如何对数据帧进行分组，然后计算 R 中的不同值
How to group a dataframe, and then count the distinct values in R
我在 R 中有一个数据框，它有 43 个变量和超过 80 行。我想根据一个变量——地理区域对数据进行分组，然后计算一个变量的不同值（有多少个 0、1、2、3 和 NA 等）。
我知道 tidyverse 中的 group_by 和 summarize 函数，我知道我可以使用 "sum" 和 "mean" 等函数，但是我想数
我试过了
est1 <- df %>%
group_by(region) %>%
summarize(count)
数据如下所示：
iso3 Country WHOregion WBIncomeGroup UrbanSanPol UrbanSanWom UrbanSanExt RuralSanPol RuralSanWom
<chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 AFG Afghanistan EMRO Low income 0 <NA> <NA> 1 1
2 ALB Albania EURO Upper middle income 1 0 0 1 0
3 ARG Argentina PAHO Upper middle income 1 0 0.5 1 0
4 AZE Azerbaijan EURO Upper middle income 1 1 0.5 1 1
5 BDI Burundi AFRO Low income 1 1 0.5 1 1
6 BFA Burkina Faso AFRO Low income 1 1 1 1 1
但这不是我想要的。有人可以帮忙吗？
structure(list(iso3 = c("AFG", "ALB", "ARG", "AZE", "BDI", "BFA",
"BGD", "BIH", "BLR", "BOL"), Country = c("Afghanistan", "Albania",
"Argentina", "Azerbaijan", "Burundi", "Burkina Faso", "Bangladesh",
"Bosnia and Herzegovina", "Belarus", "Bolivia (Plurinational State of)"
), WHOregion = c("EMRO", "EURO", "PAHO", "EURO", "AFRO", "AFRO",
"SEARO", "EURO", "EURO", "PAHO"), WBIncomeGroup = c("Low income",
"Upper middle income", "Upper middle income", "Upper middle income",
"Low income", "Low income", "Lower middle income", "Upper middle income",
"Upper middle income", "Lower middle income"), UrbanSanPol = c("0",
"1", "1", "1", "1", "1", "1", "1", "1", "1"), UrbanSanWom = c(NA,
"0", "0", "1", "1", "1", "1", "0", NA, "0"), UrbanSanExt = c(NA,
"0", "0.5", "0.5", "0.5", "1", "0.5", "0", "0.5", "0"), RuralSanPol = c("1",
"1", "1", "1", "1", "1", "1", "1", "1", "1"), RuralSanWom = c("1",
"0", "0", "1", "1", "1", "1", "0", NA, "0"), RuralSanExt = c("0.5",
"0", "0", "0.5", "0.5", "1", "0.5", "0", "0.5", "0.5"), UrbanDWPol = c("0",
"1", "1", "1", "1", "1", "1", "1", "1", "1"), UrbanDWWom = c(NA,
"0", "0", "1", "1", "1", "1", "0", NA, "0"), UrbanDWExt = c(NA,
"0", "0.5", "1", "0", "0.5", "0.5", "0.5", "0.5", "0"), RuralDWPol = c("1",
"1", "1", "1", "1", "1", "1", "1", "1", "1"), RuralDWWom = c("1",
"0", "0", "1", "1", "1", "1", "0", NA, "0"), RuralDWExt = c("0.5",
"0", "0", "1", "0.5", "1", "0.5", "0.5", "0.5", "0.5"), HygienePol = c("1",
"1", "0", "1", "1", "1", "1", "1", "1", "0"), HygieneWom = c("1",
NA, NA, "1", "1", "1", "1", "0", NA, "0"), HygieneExt = c("0.5",
NA, NA, "0", "0.5", "0", "0.5", "0", "0.5", "0"), WASHHealthPol = c("1",
"1", "0", "1", "1", "1", "1", "1", "0", "0"), WASHHealthWom = c("0",
NA, NA, "1", "1", "1", "1", "0", NA, "0"), WASHHealthExt = c("0",
NA, "0.5", "1", "0", "0.5", "0", "0", NA, "0"), WpollutionPol = c("1",
"1", "1", "1", "1", "1", "1", "1", "1", "0"), WpollutionWom = c("1",
NA, "0", "1", "1", "1", "1", "0", NA, "0"), WpollutionExt = c("0",
NA, "0", "1", "0", "0.5", "0", "0", "0.5", "0"), WQMPol = c("1",
"1", "1", "1", "1", "1", "1", "1", "1", "0"), WQMWom = c("1",
NA, "0", "1", "1", "1", "1", "0", NA, "0"), WQMExt = c("0", NA,
"0", "1", "0", "0.5", "0", "0", "0.5", "0"), WatRightPol = c("0",
"1", "1", "1", NA, "1", "1", "1", "1", "1"), WatRightWom = c("0",
NA, "0", "1", NA, "1", "1", "0", NA, "0"), WatRightExt = c("0",
NA, "0.5", "1", NA, "1", "0", "0", "0.5", "0.5"), WRMPol = c("1",
"1", "1", "1", "1", "1", "1", "1", "1", "1"), WRMWom = c("0",
NA, "0", "1", "1", "1", "1", "0", NA, "0"), WRMExt = c("0", NA,
"0.5", "1", "0.5", "1", "0", "0", "0.5", "0"), EnvProtPol = c("1",
"1", "1", "1", "1", "1", "1", "1", "1", "1"), EnvProtWom = c("0",
NA, "0", "1", "1", "1", "1", "0", NA, "0"), EnvProtExt = c("0",
NA, "0", "1", "0", "1", "0", "0", "0.5", "0"), `SDG regions` = c("Central Asia (M49) and Southern Asia (MDG=M49)",
"Northern America (M49) and Europe (M49)", "Latin America and the Caribbean (MDG=M49)",
"Western Asia (M49) and Northern Africa (M49)", "Sub-Saharan Africa (M49)",
"Sub-Saharan Africa (M49)", "Central Asia (M49) and Southern Asia (MDG=M49)",
"Northern America (M49) and Europe (M49)", "Northern America (M49) and Europe (M49)",
"Latin America and the Caribbean (MDG=M49)"), M49_level1 = c("Asia (M49)",
"Europe (M49)", "Latin America and the Caribbean (MDG=M49)",
"Asia (M49)", "Sub-Saharan Africa (M49)", "Sub-Saharan Africa (M49)",
"Asia (M49)", "Europe (M49)", "Europe (M49)", "Latin America and the Caribbean (MDG=M49)"
), M49_level2 = c("Southern Asia (MDG=M49)", "Southern Europe (M49)",
"South America (M49)", "Western Asia (M49)", "Eastern Africa (M49)",
"Western Africa (M49)", "Southern Asia (MDG=M49)", "Southern Europe (M49)",
"Eastern Europe (M49)", "South America (M49)"), LDCs = c("Least Developed Countries (LDCs)",
NA, NA, NA, "Least Developed Countries (LDCs)", "Least Developed Countries (LDCs)",
"Least Developed Countries (LDCs)", NA, NA, NA), LLDCS_SIDS = c("Landlocked developing countries (LLDCs)",
NA, NA, "Landlocked developing countries (LLDCs)", "Landlocked developing countries (LLDCs)",
"Landlocked developing countries (LLDCs)", NA, NA, NA, "Landlocked developing countries (LLDCs)"
), `Income group` = c("Low income", "Upper middle income", "Upper middle income",
"Upper middle income", "Low income", "Low income", "Lower middle income",
"Upper middle income", "Upper middle income", "Lower middle income"
)), .Names = c("iso3", "Country", "WHOregion", "WBIncomeGroup",
"UrbanSanPol", "UrbanSanWom", "UrbanSanExt", "RuralSanPol", "RuralSanWom",
"RuralSanExt", "UrbanDWPol", "UrbanDWWom", "UrbanDWExt", "RuralDWPol",
"RuralDWWom", "RuralDWExt", "HygienePol", "HygieneWom", "HygieneExt",
"WASHHealthPol", "WASHHealthWom", "WASHHealthExt", "WpollutionPol",
"WpollutionWom", "WpollutionExt", "WQMPol", "WQMWom", "WQMExt",
"WatRightPol", "WatRightWom", "WatRightExt", "WRMPol", "WRMWom",
"WRMExt", "EnvProtPol", "EnvProtWom", "EnvProtExt", "SDG regions",
"M49_level1", "M49_level2", "LDCs", "LLDCS_SIDS", "Income group"
), row.names = c(NA, -10L), class = c("tbl_df", "tbl", "data.frame"
在此处输入代码
Imagine I have three columns. The first is a list of countries (France, Germany, etc). The second is a list of regions (Asia, Europe), the third is a discrete value for each country (number of Olympic Gold medals). I want to group all the data by region, and count how many times for each region, 0 occurs, 1 occurs, 2 occurs.
根据你在评论中所说的，以及我的理解：
解读：
df %>% select(continent,countries,medals) %>% group_by(continent,countries) %>% summarize(count =n())
另一种解释：你想要的是每个大陆和它获得的不同奖牌数。
数字是该国获得的奥运奖牌数。
df <- as.data.frame(matrix(c("Asia","Asia","Asia","Asia","Europe","Europe","India","China","Bangladesh","Japan","Spain", "Italy",6,3,4,4,3,3),ncol = 3))
df %>% group_by(V1,V3) %>% summarise(count= n()) %>% spread(V3,count)
给我一个输出
# A tibble: 2 x 4
# Groups: V1 [2]
V1 `3` `4` `6`
* <fctr> <int> <int> <int>
1 Asia 1 2 1
2 Europe 2 NA NA
试试这个；需要 dplyr 和 tidyverse
distinct_cnt <- input_df %>%
gather(variable, value) %>%
group_by(variable) %>%
summarise(n_distinct(value))
我在 R 中有一个数据框，它有 43 个变量和超过 80 行。我想根据一个变量——地理区域对数据进行分组，然后计算一个变量的不同值（有多少个 0、1、2、3 和 NA 等）。
我知道 tidyverse 中的 group_by 和 summarize 函数，我知道我可以使用 "sum" 和 "mean" 等函数，但是我想数
我试过了
est1 <- df %>%
group_by(region) %>%
summarize(count)
数据如下所示：
iso3 Country WHOregion WBIncomeGroup UrbanSanPol UrbanSanWom UrbanSanExt RuralSanPol RuralSanWom
<chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
1 AFG Afghanistan EMRO Low income 0 <NA> <NA> 1 1
2 ALB Albania EURO Upper middle income 1 0 0 1 0
3 ARG Argentina PAHO Upper middle income 1 0 0.5 1 0
4 AZE Azerbaijan EURO Upper middle income 1 1 0.5 1 1
5 BDI Burundi AFRO Low income 1 1 0.5 1 1
6 BFA Burkina Faso AFRO Low income 1 1 1 1 1
但这不是我想要的。有人可以帮忙吗？
structure(list(iso3 = c("AFG", "ALB", "ARG", "AZE", "BDI", "BFA",
"BGD", "BIH", "BLR", "BOL"), Country = c("Afghanistan", "Albania",
"Argentina", "Azerbaijan", "Burundi", "Burkina Faso", "Bangladesh",
"Bosnia and Herzegovina", "Belarus", "Bolivia (Plurinational State of)"
), WHOregion = c("EMRO", "EURO", "PAHO", "EURO", "AFRO", "AFRO",
"SEARO", "EURO", "EURO", "PAHO"), WBIncomeGroup = c("Low income",
"Upper middle income", "Upper middle income", "Upper middle income",
"Low income", "Low income", "Lower middle income", "Upper middle income",
"Upper middle income", "Lower middle income"), UrbanSanPol = c("0",
"1", "1", "1", "1", "1", "1", "1", "1", "1"), UrbanSanWom = c(NA,
"0", "0", "1", "1", "1", "1", "0", NA, "0"), UrbanSanExt = c(NA,
"0", "0.5", "0.5", "0.5", "1", "0.5", "0", "0.5", "0"), RuralSanPol = c("1",
"1", "1", "1", "1", "1", "1", "1", "1", "1"), RuralSanWom = c("1",
"0", "0", "1", "1", "1", "1", "0", NA, "0"), RuralSanExt = c("0.5",
"0", "0", "0.5", "0.5", "1", "0.5", "0", "0.5", "0.5"), UrbanDWPol = c("0",
"1", "1", "1", "1", "1", "1", "1", "1", "1"), UrbanDWWom = c(NA,
"0", "0", "1", "1", "1", "1", "0", NA, "0"), UrbanDWExt = c(NA,
"0", "0.5", "1", "0", "0.5", "0.5", "0.5", "0.5", "0"), RuralDWPol = c("1",
"1", "1", "1", "1", "1", "1", "1", "1", "1"), RuralDWWom = c("1",
"0", "0", "1", "1", "1", "1", "0", NA, "0"), RuralDWExt = c("0.5",
"0", "0", "1", "0.5", "1", "0.5", "0.5", "0.5", "0.5"), HygienePol = c("1",
"1", "0", "1", "1", "1", "1", "1", "1", "0"), HygieneWom = c("1",
NA, NA, "1", "1", "1", "1", "0", NA, "0"), HygieneExt = c("0.5",
NA, NA, "0", "0.5", "0", "0.5", "0", "0.5", "0"), WASHHealthPol = c("1",
"1", "0", "1", "1", "1", "1", "1", "0", "0"), WASHHealthWom = c("0",
NA, NA, "1", "1", "1", "1", "0", NA, "0"), WASHHealthExt = c("0",
NA, "0.5", "1", "0", "0.5", "0", "0", NA, "0"), WpollutionPol = c("1",
"1", "1", "1", "1", "1", "1", "1", "1", "0"), WpollutionWom = c("1",
NA, "0", "1", "1", "1", "1", "0", NA, "0"), WpollutionExt = c("0",
NA, "0", "1", "0", "0.5", "0", "0", "0.5", "0"), WQMPol = c("1",
"1", "1", "1", "1", "1", "1", "1", "1", "0"), WQMWom = c("1",
NA, "0", "1", "1", "1", "1", "0", NA, "0"), WQMExt = c("0", NA,
"0", "1", "0", "0.5", "0", "0", "0.5", "0"), WatRightPol = c("0",
"1", "1", "1", NA, "1", "1", "1", "1", "1"), WatRightWom = c("0",
NA, "0", "1", NA, "1", "1", "0", NA, "0"), WatRightExt = c("0",
NA, "0.5", "1", NA, "1", "0", "0", "0.5", "0.5"), WRMPol = c("1",
"1", "1", "1", "1", "1", "1", "1", "1", "1"), WRMWom = c("0",
NA, "0", "1", "1", "1", "1", "0", NA, "0"), WRMExt = c("0", NA,
"0.5", "1", "0.5", "1", "0", "0", "0.5", "0"), EnvProtPol = c("1",
"1", "1", "1", "1", "1", "1", "1", "1", "1"), EnvProtWom = c("0",
NA, "0", "1", "1", "1", "1", "0", NA, "0"), EnvProtExt = c("0",
NA, "0", "1", "0", "1", "0", "0", "0.5", "0"), `SDG regions` = c("Central Asia (M49) and Southern Asia (MDG=M49)",
"Northern America (M49) and Europe (M49)", "Latin America and the Caribbean (MDG=M49)",
"Western Asia (M49) and Northern Africa (M49)", "Sub-Saharan Africa (M49)",
"Sub-Saharan Africa (M49)", "Central Asia (M49) and Southern Asia (MDG=M49)",
"Northern America (M49) and Europe (M49)", "Northern America (M49) and Europe (M49)",
"Latin America and the Caribbean (MDG=M49)"), M49_level1 = c("Asia (M49)",
"Europe (M49)", "Latin America and the Caribbean (MDG=M49)",
"Asia (M49)", "Sub-Saharan Africa (M49)", "Sub-Saharan Africa (M49)",
"Asia (M49)", "Europe (M49)", "Europe (M49)", "Latin America and the Caribbean (MDG=M49)"
), M49_level2 = c("Southern Asia (MDG=M49)", "Southern Europe (M49)",
"South America (M49)", "Western Asia (M49)", "Eastern Africa (M49)",
"Western Africa (M49)", "Southern Asia (MDG=M49)", "Southern Europe (M49)",
"Eastern Europe (M49)", "South America (M49)"), LDCs = c("Least Developed Countries (LDCs)",
NA, NA, NA, "Least Developed Countries (LDCs)", "Least Developed Countries (LDCs)",
"Least Developed Countries (LDCs)", NA, NA, NA), LLDCS_SIDS = c("Landlocked developing countries (LLDCs)",
NA, NA, "Landlocked developing countries (LLDCs)", "Landlocked developing countries (LLDCs)",
"Landlocked developing countries (LLDCs)", NA, NA, NA, "Landlocked developing countries (LLDCs)"
), `Income group` = c("Low income", "Upper middle income", "Upper middle income",
"Upper middle income", "Low income", "Low income", "Lower middle income",
"Upper middle income", "Upper middle income", "Lower middle income"
)), .Names = c("iso3", "Country", "WHOregion", "WBIncomeGroup",
"UrbanSanPol", "UrbanSanWom", "UrbanSanExt", "RuralSanPol", "RuralSanWom",
"RuralSanExt", "UrbanDWPol", "UrbanDWWom", "UrbanDWExt", "RuralDWPol",
"RuralDWWom", "RuralDWExt", "HygienePol", "HygieneWom", "HygieneExt",
"WASHHealthPol", "WASHHealthWom", "WASHHealthExt", "WpollutionPol",
"WpollutionWom", "WpollutionExt", "WQMPol", "WQMWom", "WQMExt",
"WatRightPol", "WatRightWom", "WatRightExt", "WRMPol", "WRMWom",
"WRMExt", "EnvProtPol", "EnvProtWom", "EnvProtExt", "SDG regions",
"M49_level1", "M49_level2", "LDCs", "LLDCS_SIDS", "Income group"
), row.names = c(NA, -10L), class = c("tbl_df", "tbl", "data.frame"
在此处输入代码
Imagine I have three columns. The first is a list of countries (France, Germany, etc). The second is a list of regions (Asia, Europe), the third is a discrete value for each country (number of Olympic Gold medals). I want to group all the data by region, and count how many times for each region, 0 occurs, 1 occurs, 2 occurs.
根据你在评论中所说的，以及我的理解：
解读：
df %>% select(continent,countries,medals) %>% group_by(continent,countries) %>% summarize(count =n())
另一种解释：你想要的是每个大陆和它获得的不同奖牌数。
数字是该国获得的奥运奖牌数。
df <- as.data.frame(matrix(c("Asia","Asia","Asia","Asia","Europe","Europe","India","China","Bangladesh","Japan","Spain", "Italy",6,3,4,4,3,3),ncol = 3))
df %>% group_by(V1,V3) %>% summarise(count= n()) %>% spread(V3,count)
给我一个输出
# A tibble: 2 x 4
# Groups: V1 [2]
V1 `3` `4` `6`
* <fctr> <int> <int> <int>
1 Asia 1 2 1
2 Europe 2 NA NA
试试这个；需要 dplyr 和 tidyverse
distinct_cnt <- input_df %>%
gather(variable, value) %>%
group_by(variable) %>%
summarise(n_distinct(value))