运行 多个geojson文件分析
Running Analysis on Multiple geojson files
我以前主要在QGIS中处理过大约113个geojson文件。我现在的目标是能够同时将所有文件导入 R 并对附加到每个相应层的基础属性表进行分析。我已经找到了导入一个文件并在转换为数据框后进行任何所需分析的最佳方法。我在文件夹中的文件都是这样的：0cfb16c1-90c2-412d-bb60-2fec34c75e9a.geojson
我在这一步中使用的代码是：
library(rgdal)
map1 <- readOGR(dsn = "/Users/chris/Documents/GeorgetownMPPMSFS/McCourtMPP/BIGWork/BIGDataFiles/maps/sampled_maps/0cfb16c1-90c2-412d-bb60-2fec34c75e9a.geojson", layer = "0cfb16c1-90c2-412d-bb60-2fec34c75e9a")
summary(map1)
map1 <- as.data.frame(map1)
我想 运行 在所有 geojson 文件的地图上进行相同的分析，而不必一一分析。我进行的与选举重新划分指标相关的分析包含在此处：
cfbdata$reptotal <- (cfbdata$surveyed_republican_percentage/100)*cfbdata$surveyed_total
cfbdata$demtotal <- (cfbdata$surveyed_democrat_percentage/100)*cfbdata$surveyed_total
cfbdata$NAME <- NULL
aggdata <-aggregate(cfbdata, by=list(cfbdata$cluster),
FUN=sum, na.rm=TRUE)
# Rep district victory is 1 and Dem district victory is 0
aggdata$result <- ifelse(aggdata$reptotal > aggdata$demtotal,1, ifelse(aggdata$demtotal > aggdata$reptotal,0, NA))
EffGapCalc <- subset(aggdata, select=c("cluster","reptotal","demtotal","surveyed_total", "result"))
# Step 1: Calculate Dem Wasted, Rep Wasted, and Net Wasted
EffGapCalc$repwasted <- ifelse(EffGapCalc$result == 1, EffGapCalc$reptotal - (.51*EffGapCalc$surveyed_total), ifelse(EffGapCalc$result == 0, EffGapCalc$reptotal, NA))
EffGapCalc$demwasted <- ifelse(EffGapCalc$result == 0, EffGapCalc$demtotal - (.51 * EffGapCalc$surveyed_total), ifelse(EffGapCalc$result == 1, EffGapCalc$demtotal, NA))
EffGapCalc$netwasted <- abs(EffGapCalc$repwasted - EffGapCalc$demwasted)
# Step 2: Sum Total Wasted Rep and Dem Votes
totrepwasted <- sum(EffGapCalc$repwasted)
totdemwasted <- sum(EffGapCalc$demwasted)
netwaste <- ifelse(totrepwasted>totdemwasted, totrepwasted-totdemwasted, ifelse(totrepwasted<totdemwasted, totdemwasted-totrepwasted))
netwaste
# Democrats had a net waste (more wasted votes) of 74289.6
# Step 3: Divide Net Wasted by Total Number of Votes Case
sum(EffGapCalc$surveyed_total)
totalsurvtot <- sum(EffGapCalc$surveyed_total)
netwaste/totalsurvtot
# Efficiency Gap = .0359 [3.60%]
目标是 运行 对所有 113 个 GEOJSON 文件进行相同的分析，并获得 113 "Efficiency Gap" 个数字的列表，如上面的 .0359。
我在 Whosebug 和其他地方搜索了很多问题，但没有找到合适的解决方案。虽然我最初认为 for 循环最适合这个，但根据我在其他地方读到的内容，看来 lapply() 实际上可能是更好的选择。我面临的挑战是确保作为 'lapply()'
的一部分正确导入
我尝试使用但失败的代码是：
library(rgdal)
fileNames <- list.files(path = "/Users/chris/Documents/GeorgetownMPPMSFS/McCourtMPP/BIGWork/BIGDataFiles/maps/sampled_maps", pattern="*.geojson", full.names = TRUE)
lapply(fileNames, function(x) {
map1 <- readOGR(dsn = x, layer = x)
map1 <- as.data.frame(map1)
out <- map1$reptotal <- (map1$surveyed_republican_percentage/100)*map1$surveyed_total;
map1$demtotal <- (map1$surveyed_democrat_percentage/100)*map1$surveyed_total;
map1$NAME <- NULL;
aggdata <-aggregate(map1, by=list(map1$cluster),
FUN=sum, na.rm=TRUE);
aggdata$result <- ifelse(aggdata$reptotal > aggdata$demtotal,1, ifelse(aggdata$demtotal > aggdata$reptotal,0, NA));
EffGapCalc <- subset(aggdata, select=c("cluster","reptotal","demtotal","surveyed_total", "result"));
# Step 1: Calculate Dem Wasted, Rep Wasted, and Net Wasted
EffGapCalc$repwasted <- ifelse(EffGapCalc$result == 1, EffGapCalc$reptotal - (.51*EffGapCalc$surveyed_total), ifelse(EffGapCalc$result == 0, EffGapCalc$reptotal, NA));
EffGapCalc$demwasted <- ifelse(EffGapCalc$result == 0, EffGapCalc$demtotal - (.51 * EffGapCalc$surveyed_total), ifelse(EffGapCalc$result == 1, EffGapCalc$demtotal, NA));
EffGapCalc$netwasted <- abs(EffGapCalc$repwasted - EffGapCalc$demwasted);
# Step 2: Sum Total Wasted Rep and Dem Votes
totrepwasted <- sum(EffGapCalc$repwasted);
totdemwasted <- sum(EffGapCalc$demwasted);
netwaste <- ifelse(totrepwasted>totdemwasted, totrepwasted-totdemwasted, ifelse(totrepwasted<totdemwasted, totdemwasted-totrepwasted));
netwaste
# Step 3: Divide Net Wasted by Total Number of Votes Case
totalsurvtot <- sum(EffGapCalc$surveyed_total);
netwaste/totalsurvtot;
write.table(out, "/Users/chris/Documents/GeorgetownMPPMSFS/McCourtMPP/BIGWork/BIGDataFiles", sep="\t", quote=F, row.names=F, col.names=T)
})
这两天我一直在努力弄明白这一点，只是越来越困惑了。任何帮助将不胜感激！
简单测试代码：
lapply(fileNames, function(x) {
map1 <- readOGR(dsn = x, layer = x)
}
假设你的情况失败了，我们知道问题出在这一行。这使得这里的人更容易看到它是一个更简单的问题。请始终尽量减少您的问题，这将帮助我们帮助您，并且在许多情况下，它可以让您自己解决。进行中...
readOGR 对于 geoJSON 需要一个文件路径和一个层名称，并且该代码将把文件路径作为层名称提供，就像这样，使用来自 [=18= 的测试文件] 包::
> testfile <- list.files(path = path, pattern="*.geojson", full.names = TRUE)[5]
快速检查我们已经得到它：
> file.exists(testfile)
[1] TRUE
然后尝试阅读：
> d = readOGR(dsn=testfile, layer=testfile)
Error in ogrInfo(dsn = dsn, layer = layer, encoding = encoding, use_iconv = use_iconv, :
Cannot open layer
那么我们如何从文件路径中获取图层名称呢？为此，我们有 ogrListLayers：
> ogrListLayers(testfile)
[1] "OGRGeoJSON"
attr(,"driver")
[1] "GeoJSON"
attr(,"nlayers")
[1] 1
现在看起来很奇怪，但它是一个图层名称向量和一些您可以为此忽略的额外属性。本次测试图层的图层名称为"OGRGeoJSON"。假设您的 geoJSON 已知只有一层，您可以这样做：
> d = readOGR(dsn=testfile, layer=ogrListLayers(testfile))
OGR data source with driver: GeoJSON
Source: "/home/rowlings/R/x86_64-pc-linux-gnu-library/3.4/geojson/examples/linestring_one.geojson", layer: "OGRGeoJSON"
with 1 features
It has 2 fields
Warning message:
In readOGR(dsn = testfile, layer = ogrListLayers(testfile)) :
Z-dimension discarded
现在我认为要么 geoJSON 只能有一层，要么 readOGR 默认为第一层，所以如果你知道你的 geoJSON 中只有一层，你可以 省去 layer= 参数并返回相同的对象：
> d2 = readOGR(dsn=testfile)
OGR data source with driver: GeoJSON
Source: "/home/rowlings/R/x86_64-pc-linux-gnu-library/3.4/geojson/examples/linestring_one.geojson", layer: "OGRGeoJSON"
with 1 features
It has 2 fields
Warning message:
In readOGR(dsn = testfile) : Z-dimension discarded
我以前主要在QGIS中处理过大约113个geojson文件。我现在的目标是能够同时将所有文件导入 R 并对附加到每个相应层的基础属性表进行分析。我已经找到了导入一个文件并在转换为数据框后进行任何所需分析的最佳方法。我在文件夹中的文件都是这样的：0cfb16c1-90c2-412d-bb60-2fec34c75e9a.geojson
我在这一步中使用的代码是：
library(rgdal)
map1 <- readOGR(dsn = "/Users/chris/Documents/GeorgetownMPPMSFS/McCourtMPP/BIGWork/BIGDataFiles/maps/sampled_maps/0cfb16c1-90c2-412d-bb60-2fec34c75e9a.geojson", layer = "0cfb16c1-90c2-412d-bb60-2fec34c75e9a")
summary(map1)
map1 <- as.data.frame(map1)
我想 运行 在所有 geojson 文件的地图上进行相同的分析，而不必一一分析。我进行的与选举重新划分指标相关的分析包含在此处：
cfbdata$reptotal <- (cfbdata$surveyed_republican_percentage/100)*cfbdata$surveyed_total
cfbdata$demtotal <- (cfbdata$surveyed_democrat_percentage/100)*cfbdata$surveyed_total
cfbdata$NAME <- NULL
aggdata <-aggregate(cfbdata, by=list(cfbdata$cluster),
FUN=sum, na.rm=TRUE)
# Rep district victory is 1 and Dem district victory is 0
aggdata$result <- ifelse(aggdata$reptotal > aggdata$demtotal,1, ifelse(aggdata$demtotal > aggdata$reptotal,0, NA))
EffGapCalc <- subset(aggdata, select=c("cluster","reptotal","demtotal","surveyed_total", "result"))
# Step 1: Calculate Dem Wasted, Rep Wasted, and Net Wasted
EffGapCalc$repwasted <- ifelse(EffGapCalc$result == 1, EffGapCalc$reptotal - (.51*EffGapCalc$surveyed_total), ifelse(EffGapCalc$result == 0, EffGapCalc$reptotal, NA))
EffGapCalc$demwasted <- ifelse(EffGapCalc$result == 0, EffGapCalc$demtotal - (.51 * EffGapCalc$surveyed_total), ifelse(EffGapCalc$result == 1, EffGapCalc$demtotal, NA))
EffGapCalc$netwasted <- abs(EffGapCalc$repwasted - EffGapCalc$demwasted)
# Step 2: Sum Total Wasted Rep and Dem Votes
totrepwasted <- sum(EffGapCalc$repwasted)
totdemwasted <- sum(EffGapCalc$demwasted)
netwaste <- ifelse(totrepwasted>totdemwasted, totrepwasted-totdemwasted, ifelse(totrepwasted<totdemwasted, totdemwasted-totrepwasted))
netwaste
# Democrats had a net waste (more wasted votes) of 74289.6
# Step 3: Divide Net Wasted by Total Number of Votes Case
sum(EffGapCalc$surveyed_total)
totalsurvtot <- sum(EffGapCalc$surveyed_total)
netwaste/totalsurvtot
# Efficiency Gap = .0359 [3.60%]
目标是 运行 对所有 113 个 GEOJSON 文件进行相同的分析，并获得 113 "Efficiency Gap" 个数字的列表，如上面的 .0359。
我在 Whosebug 和其他地方搜索了很多问题，但没有找到合适的解决方案。虽然我最初认为 for 循环最适合这个，但根据我在其他地方读到的内容，看来 lapply() 实际上可能是更好的选择。我面临的挑战是确保作为 'lapply()'
我尝试使用但失败的代码是：
library(rgdal)
fileNames <- list.files(path = "/Users/chris/Documents/GeorgetownMPPMSFS/McCourtMPP/BIGWork/BIGDataFiles/maps/sampled_maps", pattern="*.geojson", full.names = TRUE)
lapply(fileNames, function(x) {
map1 <- readOGR(dsn = x, layer = x)
map1 <- as.data.frame(map1)
out <- map1$reptotal <- (map1$surveyed_republican_percentage/100)*map1$surveyed_total;
map1$demtotal <- (map1$surveyed_democrat_percentage/100)*map1$surveyed_total;
map1$NAME <- NULL;
aggdata <-aggregate(map1, by=list(map1$cluster),
FUN=sum, na.rm=TRUE);
aggdata$result <- ifelse(aggdata$reptotal > aggdata$demtotal,1, ifelse(aggdata$demtotal > aggdata$reptotal,0, NA));
EffGapCalc <- subset(aggdata, select=c("cluster","reptotal","demtotal","surveyed_total", "result"));
# Step 1: Calculate Dem Wasted, Rep Wasted, and Net Wasted
EffGapCalc$repwasted <- ifelse(EffGapCalc$result == 1, EffGapCalc$reptotal - (.51*EffGapCalc$surveyed_total), ifelse(EffGapCalc$result == 0, EffGapCalc$reptotal, NA));
EffGapCalc$demwasted <- ifelse(EffGapCalc$result == 0, EffGapCalc$demtotal - (.51 * EffGapCalc$surveyed_total), ifelse(EffGapCalc$result == 1, EffGapCalc$demtotal, NA));
EffGapCalc$netwasted <- abs(EffGapCalc$repwasted - EffGapCalc$demwasted);
# Step 2: Sum Total Wasted Rep and Dem Votes
totrepwasted <- sum(EffGapCalc$repwasted);
totdemwasted <- sum(EffGapCalc$demwasted);
netwaste <- ifelse(totrepwasted>totdemwasted, totrepwasted-totdemwasted, ifelse(totrepwasted<totdemwasted, totdemwasted-totrepwasted));
netwaste
# Step 3: Divide Net Wasted by Total Number of Votes Case
totalsurvtot <- sum(EffGapCalc$surveyed_total);
netwaste/totalsurvtot;
write.table(out, "/Users/chris/Documents/GeorgetownMPPMSFS/McCourtMPP/BIGWork/BIGDataFiles", sep="\t", quote=F, row.names=F, col.names=T)
})
这两天我一直在努力弄明白这一点，只是越来越困惑了。任何帮助将不胜感激！
简单测试代码：
lapply(fileNames, function(x) {
map1 <- readOGR(dsn = x, layer = x)
}
假设你的情况失败了，我们知道问题出在这一行。这使得这里的人更容易看到它是一个更简单的问题。请始终尽量减少您的问题，这将帮助我们帮助您，并且在许多情况下，它可以让您自己解决。进行中...
readOGR 对于 geoJSON 需要一个文件路径和一个层名称，并且该代码将把文件路径作为层名称提供，就像这样，使用来自 [=18= 的测试文件] 包::
> testfile <- list.files(path = path, pattern="*.geojson", full.names = TRUE)[5]
快速检查我们已经得到它：
> file.exists(testfile)
[1] TRUE
然后尝试阅读：
> d = readOGR(dsn=testfile, layer=testfile)
Error in ogrInfo(dsn = dsn, layer = layer, encoding = encoding, use_iconv = use_iconv, :
Cannot open layer
那么我们如何从文件路径中获取图层名称呢？为此，我们有 ogrListLayers：
> ogrListLayers(testfile)
[1] "OGRGeoJSON"
attr(,"driver")
[1] "GeoJSON"
attr(,"nlayers")
[1] 1
现在看起来很奇怪，但它是一个图层名称向量和一些您可以为此忽略的额外属性。本次测试图层的图层名称为"OGRGeoJSON"。假设您的 geoJSON 已知只有一层，您可以这样做：
> d = readOGR(dsn=testfile, layer=ogrListLayers(testfile))
OGR data source with driver: GeoJSON
Source: "/home/rowlings/R/x86_64-pc-linux-gnu-library/3.4/geojson/examples/linestring_one.geojson", layer: "OGRGeoJSON"
with 1 features
It has 2 fields
Warning message:
In readOGR(dsn = testfile, layer = ogrListLayers(testfile)) :
Z-dimension discarded
现在我认为要么 geoJSON 只能有一层，要么 readOGR 默认为第一层，所以如果你知道你的 geoJSON 中只有一层，你可以 省去 layer= 参数并返回相同的对象：
> d2 = readOGR(dsn=testfile)
OGR data source with driver: GeoJSON
Source: "/home/rowlings/R/x86_64-pc-linux-gnu-library/3.4/geojson/examples/linestring_one.geojson", layer: "OGRGeoJSON"
with 1 features
It has 2 fields
Warning message:
In readOGR(dsn = testfile) : Z-dimension discarded