如何 运行 循环中的多个查询并将该数据保存到数据框中？
How to run several queries in a loop and save that data into a dataframe?
我正在尝试通过 R 运行 多个 SQL 查询，每个查询的差异在于一个搜索参数（邮政编码），运行 对每个结果进行一些简单的计算，然后将调查结果保存到新的数据框中。
我正在使用 for 循环执行 SQL 查询，在进行计算时我没有遇到任何问题，但在代码末尾，我收到的只是一个数据框，其中一行在数据框的整个长度上都是重复的。
我认为问题在于我如何将最终计算 (dataframe:Togetic) 传递到最终结果 (dateframe: Togekiss)，但我无法正确解决该问题。
这是我的代码：
ALLZIP 是我正在使用的所有邮政编码的列表。
为了简洁起见，我删除了我的计算。
#Sample ALLZIP
ALLZIP <- c(10453,10457,10460,11238,11004)
ALLZIP<-as.data.frame(ALLZIP)
#Storage
Togekiss <-as.data.frame(matrix(NA,nrow = 15, ncol=length(ALLZIP$ALLZIP)))
names(Togekiss)<-ALLZIP$ALLZIP
j <- 1
for(i in (ALLZIP$ALLZIP)){
print(i)
Togepi = sqlQuery(dbhandle,query=paste0("SELECT RaceCode,COUNT(*) AS 'num'FROM [DIS_SYNDROMIC].[dbo].[PatientVisits]WHERE YEAR([AdmissionDateTime])=2016 AND Zip LIKE '",ALLZIP$ALLZIP[1],"' GROUP BY RaceCode ORDER BY 2 DESC"))
Togepi <-as.data.frame(Togepi)
Togepi$RaceCode <- gsub("BL|OT|B|2056-0|AA|2052-9|2075-0","2054-5",Togepi$RaceCode)
Togepi$RaceCode <- gsub("1004-1|1840-8","1002-5",Togepi$RaceCode)
Togepi$RaceCode <- gsub("2041-2|2045-3|2031-3|2034-7|2039-6|AS|2032-1|2044-6|A|2037-0|2035-4|2033-9|2048-7|2050-3|2049-5|2051-1|2042-0|2030-5|2029-7|2040-4|2043-8|2038-8|2046-1|2047-9","2028-9",Togepi$RaceCode)
Togepi$RaceCode <- gsub("2096-6|2091-7|2082-6|2500-7|2093-3|2076-8|2079-2|2087-5|2090-9|2088-3|2086-7|2081-8|2101-4|2098-22036-2|2100-6|2097-4|2080-0|2094-1|2089-1|2104-8","2076-8",Togepi$RaceCode)
Togepi$RaceCode <- gsub("OT|O","2131-1",Togepi$RaceCode)
Togepi$RaceCode <- gsub("WH|W","2106-3",Togepi$RaceCode)
Togepi<-tapply(Togepi$num,Togepi$RaceCode, FUN=sum)
#Getting a new data frame
EL<-sum(Togepi["1002-5"],Togepi["2028-9"],Togepi["2054-5"],Togepi["2076-8"],Togepi["2131-1"],Togepi["2106-3"])
Togetic<-c(Togepi["1002-5"],Togepi["2028-9"],Togepi["2054-5"],Togepi["2076-8"],Togepi["2131-1"],Togepi["2106-3"],sum(Togepi)-sum(Togepi["1002-5"],Togepi["2028-9"],Togepi["2054-5"],Togepi["2076-8"],Togepi["2131-1"],Togepi["2106-3"]),sum(Togepi),(Togepi["1002-5"]/sum(Togepi))*100,(Togepi["2028-9"]/sum(Togepi))*100,(Togepi["2054-5"]/sum(Togepi))*100,(Togepi["2076-8"]/sum(Togepi))*100,(Togepi["2131-1"]/sum(Togepi))*100,(Togepi["2106-3"]/sum(Togepi))*100, ((sum(Togepi)-EL)/sum(Togepi))*100)
Togetic<-as.data.frame(Togetic)
rownames(Togetic)<-c("American Indian or Alaska Native ","Asian","Black or African American","Pacific Islander","Other","White","No Info","Total","Percentage American Indian","Percentage Asian","Percentage Black or African American","Percentage Pacific Islander","Percentage Other","Percentage White","Percentage Missing")
colnames(Togetic)<- paste0(ALLZIP$ALLZIP[i])
Togekiss[,j]<-Togetic
j <- j+1
}
rownames(Togekiss)<-c("American Indian or Alaska Native ","Asian","Black or African American","Pacific Islander","Other","White","No Info","Total","Percentage American Indian","Percentage Asian","Percentage Black or African American","Percentage Pacific Islander","Percentage Other","Percentage White","Percentage Missing")
Togekiss<-round(Togekiss,digits=2)
您正在用每次循环迭代覆盖您的数据框。尝试使用它而不是 Togepi = sqlQuery() Togepi <-as.data.frame(Togepi)
temp.df = sqlQuery(YOUR SQL HERE)
if(i==1)
{Togepi <-as.data.frame(temp.df)}
else
{Togepi <- rbind(Togepi,s.data.frame(temp.df)}
好的，所以我不知道你的 Togetic 是什么样子，但如果那确实是应该添加到数据中的单行。frame/matrix 这可能是一个可行的选择：
ALLZIP <- c(10453,10457,10460,11238,11004)
ALLZIP<-as.data.frame(ALLZIP)
allZipCodes <- apply(ALLZIP, 1, function(zipcode) {
# Each zipcode here is basically ALLZIP[i,1]
Togepi = as.data.frame( sqlQuery(dbhandle,query=paste0("SELECT RaceCode,COUNT(*) AS 'num'FROM [DIS_SYNDROMIC].[dbo].[PatientVisits]WHERE YEAR([AdmissionDateTime])=2016 AND Zip LIKE '",
zipcode, #this is ALLZIP$ALLZIP[i]
"' GROUP BY RaceCode ORDER BY 2 DESC")) )
colnames(Togetic) <- zipcode
return(Togetic) # This would be the row you wanted to update in Togekiss.
})
# allZipCodes contains a list of all your calculations, by executing a function on each of these elements with do.call we can get a combined matrix.
do.call(rbind, allZipCodes)
你能试试这个吗，如果有效请告诉我？如果没有，你能告诉我 Togetic 里有什么吗？
我正在尝试通过 R 运行 多个 SQL 查询，每个查询的差异在于一个搜索参数（邮政编码），运行 对每个结果进行一些简单的计算，然后将调查结果保存到新的数据框中。
我正在使用 for 循环执行 SQL 查询，在进行计算时我没有遇到任何问题，但在代码末尾，我收到的只是一个数据框，其中一行在数据框的整个长度上都是重复的。
我认为问题在于我如何将最终计算 (dataframe:Togetic) 传递到最终结果 (dateframe: Togekiss)，但我无法正确解决该问题。
这是我的代码：
ALLZIP 是我正在使用的所有邮政编码的列表。 为了简洁起见，我删除了我的计算。
#Sample ALLZIP
ALLZIP <- c(10453,10457,10460,11238,11004)
ALLZIP<-as.data.frame(ALLZIP)
#Storage
Togekiss <-as.data.frame(matrix(NA,nrow = 15, ncol=length(ALLZIP$ALLZIP)))
names(Togekiss)<-ALLZIP$ALLZIP
j <- 1
for(i in (ALLZIP$ALLZIP)){
print(i)
Togepi = sqlQuery(dbhandle,query=paste0("SELECT RaceCode,COUNT(*) AS 'num'FROM [DIS_SYNDROMIC].[dbo].[PatientVisits]WHERE YEAR([AdmissionDateTime])=2016 AND Zip LIKE '",ALLZIP$ALLZIP[1],"' GROUP BY RaceCode ORDER BY 2 DESC"))
Togepi <-as.data.frame(Togepi)
Togepi$RaceCode <- gsub("BL|OT|B|2056-0|AA|2052-9|2075-0","2054-5",Togepi$RaceCode)
Togepi$RaceCode <- gsub("1004-1|1840-8","1002-5",Togepi$RaceCode)
Togepi$RaceCode <- gsub("2041-2|2045-3|2031-3|2034-7|2039-6|AS|2032-1|2044-6|A|2037-0|2035-4|2033-9|2048-7|2050-3|2049-5|2051-1|2042-0|2030-5|2029-7|2040-4|2043-8|2038-8|2046-1|2047-9","2028-9",Togepi$RaceCode)
Togepi$RaceCode <- gsub("2096-6|2091-7|2082-6|2500-7|2093-3|2076-8|2079-2|2087-5|2090-9|2088-3|2086-7|2081-8|2101-4|2098-22036-2|2100-6|2097-4|2080-0|2094-1|2089-1|2104-8","2076-8",Togepi$RaceCode)
Togepi$RaceCode <- gsub("OT|O","2131-1",Togepi$RaceCode)
Togepi$RaceCode <- gsub("WH|W","2106-3",Togepi$RaceCode)
Togepi<-tapply(Togepi$num,Togepi$RaceCode, FUN=sum)
#Getting a new data frame
EL<-sum(Togepi["1002-5"],Togepi["2028-9"],Togepi["2054-5"],Togepi["2076-8"],Togepi["2131-1"],Togepi["2106-3"])
Togetic<-c(Togepi["1002-5"],Togepi["2028-9"],Togepi["2054-5"],Togepi["2076-8"],Togepi["2131-1"],Togepi["2106-3"],sum(Togepi)-sum(Togepi["1002-5"],Togepi["2028-9"],Togepi["2054-5"],Togepi["2076-8"],Togepi["2131-1"],Togepi["2106-3"]),sum(Togepi),(Togepi["1002-5"]/sum(Togepi))*100,(Togepi["2028-9"]/sum(Togepi))*100,(Togepi["2054-5"]/sum(Togepi))*100,(Togepi["2076-8"]/sum(Togepi))*100,(Togepi["2131-1"]/sum(Togepi))*100,(Togepi["2106-3"]/sum(Togepi))*100, ((sum(Togepi)-EL)/sum(Togepi))*100)
Togetic<-as.data.frame(Togetic)
rownames(Togetic)<-c("American Indian or Alaska Native ","Asian","Black or African American","Pacific Islander","Other","White","No Info","Total","Percentage American Indian","Percentage Asian","Percentage Black or African American","Percentage Pacific Islander","Percentage Other","Percentage White","Percentage Missing")
colnames(Togetic)<- paste0(ALLZIP$ALLZIP[i])
Togekiss[,j]<-Togetic
j <- j+1
}
rownames(Togekiss)<-c("American Indian or Alaska Native ","Asian","Black or African American","Pacific Islander","Other","White","No Info","Total","Percentage American Indian","Percentage Asian","Percentage Black or African American","Percentage Pacific Islander","Percentage Other","Percentage White","Percentage Missing")
Togekiss<-round(Togekiss,digits=2)
您正在用每次循环迭代覆盖您的数据框。尝试使用它而不是 Togepi = sqlQuery() Togepi <-as.data.frame(Togepi)
temp.df = sqlQuery(YOUR SQL HERE)
if(i==1)
{Togepi <-as.data.frame(temp.df)}
else
{Togepi <- rbind(Togepi,s.data.frame(temp.df)}
好的，所以我不知道你的 Togetic 是什么样子，但如果那确实是应该添加到数据中的单行。frame/matrix 这可能是一个可行的选择：
ALLZIP <- c(10453,10457,10460,11238,11004)
ALLZIP<-as.data.frame(ALLZIP)
allZipCodes <- apply(ALLZIP, 1, function(zipcode) {
# Each zipcode here is basically ALLZIP[i,1]
Togepi = as.data.frame( sqlQuery(dbhandle,query=paste0("SELECT RaceCode,COUNT(*) AS 'num'FROM [DIS_SYNDROMIC].[dbo].[PatientVisits]WHERE YEAR([AdmissionDateTime])=2016 AND Zip LIKE '",
zipcode, #this is ALLZIP$ALLZIP[i]
"' GROUP BY RaceCode ORDER BY 2 DESC")) )
colnames(Togetic) <- zipcode
return(Togetic) # This would be the row you wanted to update in Togekiss.
})
# allZipCodes contains a list of all your calculations, by executing a function on each of these elements with do.call we can get a combined matrix.
do.call(rbind, allZipCodes)
你能试试这个吗，如果有效请告诉我？如果没有，你能告诉我 Togetic 里有什么吗？