Merge pull request #146 from JaerongA/metrics

Remap `metrics.csv` column names
datajoint · Apr 19, 2023 · 6aef807 · 6aef807
2 parents 5abecc3 + 6b069e6
commit 6aef807
Show file tree

Hide file tree

Showing 6 changed files with 30 additions and 3 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,6 +3,10 @@
 Observes [Semantic Versioning](https://semver.org/spec/v2.0.0.html) standard and
  [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) convention.
 
+## [0.2.7] - 2023-04-19
+
++ Bugfix - A name remapping dictionary was added to ensure consistency between the column names of the `metrics.csv` file and the attribute names of the `QualityMetrics` table
+
 ## [0.2.6] - 2023-04-17
 
 + Fix - Update Pandas DataFrame column name to insert `pt_ratio` in `QualityMetrics.Waveform` table
@@ -101,6 +105,7 @@ Observes [Semantic Versioning](https://semver.org/spec/v2.0.0.html) standard and
 + Add - Probe table supporting: Neuropixels probes 1.0 - 3A, 1.0 - 3B, 2.0 - SS,
   2.0 - MS
 
+[0.2.7]: https://github.com/datajoint/element-array-ephys/releases/tag/0.2.7
 [0.2.6]: https://github.com/datajoint/element-array-ephys/releases/tag/0.2.6
 [0.2.5]: https://github.com/datajoint/element-array-ephys/releases/tag/0.2.5
 [0.2.4]: https://github.com/datajoint/element-array-ephys/releases/tag/0.2.4

diff --git a/element_array_ephys/ephys_acute.py b/element_array_ephys/ephys_acute.py
@@ -1353,6 +1353,11 @@ def make(self, key):
         kilosort_dir = find_full_path(get_ephys_root_data_dir(), output_dir)
 
         metric_fp = kilosort_dir / "metrics.csv"
+        rename_dict = {
+            "isi_viol": "isi_violation",
+            "num_viol": "number_violation",
+            "contam_rate": "contamination_rate",
+        }
 
         if not metric_fp.exists():
             raise FileNotFoundError(f"QC metrics file not found: {metric_fp}")
@@ -1361,6 +1366,7 @@ def make(self, key):
         metrics_df.set_index("cluster_id", inplace=True)
         metrics_df.replace([np.inf, -np.inf], np.nan, inplace=True)
         metrics_df.columns = metrics_df.columns.str.lower()
+        metrics_df.rename(columns=rename_dict, inplace=True)
         metrics_list = [
             dict(metrics_df.loc[unit_key["unit"]], **unit_key)
             for unit_key in (CuratedClustering.Unit & key).fetch("KEY")

diff --git a/element_array_ephys/ephys_chronic.py b/element_array_ephys/ephys_chronic.py
@@ -1282,6 +1282,11 @@ def make(self, key):
         kilosort_dir = find_full_path(get_ephys_root_data_dir(), output_dir)
 
         metric_fp = kilosort_dir / "metrics.csv"
+        rename_dict = {
+            "isi_viol": "isi_violation",
+            "num_viol": "number_violation",
+            "contam_rate": "contamination_rate",
+        }
 
         if not metric_fp.exists():
             raise FileNotFoundError(f"QC metrics file not found: {metric_fp}")
@@ -1290,6 +1295,7 @@ def make(self, key):
         metrics_df.set_index("cluster_id", inplace=True)
         metrics_df.replace([np.inf, -np.inf], np.nan, inplace=True)
         metrics_df.columns = metrics_df.columns.str.lower()
+        metrics_df.rename(columns=rename_dict, inplace=True)
         metrics_list = [
             dict(metrics_df.loc[unit_key["unit"]], **unit_key)
             for unit_key in (CuratedClustering.Unit & key).fetch("KEY")

diff --git a/element_array_ephys/ephys_no_curation.py b/element_array_ephys/ephys_no_curation.py
@@ -1293,6 +1293,11 @@ def make(self, key):
         kilosort_dir = find_full_path(get_ephys_root_data_dir(), output_dir)
 
         metric_fp = kilosort_dir / "metrics.csv"
+        rename_dict = {
+            "isi_viol": "isi_violation",
+            "num_viol": "number_violation",
+            "contam_rate": "contamination_rate",
+        }
 
         if not metric_fp.exists():
             raise FileNotFoundError(f"QC metrics file not found: {metric_fp}")
@@ -1301,6 +1306,7 @@ def make(self, key):
         metrics_df.set_index("cluster_id", inplace=True)
         metrics_df.replace([np.inf, -np.inf], np.nan, inplace=True)
         metrics_df.columns = metrics_df.columns.str.lower()
+        metrics_df.rename(columns=rename_dict, inplace=True)
         metrics_list = [
             dict(metrics_df.loc[unit_key["unit"]], **unit_key)
             for unit_key in (CuratedClustering.Unit & key).fetch("KEY")

diff --git a/element_array_ephys/ephys_precluster.py b/element_array_ephys/ephys_precluster.py
@@ -616,7 +616,6 @@ def make(self, key):
                 ][recorded_site]
                 electrode_keys.append(probe_electrodes[(shank, shank_col, shank_row)])
         elif acq_software == "Open Ephys":
-
             session_dir = find_full_path(
                 get_ephys_root_data_dir(), get_session_directory(key)
             )
@@ -1270,6 +1269,11 @@ def make(self, key):
         kilosort_dir = find_full_path(get_ephys_root_data_dir(), output_dir)
 
         metric_fp = kilosort_dir / "metrics.csv"
+        rename_dict = {
+            "isi_viol": "isi_violation",
+            "num_viol": "number_violation",
+            "contam_rate": "contamination_rate",
+        }
 
         if not metric_fp.exists():
             raise FileNotFoundError(f"QC metrics file not found: {metric_fp}")
@@ -1278,7 +1282,7 @@ def make(self, key):
         metrics_df.set_index("cluster_id", inplace=True)
         metrics_df.replace([np.inf, -np.inf], np.nan, inplace=True)
         metrics_df.columns = metrics_df.columns.str.lower()
-
+        metrics_df.rename(columns=rename_dict, inplace=True)
         metrics_list = [
             dict(metrics_df.loc[unit_key["unit"]], **unit_key)
             for unit_key in (CuratedClustering.Unit & key).fetch("KEY")

diff --git a/element_array_ephys/version.py b/element_array_ephys/version.py
@@ -1,2 +1,2 @@
 """Package metadata."""
-__version__ = "0.2.6"
+__version__ = "0.2.7"