Match feature table and ordination

empress/core.py

@@ -138,7 +138,7 @@ def _validate_and_match_data(self, ignore_missing_samples,
         # table for the rest of this visualizer.
         self.table, self.samples, self.tip_md, self.int_md = match_inputs(
             self.tree, self.table.T, self.samples, self.features,
-            ignore_missing_samples, filter_missing_features
+            self.ordination, ignore_missing_samples, filter_missing_features
         )
         # remove unobserved features from the phylogeny
         if filter_unobserved_features_from_phylogeny:

empress/tools.py

@@ -60,6 +60,7 @@ def match_inputs(
     table,
     sample_metadata,
     feature_metadata=None,
+    ordination=None,
     ignore_missing_samples=False,
     filter_missing_features=False
 ):
@@ -87,6 +88,8 @@ def match_inputs(
         IDs and the columns should describe different feature metadata fields'
         names. (Feature IDs here can describe tips or internal nodes in the
         tree.)
+    ordination: skbio.OrdinationResults, optional
+        The ordination to display in a tandem plot.
     ignore_missing_samples: bool
         If True, pads missing samples (i.e. samples in the table but not the
         metadata) with placeholder metadata. If False, raises a
@@ -136,6 +139,8 @@ def match_inputs(
                metadata, AND ignore_missing_samples is False.
             5. The feature metadata was passed, but no features present in it
                are also present as tips or internal nodes in the tree.
+            6. The ordination AND feature table don't have exactly the same
+               samples.
 
     References
     ----------
@@ -271,6 +276,17 @@ def match_inputs(
                 "either as tips or as internal nodes."
             )
 
+    if ordination is not None:
+        # tandem plots require a 1-1 match between feature table and ordination
+        mismatched = set(ordination.samples.index) ^ set(ff_table.columns)
+
+        if mismatched:
+            raise DataMatchingError(
+                "The feature table does not have exactly the same samples as "
+                "the ordination. These are the problematic sample identifiers:"
+                " %s" % (', '.join(sorted(mismatched)))
+            )
+
     return ff_table, sf_sample_metadata, tip_metadata, int_metadata
 
 

tests/python/test_tools.py

@@ -8,7 +8,7 @@
 import unittest
 import pandas as pd
 from pandas.testing import assert_frame_equal
-from skbio import TreeNode
+from skbio import TreeNode, OrdinationResults
 from empress import Tree, tools
 from empress.taxonomy_utils import split_taxonomy
 from bp import parse_newick, from_skbio_treenode
@@ -73,6 +73,25 @@ def setUp(self):
             "Level 7", "Confidence"
         ]
 
+        eigvals = pd.Series([0.50, 0.25, 0.25],
+                            index=['PC1', 'PC2', 'PC3'])
+        samples = [[0.1, 0.2, 0.3],
+                   [0.2, 0.3, 0.4],
+                   [0.3, 0.4, 0.5],
+                   [0.4, 0.5, 0.6]]
+        proportion_explained = pd.Series([15.5, 12.2, 8.8],
+                                         index=['PC1', 'PC2', 'PC3'])
+        samples_df = pd.DataFrame(samples,
+                                  index=['Sample1', 'Sample2', 'Sample3',
+                                         'Sample4'],
+                                  columns=['PC1', 'PC2', 'PC3'])
+        self.ordination = OrdinationResults(
+                'PCoA',
+                'Principal Coordinate Analysis',
+                eigvals,
+                samples_df,
+                proportion_explained=proportion_explained)
+
     def test_fill_missing_node_names(self):
         t = Tree.from_tree(self.tree)
         tools.fill_missing_node_names(t)
@@ -91,6 +110,20 @@ def test_match_inputs_nothing_dropped(self):
         self.assertIsNone(t_md)
         self.assertIsNone(i_md)
 
+    def test_match_inputs_nothing_dropped_with_ordination(self):
+        # everything is the same since the ordination has a 1:1 match to the
+        # feature table
+        filtered_table, filtered_sample_md, t_md, i_md = tools.match_inputs(
+            self.bp_tree, self.table, self.sample_metadata,
+            ordination=self.ordination
+        )
+
+        assert_frame_equal(filtered_table, self.table)
+        assert_frame_equal(filtered_sample_md, self.sample_metadata)
+        # We didn't pass in any feature metadata, so we shouldn't get any out
+        self.assertIsNone(t_md)
+        self.assertIsNone(i_md)
+
     def test_match_inputs_only_1_feature_in_table(self):
         # This is technically allowed (so long as this 1 feature is a tree tip)
         tiny_table = self.table.loc[["a"]]
@@ -381,6 +414,19 @@ def test_match_inputs_feature_metadata_only_internal_node_metadata(self):
         self.assertListEqual(list(t_fm.columns), self.exp_split_fm_cols)
         self.assertListEqual(list(i_fm.columns), self.exp_split_fm_cols)
 
+    def test_failed_match_to_ordination(self):
+        self.ordination.samples.index = pd.Index(['Sample1', 'Zample2',
+                                                  'Sample3', 'Sample4'])
+
+        with self.assertRaisesRegex(
+            tools.DataMatchingError,
+            "The feature table does not have exactly the same samples as the "
+            "ordination. These are the problematic sample identifiers: Sample2"
+            ", Zample2"
+        ):
+            tools.match_inputs(self.bp_tree, self.table, self.sample_metadata,
+                               ordination=self.ordination)
+
     def test_shifting(self):
         # helper test function to count number of bits in the number
         def _count_bits(n):