Remove _norm from file paths

angelolab · Jul 12, 2021 · 723a1b2 · 723a1b2
1 parent 962112d
commit 723a1b2
Show file tree

Hide file tree

Showing 3 changed files with 7 additions and 8 deletions.
diff --git a/ark/phenotyping/run_pixel_som.R b/ark/phenotyping/run_pixel_som.R
@@ -44,8 +44,7 @@ markers <- colnames(somWeights)
 print("Mapping data to cluster labels")
 for (i in 1:length(fovs)) {
     # read in pixel data
-    fovName <- file.path(fovs[i], "norm", fsep="_")
-    fileName <- file.path(fovName, "feather", fsep=".")
+    fileName <- file.path(fovs[i], "feather", fsep=".")
     matPath <- file.path(pixelMatDir, fileName)
     fovPixelData <- arrow::read_feather(matPath)
 

diff --git a/ark/phenotyping/som_utils.py b/ark/phenotyping/som_utils.py
@@ -79,9 +79,9 @@ def preprocess_row_sums(fovs, channels, base_dir, pre_dir='pixel_mat_preprocesse
 
         pixel_data = normalize_rows(pixel_data, channels)
 
-        # write the normalized data
+        # write the normalized data, overwrite with sum normalized values
         feather.write_dataframe(pixel_data,
-                                os.path.join(preprocessed_path, fov + '_norm.feather'),
+                                os.path.join(preprocessed_path, fov + '.feather'),
                                 compression='uncompressed')
 
 
@@ -540,7 +540,7 @@ def cluster_pixels(fovs, base_dir, pre_dir='pixel_mat_preprocessed',
     preprocess_row_sums(fovs, weights.columns.values, base_dir, pre_dir)
 
     # ensure the norm vals columns are valid indexes
-    sum_norm_files = io_utils.list_files(preprocessed_path, substrs='_norm.feather')
+    sum_norm_files = io_utils.list_files(preprocessed_path, substrs='.feather')
     norm_vals = feather.read_dataframe(os.path.join(base_dir, norm_vals_name))
     sample_fov = feather.read_dataframe(os.path.join(base_dir, pre_dir, sum_norm_files[0]))
     sample_fov = sample_fov.drop(

diff --git a/ark/phenotyping/som_utils_test.py b/ark/phenotyping/som_utils_test.py
@@ -278,15 +278,15 @@ def test_preprocess_row_sums():
         som_utils.preprocess_row_sums(fovs, chans, temp_dir, 'pixel_mat_preprocessed')
 
         for fov in fovs:
-            # assert we actually created a fov_norm.feather file
+            # assert we still have a fov.feather file
             assert os.path.exists(
-                os.path.join(temp_dir, 'pixel_mat_preprocessed', fov + '_norm.feather')
+                os.path.join(temp_dir, 'pixel_mat_preprocessed', fov + '.feather')
             )
 
             # read the row preprocessed data in
             fov_row_pre = feather.read_dataframe(os.path.join(temp_dir,
                                                               'pixel_mat_preprocessed',
-                                                              fov + '_norm.feather'))
+                                                              fov + '.feather'))
 
             # drop the metadata columns
             fov_row_pre = fov_row_pre.drop(