Refactor: Rename AnalysisHit to SubjectSuggestion. Part of #267

annif/backend/backend.py

@@ -37,7 +37,7 @@ def _suggest(self, text, project, params):
 
     def suggest(self, text, project, params=None):
         """Suggest subjects for the input text and return a list of subjects
-        represented as a list of AnalysisHit objects."""
+        represented as a list of SubjectSuggestion objects."""
         beparams = dict(self.params)
         if params is not None:
             beparams.update(params)

annif/backend/dummy.py

@@ -1,7 +1,7 @@
 """Dummy backend for testing basic interaction of projects and backends"""
 
 
-from annif.hit import AnalysisHit, ListAnalysisResult
+from annif.hit import SubjectSuggestion, ListAnalysisResult
 from . import backend
 
 
@@ -16,9 +16,9 @@ def initialize(self):
 
     def _suggest(self, text, project, params):
         score = float(params.get('score', 1.0))
-        return ListAnalysisResult([AnalysisHit(uri=self.uri,
-                                               label=self.label,
-                                               score=score)],
+        return ListAnalysisResult([SubjectSuggestion(uri=self.uri,
+                                                     label=self.label,
+                                                     score=score)],
                                   project.subjects)
 
     def learn(self, corpus, project):

annif/backend/fasttext.py

@@ -3,7 +3,7 @@
 import collections
 import os.path
 import annif.util
-from annif.hit import AnalysisHit, ListAnalysisResult
+from annif.hit import SubjectSuggestion, ListAnalysisResult
 from annif.exception import NotInitializedException
 import fastText
 from . import backend
@@ -127,7 +127,7 @@ def _suggest_chunks(self, chunktexts, project):
         results = []
         for score, label in best_labels[:limit]:
             subject = self._label_to_subject(project, label)
-            results.append(AnalysisHit(
+            results.append(SubjectSuggestion(
                 uri=subject[0],
                 label=subject[1],
                 score=score / len(chunktexts)))

annif/backend/http.py

@@ -4,7 +4,7 @@
 
 import requests
 import requests.exceptions
-from annif.hit import AnalysisHit, ListAnalysisResult
+from annif.hit import SubjectSuggestion, ListAnalysisResult
 from . import backend
 
 
@@ -35,9 +35,9 @@ def _suggest(self, text, project, params):
             results = response
 
         try:
-            return ListAnalysisResult([AnalysisHit(uri=h['uri'],
-                                                   label=h['label'],
-                                                   score=h['score'])
+            return ListAnalysisResult([SubjectSuggestion(uri=h['uri'],
+                                                         label=h['label'],
+                                                         score=h['score'])
                                        for h in results
                                        if h['score'] > 0.0],
                                       project.subjects)

annif/backend/pav.py

@@ -53,7 +53,7 @@ def _normalize_hits(self, hits, source_project):
             else:  # default to raw score
                 score = hit.score
             pav_result.append(
-                annif.hit.AnalysisHit(
+                annif.hit.SubjectSuggestion(
                     uri=hit.uri,
                     label=hit.label,
                     score=score))

annif/hit.py

@@ -5,12 +5,12 @@
 import numpy as np
 
 
-AnalysisHit = collections.namedtuple('AnalysisHit', 'uri label score')
+SubjectSuggestion = collections.namedtuple('AnalysisHit', 'uri label score')
 WeightedHits = collections.namedtuple('WeightedHits', 'hits weight')
 
 
 class HitFilter:
-    """A reusable filter for filtering AnalysisHit objects."""
+    """A reusable filter for filtering SubjectSuggestion objects."""
 
     def __init__(self, limit=None, threshold=0.0):
         self._limit = limit
@@ -29,7 +29,7 @@ class AnalysisResult(metaclass=abc.ABCMeta):
     @property
     @abc.abstractmethod
     def hits(self):
-        """Return the hits as an ordered sequence of AnalysisHit objects,
+        """Return the hits as an ordered sequence of SubjectSuggestion objects,
         highest scores first."""
         pass  # pragma: no cover
 
@@ -110,7 +110,7 @@ def _vector_to_hits(self):
                 continue  # we can skip the remaining ones
             subject = self._subject_index[subject_id]
             hits.append(
-                AnalysisHit(
+                SubjectSuggestion(
                     uri=subject[0],
                     label=subject[1],
                     score=score))

annif/project.py

@@ -168,7 +168,7 @@ def vectorizer(self):
 
     def suggest(self, text, backend_params=None):
         """Suggest subjects the given text by passing it to the backend. Returns a
-        list of AnalysisHit objects ordered by decreasing score."""
+        list of SubjectSuggestion objects ordered by decreasing score."""
 
         logger.debug('Suggesting subjects for text "%s..." (len=%d)',
                      text[:20], len(text))

tests/test_eval.py

@@ -93,13 +93,13 @@ def test_evaluation_batch(subject_index):
     gold_set = annif.corpus.SubjectSet.from_string(
         '<http://www.yso.fi/onto/yso/p10849>\tarkeologit')
     hits1 = annif.hit.ListAnalysisResult([
-        annif.hit.AnalysisHit(
+        annif.hit.SubjectSuggestion(
             uri='http://www.yso.fi/onto/yso/p10849',
             label='arkeologit',
             score=1.0)], subject_index)
     batch.evaluate(hits1, gold_set)
     hits2 = annif.hit.ListAnalysisResult([
-        annif.hit.AnalysisHit(
+        annif.hit.SubjectSuggestion(
             uri='http://www.yso.fi/onto/yso/p1747',
             label='egyptologit',
             score=1.0)], subject_index)

tests/test_hit.py

@@ -1,6 +1,6 @@
 """Unit tests for hit processing in Annif"""
 
-from annif.hit import AnalysisHit, AnalysisResult, LazyAnalysisResult, \
+from annif.hit import SubjectSuggestion, AnalysisResult, LazyAnalysisResult, \
     ListAnalysisResult, HitFilter
 from annif.corpus import SubjectIndex
 import numpy as np
@@ -9,9 +9,9 @@
 def generate_hits(n, subject_index):
     hits = []
     for i in range(n):
-        hits.append(AnalysisHit(uri='http://example.org/{}'.format(i),
-                                label='hit {}'.format(i),
-                                score=1.0 / (i + 1)))
+        hits.append(SubjectSuggestion(uri='http://example.org/{}'.format(i),
+                                      label='hit {}'.format(i),
+                                      score=1.0 / (i + 1)))
     return ListAnalysisResult(hits, subject_index)
 
 
@@ -31,7 +31,7 @@ def test_hitfilter_threshold(subject_index):
 
 def test_hitfilter_zero_score(subject_index):
     orighits = ListAnalysisResult(
-        [AnalysisHit(uri='uri', label='label', score=0.0)],
+        [SubjectSuggestion(uri='uri', label='label', score=0.0)],
         subject_index)
     hits = HitFilter()(orighits)
     assert isinstance(hits, AnalysisResult)
@@ -54,11 +54,11 @@ def test_analysishits_vector(document_corpus):
     subjects = SubjectIndex(document_corpus)
     hits = ListAnalysisResult(
         [
-            AnalysisHit(
+            SubjectSuggestion(
                 uri='http://www.yso.fi/onto/yso/p7141',
                 label='sinetit',
                 score=1.0),
-            AnalysisHit(
+            SubjectSuggestion(
                 uri='http://www.yso.fi/onto/yso/p6479',
                 label='viikingit',
                 score=0.5)],
@@ -79,7 +79,7 @@ def test_analysishits_vector_notfound(document_corpus):
     subjects = SubjectIndex(document_corpus)
     hits = ListAnalysisResult(
         [
-            AnalysisHit(
+            SubjectSuggestion(
                 uri='http://example.com/notfound',
                 label='not found',
                 score=1.0)],