start to add tests and testing material

tests/data/conversations_parameters.yml

@@ -0,0 +1,56 @@
+package_version: 0.2.0
+date: '20240704_184950'
+parameters:
+  path: output/conversations
+  destination: output/conversations/extra/std_conv.csv
+  pipeline: standard
+  setname: custom_conv
+  recordings: null
+  from_time: null
+  to_time: null
+  rec_cols: null
+  child_cols: null
+  threads: 1
+  dataset_hash: 710ebfe1f4b118f8a48f69d896c6675bb72ef6ba
+  features_list:
+  - callable: who_initiated
+    args: {}
+    name: initiator
+  - callable: who_finished
+    args: {}
+    name: finisher
+  - callable: voc_total_dur
+    args: {}
+    name: total_duration_of_vocalisations
+  - callable: voc_speaker_count
+    args:
+      speaker: CHI
+    name: CHI_voc_count
+  - callable: voc_speaker_count
+    args:
+      speaker: FEM
+    name: FEM_voc_count
+  - callable: voc_speaker_count
+    args:
+      speaker: MAL
+    name: MAL_voc_count
+  - callable: voc_speaker_count
+    args:
+      speaker: OCH
+    name: OCH_voc_count
+  - callable: voc_speaker_dur
+    args:
+      speaker: CHI
+    name: CHI_voc_dur
+  - callable: voc_speaker_dur
+    args:
+      speaker: FEM
+    name: FEM_voc_dur
+  - callable: voc_speaker_dur
+    args:
+      speaker: MAL
+    name: MAL_voc_dur
+  - callable: voc_speaker_dur
+    args:
+      speaker: OCH
+    name: OCH_voc_dur

tests/data/list_features_conv.csv

@@ -0,0 +1,6 @@
+callable,name,speaker
+who_initiated,initiator,
+who_finished,finisher,
+participants,participants,
+voc_dur_contribution,chi_dur_contrib,CHI
+voc_dur_contribution,fem_dur_contrib,FEM

tests/test_conversations.py

@@ -0,0 +1,206 @@
+from functools import partial
+import numpy as np
+import os
+import pandas as pd
+import pytest
+import shutil
+from pathlib import Path
+
+from ChildProject.projects import ChildProject
+from ChildProject.annotations import AnnotationManager
+from ChildProject.pipelines.conversations import (Conversations, StandardConversations, CustomConversations,
+                                                 ConversationsSpecificationPipeline)
+
+from ChildProject.pipelines.conversationFunctions import conversationFunction, RESERVED
+
+PATH = Path('output/conversations')
+
+
+def fake_vocs(data, filename):
+    return data
+
+
+@pytest.fixture(scope="function")
+def project(request):
+    if os.path.exists(PATH):
+        # shutil.copytree(src="examples/valid_raw_data", dst="output/annotations")
+        shutil.rmtree(PATH)
+    shutil.copytree(src="examples/valid_raw_data", dst=PATH)
+
+    project = ChildProject(PATH)
+    project.read()
+
+    yield project
+
+
+@pytest.fixture(scope="function")
+def am(request, project):
+    am = AnnotationManager(project)
+    project.recordings['duration'] = [100000000, 2000000] #force longer durations to allow for imports
+    yield am
+
+@pytest.fixture(scope="function")
+def segments(request):
+    segments = pd.read_csv("tests/data/csv.csv")
+    segments.loc[2:4, 'conv_count'] = 1
+    segments.loc[8:9, 'conv_count'] = 2
+    segments.loc[10:11, 'conv_count'] = 3
+
+    yield segments
+
+
+def test_failures(project):
+    features = pd.DataFrame([["who_initiated", "initiator", pd.NA],
+                             ["who_finished", "finisher", pd.NA],
+                             ["voc_speaker_count", "CHI_voc_count", 'CHI'],
+                             ], columns=['callable', 'name', 'speaker'])
+
+    exception_caught = False
+    try:
+        standard = StandardConversations(project, setname="unknown")
+    except ValueError as e:
+        exception_caught = True
+
+    assert (
+            exception_caught is True
+    ), "StandardConversations failed to throw an exception despite an invalid set being provided"
+
+    exception_caught = False
+    try:
+        custom = CustomConversations(project, setname="unknown", features='tests/data/list_features_conv.csv')
+    except ValueError as e:
+        exception_caught = True
+
+    assert (
+            exception_caught is True
+    ), "CustomConversations failed to throw an exception despite an invalid set being provided"
+
+
+@pytest.mark.parametrize("error,col_change,new_value",
+                         [(ValueError, 'name', 'finisher'),
+                          (ValueError, 'callable', 'made_up_function'),
+                          (TypeError, 'speaker', 'FEM'),
+                          (None, None, None),
+                          ])
+def test_conversations(project, am, segments, error, col_change, new_value):
+
+    am.import_annotations(
+        pd.DataFrame(
+            [{  "set": "custom_conv",
+                "raw_filename": "file.its",
+                "time_seek": 0,
+                "recording_filename": "sound.wav",
+                "range_onset": 0,
+                "range_offset": 30000000,
+                "format": "csv",
+            }]
+        ),
+        import_function=partial(fake_vocs, segments),
+    )
+
+    features = pd.DataFrame([["who_initiated", "initiator", pd.NA],
+                               ["who_finished", "finisher", pd.NA],
+                               ["voc_speaker_count", "CHI_voc_count", 'CHI'],
+                              ], columns=['callable', 'name', 'speaker'])
+
+    if error:
+        with pytest.raises(error):
+            features.iloc[0, features.columns.get_loc(col_change)] = new_value
+            cm = Conversations(project, 'custom_conv', features)
+            cm.extract()
+    else:
+        cm = Conversations(project, 'custom_conv', features)
+        results = cm.extract()
+
+        cm.conversations.to_csv("tests/truth/python_conversations.csv",index=False)
+        truth = pd.read_csv("tests/truth/python_conversations.csv")
+
+        pd.testing.assert_frame_equal(truth, results)
+
+        pd.testing.assert_frame_equal(results, truth, check_like=True)
+
+#TODO adapt
+def test_standard(project, am, segments):
+    am.import_annotations(
+        pd.DataFrame(
+            [{"set": "custom_conv",
+              "raw_filename": "file.its",
+              "time_seek": 0,
+              "recording_filename": "sound.wav",
+              "range_onset": 0,
+              "range_offset": 30000000,
+              "format": "csv",
+              }]
+        ),
+        import_function=partial(fake_vocs, segments),
+    )
+
+    std = StandardConversations(project, setname='custom_conv',rec_cols='date_iso', child_cols='experiment,child_dob')
+    std.extract()
+
+    # std.conversations.to_csv("tests/truth/standard_conversations.csv", index=False)
+    truth = pd.read_csv("tests/truth/standard_conversations.csv")
+
+    pd.testing.assert_frame_equal(std.conversations, truth, check_like=True)
+
+
+#TODO adapt
+def test_custom(project, am, segments):
+    am.import_annotations(
+        pd.DataFrame(
+            [{"set": "custom_conv",
+              "raw_filename": "file.its",
+              "time_seek": 0,
+              "recording_filename": "sound.wav",
+              "range_onset": 0,
+              "range_offset": 30000000,
+              "format": "csv",
+              }]
+        ),
+        import_function=partial(fake_vocs, segments),
+    )
+
+    parameters = "tests/data/list_features_conv.csv"
+
+    cm = CustomConversations(project, 'custom_conv', parameters)
+    cm.extract()
+
+    # cm.conversations.to_csv("tests/truth/custom_conversations.csv", index=False)
+    truth = pd.read_csv("tests/truth/custom_conversations.csv")
+
+    pd.testing.assert_frame_equal(cm.conversations, truth, check_like=True)
+
+
+#TODO adapt
+def test_specs(project, am, segments):
+    am.import_annotations(
+        pd.DataFrame(
+            [{"set": "custom_conv",
+              "raw_filename": "file.its",
+              "time_seek": 0,
+              "recording_filename": "sound.wav",
+              "range_onset": 0,
+              "range_offset": 30000000,
+              "format": "csv",
+              }]
+        ),
+        import_function=partial(fake_vocs, segments),
+    )
+
+    csp = ConversationsSpecificationPipeline()
+
+    parameters = "tests/data/conversations_parameters.yml"
+    csp.run(parameters)
+
+    output = pd.read_csv(csp.destination)
+    output.to_csv("tests/truth/specs_conversations.csv", index=False)
+    truth = pd.read_csv("tests/truth/specs_conversations.csv")
+
+    pd.testing.assert_frame_equal(output, truth, check_like=True)
+
+    new_params = csp.parameters_path
+    csp.run(new_params)
+
+    output = pd.read_csv(csp.destination)
+
+    pd.testing.assert_frame_equal(output, truth, check_like=True)

tests/test_metrics.py

@@ -36,7 +36,7 @@ def am(request, project):
     project.recordings['duration'] = [100000000, 2000000] #force longer durations to allow for imports
     yield am    
 
-#decorating functions with reserved kwargs should fail
+# decorating functions with reserved kwargs should fail
 @pytest.mark.parametrize("error", [ValueError, ])
 def test_decorator(error):
     for reserved in RESERVED:

tests/truth/custom_conversations.csv

@@ -0,0 +1,4 @@
+conversation_onset,conversation_offset,voc_count,conv_count,interval_last_conv,recording_filename,initiator,finisher,participants,chi_dur_contrib,fem_dur_contrib
+1984136,1988951,3,1.0,,sound.wav,CHI,FEM,CHI/OCH/FEM,0.1286786786786787,0.5193693693693694
+28284010,28287945,2,2.0,26295059.0,sound.wav,OCH,OCH,OCH/MAL,,
+28288492,28294692,2,3.0,2917.0,sound.wav,OCH,MAL,OCH/MAL,,

tests/truth/python_conversations.csv

@@ -0,0 +1,4 @@
+conversation_onset,conversation_offset,voc_count,conv_count,interval_last_conv,recording_filename,initiator,finisher,CHI_voc_count
+1984136,1988951,3,1.0,,sound.wav,CHI,FEM,1
+28284010,28287945,2,2.0,26295059.0,sound.wav,OCH,OCH,0
+28288492,28294692,2,3.0,2917.0,sound.wav,OCH,MAL,0

tests/truth/standard_conversations.csv

@@ -0,0 +1,4 @@
+conversation_onset,conversation_offset,voc_count,conv_count,interval_last_conv,recording_filename,initiator,finisher,total_duration_of_vocalisations,CHI_voc_count,FEM_voc_count,MAL_voc_count,OCH_voc_count,CHI_voc_dur,FEM_voc_dur,MAL_voc_dur,OCH_voc_dur,child_id,date_iso,experiment,child_dob
+1984136,1988951,3,1.0,,sound.wav,CHI,FEM,6660,1,1,0,1,857.0,3459.0,,2344,1,2020-04-20,test,2020-01-01
+28284010,28287945,2,2.0,26295059.0,sound.wav,OCH,OCH,4089,0,0,1,1,,,154.0,3935,1,2020-04-20,test,2020-01-01
+28288492,28294692,2,3.0,2917.0,sound.wav,OCH,MAL,1001,0,0,1,1,,,486.0,515,1,2020-04-20,test,2020-01-01