remove nono-breaking spaces

HISTORY.md

@@ -40,7 +40,7 @@
 # 0.5.3
 * FIX FragPipe loading issue
 
-# 0.5.2
+# 0.5.2
 * FIX FragPipe import #173
 
 # 0.5.1

alphastats/DataSet_Preprocess.py

@@ -154,7 +154,7 @@ def _filter(self):
             logging.info("Contaminatons have already been filtered.")
             return
 
-        #  print column names with contamination
+        # print column names with contamination
         protein_groups_to_remove = self.rawinput[
             self.rawinput[self.filter_columns].any(axis=1)
         ][self.index_column].tolist()

alphastats/gui/AlphaPeptStats.py

@@ -58,4 +58,4 @@
 # https://discuss.streamlit.io/t/icons-for-the-multi-app-page-menu-in-the-sidebar-other-than-emojis/27222
 # https://icons.getbootstrap.com/
 # https://medium.com/codex/create-a-multi-page-app-with-the-new-streamlit-option-menu-component-3e3edaf7e7ad
-#  https://lightrun.com/answers/streamlit-streamlit-set-multipage-app-emoji-in-stpage_config-not-filename
+# https://lightrun.com/answers/streamlit-streamlit-set-multipage-app-emoji-in-stpage_config-not-filename

alphastats/loader/AlphaPeptLoader.py

@@ -44,7 +44,7 @@ def __init__(
         self._add_contamination_reverse_column()
         self._add_contamination_column()
         self._read_all_column_names_as_string()
-        #  make ProteinGroup column
+        # make ProteinGroup column
         self.rawinput["ProteinGroup"] = self.rawinput[self.index_column].map(
             self.standardize_protein_group_column
         )

alphastats/loader/BaseLoader.py

@@ -82,13 +82,13 @@ def _check_if_file_exists(self, file):
             raise OSError(f"{file} does not exist.")
 
     def _add_contamination_column(self):
-        #  load df with potential contamination from fasta file
+        # load df with potential contamination from fasta file
         contaminations_path = (
             importlib_resources.files(__package__) / "../data/contaminations.txt"
         )
         contaminations = pd.read_csv(contaminations_path, sep="\t")
         contaminations_ids = contaminations["Uniprot ID"].to_list()
-        #  add column with True False
+        # add column with True False
 
         self.rawinput["contamination_library"] = np.where(
             self.rawinput[self.index_column].isin(contaminations_ids), True, False

alphastats/loader/FragPipeLoader.py

@@ -36,10 +36,10 @@ def __init__(
 """
 # https://github.com/Nesvilab/MSFragger/wiki/Interpreting-MSFragger-Output
 
-#  SAMPLE
+# SAMPLE
 # columm Spectrum
 
 # https://fragpipe.nesvilab.org/docs/tutorial_fragpipe_outputs.html#combined_proteintsv
 # Frag pipe
 # https://github.com/Nesvilab/philosopher/wiki/Combined-protein-reports
-#  ProteinProphet: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5863791/
+# ProteinProphet: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5863791/

alphastats/loader/GenericLoader.py

@@ -53,7 +53,7 @@ def _extract_sample_names(self, metadata: pd.DataFrame, sample_column: str):
     def load_file(self, file_path):
         if isinstance(file_path, pd.DataFrame):
             df = file_path
-        #  loading file needs to be more beautiful
+        # loading file needs to be more beautiful
         elif file_path.endswith(".xlsx"):
             df = pd.read_excel(file_path)
             # find robust way to detect file format

alphastats/plots/DimensionalityReduction.py

@@ -166,7 +166,7 @@ def _plot(self, sample_names, group_color):
             fig_dict["data"][count]["hovertemplate"] = hover
         fig = go.Figure(fig_dict)
 
-        #  save plotting data in figure object
+        # save plotting data in figure object
         fig = plotly_object(fig)
         self._update_figure_attributes(
             fig,

alphastats/plots/IntensityPlot.py

@@ -78,7 +78,7 @@ def _add_significance(plot):
 
         group1, group2 = data[0]["name"], data[1]["name"]
         y_array1, y_array2 = data[0]["y"], data[1]["y"]
-        #  do ttest
+        # do ttest
         pvalue = scipy.stats.ttest_ind(y_array1, y_array2).pvalue
 
         pvalue_text = "<i>p=" + str(round(pvalue, 4)) + "</i>"
@@ -136,7 +136,7 @@ def _add_significance(plot):
         return plot
 
     def _prepare_data(self):
-        #  TODO use difflib to find similar ProteinId if ProteinGroup is not present
+        # TODO use difflib to find similar ProteinId if ProteinGroup is not present
         df = (
             self.mat[[self.protein_id]]
             .reset_index()

alphastats/plots/VolcanoPlot.py

@@ -332,7 +332,7 @@ def _anova(self):
         mat_transpose = self.mat.transpose()
         fc = self._calculate_foldchange(mat_transpose, group1_samples, group2_samples)
 
-        #  check how column is ordered
+        # check how column is ordered
         self.pvalue_column = self.group1 + " vs. " + self.group2 + " Tukey Test"
 
         if self.pvalue_column not in result_df.columns:
@@ -402,7 +402,7 @@ def get_colored_labels(self):
             self.res["label"] = np.where(
                 self.res.color != "non_sig", self.res[label_column], ""
             )
-            #  replace nas with empty string (can cause error when plotting with gene names)
+            # replace nas with empty string (can cause error when plotting with gene names)
             self.res["label"] = self.res["label"].fillna("")
             self.res = self.res[self.res["label"] != ""]
         if "color" not in self.res.columns:
@@ -427,7 +427,7 @@ def get_colored_labels_df(self):
             self.res["label"] = np.where(
                 self.res.color != "non_sig", self.res[label_column], ""
             )
-            #  replace nas with empty string (can cause error when plotting with gene names)
+            # replace nas with empty string (can cause error when plotting with gene names)
             self.res["label"] = self.res["label"].fillna("")
             self.res = self.res[self.res["label"] != ""]
         if "color" not in self.res.columns:
@@ -447,7 +447,7 @@ def _add_labels_plot(self):
         self.res["label"] = np.where(
             self.res.color != "non_sig", self.res[label_column], ""
         )
-        #  replace nas with empty string (can cause error when plotting with gene names)
+        # replace nas with empty string (can cause error when plotting with gene names)
         self.res["label"] = self.res["label"].fillna("")
         self.res["label"] = [
             ";".join([i for i in j.split(";") if i]) for j in self.res["label"].tolist()
@@ -536,7 +536,7 @@ def _plot(self):
         self.plot.update_layout(showlegend=False)
         self.plot.update_layout(width=600, height=700)
 
-        #  save plotting data in figure object
+        # save plotting data in figure object
         self.plot = plotly_object(self.plot)
         self._update_figure_attributes(
             self.plot,

alphastats/statistics/Anova.py

@@ -54,7 +54,7 @@ def _perform_anova(self) -> pd.DataFrame:
         return anova_df
 
     def _prepare_data(self):
-        #  generated list of list with samples
+        # generated list of list with samples
         subgroup = self.metadata[self.column].unique().tolist()
         self.all_groups = []
         for sub in subgroup:
@@ -66,7 +66,7 @@ def _prepare_data(self):
         self.mat_transpose = self.mat[self.protein_ids_list].transpose()
 
     def _create_tukey_df(self, anova_df: pd.DataFrame) -> pd.DataFrame:
-        #  combine tukey results with anova results
+        # combine tukey results with anova results
         df = (
             self.mat[self.protein_ids_list]
             .reset_index()

alphastats/statistics/DifferentialExpressionAnalysis.py

@@ -60,7 +60,7 @@ def _prepare_anndata(self):
         reduced_matrix = reduced_matrix.loc[:, (reduced_matrix != 0).any(axis=0)]
         # sort metadata according to matrix values
         list_to_sort = reduced_matrix.index.to_list()
-        #  reduce metadata
+        # reduce metadata
         obs_metadata = (
             self.metadata[self.metadata[self.sample].isin(group_samples)]
             .set_index(self.sample)

nbs/getting_started.ipynb

@@ -744,7 +744,7 @@
    "id": "b8244053-e920-447d-a405-7049507733a9",
    "metadata": {},
    "source": [
-    "## 3. Preprocess"
+    "## 3. Preprocess"
    ]
   },
   {

nbs/liu_2019.ipynb

@@ -5,7 +5,7 @@
    "id": "6b8d1145-74ff-40ef-914c-9a3fb21822d6",
    "metadata": {},
    "source": [
-    "# Plasma proteome profiling discovers novel proteins associated with non-alcoholic fatty liver disease\n",
+    "# Plasma proteome profiling discovers novel proteins associated with non-alcoholic fatty liver disease\n",
     "Liu et al. 2019\n",
     "\n",
     "In this notebook we want to reproduce the results from [Liu et al](https://doi.org/10.15252/msb.20188793). The aim is to identify proteins associated with non-alcoholic fatty liver disease (NAFLD)."
@@ -230,7 +230,7 @@
    "id": "9bcd5cda-0c9c-4e1a-9bcf-918a67cbbb35",
    "metadata": {},
    "source": [
-    "## Plot Intensity"
+    "## Plot Intensity"
    ]
   },
   {

tests/test_DataSet.py

@@ -45,7 +45,7 @@ def test_check_loader_no_error(self):
             # nothing raised -> ok
 
         def test_check_loader_error_invalid_column(self):
-            #  invalid index column
+            # invalid index column
             with self.assertRaises(ValueError):
                 self.loader.index_column = 100
                 self.obj._check_loader(loader=self.loader)
@@ -57,13 +57,13 @@ def test_check_loader_error_empty_df(self):
                 self.obj._check_loader(loader=self.loader)
 
         def test_check_loader_error_invalid_loader(self):
-            #  invalid loader, class
+            # invalid loader, class
             with self.assertRaises(LoaderError):
                 df = pd.DataFrame()
                 self.obj._check_loader(loader=df)
 
         def test_load_metadata(self):
-            #  is dataframe loaded
+            # is dataframe loaded
             self.assertIsInstance(self.obj.metadata, pd.DataFrame)
             self.assertFalse(self.obj.metadata.empty)
 
@@ -83,7 +83,7 @@ def test_load_metadata_warning(self, mock):
             mock.assert_called_once()
 
         def test_create_matrix(self):
-            #  matrix dimensions
+            # matrix dimensions
             self.assertEqual(self.obj.mat.shape, self.matrix_dim)
             # does the matrix only contain floats/integers and NAs
             is_dtype_numeric = list(
@@ -109,7 +109,7 @@ def test_preprocess_filter(self, mock):
             # is the new matrix smaller than the older matrix
             self.obj.preprocess(remove_contaminations=True)
             self.assertEqual(self.obj.mat.shape, self.matrix_dim_filtered)
-            #  info has been printed at least once
+            # info has been printed at least once
             mock.assert_called_once()
 
         @patch("logging.Logger.info")
@@ -176,7 +176,7 @@ def test_plot_sampledistribution(self):
             plot_dict = plot.to_plotly_json()
             # check if plotly object is not empty
             self.assertEqual(len(plot_dict.get("data")), 1)
-            #  check if it is logscale
+            # check if it is logscale
             self.assertEqual(plot_dict.get("layout").get("yaxis").get("type"), "log")
 
         def test_reset_preprocessing(self):
@@ -190,7 +190,7 @@ def test_reset_preprocessing(self):
 
 
 class TestAlphaPeptDataSet(BaseTestDataSet.BaseTest):
-    #  do testing which requires extra files only on TestAlphaPeptDataSet
+    # do testing which requires extra files only on TestAlphaPeptDataSet
     # to reduce the amount of compariosn files required
     def setUp(self):
         self.loader = AlphaPeptLoader(file="testfiles/alphapept/results_proteins.csv")
@@ -203,7 +203,7 @@ def setUp(self):
         # expected dimensions of matrix
         self.matrix_dim = (2, 3781)
         self.matrix_dim_filtered = (2, 3707)
-        #  metadata column to compare for PCA, t-test, etc.
+        # metadata column to compare for PCA, t-test, etc.
         self.comparison_column = "disease"
 
     def test_dataset_without_metadata(self):
@@ -235,7 +235,7 @@ def test_remove_misc_samples_in_metadata(self, mock):
             metadata_path_or_df=df,
             sample_column="sample",
         )
-        #  is sample C removed
+        # is sample C removed
         self.assertEqual(self.obj.metadata.shape, (2, 2))
         mock.assert_called_once()
 
@@ -358,11 +358,11 @@ def test_plot_sampledistribution_group(self):
         self.assertIsInstance(plot, plotly.graph_objects.Figure)
         # convert plotly object to dict
         plot_dict = plot.to_plotly_json()
-        #  check if it doesnt get transformed to logscale
+        # check if it doesnt get transformed to logscale
         self.assertEqual(plot_dict.get("layout").get("yaxis").get("type"), None)
         # check if there are two groups control and disease
         self.assertEqual(plot_dict.get("data")[0].get("legendgroup"), "control")
-        #  check that it is boxplot and not violinplot
+        # check that it is boxplot and not violinplot
         is_boxplot = "boxmode" in plot_dict.get("layout")
         self.assertTrue(is_boxplot)
 
@@ -820,7 +820,7 @@ def test_plot_intensity_box(self):
             protein_id="A0A075B6H7", group="grouping1", method="box", log_scale=True
         )
         plot_dict = plot.to_plotly_json()
-        #  log scale
+        # log scale
         self.assertEqual(plot_dict.get("layout").get("yaxis").get("type"), "log")
         is_boxplot = "boxmode" in plot_dict.get("layout")
         self.assertTrue(is_boxplot)

tests/test_loaders.py

@@ -18,7 +18,7 @@
 
 
 class BaseTestLoader:
-    #  parent class of test loader for common tests among loaders
+    # parent class of test loader for common tests among loaders
     # this is wrapped in a nested class so it doesnt get called separatly when testing
     # plus to avoid multiple inheritance
     class BaseTest(unittest.TestCase):
@@ -43,7 +43,7 @@ def test_check_if_columns_are_present_no_error(self):
 
         @patch("logging.Logger.warning")
         def test_check_if_indexcolumn_is_unique_warning(self, mock):
-            #  check if indexcolumn is unique
+            # check if indexcolumn is unique
             # check if error gets raised when duplicate
             obj = copy.deepcopy(self.obj)
             obj.rawinput[obj.index_column] = "non unique"
@@ -52,7 +52,7 @@ def test_check_if_indexcolumn_is_unique_warning(self, mock):
 
         # @patch("logging.Logger.warning")
         # def test_check_if_indexcolumn_is_unique_no_warning(self,mock):
-        #  check if indexcolumn is unique
+        # check if indexcolumn is unique
         # self.obj.check_if_indexcolumn_is_unique()
         # mock.assert_not_called()