Merge pull request #51 from llegregam/Dev

Dev

.github/workflows/tests.yml

@@ -10,7 +10,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, windows-latest, macos-latest]
-        python-version: [ '3.8', '3.9', '3.10']
+        python-version: [ '3.8', '3.9', '3.10', '3.11', '3.12']
 
     steps:
       - uses: actions/checkout@v3

ms_reader/__init__.py

@@ -1 +1 @@
-__version__ = "1.6.1"
+__version__ = "1.6.2"

ms_reader/app.py

@@ -214,13 +214,13 @@ def convert_df(df):
         try:
             reader.handle_calibration()
         except Exception as e:
-            st.error("There was an error while handling the calibration data")
+            st.error(f"There was an error while handling the calibration data:\n{e}")
             raise
     if report_box:
         try:
             reader.generate_report(metabolites_to_drop)
         except Exception as e:
-            st.error("There was an error while generating the report")
+            st.error(f"There was an error while generating the report:\n{e}")
             raise
         if preview:
             with st.expander("Show report"):
@@ -288,4 +288,4 @@ def convert_df(df):
         reader.export_stat_output(destination, pca=True)
         if conc_box or lloq_box:
             st.warning("**WARNING:** The PCA output only exports areas and ratios")
-        st.success("The input for GraphStatR has been generated (PCA mode)")
+        st.success("The input for GraphStatR has been generated (PCA mode)")

ms_reader/extract.py

@@ -270,10 +270,8 @@ def _replace_nf(self):
         Replace initial N/F with 0
         :return: None
         """
-        self.data.loc[:, "Area"] = \
-            self.data.loc[:, "Area"].replace("N/F", 0).copy()
-        self.data.loc[:, "Calculated Amt"] = \
-            self.data.loc[:, "Calculated Amt"].replace("N/F", 0).copy()
+        self.data["Area"] = self.data["Area"].replace("N/F", 0)
+        self.data["Calculated Amt"] = self.data["Calculated Amt"].replace("N/F", 0).copy()
 
     def _split_dataframes(self):
         """
@@ -320,7 +318,7 @@ def _get_excluded(self):
         Replace excluded points concentration with 'excluded'
         :return: None
         """
-        self.calib_data.loc[:, "Calculated Amt"] = pd.to_numeric(
+        self.calib_data["Calculated Amt"] = pd.to_numeric(
             self.calib_data["Calculated Amt"]
         )
         self.calib_data.loc[
@@ -580,7 +578,7 @@ def _handle_conc_norm(self, cols, base_unit):
         """
         # normalise
         self._generate_normalised_concentrations(cols)
-        # map "ND" to negative and null values
+        # applymap "ND" to negative and null values
         self.quantities = self.quantities.applymap(format)
         self.normalised_quantities = \
             self.normalised_quantities.applymap(format)
@@ -622,7 +620,7 @@ def _handle_conc_no_norm(self, cols, base_unit):
 
         # generate loq_table
         self.loq_table = self._define_loq(self.concentration_table.copy())
-        # map "ND" to negative and null values
+        # applymap "ND" to negative and null values
         self.concentration_table = self.concentration_table.applymap(
             format
         )

ms_reader/skyline_convert.py

@@ -23,28 +23,29 @@
     "Blank": "Unknown"
 }
 
-def convert_column_names(df):
 
+def convert_column_names(df):
     return df.rename(MAPPING, axis=1)
 
-def convert_sample_types(value):
 
+def convert_sample_types(value):
     if value in SAMPLE_TYPE_MAPPING.keys():
         return SAMPLE_TYPE_MAPPING[value]
     return value
 
-def convert_accuracy_to_diff(value):
 
+def convert_accuracy_to_diff(value):
     if value != np.nan:
         return round(float(str(value).replace("%", ""))-100, 1)
 
-def convert_calculated_amt(value):
 
+def convert_calculated_amt(value):
     if type(value) == str:
         if "Normalized Area" in value or "NaN" in value:
             return np.nan
         return float(str(value).replace(" uM", ""))
 
+
 def handle_na(row):
     if "(heavy)" in row["Precursor"]:
         row["Compound"] = row["Compound"] + " C13"
@@ -62,15 +63,15 @@ def handle_na(row):
             print(f"Area value = {row['Area']}\nCalculated Amt value = {row['Calculated Amt']}")
     return row
 
+
 def import_skyline_dataset(skyline_file):
     """
     Import skyline dataset and transform into MS_Reader compatible format
 
     :param skyline_file: Bytes file containing skyline data (tabular format)
     """
-
     # Get copy of file binary to dodge any wierd effects when file is read twice by pandas
-    #file = copy(skyline_file)
+    # file = copy(skyline_file)
     filename_extension = skyline_file.name[-3:]
     if filename_extension not in ["tsv", "txt"]:
         raise TypeError(
@@ -79,7 +80,7 @@ def import_skyline_dataset(skyline_file):
         )
 
     data = pd.read_csv(skyline_file, sep="\t")
-    #if len(data.columns) == 1:
+    # if len(data.columns) == 1:
     #    data = pd.read_csv(file, sep="\t")
     data = convert_column_names(data)
     data["Sample Type"] = data["Sample Type"].apply(convert_sample_types)
@@ -93,20 +94,21 @@ def import_skyline_dataset(skyline_file):
 
     return data
 
+
 if __name__ == "__main__":
 
-    #df = pd.read_csv(,sep=",")
-    #print(df.columns)
-    #converted_df = convert_column_names(df)
-    #print(converted_df.columns)
-    #print(converted_df["Sample Type"].unique())
-    #converted_df["Sample Type"] = converted_df["Sample Type"].apply(convert_sample_types)
-    #print(converted_df["Sample Type"].unique())
-    #print(converted_df["%Diff"])
-    #converted_df["%Diff"] = converted_df["%Diff"].apply(convert_accuracy_to_diff).fillna("NA")
-    #print(converted_df["%Diff"])
-    #converted_df["Calculated Amt"] = converted_df["Calculated Amt"].apply(convert_calculated_amt)
-    #converted_df = converted_df.apply(handle_na, axis=1)
-    #converted_df.to_excel(r"C:\Users\legregam\Desktop\test\test.xlsx", index=False)
+    # df = pd.read_csv(,sep=",")
+    # print(df.columns)
+    # converted_df = convert_column_names(df)
+    # print(converted_df.columns)
+    # print(converted_df["Sample Type"].unique())
+    # converted_df["Sample Type"] = converted_df["Sample Type"].apply(convert_sample_types)
+    # print(converted_df["Sample Type"].unique())
+    # print(converted_df["%Diff"])
+    # converted_df["%Diff"] = converted_df["%Diff"].apply(convert_accuracy_to_diff).fillna("NA")
+    # print(converted_df["%Diff"])
+    # converted_df["Calculated Amt"] = converted_df["Calculated Amt"].apply(convert_calculated_amt)
+    # converted_df = converted_df.apply(handle_na, axis=1)
+    # converted_df.to_excel(r"C:\Users\legregam\Desktop\test\test.xlsx", index=False)
     data = import_skyline_dataset(r"C:\Users\legregam\PycharmProjects\MSReader\tests\data\skyline\Quantif-MC.csv")
     data.to_excel(r"C:\Users\legregam\Desktop\test\test2.xlsx")

setup.cfg

@@ -3,8 +3,8 @@ name = ms_reader
 version = attr: ms_reader.__version__
 author = Loïc Le Grégam
 author_email = [email protected]
-description = Package for parsing a Tracefinder file containing processed Mass Spectrometry data
-long_description = file: README.rst
+description = Package for parsing a Tracefinder or Skyline file containing processed Mass Spectrometry data
+long_description = file: README.md
 long_description_content_type = text/markdown
 url = https://github.com/llegregam/MSReader
 project_urls =