gistfile1.clj

(defn data->maps "Turns a vector of vectors into a seq of maps"
  [keys data]
  (map #(zipmap keys %) data))

(defn data-merge
  "Merge two data sets on the given key"
  [merge-key a b]
  (let [indexed-b (zipmap (map merge-key b) b)]
    (map #(into % (indexed-b (merge-key %))) (filter #(contains? indexed-b (merge-key %)) a))))
        
(def d1 (data->maps [:id :c1 :c2] [[:a 1 2] [:b 3 4] [:c 5 6]]))
(def d2 (data->maps [:id :c3 :c4] [[:a 7 8] [:b 9 10] [:d 11 12]]))

(data-merge :id d1 d2)

; Incanter's version is a right join, not an inner join
(def d3 (dataset [:id :c1 :c2] [[:a 1 2] [:b 3 4] [:c 5 6]]))
(def d4 (dataset [:id :c3 :c4] [[:a 7 8] [:b 9 10] [:d 11 12]])
($join [:id :id] d3 d4)