add similarityanalysis and unimplemented tests.

phasecalculator/analysis/similarityanalysis.py

@@ -15,14 +15,193 @@
 #    You should have received a copy of the GNU Affero General Public License
 #    along with this program.  If not, see <https://www.gnu.org/licenses/>.
 """
-Created on Tue Jan  7 16:34:17 2020
+Script to carry out similarity analysis.
 
 @author: Mark
 """
 
 import logging
+import pandas
+import pathlib
+import puresolventinformation.information as pureinf
+import solventmapcreator.polynomialanalysis.multidimensionclustering as multicluster
+import phasecalculator.io.polynomialio as polyio
 
 logging.basicConfig()
 LOGGER = logging.getLogger(__name__)
 LOGGER.setLevel(logging.WARN)
 
+def read_polynomial_files(poly_filename_list, **kwargs):
+    """Parse each file, and then returns the dictionary of information, by solvent ID.
+
+    Parameters
+    ----------
+    poly_filename_list : list
+        list of polynomial file names.
+    suffix : str, optional
+        polynomial file suffix.
+    temperature_dir : bool, optional
+        if files are in temperature based directories, indicates to include
+        the preceding directory name in solvent ID to be able to distiguish
+        the same solvent composition at different temperatures.
+
+    Returns
+    -------
+    dict
+        dict of polynomial data by solvent ID.
+
+    """
+    return polyio.read_poly_data_to_dict(poly_filename_list, **kwargs)
+
+PURE_SOLVENT_INFO = read_polynomial_files(pureinf.get_polynomial_filenames(), suffix="free_poly_split_fit.csv")
+
+def compare_all_solvents(poly_filename_list, output_dir, output_filename):
+    """
+
+    Parameters
+    ----------
+    poly_filename_list : TYPE
+        DESCRIPTION.
+    output_dir : TYPE
+        DESCRIPTION.
+    output_filename : TYPE
+        DESCRIPTION.
+
+    Returns
+    -------
+    None.
+
+    """
+    poly_data_by_id = read_polynomial_files(poly_filename_list, 
+                                            suffix="free_poly_split_fit.csv",
+                                            temperature_dir=True)
+    sim_dframe = calculate_similarity_matrix({**poly_data_by_id, **PURE_SOLVENT_INFO})
+    output_filename = (pathlib.Path(output_dir) / output_filename).as_posix()
+    write_frame_to_file(sim_dframe, output_filename)
+
+def compare_with_pure_solvents(poly_filename_list, output_dir):
+    """
+
+    Parameters
+    ----------
+    poly_filename_list : TYPE
+        DESCRIPTION.
+    output_dir : TYPE
+        DESCRIPTION.
+
+    Returns
+    -------
+    None.
+
+    """
+    poly_data_by_id = read_polynomial_files(poly_filename_list, 
+                                            suffix="free_poly_split_fit.csv",
+                                            temperature_dir=True)
+    sim_dframe = calculate_similarity_matrix({**poly_data_by_id, **PURE_SOLVENT_INFO})
+    for solv_id in poly_data_by_id.keys():
+        output_filename = create_slice_output_filename(solv_id, output_dir)
+        similarity_slice = extract_comparison_to_pure_solvents(sim_dframe, solv_id)
+        write_frame_to_file(similarity_slice, output_filename)
+
+    
+def compare_solvent_list(poly_filename_list, output_dir, output_filename):
+    """
+
+    Parameters
+    ----------
+    poly_filename_list : TYPE
+        DESCRIPTION.
+    output_dir : TYPE
+        DESCRIPTION.
+    output_filename : TYPE
+        DESCRIPTION.
+
+    Returns
+    -------
+    None.
+
+    """
+    poly_data_by_id = read_polynomial_files(poly_filename_list, 
+                                            suffix="free_poly_split_fit.csv",
+                                            temperature_dir=True)
+    sim_dframe = calculate_similarity_matrix(poly_data_by_id)
+    output_filename = (pathlib.Path(output_dir) / output_filename).as_posix()
+    write_frame_to_file(sim_dframe, output_filename)
+
+def create_slice_output_filename(solv_id, output_dir):
+    """
+
+    Parameters
+    ----------
+    solv_id : TYPE
+        DESCRIPTION.
+    output_dir : TYPE
+        DESCRIPTION.
+
+    Returns
+    -------
+    TYPE
+        DESCRIPTION.
+
+    """
+    filename = solv_id.replace(",","_") + ".csv"
+    return (pathlib.Path(output_dir) / filename).as_posix()
+
+    
+def write_frame_to_file(dframe, output_filename):
+    """
+
+    Parameters
+    ----------
+    dframe : TYPE
+        DESCRIPTION.
+    output_filename : TYPE
+        DESCRIPTION.
+
+    Returns
+    -------
+    None.
+
+    """
+    dframe.to_csv(output_filename, sep="\t")
+
+def extract_comparison_to_pure_solvents(similarity_dframe, solv_id):
+    """
+
+    Parameters
+    ----------
+    similarity_dframe : TYPE
+        DESCRIPTION.
+    solv_id : TYPE
+        DESCRIPTION.
+
+    Returns
+    -------
+    TYPE
+        DESCRIPTION.
+
+    """
+    return similarity_dframe.loc[solv_id, PURE_SOLVENT_INFO.keys()].sort()
+    
+def calculate_similarity_matrix(poly_data_by_id):
+    """
+
+    Parameters
+    ----------
+    poly_data_by_id : TYPE
+        DESCRIPTION.
+
+    Returns
+    -------
+    TYPE
+        DESCRIPTION.
+
+    """
+    x_values_list, norm_coefficients = pureinf.get_similarity_domain_information()
+    stacked_matrix, norm_coeffs = multicluster.generate_normalised_rmsd_matrix_stack(
+        x_values_list, 8, poly_data_by_id, norm_coefficients=norm_coefficients
+    )
+    mean_matrix = multicluster.condense_matrix_to_mean(stacked_matrix)
+    labels = sorted(poly_data_by_id.keys())
+    return pandas.DataFrame(mean_matrix,index=labels, columns=labels)
+    

phasecalculator/test/analysistest/similarityanalysistest.py

+# -*- coding: utf-8 -*-
+#    phasecalculator calculates FGIPs, solvent similarity and VLE with SSIMPLE.
+#    Copyright (C) 2019  Mark D. Driver
+#
+#    phasecalculator is free software: you can redistribute it and/or modify
+#    it under the terms of the GNU Affero 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 Affero General Public License for more details.
+#
+#    You should have received a copy of the GNU Affero General Public License
+#    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+"""
+Script for similarity analysis tests.
+
+@author: Mark
+"""
+
+import logging
+import unittest
+import pandas
+import pathlib
+import numpy as np
+import phasecalculator.analysis.similarityanalysis as simanalysis
+
+
+logging.basicConfig()
+LOGGER = logging.getLogger(__name__)
+LOGGER.setLevel(logging.WARN)
+
+class SimilarityAnalysisTestCase(unittest.TestCase):
+    """Test case for similarity analysis."""
+    def setUp(self):
+        """Set up before tests.
+
+        Returns
+        -------
+        None.
+
+        """
+    def tearDown(self):
+        """Clean up after tests.
+
+        Returns
+        -------
+        None.
+
+        """
+    def test_read_polynomial_files(self):
+        """Test
+
+        Returns
+        -------
+        None.
+
+        """
+        self.fail("not implemented")
+    def test_compare_all_solvents(self):
+        """Test
+
+        Returns
+        -------
+        None.
+
+        """
+        self.fail("not implemented")
+    def test_compare_with_pure_solvents(self):
+        """Test
+
+        Returns
+        -------
+        None.
+
+        """
+        self.fail("not implemented")
+    def test_compare_solvent_list(self):
+        """Test
+
+        Returns
+        -------
+        None.
+
+        """
+        self.fail("not implemented")
+    def test_write_frame_to_file(self):
+        """Test
+
+        Returns
+        -------
+        None.
+
+        """
+        self.fail("not implemented")
+    def test_extract_comparison_to_pure_solvents(self):
+        """Test
+
+        Returns
+        -------
+        None.
+
+        """
+        self.fail("not implemented")
+    def test_calculate_similarity_matrix(self):
+        """Test
+
+        Returns
+        -------
+        None.
+
+        """
+        self.fail("not implemented")
\ No newline at end of file