alpha("green3",0.8),border=alpha("green3",0.8) )
spc_pol5[[i]]<-circ_SPDF
gc() #collecting garbage before a nuw run
}
}
dev.off()
dev.off() #to close that pdf I started before the loop
ptime2<- proc.time() - ptime1 #just checking the time
ptime2
read_training_data使用张量流读取器对象
感谢您的帮助! (还有p.s.我的数据是二进制的)
答案 0 :(得分:3)
如果您只想将数据读入内存,那么this answer会提供您需要的详细信息,即使用file_io模块。
也就是说,您可能需要考虑使用TensorFlow的内置读取机制,因为它们可以更高效。
可以找到有关阅读的信息here。最新且最伟大的(但尚未成为官方&#34;核心&#34; TensorFlow的一部分)是数据集API(更多信息here)。
要记住的一些事情:
如果对一个或多个问题的回答是肯定的,尤其是后两个问题,请考虑使用读者。
答案 1 :(得分:1)
价值多少。我在读取文件时也遇到了问题,特别是从datalab笔记本中的Google云存储中读取二进制文件时。我设法做到的第一种方法是使用gs-utils将文件复制到本地文件系统,然后使用tensorflow正常读取文件。文件复制完成后,将在此处进行演示。
这是我的设置单元格
import math
import shutil
import numpy as np
import pandas as pd
import tensorflow as tf
tf.logging.set_verbosity(tf.logging.INFO)
pd.options.display.max_rows = 10
pd.options.display.float_format = '{:.1f}'.format
这是一个用于在本地读取文件以进行完整性检查的单元格。
# this works for reading local file
audio_binary_local = tf.read_file("100852.mp3")
waveform = tf.contrib.ffmpeg.decode_audio(audio_binary_local, file_format='mp3',
samples_per_second=44100, channel_count=2)
# this will show that it has two channels of data
with tf.Session() as sess:
result = sess.run(waveform)
print (result)
这里是直接从gs:文件中读取二进制文件。
# this works for remote files in gs:
gsfilename = 'gs://proj-getting-started/UrbanSound/data/air_conditioner/100852.mp3'
# python 2
#audio_binary_remote = tf.gfile.Open(gsfilename).read()
# python 3
audio_binary_remote = tf.gfile.Open(gsfilename, 'rb').read()
waveform = tf.contrib.ffmpeg.decode_audio(audio_binary_remote, file_format='mp3', samples_per_second=44100, channel_count=2)
# this will show that it has two channels of data
with tf.Session() as sess:
result = sess.run(waveform)
print (result)