Merge branch 'feature_statistics' into 'develop'

Feature statistics

See merge request hellerdev/lifescale_utils!3

README.md

@@ -7,12 +7,30 @@ Data analysis tools for lifescale with GUI.
 The program *ls2csv* reads the content of the xlsm files written by lifescale units, parses the data and writes them to three csv 
 files (where `[run-name]` is the name from the settings sheet):
   * `Masses_Vibrio_[run-name].csv`: Data series from the sheet AcquisitionIntervals.
-  * `SampleMetadata_[run-name].csv`: Data from the sheet PanelData.
-  * `Summary_[run-name].csv`: Data from the sheet IntervalAnalysis plus sample related data from AcquisitionIntervals.
+  * `Metadata_[run-name].csv`: Data from the sheet PanelData.
+  * `SampleSummary_[run-name].csv`: Data from the sheet IntervalAnalysis plus sample related data from AcquisitionIntervals.
 
 ### Usage:
-  * Conversion: `ls2csv -i [path and nale of xlsm file] -o [outpur directory]`
-  * Help: `ls2csv -h`
+```
+ls2csv -i [path and nale of xlsm file] -o [outpur directory] [-s] [-nv]
+
+options:
+  -h, --help            show this help message and exit
+  -i INPUT_XLSM, --input-xlsm INPUT_XLSM
+                        Path and name of the input xlsm file created by
+                        lifescale. (default: None)
+  -o OUT_DIR, --out-dir OUT_DIR
+                        Output directory for the CSV files. (default: None)
+  -nv, --not-verbose    Disable command line status messages. (default: False)
+  -s, --sample-stats    Calculate sample statistics of masses (median, std.
+                        deviation, quartiles, interquartile range) and add
+                        them to the SampleSummary output CSV file (columns:
+                        Mass_median, Mass_std, Mass_q25, Mass_q75,Mass_iqr).
+                        (default: False)
+  -t, --sort-masses-by-time
+                        Sort data in the Masses CSV file by acquisition time.
+                        (default: False)
+```
 
 
 # License and copyright

lifescale/command_line/__init__.py

+"""LifeScale utils command line interface module.
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+:Authors:
+    Andreas Hellerschmied (heller182@gmx.at)
+"""
\ No newline at end of file

lifescale/command_line/command_line.py

 """Command line interface of lifescale utils.
 
 Copyright (C) 2022  Andreas Hellerschmied <heller182@gmx.at>
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program.  If not, see <https://www.gnu.org/licenses/>.
 """
 
 from lifescale.scripts.ls2csv import ls2csv as ls2csv_main
@@ -36,13 +49,27 @@ def ls2csv():
     parser.add_argument("-o", "--out-dir", type=is_dir, required=True, help="Output directory for the CSV files.")
     parser.add_argument("-nv", "--not-verbose", required=False, help="Disable command line status messages.",
                         action='store_true')
-    # parser.add_argument("--out-dir", type=is_dir, required=False,
-    #                     help="path to output directory", default=OUT_PATH)
+    parser.add_argument("-s", "--sample-stats", required=False, help="Calculate sample statistics of masses (median, "
+                                                                     "std. deviation, quartiles, interquartile range) "
+                                                                     "and add them to the "
+                                                                     "SampleSummary output CSV file (columns: "
+                                                                     "Mass_median, Mass_std, Mass_q25, Mass_q75,"
+                                                                     "Mass_iqr).",
+                        action='store_true')
+    parser.add_argument("-t", "--sort-masses-by-time", required=False, help="Sort data in the Masses CSV file by "
+                                                                            "acquisition time.",
+                        action='store_true')
+
     args = parser.parse_args()
     verbose = not args.not_verbose
 
-    return ls2csv_main(xlsm_filename=args.input_xlsm, output_dir=args.out_dir, verbose=verbose)
+    return ls2csv_main(xlsm_filename=args.input_xlsm,
+                       output_dir=args.out_dir,
+                       sample_stats=args.sample_stats,
+                       sort_by_time=args.sort_masses_by_time,
+                       verbose=verbose)
 
 
 if __name__ == '__main__':
+    """Main function for debugging and testing."""
     ls2csv()

lifescale/models/__init__.py

+"""LifeScale utils objects module.
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+:Authors:
+    Andreas Hellerschmied (heller182@gmx.at)
+"""
\ No newline at end of file

lifescale/models/ls_data.py

@@ -132,7 +132,7 @@ class LSData:
         input_xlsm_filename : str
             Filename and path of the xlsm file written by LifeScale.
         verbose : bool, optional (default = `True`)
-            If `True`. status messages are written to the command line.
+            If `True`, status messages are written to the command line.
 
         Returns
         -------
@@ -140,7 +140,7 @@ class LSData:
             Contains all LS output data loaded from the given xlsm file.
         """
 
-        REQUIRED_XLSM_SHEET_NAMES = [
+        REQUIRED_XLSM_SHEET_NAMES = [  # Raise an exception if they are not present in the input xlsm file.
             'AcquisitionIntervals',
             'IntervalAnalysis',
             'PanelData',
@@ -386,6 +386,8 @@ class LSData:
             zip(id_list, well_list, interval_num_list, time_list, masses_list, volume_list, total_num_particles_list,
                 transit_time_list, pressure_drop_list)),
             columns=df_masses_columns)
+        df_masses['Id'] = df_masses['Id'].astype(int)
+        df_masses['IntervalNumber'] = df_masses['IntervalNumber'].astype(int)
 
         # Sensor:
         # sensor_dict = {}
@@ -410,8 +412,24 @@ class LSData:
                    df_masses=df_masses,
                    )
 
-    def export_csv_files(self, output_filepath, verbose=True, sort_by_time=False):
-        """Write CSV files to output directory"""
+    def export_csv_files(self, output_filepath, sort_by_time=False, verbose=True):
+        """Write CSV files to output directory
+
+        Parameters
+        ----------
+        output_filepath : str
+            Path to the output directory.
+        sort_by_time : bool, optional (default=`False`)
+            Sort data in the Masses CSV file by the observation time.
+        verbose : bool, optional (default = `True`)
+            If `True`, status messages are written to the command line.
+
+        Returns
+        -------
+        :py:obj:`.LSData`
+            Contains all LS output data loaded from the given xlsm file.
+
+        """
         if verbose:
             print('Write output')
 
@@ -426,7 +444,7 @@ class LSData:
             filename_ending = f'{self.run_name}.csv'
 
         # Write PanelData:
-        filename = os.path.join(output_filepath, f'SampleMetadata_{filename_ending}')
+        filename = os.path.join(output_filepath, f'Metadata_{filename_ending}')
         if verbose:
             print(f'Write PanelData to: {filename}')
         self.df_panel_data.to_csv(filename, index=False)
@@ -444,14 +462,32 @@ class LSData:
             self.df_masses.to_csv(filename, index=False)
 
         # Write IntervalAnalysis:
-        filename = os.path.join(output_filepath, f'Summary_{filename_ending}')
+        filename = os.path.join(output_filepath, f'SamplesSummary_{filename_ending}')
         if verbose:
             print(f'Write IntervalAnalysis to: {filename}')
         self.df_interval_analysis.to_csv(filename, index=False)
 
         # TODO: Output format (number of digits)
         # TODO: Select columns for output (settable as parameter + default settings for each csv file)
-        # TODO: Optionally order data series by time (parameter)?!
+
+    def calc_sample_statistics(self, verbose=True):
+        """Calculate statistical values for each sample and add it to the self.df_interval_analysis."""
+        if verbose:
+            print('Calculate sample statistics.')
+
+        for idx, row in self.df_interval_analysis.iterrows():
+            tmp_filter = (self.df_masses['Id'] == row.Id) & (self.df_masses['IntervalNumber'] == row.IntervalNumber)
+            tmp_filter_1 = (self.df_interval_analysis['Id'] == row.Id) & \
+                           (self.df_interval_analysis['IntervalNumber'] == row.IntervalNumber)
+            self.df_interval_analysis.loc[tmp_filter_1, 'Mass_median'] = self.df_masses.loc[tmp_filter, 'Mass'].median()
+            self.df_interval_analysis.loc[tmp_filter_1, 'Mass_std'] = self.df_masses.loc[tmp_filter, 'Mass'].std()
+            self.df_interval_analysis.loc[tmp_filter_1, 'Mass_q25'] = \
+                self.df_masses.loc[tmp_filter, 'Mass'].quantile(0.25)
+            self.df_interval_analysis.loc[tmp_filter_1, 'Mass_q75'] = \
+                self.df_masses.loc[tmp_filter, 'Mass'].quantile(0.75)
+            self.df_interval_analysis.loc[tmp_filter_1, 'Mass_iqr'] = \
+                self.df_interval_analysis.loc[tmp_filter_1, 'Mass_q75'] - \
+                self.df_interval_analysis.loc[tmp_filter_1, 'Mass_q25']
 
     @property
     def get_number_of_observations(self):
@@ -513,4 +549,4 @@ if __name__ == '__main__':
     ls_data = LSData.from_xlsm_file(input_xlsm_filename=xlsm_filename)
     ls_data.export_csv_files(output_directory)
 
-    print('test')
+    print('End')

lifescale/scripts/__init__.py

+"""LifeScale utils scripts module.
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+:Authors:
+    Andreas Hellerschmied (heller182@gmx.at)
+"""
\ No newline at end of file

lifescale/scripts/ls2csv.py

 """Conversion program from xlsm to csv.
 
-Copyright (C) 2022  Andreas Hellerschmied <heller182@gmx.at>"""
+Copyright (C) 2022  Andreas Hellerschmied <heller182@gmx.at>
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program.  If not, see <https://www.gnu.org/licenses/>.
+"""
 
 from lifescale.models.ls_data import LSData
 
 
-def ls2csv(xlsm_filename, output_dir, verbose=True):
+def ls2csv(xlsm_filename, output_dir, sample_stats=True, sort_by_time=False, verbose=True):
     """Convert lifescale output file (xlsm) to csv files."""
     ls_data = LSData.from_xlsm_file(input_xlsm_filename=xlsm_filename, verbose=verbose)
-    ls_data.export_csv_files(output_dir, verbose=verbose)
+    if sample_stats:
+        ls_data.calc_sample_statistics(verbose=verbose)
+    ls_data.export_csv_files(output_dir, sort_by_time=sort_by_time, verbose=verbose)