From e6b3d92913044066c1199fbca7e4554729adc03d Mon Sep 17 00:00:00 2001
From: Filip Gralinski <filipg@amu.edu.pl>
Date: Tue, 25 Aug 2015 21:26:51 +0200
Subject: [PATCH] --init handles BLEU metric now

---
 README.md                    | 29 ++++++++++++++++++++++-------
 src/GEval/CreateChallenge.hs | 19 +++++++++++++++++++
 2 files changed, 41 insertions(+), 7 deletions(-)

diff --git a/README.md b/README.md
index f96e740..96a06d4 100644
--- a/README.md
+++ b/README.md
@@ -10,20 +10,22 @@ machine learning algorithms are available here.
 ## Installing
 
 You need [Haskell Stack](https://github.com/commercialhaskell/stack),
-then install with:
+then install GEval with:
 
     git clone https://github.com/filipg/geval
     cd geval
     stack setup
     stack install
 
-By default `geval` library is installed in `$HOME/.local/bin`, so to
-run `geval` you need to either add `$HOME/.local/bin` to `$PATH` or to
-type:
+By default `geval` library is installed in `$HOME/.local/bin`, so in
+order to run `geval` you need to either add `$HOME/.local/bin` to
+`$PATH` or to type:
 
     PATH="$HOME/.local/bin" geval
 
-## Directory structure of a Gonito challenge
+## Preparing a Gonito challenge
+
+### Directory structure of a Gonito challenge
 
 A definition of a Gonito challenge should be put in a separate
 directory (preferably as a separate Git repo). Such a directory should
@@ -38,8 +40,8 @@ have the following structure:
 * `train/` — subdirectory with training data (if training data are
   supplied for a given Gonito challenge at all)
 * `train/train.tsv` — the usual name of training data (this name is
-  not required and could be more than file), the first column is the
-  target (predicted value), the other columns represent features, no
+  not required and could be more than one file), the first column is the
+  target (predicted) value, the other columns represent features, no
   header is assumed
 * `dev-0/` — subdirectory with a development set (a sample test set,
   which won't be used for the final evaluation)
@@ -56,3 +58,16 @@ have the following structure:
   organizers of a Gonito challenge, see notes on the structure of
   commits below
 * `test-B`, `test-C`, ... — other alternative test sets (if supplied)
+
+### Initiating a Gonito challenge with geval
+
+You can use `geval` to initiate a Gonito challenge:
+
+   geval --init --expected-directory my-challenge
+
+(This will generate a sample toy challenge with guessing the mass of a planet).
+
+A metric (other than the default root-mean-square error) can be given
+to generate another type of a toy challenge:
+
+   geval --init --expected-directory my-mt-challenge --metric BLEU
diff --git a/src/GEval/CreateChallenge.hs b/src/GEval/CreateChallenge.hs
index 3edbcec..9d8240e 100644
--- a/src/GEval/CreateChallenge.hs
+++ b/src/GEval/CreateChallenge.hs
@@ -68,6 +68,11 @@ configContents metric testName = [i|
 |]
 
 trainContents :: Metric -> String
+trainContents BLEU = [hereLit|alussa loi jumala taivaan ja maan	he mea hanga na te atua i te timatanga te rangi me te whenua
+ja maa oli autio ja tyhjä , ja pimeys oli syvyyden päällä	a kahore he ahua o te whenua , i takoto kau ; he pouri ano a runga i te mata o te hohonu
+ja jumalan henki liikkui vetten päällä	na ka whakapaho te wairua o te atua i runga i te kare o nga wai
+|]
+
 trainContents _ = [hereLit|0.06	0.39	0	0.206
 1.00	1.00	1	0.017
 317.8	5.20	67	0.048
@@ -75,21 +80,35 @@ trainContents _ = [hereLit|0.06	0.39	0	0.206
 |]
 
 devInContents :: Metric -> String
+devInContents BLEU = [hereLit|ja jumala sanoi : " tulkoon valkeus " , ja valkeus tuli
+ja jumala näki , että valkeus oli hyvä ; ja jumala erotti valkeuden pimeydestä
+|]
 devInContents _ = [hereLit|0.72	0	0.007
 9.54	62	0.054
 |]
 
 devExpectedContents :: Metric -> String
+devExpectedContents BLEU = [hereLit|a ka ki te atua , kia marama : na ka marama
+a ka kite te atua i te marama , he pai : a ka wehea e te atua te marama i te pouri
+|]
 devExpectedContents _ = [hereLit|0.82
 95.2
 |]
 
 testInContents :: Metric -> String
+testInContents BLEU = [hereLit|ja jumala kutsui valkeuden päiväksi , ja pimeyden hän kutsui yöksi
+ja tuli ehtoo , ja tuli aamu , ensimmäinen päivä
+|]
+
 testInContents _ = [hereLit|1.52	2	0.093
 30.06	14	0.009
 |]
 
 testExpectedContents :: Metric -> String
+testExpectedContents BLEU = [hereLit|na ka huaina e te atua te marama ko te awatea , a ko te pouri i huaina e ia ko te po
+a ko te ahiahi , ko te ata , he ra kotahi
+|]
+
 testExpectedContents _ = [hereLit|0.11
 17.2
 |]