Question

我正在尝试提取合并energy <- structure(list(nodes = structure(list(name = structure(c(15L, 11L, 8L, 17L, 7L, 10L, 2L, 1L, 12L, 4L, 14L, 3L, 9L, 16L, 13L, 6L, 5L), .Label = c("Biomass", "Coal", "Commericial", "Electricity", "Energy Services", "Exports", "Geothermal", "Hydro", "Industrial", "Natural Gas", "Nuclear", "Petroleum", "Rejected Energy", "Residential", "Solar", "Transportation", "Wind"), class = "factor")), .Names = "name", class = "data.frame", row.names = c(NA, -17L)), links = structure(list(source = c(0L, 0L, 1L, 2L, 2L, 3L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 5L, 6L, 6L, 7L, 7L, 7L, 7L, 7L, 8L, 8L, 8L, 8L, 8L, 9L, 9L, 9L, 9L, 9L, 9L, 10L, 10L, 11L, 11L, 12L, 12L, 13L, 13L), target = c(9L, 10L, 9L, 9L, 12L, 9L, 9L, 10L, 11L, 9L, 10L, 11L, 12L, 13L, 9L, 12L, 9L, 10L, 11L, 12L, 13L, 9L, 10L, 11L, 12L, 13L, 10L, 11L, 12L, 13L, 14L, 15L, 14L, 16L, 14L, 16L, 14L, 16L, 14L, 16L), value = c(0.25, 0.28, 8.34, 2.38, 0.01, 1.81, 0.16, 0.04, 0.02, 9.99, 4.75, 3.3, 9.36, 0.92, 14.3, 1.41, 0.52, 0.45, 0.13, 2.28, 1.35, 0.28, 0.98, 0.56, 8.2, 25.4, 4.78, 4.63, 3.27, 0.03, 25.4, 0.08, 3.95, 7.33, 3.05, 5.66, 4.91, 19.6, 21.9, 5.81), energy_type = structure(c(12L, 12L, 9L, 7L, 7L, 13L, 6L, 6L, 6L, 8L, 8L, 8L, 8L, 8L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 10L, 10L, 10L, 10L, 10L, 3L, 3L, 3L, 3L, 11L, 5L, 11L, 4L, 11L, 4L, 11L, 4L, 11L, 4L), .Label = c("Biomass", "Coal", "Electricity", "Energy Services", "Exports", "Geothermal", "Hydro", "Natural", "Nuclear", "Petroleum", "Rejected Energy", "Solar", "Wind"), class = "factor")), .Names = c("source", "target", "value", "energy_type"), class = "data.frame", row.names = c(NA, -40L))), .Names = c("nodes", "links")) library(networkD3) sankeyNetwork(Links = energy$links, Nodes = energy$nodes, Source = "source", Target = "target", Value = "value", NodeID = "name", units = "Quads", LinkGroup = 'energy_type', colourScale = JS( 'd3.scaleOrdinal() .domain(["Solar","Nuclear","Hydro","Wind","Geothermal","Natural Gas","Coal","Biomass","Petroleum","Electricity","Residential","Commericial","Industrial","Transportation","Rejected Energy","Exports","Energy Services"]) .range(["#FFFF00","#FF0000","#0000FF","#800080","#A52A2A","#00FFFF","#000000","#00FF00","#008000","#FFA500","#FAAFBE","#FAAFBE","#FAAFBE","#FAAFBE","#C0C0C0","#FFA500","#808080"])' ), fontSize = 12, nodeWidth = 75, iterations = 100) # putting in a data.frame might help see problems color_scale <- data.frame( range = c("#FFFF00","#FF0000","#0000FF","#800080","#A52A2A","#00FFFF","#000000","#00FF00","#008000","#FFA500","#FAAFBE","#FAAFBE","#FAAFBE","#FAAFBE","#C0C0C0","#FFA500","#808080"), domain = c("Solar","Nuclear","Hydro","Wind","Geothermal","Natural Gas","Coal","Biomass","Petroleum","Electricity","Residential","Commericial","Industrial","Transportation","Rejected Energy","Exports","Energy Services"), nodes = energy$nodes, stringsAsFactors = FALSE ) # once corrected color_scale can be used like this sankeyNetwork( Links = energy$links, Nodes = energy$nodes, Source = "source", Target = "target", Value = "value", NodeID = "name", units = "Quads", LinkGroup = 'energy_type', colourScale = JS( sprintf( 'd3.scaleOrdinal() .domain(%s) .range(%s) ', jsonlite::toJSON(color_scale$domain), jsonlite::toJSON(color_scale$range) ) ), fontSize = 12, nodeWidth = 75, iterations = 100 ) # if we change Natural Gas to Natural then # the cyan appears as desired color_scale[6,2] <- "Natural"，GROUP BY和ORDER BY的记录，但我没有得到结果/期望的结果。这是我的表HAVING：

test

我想要的结果是这样的：

+--------------------------------------+-----+---------------------+------+
| id                                   | no  | date_entered        | name |
+--------------------------------------+-----+----------------------------+
| c44d1977-0193-a2f1-00f9-57e4c53ba416 | 104 | 2016-09-23 06:02:16 | Z-44 |
| ca1879a2-df08-4fe3-b144-57e4d2ab0c62 | 104 | 2016-09-23 06:57:35 | Z-44 |
| 5dd46d35-358a-314e-30fa-57e4d2ca92ad | 104 | 2016-09-23 06:59:17 | Z-44 |
| d474cc6a-e7a1-15d1-d209-57e4c5aa607d | 105 | 2016-09-23 05:03:08 | Z-45 |
| db77b687-763d-b63a-be77-57e4d2e246fb | 105 | 2016-09-23 05:51:41 | Z-45 |
| 70f0f514-c0fd-ddfd-55a6-57e4d21b5e3c | 106 | 2016-09-23 05:29:39 | Z-46 |
+--------------------------------------+-----+---------------------+------+

这里我只想获取那些属于同一+--------------------------------------+-----+----------+ | id | no | COUNT(*) | +--------------------------------------+-----+----------+ | 5dd46d35-358a-314e-30fa-57e4d2ca92ad | 104 | 3 | | db77b687-763d-b63a-be77-57e4d2e246fb | 105 | 3 | +--------------------------------------+-----+----------+并且是最旧的记录。此查询也应该在有多个记录属于同一no的情况下运行。所以这是我正在使用的查询

no

但我得到了这个结果

SELECT id, no, COUNT(*) 
FROM test 
GROUP BY no 
HAVING COUNT(*) > 1 
ORDER BY date_entered DESC;

现在，我已经四处寻求帮助了，我得到了这个How to combine GROUP BY, ORDER BY and HAVING，并且在+--------------------------------------+-----+----------+ | id | no | COUNT(*) | +--------------------------------------+-----+----------+ | c44d1977-0193-a2f1-00f9-57e4c53ba416 | 104 | 3 | | d474cc6a-e7a1-15d1-d209-57e4c5aa607d | 105 | 3 | +--------------------------------------+-----+----------+的已接受答案中提到了，所以我也尝试了这个查询：

However, you need to pick the fields you ACTUALLY WANT then select only those and group by them

但执行此查询后，我没有。请在这里指导我。

Answer 1

一种方法是使用substring_index() / group_concat()技巧：

SELECT SUBSTRING_INDEX(GROUP_CONCAT(id ORDER BY date_entered DESC), ',', 1) as id,
       no, COUNT(*) 
FROM test 
GROUP BY no 
HAVING COUNT(*) > 1 ;

这种方法有一些限制。 GROUP_CONCAT()的默认内部大小为1,024字节。这很容易重新配置，但它假定您没有给定数量的太多ID。

有其他方法，使用变量或更复杂的SQL语句。但是，这是最适合您当前查询的。

没有使用GROUP BY，ORDER BY和HAVING得到结果

1 个答案: