From 67393144c60bbb2b487c67cd8f7e5465eeb48e55 Mon Sep 17 00:00:00 2001
From: Holger Frey <frey@imtek.de>
Date: Tue, 16 Feb 2021 16:48:35 +0100
Subject: [PATCH] added new submodule 'utils'

---
 sensospot_data/__init__.py      |  1 +
 sensospot_data/normalisation.py | 12 +++---------
 sensospot_data/utils.py         |  6 ++++++
 tests/test_normailsation.py     | 13 ++-----------
 tests/test_sensovation_data.py  |  1 +
 tests/test_utils.py             | 14 ++++++++++++++
 6 files changed, 27 insertions(+), 20 deletions(-)
 create mode 100644 sensospot_data/utils.py
 create mode 100644 tests/test_utils.py

diff --git a/sensospot_data/__init__.py b/sensospot_data/__init__.py
index a8f393a..33f35b1 100644
--- a/sensospot_data/__init__.py
+++ b/sensospot_data/__init__.py
@@ -12,6 +12,7 @@ import click
 
 from .parser import parse_file, parse_folder  # noqa: F401
 from .parameters import ExposureInfo, get_measurement_params  # noqa: F401
+from .utils import split_data_frame
 
 
 @click.command()
diff --git a/sensospot_data/normalisation.py b/sensospot_data/normalisation.py
index 8e37bcc..074d5ea 100644
--- a/sensospot_data/normalisation.py
+++ b/sensospot_data/normalisation.py
@@ -21,13 +21,7 @@ PROBE_MULTI_INDEX = [
     RAW_DATA_POS_ID,
 ]
 
-
-def _split_data_frame(data_frame, column):
-    """ splits a data frame on unique column values """
-    values = data_frame[column].unique()
-    masks = {value: (data_frame[column] == value) for value in values}
-    return {value: data_frame[mask] for value, mask in masks.items()}
-
+from .utils import split_data_frame
 
 def _infer_exposure_from_parameters(data_frame):
     """infer the exposures from measurement parameters
@@ -90,7 +84,7 @@ def reduce_overflow(data_frame, column=RAW_DATA_SPOT_MEAN, limit=0.5):
     """ reduces the data set per channel, eliminating overflowing spots """
     data_frame = _check_overflow_limit(data_frame, column, limit)
 
-    split_frames = _split_data_frame(data_frame, SETTINGS_EXPOSURE_CHANNEL)
+    split_frames = split_data_frame(data_frame, SETTINGS_EXPOSURE_CHANNEL)
 
     return {
         channel_id: _reduce_overflow_in_channel(channel_frame)
@@ -101,7 +95,7 @@ def reduce_overflow(data_frame, column=RAW_DATA_SPOT_MEAN, limit=0.5):
 def _reduce_overflow_in_channel(channel_frame):
     """ does the heavy lifting for reduce_overflow """
 
-    split_frames = _split_data_frame(channel_frame, SETTINGS_EXPOSURE_TIME)
+    split_frames = split_data_frame(channel_frame, SETTINGS_EXPOSURE_TIME)
 
     if len(split_frames) == 1:
         # shortcut, if there is only one exposure in the channel
diff --git a/sensospot_data/utils.py b/sensospot_data/utils.py
new file mode 100644
index 0000000..e2060da
--- /dev/null
+++ b/sensospot_data/utils.py
@@ -0,0 +1,6 @@
+
+def split_data_frame(data_frame, column):
+    """ splits a data frame on unique column values """
+    values = data_frame[column].unique()
+    masks = {value: (data_frame[column] == value) for value in values}
+    return {value: data_frame[mask] for value, mask in masks.items()}
diff --git a/tests/test_normailsation.py b/tests/test_normailsation.py
index b9160d3..0825bfd 100644
--- a/tests/test_normailsation.py
+++ b/tests/test_normailsation.py
@@ -32,15 +32,6 @@ def df_wop(data_frame_without_params):
     return data_frame_without_params.copy()
 
 
-def test_split_data_frame(df_wp):
-    from sensospot_data.normalisation import _split_data_frame
-
-    result = _split_data_frame(df_wp, "Well.Row")
-
-    assert set(result.keys()) == set("ABC")
-    for key, value_df in result.items():
-        assert set(value_df["Well.Row"].unique()) == {key}
-
 
 def test_infer_exposure_from_parameters(df_wp):
     from sensospot_data.normalisation import _infer_exposure_from_parameters
@@ -206,13 +197,13 @@ def test_reduce_overflow(normalization_data_frame):
 
 
 def test_infer_normalization_map(normalization_data_frame):
+    from sensospot_data.utils import split_data_frame
     from sensospot_data.normalisation import (
-        _split_data_frame,
         _infer_normalization_map,
     )
 
     normalization_data_frame.loc[5, "Exposure.Channel"] = "Cy3"
-    split_frames = _split_data_frame(
+    split_frames = split_data_frame(
         normalization_data_frame, "Exposure.Channel"
     )
 
diff --git a/tests/test_sensovation_data.py b/tests/test_sensovation_data.py
index f8fa40c..20f5289 100644
--- a/tests/test_sensovation_data.py
+++ b/tests/test_sensovation_data.py
@@ -7,3 +7,4 @@ def test_import_api():
     from sensospot_data import parse_file  # noqa: F401
     from sensospot_data import parse_folder  # noqa: F401
     from sensospot_data import get_measurement_params  # noqa: F401
+    from sensospot_data import split_data_frame  # noqa: F401
\ No newline at end of file
diff --git a/tests/test_utils.py b/tests/test_utils.py
new file mode 100644
index 0000000..db8d7a0
--- /dev/null
+++ b/tests/test_utils.py
@@ -0,0 +1,14 @@
+
+from .conftest import EXAMPLE_DIR_WITH_PARAMS
+
+def test_split_data_frame(example_dir):
+    from sensospot_data.parser import parse_folder
+    from sensospot_data.utils import split_data_frame
+
+    data_frame = parse_folder(example_dir / EXAMPLE_DIR_WITH_PARAMS)
+
+    result = split_data_frame(data_frame, "Well.Row")
+
+    assert set(result.keys()) == set("ABC")
+    for key, value_df in result.items():
+        assert set(value_df["Well.Row"].unique()) == {key}
\ No newline at end of file