Make sure test cases create the dummy data correctly for existing_data

src/toffy/normalize.py

@@ -230,7 +230,6 @@ def combine_run_metrics(run_dir, substring, warn_overwrite=True):
 
     if substring + "_combined.csv" in files:
         if warn_overwrite:
-            print("Warning of overwriting!")
             warnings.warn(
                 "Removing previously generated combined {} file in {}".format(substring, run_dir)
             )

src/toffy/watcher_callbacks.py

@@ -1,5 +1,6 @@
 import inspect
 import os
+import warnings
 from dataclasses import dataclass, field
 from typing import Iterable
 

tests/fov_watcher_test.py

@@ -7,15 +7,19 @@
 from pathlib import Path
 from unittest.mock import patch
 
+import numpy as np
+import pandas as pd
 import pytest
 from alpineer import io_utils
 from pytest_cases import parametrize_with_cases
 
 from toffy.fov_watcher import start_watcher
 from toffy.json_utils import write_json_file
+from toffy.settings import QC_COLUMNS, QC_SUFFIXES
 from toffy.watcher_callbacks import build_callbacks
 
 from .utils.test_utils import (
+    TEST_CHANNELS,
     RunStructureCases,
     RunStructureTestContext,
     WatcherCases,
@@ -161,12 +165,30 @@ def test_watcher(
 
             # if existing_data set to True, test case where a FOV has already been extracted
             if existing_data:
-                os.makedirs(os.path.join(tiff_out_dir, RUN_DIR_NAME, "fov-1-scan-1"))
-                Path(os.path.join(qc_out_dir, "fov-1-scan-1_nonzero_mean_stats.csv")).touch()
-                Path(os.path.join(qc_out_dir, "fov-1-scan-1_total_intensity_stats.csv")).touch()
-                Path(os.path.join(qc_out_dir, "fov-1-scan-1_percentile_99_9_stats.csv")).touch()
-                Path(os.path.join(mph_out_dir, "fov-1-scan-1-mph_pulse.csv")).touch()
-                Path(os.path.join(pulse_out_dir, "fov-1-scan-1-pulse_heights.csv")).touch()
+                os.makedirs(os.path.join(tiff_out_dir, "fov-2-scan-1"))
+
+                os.makedirs(qc_out_dir)
+                for qcs, qcc in zip(QC_SUFFIXES, QC_COLUMNS):
+                    df_qc = pd.DataFrame(
+                        np.random.rand(len(TEST_CHANNELS), 3), columns=["fov", "channel", qcc]
+                    )
+                    df_qc["fov"] = "fov-2-scan-1"
+                    df_qc["channel"] = TEST_CHANNELS
+                    df_qc.to_csv(os.path.join(qc_out_dir, f"fov-2-scan-1_{qcs}.csv"), index=False)
+
+                os.makedirs(mph_out_dir)
+                df_mph = pd.DataFrame(
+                    np.random.rand(1, 4), columns=["fov", "MPH", "total_count", "time"]
+                )
+                df_mph["fov"] = "fov-2-scan-1"
+                df_mph.to_csv(os.path.join(mph_out_dir, "fov-2-scan-1-mph_pulse.csv"), index=False)
+
+                os.makedirs(pulse_out_dir)
+                df_ph = pd.DataFrame(np.random.rand(10, 3), columns=["mass", "fov", "pulse_height"])
+                df_ph["fov"] = "fov-2-scan-1"
+                df_ph.to_csv(
+                    os.path.join(pulse_out_dir, "fov-2-scan-1-pulse_heights.csv"), index=False
+                )
 
             # `_slow_copy_sample_tissue_data` mimics the instrument computer uploading data to the
             # client access computer.  `start_watcher` is made async here since these processes
@@ -183,7 +205,7 @@ def test_watcher(
                 # watcher completion is checked every second
                 # zero-size files are halted for 1 second or until they have non zero-size
                 if existing_data:
-                    with pytest.warns(UserWarning, match="already extracted for FOV fov-1-scan-1"):
+                    with pytest.warns(UserWarning, match="already extracted for FOV fov-2-scan-1"):
                         res_scan = pool.apply_async(
                             start_watcher,
                             (

tests/utils/test_utils.py

@@ -18,6 +18,48 @@
 from toffy.json_utils import write_json_file
 from toffy.settings import QC_COLUMNS, QC_SUFFIXES
 
+TEST_CHANNELS = [
+    "Calprotectin",
+    "Chymase",
+    "SMA",
+    "Vimentin",
+    "LAG3",
+    "CD4",
+    "CD69",
+    "FAP",
+    "FOXP3",
+    "PD1",
+    "CD31",
+    "Biotin",
+    "Ecadherin",
+    "CD56",
+    "CD38",
+    "TCF1 TCF7",
+    "TBET",
+    "CD45RB",
+    "CD68",
+    "CD11c",
+    "CD8",
+    "CD3e",
+    "IDO1",
+    "CD45RO",
+    "TIM-3",
+    "CD163",
+    "CD20",
+    "FN1",
+    "Glut1",
+    "HLADR",
+    "CD14",
+    "CD45",
+    "Cytokeratin17",
+    "COL1A1",
+    "H3K27me3",
+    "CD57",
+    "H3K9ac",
+    "Ki67",
+    "HLA1 class ABC",
+]
+
 
 def make_run_file(tmp_dir, prefixes=[], include_nontiled=False):
     """Create a run subir and run json in the provided dir and return the path to this new dir."""