Question

我最近采取了使用sqldf软件包的方式，所以我可能会忽略这一点我正在尝试制作一个“选择案例”而不是嵌套的ifelse（）。我第一次做了一个，它的工作原理。

    cohort$activite = 
sqldf("select case activite when 1 then 'actif a plein temps'  
                            when 2 then 'actif a temps partiel'  
                            when 3 then 'actif en milieu'  
                            ELSE 'Données manquantes' END   
        from cohort")

然后在我的脚本中运行另一个，我收到了这个错误：

    cohort$motifs_ini=
sqldf("select case motifs_ini when 1 then 'contre indication medicale'  
                              when 2 then 'refus du patient'   
                              when 4 then 'bilan en cours'   
                              when 3 then 'autre motif'  
                              when 99 then 'Non precise'  
                              ELSE 'Données Manquantes' END  
      from cohort") 

Erreur dans sqliteExecStatement(con, statement, bind.data) :   
RS-DBI driver: (error in statement: no such table: cohort)  
De plus : Message d'avis :  
In value[[3L]](cond) :  
RAW() can only be applied to a 'raw', not a 'character'

我不明白为什么我有这个错误。数据帧存在，我已经使用相同类型的命令修改了一个变量。是因为我试图攻击相同的data.frame吗？任何帮助都会很合适。

编辑：这是我的9213行数据帧的6个第一行。

structure(list(dure_ttt = c(1402L, 556L, 778L, 30L, 123L, 241L
), sexe = c(1L, 2L, 1L, 1L, 2L, 1L), nephro_ini1 = structure(c(68L, 
68L, 68L, 68L, 68L, 68L), .Label = c("0108NL", "0401NL", "0404NL", 
"0405NL", "0406NL", "0407NL", "0408NL", "0409NL", "0410NL", "0411NL", 
"0412NL", "0413NL", "0415NL", "0416NL", "0417NL", "0418NL", "0419NL", 
"0420NL", "0421NL", "0422NL", "0423NL", "0424NL", "0425NL", "0441NL", 
"0442NL", "0443NL", "0446NL", "0447NL", "0448NL", "0449NL", "0450NL", 
"0455NL", "0456NL", "0457NL", "0458NL", "0502NL", "0521NL", "0522NL", 
"0523NL", "0524NL", "0525NL", "0526NL", "0527NL", "0528NL", "0529NL", 
"0530NL", "0531NL", "0532NL", "0533NL", "0534NL", "0535NL", "0536NL", 
"0537NL", "0601NL", "0602NL", "0603NL", "0604NL", "0605NL", "0606NL", 
"0607NL", "0608NL", "0701NL", "0702NL", "0703NL", "0801NL", "0802NL", 
"0804NL", "0NL", "1107NL", "1108NL", "1141NL", "1145NL", "1308NL", 
"1337NL", "1352NL", "1414NL", "1415NL", "1416NL", "1417NL", "1435NL", 
"1501NL", "1502NL", "1503NL", "1505NL", "1506NL", "1507NL", "1521NL", 
"1522NL", "1523NL", "1531NL", "1535NL", "1536NL", "1540NL", "1542NL", 
"1551NL", "1552NL", "1554NL", "1558NL", "1749NL", "1801NL", "1804NL", 
"1805NL", "1806NL", "1812NL", "1813NL", "1814NL", "1817NL", "1823NL", 
"2213NL", "2215NL", "2216NL", "2307NL", "2311NL", "2314NL", "2318NL", 
"3202NL"), class = "factor"), catheter = c(1L, 1L, 1L, 0L, 1L, 
0L), urgence = c(0L, 0L, 1L, 0L, 0L, 0L), activite = c(8L, 4L, 
4L, 10L, 10L, 0L), nb_comorbidite_ini = c(2L, 6L, 6L, 3L, 2L, 
1L), presence_comorbidite_ini = c(1L, 1L, 1L, 1L, 1L, 1L), nb_acv_ini = c(1L, 
1L, 3L, 3L, 0L, 0L), presence_acv_ini = c(1L, 1L, 1L, 1L, 0L, 
0L), diabete_ini = c(0L, 0L, 0L, 0L, 0L, 0L), type_diabete_ini = c(99L, 
99L, 99L, 99L, 99L, 99L), insuline_ini = c(0L, 0L, 0L, 0L, 0L, 
0L), hta_ini = c(1L, 1L, 1L, 0L, 0L, 1L), hypercholesterolemie_ini = c(0L, 
1L, 0L, 0L, 1L, 0L), fumeur_ini = c(0L, 1L, 1L, 0L, 0L, 0L), 
    ex_fumeur_ini = c(0L, 0L, 0L, 0L, 0L, 0L), insuff_respiratoire_ini = c(0L, 
    1L, 0L, 0L, 0L, 0L), oxygenotherapie_ini = c(0L, 0L, 0L, 
    0L, 0L, 0L), insuffisance_cardiaque_ini = c(0L, 0L, 1L, 1L, 
    0L, 0L), stade_IC_ini = c(99L, 99L, 1L, 3L, 99L, 99L), infarctus_ini = c(0L, 
    0L, 1L, 1L, 0L, 0L), angor_ini = c(0L, 0L, 0L, 0L, 0L, 0L
    ), arythmie_ini = c(1L, 0L, 0L, 1L, 0L, 0L), arterite_MI_ini = c(0L, 
    1L, 1L, 0L, 0L, 0L), stade_arterite_MI_ini = c(99L, 1L, 3L, 
    99L, 99L, 99L), avc_ini = c(0L, 0L, 0L, 0L, 0L, 0L), ait_ini = c(0L, 
    0L, 0L, 0L, 0L, 0L), cancer_ini = c(0L, 0L, 0L, 0L, 1L, 0L
    ), cirrhose_ini = c(0L, 0L, 0L, 0L, 0L, 0L), cirrhose_A_ini = c(0L, 
    0L, 0L, 0L, 0L, 0L), cirrhose_BC_ini = c(0L, 0L, 0L, 0L, 
    0L, 0L), hepatite_ini = c(0L, 0L, 0L, 0L, 0L, 0L), hepatite_B_ini = c(0L, 
    0L, 0L, 0L, 0L, 0L), hepatite_C_ini = c(0L, 0L, 0L, 0L, 0L, 
    0L), VIH_ini = c(0L, 0L, 0L, 0L, 0L, 0L), sida_ini = c(0L, 
    0L, 0L, 0L, 0L, 0L), transpl_ini = c(0L, 0L, 0L, 0L, 0L, 
    0L), nb_handicap_ini = c(0L, 1L, 1L, 0L, 0L, 0L), amputat_ini = c(0L, 
    0L, 0L, 0L, 0L, 0L), hemipl_ini = c(0L, 0L, 0L, 0L, 0L, 0L
    ), cecite_ini = c(0L, 0L, 0L, 0L, 0L, 0L), compor_ini = c(0L, 
    1L, 1L, 0L, 0L, 0L), inscri_ini = c(0L, 0L, 0L, 0L, 0L, 0L
    ), motifs_ini = c(1L, 1L, 1L, 1L, 3L, 99L), hospit_ini = c(0L, 
    1L, 0L, 1L, 1L, 0L), nbr_hospit_ini = c(0, 2, 0, 1, 1, 0), 
    duree_hospit_ini = c(99L, 2L, 99L, 2L, 2L, 99L), marche_ini = c(3L, 
    3L, 99L, 1L, 3L, 99L), structure_ini = c(1L, 1L, 1L, 1L, 
    1L, 1L), methode_ini = c(1L, 1L, 1L, 1L, 1L, 1L), voie_abord_ini = c(1L, 
    3L, NA, 4L, 3L, 1L), nb_seances_ini = c(3L, 3L, NA, 3L, 3L, 
    3L), erythropoietine_ini = c(0L, 1L, 0L, 0L, 0L, 0L)), .Names = c("dure_ttt", 
"sexe", "nephro_ini1", "catheter", "urgence", "activite", "nb_comorbidite_ini", 
"presence_comorbidite_ini", "nb_acv_ini", "presence_acv_ini", 
"diabete_ini", "type_diabete_ini", "insuline_ini", "hta_ini", 
"hypercholesterolemie_ini", "fumeur_ini", "ex_fumeur_ini", "insuff_respiratoire_ini", 
"oxygenotherapie_ini", "insuffisance_cardiaque_ini", "stade_IC_ini", 
"infarctus_ini", "angor_ini", "arythmie_ini", "arterite_MI_ini", 
"stade_arterite_MI_ini", "avc_ini", "ait_ini", "cancer_ini", 
"cirrhose_ini", "cirrhose_A_ini", "cirrhose_BC_ini", "hepatite_ini", 
"hepatite_B_ini", "hepatite_C_ini", "VIH_ini", "sida_ini", "transpl_ini", 
"nb_handicap_ini", "amputat_ini", "hemipl_ini", "cecite_ini", 
"compor_ini", "inscri_ini", "motifs_ini", "hospit_ini", "nbr_hospit_ini", 
"duree_hospit_ini", "marche_ini", "structure_ini", "methode_ini", 
"voie_abord_ini", "nb_seances_ini", "erythropoietine_ini"), row.names = c(NA, 
6L), class = "data.frame")

Answer 1

嗯，我从未使用过sqldf，但只要它返回一个数据帧，将第一个查询的结果分配给原始数据帧的列就会破坏其结构并且不允许其他查询。我尝试不分配整个结果，但只分配了第一列并且它有效：

df2$activite<- sqldf("SELECT CASE activite 
                         WHEN 1 TEHN 'actif a plein temps'  
                         WHEN 2 TEHN 'actif a temps partiel'  
                         WHEN 3 TEHN 'actif en milieu'  
                         ELSE 'Données manquantes' END   
                      from df2")[[1]]

（其中df2是你的同类群组）然后其他查询工作。也许有更规范的方式来获得你需要的......

Answer 2

@vodka答案是个好答案。 sqldf返回data.frame。因此，直接分配它将损坏您的初始data.frame（成为列表列表）。

这里只是一种返回更漂亮结果的方法。您可以使用AS分配新列名，然后使用它来分配旧列。

cohort <- data.frame(motifs_ini=c(1,2,3,4,99,100))
cohort$motifs_ini <- sqldf("SELECT CASE  motifs_ini
                               WHEN 1 THEN 'contre indication medicale'  
                               WHEN 2 THEN 'refus du patient'   
                               WHEN 4 THEN 'bilan en cours'   
                               WHEN 3 THEN 'autre motif'  
                               WHEN 99 THEN 'Non precise'  
                               ELSE 'Données Manquantes' 
                          END AS newcol
                          FROM cohort")$newcol


cohort
                  motifs_ini
1 contre indication medicale
2           refus du patient
3                autre motif
4             bilan en cours
5                Non precise
6         Données Manquantes

sqldf - sqliteExecStatement：语句中的错误：没有这样的表

2 个答案: