如何在R中随机select区和该区的村庄？
How to randomly select districts and villages in that district in R?
我有一个数据集，其中包含有关地区代码和名称、该地区街区的代码和名称以及该街区内村庄的代码和名称的信息。
基于此，我想创建一个数据集，从该地区随机选择一个街区，并在该街区随机抽取10个村庄。
我已经尝试使用示例函数和 RandomizeR 包，但可以正常工作。
I样本数据集（df）：
structure(list(district_code = c(1701L, 1701L, 1701L, 1701L,
1701L, 1701L, 1701L, 1701L, 1701L, 1701L, 1701L, 1701L), district_name = c("morena",
"morena", "morena", "morena", "morena", "morena", "morena", "morena",
"morena", "morena", "morena", "morena"), block_code = c(1701001L,
1701001L, 1701001L, 1701001L, 1701001L, 1701001L, 1701001L, 1701001L,
1701001L, 1701001L, 1701001L, 1701001L), block_name = c("ambah",
"ambah", "ambah", "ambah", "ambah", "ambah", "ambah", "ambah",
"ambah", "ambah", "ambah", "ambah"), village_code = 1701001001:1701001012,
village_name = c("badfara", "bichola", "bhandauli", "lallubasai",
"kakarari", "rithona", "goonjh", "malbasai", "aroli", "khirenta",
"dandoli", "beelpur")), row.names = c(NA, 12L), class = "data.frame")
第二个样本 (df1)
structure(list(district_code = c(3424L, 3424L, 3424L, 3424L,
3424L, 3424L, 3424L, 3424L, 3401L, 3401L, 3401L, 3401L, 3401L,
3402L, 3402L, 3402L, 3402L, 3402L, 3402L, 3402L, 3402L), district_name = c("khunti",
"khunti", "khunti", "khunti", "khunti", "khunti", "khunti", "khunti",
"ranchi", "ranchi", "ranchi", "ranchi", "ranchi", "lohardaga",
"lohardaga", "lohardaga", "lohardaga", "lohardaga", "lohardaga",
"lohardaga", "lohardaga"), block_code = c(3401020L, 3401020L,
3401020L, 3401020L, 3401020L, 3401020L, 3401020L, 3401020L, 3401024L,
3401024L, 3401024L, 3401024L, 3401024L, 3402001L, 3402001L, 3402001L,
3402001L, 3402001L, 3402001L, 3402001L, 3402001L), block_name = c("torpa",
"torpa", "torpa", "torpa", "torpa", "torpa", "torpa", "torpa",
"khelari", "khelari", "khelari", "khelari", "khelari", "lohardaga",
"lohardaga", "lohardaga", "lohardaga", "lohardaga", "lohardaga",
"lohardaga", "lohardaga"), panchayat_code = c(3401020009, 3401020010,
3401020011, 3401020012, 3401020013, 3401020014, 3401020015, 3401020016,
3401024001, 3401024002, 3401024003, 3401024004, 3401024005, 3402001001,
3402001002, 3402001003, 3402001004, 3402001005, 3402001006, 3402001007,
3402001008), panchayat_name = c("marcha", "okra", "sundari",
"tapkara", "torpa east", "torpa west", "ukrimari", "urikela",
"churi east", "churi middle", "churi north", "churi south", "churi west",
"hesal", "hirhi", "manho", "jori", "nigni", "juriya", "harmu",
"rampur")), row.names = 379:399, class = "data.frame")
> dput(jk_subset[379:409,])
structure(list(district_code = c(3424L, 3424L, 3424L, 3424L,
3424L, 3424L, 3424L, 3424L, 3401L, 3401L, 3401L, 3401L, 3401L,
3402L, 3402L, 3402L, 3402L, 3402L, 3402L, 3402L, 3402L, 3402L,
3402L, 3402L, 3402L, 3402L, 3402L, 3402L, 3402L, 3402L, 3402L
), district_name = c("khunti", "khunti", "khunti", "khunti",
"khunti", "khunti", "khunti", "khunti", "ranchi", "ranchi", "ranchi",
"ranchi", "ranchi", "lohardaga", "lohardaga", "lohardaga", "lohardaga",
"lohardaga", "lohardaga", "lohardaga", "lohardaga", "lohardaga",
"lohardaga", "lohardaga", "lohardaga", "lohardaga", "lohardaga",
"lohardaga", "lohardaga", "lohardaga", "lohardaga"), block_code = c(3401020L,
3401020L, 3401020L, 3401020L, 3401020L, 3401020L, 3401020L, 3401020L,
3401024L, 3401024L, 3401024L, 3401024L, 3401024L, 3402001L, 3402001L,
3402001L, 3402001L, 3402001L, 3402001L, 3402001L, 3402001L, 3402001L,
3402001L, 3402001L, 3402006L, 3402001L, 3402007L, 3402007L, 3402007L,
3402002L, 3402002L), block_name = c("torpa", "torpa", "torpa",
"torpa", "torpa", "torpa", "torpa", "torpa", "khelari", "khelari",
"khelari", "khelari", "khelari", "lohardaga", "lohardaga", "lohardaga",
"lohardaga", "lohardaga", "lohardaga", "lohardaga", "lohardaga",
"lohardaga", "lohardaga", "lohardaga", "kairo", "lohardaga",
"peshrar", "peshrar", "peshrar", "kisko", "kisko"), village_code = c(3401020009,
3401020010, 3401020011, 3401020012, 3401020013, 3401020014, 3401020015,
3401020016, 3401024001, 3401024002, 3401024003, 3401024004, 3401024005,
3402001001, 3402001002, 3402001003, 3402001004, 3402001005, 3402001006,
3402001007, 3402001008, 3402001009, 3402001010, 3402001011, 3402001012,
3402001013, 3402002001, 3402002002, 3402002003, 3402002004, 3402002005
), village_name = c("marcha", "okra", "sundari", "tapkara",
"torpa east", "torpa west", "ukrimari", "urikela", "churi east",
"churi middle", "churi north", "churi south", "churi west", "hesal",
"hirhi", "manho", "jori", "nigni", "juriya", "harmu", "rampur",
"bagha", "arkosa", "tigra", "guri", "bhatdhijri", "siram", "peshrar",
"rorad", "devdaria", "pakhar")), row.names = 379:409, class = "data.frame")
使用代码后的数据集示例：
3404L, 3405L, 3406L, 3407L, 3408L, 3409L, 3410L, 3411L), district_name = c("khunti",
"ranchi", "lohardaga", "gumla", "simdega", "palamu", "latehar",
"garhwa", "west singhbhum", "saraikela kharsawan", "east singhbum",
"dumka"), block_code = c(3401009L, 3401013L, 3402005L, 3403009L,
3404002L, 3405018L, 3406006L, 3407009L, 3408005L, 3409006L, 3410005L,
3411009L), block_name = c("khunti", "namkum", "bhandra", "basia",
"bolba", "tarhasi", "garu", "bhandaria", "tantnagar", "ichagarh",
"musabani", "masaliya"), village_code = c(3401009002, 3401013020,
3402005002, 3403009008, 3404002002, 3405006012, 3406006008, 3407009002,
3408005001, 3409006012, 3410005011, 3411009001), village_name = c("bhandra",
"sithiyo", "bhandra", "mamarla", "kadopani", "manjhauli 2", "ghasitola",
"bhandaria", "angardiha", "dewaltand", "ichra (north)", "aamgachi"
)), row.names = c(NA, -12L), class = c("tbl_df", "tbl", "data.frame"
))
您的示例不适合提供解决方案，因为它只包含一个 district/block。
但你可以这样做：
df %>%
group_by(district_code) %>%
filter(block_code == ifelse(length(unique(block_code)) == 1, block_code, sample(unique(block_code), size = 1))) %>%
filter(village_code %in% ifelse(length(unique(village_code)) == 1, village_code, sample(unique(village_code), size = min(10, length(unique(village_code))), replace = FALSE))) %>%
ungroup()
注意：我不完全确定你想在哪个级别进行抽样，所以这里我 select 每个区一个街区，然后是那个街区的 10 个村庄。因此，您最终会从每个地区的随机 selected 区块中得到 10 个村庄。
我有一个数据集，其中包含有关地区代码和名称、该地区街区的代码和名称以及该街区内村庄的代码和名称的信息。
基于此，我想创建一个数据集，从该地区随机选择一个街区，并在该街区随机抽取10个村庄。
我已经尝试使用示例函数和 RandomizeR 包，但可以正常工作。
I样本数据集（df）：
structure(list(district_code = c(1701L, 1701L, 1701L, 1701L,
1701L, 1701L, 1701L, 1701L, 1701L, 1701L, 1701L, 1701L), district_name = c("morena",
"morena", "morena", "morena", "morena", "morena", "morena", "morena",
"morena", "morena", "morena", "morena"), block_code = c(1701001L,
1701001L, 1701001L, 1701001L, 1701001L, 1701001L, 1701001L, 1701001L,
1701001L, 1701001L, 1701001L, 1701001L), block_name = c("ambah",
"ambah", "ambah", "ambah", "ambah", "ambah", "ambah", "ambah",
"ambah", "ambah", "ambah", "ambah"), village_code = 1701001001:1701001012,
village_name = c("badfara", "bichola", "bhandauli", "lallubasai",
"kakarari", "rithona", "goonjh", "malbasai", "aroli", "khirenta",
"dandoli", "beelpur")), row.names = c(NA, 12L), class = "data.frame")
第二个样本 (df1)
structure(list(district_code = c(3424L, 3424L, 3424L, 3424L,
3424L, 3424L, 3424L, 3424L, 3401L, 3401L, 3401L, 3401L, 3401L,
3402L, 3402L, 3402L, 3402L, 3402L, 3402L, 3402L, 3402L), district_name = c("khunti",
"khunti", "khunti", "khunti", "khunti", "khunti", "khunti", "khunti",
"ranchi", "ranchi", "ranchi", "ranchi", "ranchi", "lohardaga",
"lohardaga", "lohardaga", "lohardaga", "lohardaga", "lohardaga",
"lohardaga", "lohardaga"), block_code = c(3401020L, 3401020L,
3401020L, 3401020L, 3401020L, 3401020L, 3401020L, 3401020L, 3401024L,
3401024L, 3401024L, 3401024L, 3401024L, 3402001L, 3402001L, 3402001L,
3402001L, 3402001L, 3402001L, 3402001L, 3402001L), block_name = c("torpa",
"torpa", "torpa", "torpa", "torpa", "torpa", "torpa", "torpa",
"khelari", "khelari", "khelari", "khelari", "khelari", "lohardaga",
"lohardaga", "lohardaga", "lohardaga", "lohardaga", "lohardaga",
"lohardaga", "lohardaga"), panchayat_code = c(3401020009, 3401020010,
3401020011, 3401020012, 3401020013, 3401020014, 3401020015, 3401020016,
3401024001, 3401024002, 3401024003, 3401024004, 3401024005, 3402001001,
3402001002, 3402001003, 3402001004, 3402001005, 3402001006, 3402001007,
3402001008), panchayat_name = c("marcha", "okra", "sundari",
"tapkara", "torpa east", "torpa west", "ukrimari", "urikela",
"churi east", "churi middle", "churi north", "churi south", "churi west",
"hesal", "hirhi", "manho", "jori", "nigni", "juriya", "harmu",
"rampur")), row.names = 379:399, class = "data.frame")
> dput(jk_subset[379:409,])
structure(list(district_code = c(3424L, 3424L, 3424L, 3424L,
3424L, 3424L, 3424L, 3424L, 3401L, 3401L, 3401L, 3401L, 3401L,
3402L, 3402L, 3402L, 3402L, 3402L, 3402L, 3402L, 3402L, 3402L,
3402L, 3402L, 3402L, 3402L, 3402L, 3402L, 3402L, 3402L, 3402L
), district_name = c("khunti", "khunti", "khunti", "khunti",
"khunti", "khunti", "khunti", "khunti", "ranchi", "ranchi", "ranchi",
"ranchi", "ranchi", "lohardaga", "lohardaga", "lohardaga", "lohardaga",
"lohardaga", "lohardaga", "lohardaga", "lohardaga", "lohardaga",
"lohardaga", "lohardaga", "lohardaga", "lohardaga", "lohardaga",
"lohardaga", "lohardaga", "lohardaga", "lohardaga"), block_code = c(3401020L,
3401020L, 3401020L, 3401020L, 3401020L, 3401020L, 3401020L, 3401020L,
3401024L, 3401024L, 3401024L, 3401024L, 3401024L, 3402001L, 3402001L,
3402001L, 3402001L, 3402001L, 3402001L, 3402001L, 3402001L, 3402001L,
3402001L, 3402001L, 3402006L, 3402001L, 3402007L, 3402007L, 3402007L,
3402002L, 3402002L), block_name = c("torpa", "torpa", "torpa",
"torpa", "torpa", "torpa", "torpa", "torpa", "khelari", "khelari",
"khelari", "khelari", "khelari", "lohardaga", "lohardaga", "lohardaga",
"lohardaga", "lohardaga", "lohardaga", "lohardaga", "lohardaga",
"lohardaga", "lohardaga", "lohardaga", "kairo", "lohardaga",
"peshrar", "peshrar", "peshrar", "kisko", "kisko"), village_code = c(3401020009,
3401020010, 3401020011, 3401020012, 3401020013, 3401020014, 3401020015,
3401020016, 3401024001, 3401024002, 3401024003, 3401024004, 3401024005,
3402001001, 3402001002, 3402001003, 3402001004, 3402001005, 3402001006,
3402001007, 3402001008, 3402001009, 3402001010, 3402001011, 3402001012,
3402001013, 3402002001, 3402002002, 3402002003, 3402002004, 3402002005
), village_name = c("marcha", "okra", "sundari", "tapkara",
"torpa east", "torpa west", "ukrimari", "urikela", "churi east",
"churi middle", "churi north", "churi south", "churi west", "hesal",
"hirhi", "manho", "jori", "nigni", "juriya", "harmu", "rampur",
"bagha", "arkosa", "tigra", "guri", "bhatdhijri", "siram", "peshrar",
"rorad", "devdaria", "pakhar")), row.names = 379:409, class = "data.frame")
使用代码后的数据集示例：
3404L, 3405L, 3406L, 3407L, 3408L, 3409L, 3410L, 3411L), district_name = c("khunti",
"ranchi", "lohardaga", "gumla", "simdega", "palamu", "latehar",
"garhwa", "west singhbhum", "saraikela kharsawan", "east singhbum",
"dumka"), block_code = c(3401009L, 3401013L, 3402005L, 3403009L,
3404002L, 3405018L, 3406006L, 3407009L, 3408005L, 3409006L, 3410005L,
3411009L), block_name = c("khunti", "namkum", "bhandra", "basia",
"bolba", "tarhasi", "garu", "bhandaria", "tantnagar", "ichagarh",
"musabani", "masaliya"), village_code = c(3401009002, 3401013020,
3402005002, 3403009008, 3404002002, 3405006012, 3406006008, 3407009002,
3408005001, 3409006012, 3410005011, 3411009001), village_name = c("bhandra",
"sithiyo", "bhandra", "mamarla", "kadopani", "manjhauli 2", "ghasitola",
"bhandaria", "angardiha", "dewaltand", "ichra (north)", "aamgachi"
)), row.names = c(NA, -12L), class = c("tbl_df", "tbl", "data.frame"
))
您的示例不适合提供解决方案，因为它只包含一个 district/block。
但你可以这样做：
df %>%
group_by(district_code) %>%
filter(block_code == ifelse(length(unique(block_code)) == 1, block_code, sample(unique(block_code), size = 1))) %>%
filter(village_code %in% ifelse(length(unique(village_code)) == 1, village_code, sample(unique(village_code), size = min(10, length(unique(village_code))), replace = FALSE))) %>%
ungroup()
注意：我不完全确定你想在哪个级别进行抽样，所以这里我 select 每个区一个街区，然后是那个街区的 10 个村庄。因此，您最终会从每个地区的随机 selected 区块中得到 10 个村庄。