From 455da06aa6459da0d25b286ca6cb866ff64c4c34 Mon Sep 17 00:00:00 2001
From: Christoph Helma <helma@in-silico.ch>
Date: Thu, 20 Jun 2019 22:01:50 +0200
Subject: separate csv serialisations for batch predictions and training data,
 repeated measurements in mutagenicity dataset fixed, daphnia import fixed,
 CENTRAL_MONGO_IP removed

---
 test/dataset.rb | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

(limited to 'test/dataset.rb')

diff --git a/test/dataset.rb b/test/dataset.rb
index 8e230e0..b978512 100644
--- a/test/dataset.rb
+++ b/test/dataset.rb
@@ -137,7 +137,6 @@ class DatasetTest < MiniTest::Test
       d = Dataset.from_csv_file File.join(DATA_DIR,"batch_prediction_#{type}_small.csv")
       assert_equal Dataset, d.class
       refute_nil d.id
-      dataset = Dataset.find d.id
       assert_equal 3, d.compounds.size
     end
   end
@@ -175,10 +174,16 @@ class DatasetTest < MiniTest::Test
     datasets = [hansen,efsa,kazius]
     map = {"mutagen" => "mutagenic", "nonmutagen" => "non-mutagenic"}
     dataset = Dataset.merge datasets: datasets, features: datasets.collect{|d| d.bioactivity_features.first}, value_maps: [nil,nil,map], keep_original_features: true, remove_duplicates: true
-    assert_equal 8281, dataset.compounds.size
-    assert_equal 9, dataset.features.size
+    csv = dataset.to_training_csv
+    rows = csv.split("\n")
+    header = rows.shift
+    assert_equal "Canonical SMILES,Mutagenicity",header
+    values = rows.collect{|r| r.split(",")[1]}.uniq
+    assert_equal 2, values.size
+    assert_equal 8290, dataset.compounds.size
     c = Compound.from_smiles("C/C=C/C=O")
     assert_equal ["mutagenic"], dataset.values(c,dataset.merged_features.first)
+    assert_equal 9, dataset.features.size
   end
 
   # serialisation
@@ -203,6 +208,13 @@ class DatasetTest < MiniTest::Test
   end
 
   # special cases/details
+ 
+  def test_daphnia_import
+    d = Dataset.from_csv_file File.join(File.dirname(__FILE__),"..","data", "Acute_toxicity-Daphnia_magna.csv")
+    assert 3, d.features.size
+    assert 546, d.compounds.size
+    puts d.to_training_csv
+  end
 
   def test_dataset_accessors
     d = Dataset.from_csv_file "#{DATA_DIR}/multicolumn.csv"
-- 
cgit v1.2.3