gistfile1.clj

(ns forma-local.core
  (:use forma.thrift
        cascalog.api
        [forma.hadoop.pail :only (?pail- split-chunk-tap)])
  (:require [incanter.core :as i]
            [cascalog.ops :as c]
            [forma.trends.analysis :as analyze]
            [forma.thrift :as thrift]
            [forma.classify.logistic :as log])
  (:import [backtype.hadoop.pail Pail]))

(def ts-path "/mnt/hgfs/Dropbox/local/timeseries")
(def static-path "/mnt/hgfs/Dropbox/local/masterpail")

(defn dynamic-src [pail-path]
  (let [src (split-chunk-tap pail-path ["ndvi"])]
    (<- [?h ?v ?s ?l ?ndvi-ts]
        (src _ ?x)
        (unpack ?x :> ?dataset ?pixel-chunk ?ts ?tres _)
        (unpack ?pixel-chunk :> ?sres ?h ?v ?s ?l)
        (unpack ?ts :> _ _ ?ndvi)
        (unpack* ?ndvi :> ?ndvi-ts))))

(defn vcf-src [pail-path]
  (let [src (split-chunk-tap pail-path ["vcf"])]
    (??<-  [?h ?v ?s ?l ?vcf]
         (src _ ?x)
         (unpack ?x :> _ ?loc ?vcf-obj _ _)
         (unpack ?loc :> _ ?h ?v ?s ?l)
         (get-field-value ?vcf-obj :> ?vcf)
         (>= ?vcf 25))))

(defn hansen-src [pail-path]
  (let [src (split-chunk-tap pail-path ["hansen"])]
    (??<- [?h ?v ?s ?l ?han-int]
         (src _ ?x)
         (unpack ?x :> _ ?loc ?hansen-obj _ _)
         (unpack ?loc :> _ ?h ?v ?s ?l)
         (get-field-value ?hansen-obj :> ?hansen)
         (i/div ?hansen 100 :> ?han-int))))