add .gitignore and test of code Complete_processing_mapping_results

.gitignore.txt

+/__pycache__
+
+.cpython-310
\ No newline at end of file

Tests_unitaires/Cors_file_for_test/Corres_file_for_CPDB_unittest.csv

+inosine;17596
+L-glutamic acid;16015
+pyruvic acid;32816

Tests_unitaires/Cors_file_for_test/Corres_file_for_RAMP_unittest.csv

+inosine;chebi:17596
+L-glutamic acid;chebi:16015
+pyruvic acid;chebi:32816

Tests_unitaires/test_complete_processing_of_mapping_results.py

+import unittest
+import pandas as pd
+import os
+import tempfile
+import sys
+import openpyxl
+from unittest.mock import patch
+sys.path.append('C:\\Users\\mumec\\Desktop\\Dossier_gitlab_local\\traitement_des_données')
+from complete_processing_of_mapping_results import  *
+
+class Test_treatment_result_smapping(unittest.TestCase):
+
+   def test_pathways_selection (self):
+      result_list=pathways_selection([['alphabet','a','b'],['num','1','2'],['false_num','32','27']],['False_alphabet','false_num'])
+      self.assertIsInstance(result_list, list)
+      self.assertListEqual(result_list,[['alphabet','a','b'],['num','1','2']])
+
+   def test_similarity_matrix (self):
+      np_table,path_whith_only_1_metabolite, Metabo_path_whith_only_1_metabolite, All_metabo, f_of_metabolite, pathways_of_metabo,Names_of_pathways, all_recovery, average_recov=similarity_matrix([['Biochemical Pathways Part I', 'taurine'],['SLC-mediated transmembrane transport', 'taurine', 'succinic acid']])
+      self.assertIsInstance(np_table, np.ndarray)
+      self.assertListEqual(path_whith_only_1_metabolite,['Biochemical Pathways Part I'])
+      self.assertListEqual(Metabo_path_whith_only_1_metabolite,['taurine'] )
+      self.assertEqual(len(All_metabo),2)
+      self.assertListEqual(f_of_metabolite,[2,1])
+      self.assertEqual(len(pathways_of_metabo),2)
+      self.assertListEqual(Names_of_pathways,['Biochemical Pathways Part I','SLC-mediated transmembrane transport'])
+      self.assertEqual(len(all_recovery),2)
+      self.assertEqual(len(average_recov),2)
+
+   def test_list_frequency_1 (self):
+      metabo_f1,path_metabo_f1=list_frequency_1([2,1],['taurine', 'succinic acid'],[['Biochemical Pathways Part I','SLC-mediated transmembrane transport'],['SLC-mediated transmembrane transport']],['Biochemical Pathways Part I','SLC-mediated transmembrane transport'],[['Biochemical Pathways Part I', 'taurine'],['SLC-mediated transmembrane transport', 'taurine', 'succinic acid']])
+      self.assertListEqual(metabo_f1,['succinic acid'])
+      self.assertListEqual(path_metabo_f1,['SLC-mediated transmembrane transport(2)'])
+
+   def test_pathways_of_metabolite (self):
+      path_of_meta=pathways_of_metabolite(['taurine', 'succinic acid'],[['Biochemical Pathways Part I','SLC-mediated transmembrane transport'],['SLC-mediated transmembrane transport']])
+      self.assertIsInstance(path_of_meta, pd.DataFrame)
+
+   def test_order_frequency (self):
+      morph=order_frequency(['a biosynthesis'], ['a'], ['b degradation'], ['b'], ['a','b','c'], [5,1,2])
+      self.assertIsInstance(morph, list)
+
+   def test_recovery_position_and_pathways_name (self):
+      L_of_L=recovery_position_and_pathways_name([6,2,1],[3,1,0.5],['Biochemical Path','SLC-mediated','biosynthesis'])
+      self.assertIsInstance(L_of_L, list)
+
+   def test_df_matrix_r (self):
+      l_like=df_matrix_r(np.array([[1, 2], [2, 1]], dtype=object))
+      self.assertIsInstance(l_like, pd.DataFrame)
+
+
+class Test_import_function(unittest.TestCase):
+
+   def test_column_recovery(self):
+      self.temp_file = tempfile.NamedTemporaryFile(delete=False, mode='w', suffix='.csv')
+      self.temp_file.write("1;it;Doe\n")
+      self.temp_file.write("2;is;Smith\n")
+      self.temp_file.write("3;good;Johnson\n")
+      self.temp_file.close()
+      result = column_recovery(self.temp_file.name, 1)
+      expected_result = ['it', 'is', 'good']
+      os.remove(self.temp_file.name)
+      self.assertEqual(result, expected_result)
+
+
+   def test_recup_RAMP_pathways_list(self):
+      self.temp_RAMP = tempfile.NamedTemporaryFile(delete=False, mode='w', suffix='.csv')
+      self.temp_RAMP.write("pathwayName;pathwaySource;pathwayId;inputId;commonName\n")
+      self.temp_RAMP.write("ADME;;;chebi:17596;\n")
+      self.temp_RAMP.write("al metabo;;;chebi:16015;\n")
+      self.temp_RAMP.write("al metabo;;;chebi:32816;\n")
+      self.temp_RAMP.close()
+      self.temp_CORS = tempfile.NamedTemporaryFile(delete=False, mode='w', suffix='.csv')
+      self.temp_CORS.write("inosine;chebi:17596;\n")
+      self.temp_CORS.write("L-glutamic acid;chebi:16015;\n")
+      self.temp_CORS.write("pyruvic acid;chebi:32816;\n")
+      self.temp_CORS.close()
+      result_recup_RAMP=recup_RAMP_pathways_list(self.temp_RAMP.name,self.temp_CORS.name)
+      self.assertEqual(result_recup_RAMP, [['ADME','inosine'],['al metabo','L-glutamic acid','pyruvic acid']])
+      os.remove(self.temp_RAMP.name)
+      os.remove(self.temp_CORS.name)
+
+
+   def test_recup_CPDB_pathways_list (self):
+      self.temp_CPDB = tempfile.NamedTemporaryFile(delete=False, mode='w', suffix='.csv')
+      self.temp_CPDB.write("p-value;q-value;pathway;source;external_id;members_input_overlap;members_input_overlap_geneids;size;effective_size\n")
+      self.temp_CPDB.write("1;0;ADME;wiki;exte;17596;kc20;21;21\n")
+      self.temp_CPDB.write("1;0;al metabo;wiki;exte;16015;kc20;21;21\n")
+      self.temp_CPDB.close()
+      self.temp_CORS2 = tempfile.NamedTemporaryFile(delete=False, mode='w', suffix='.csv')
+      self.temp_CORS2.write("inosine;17596\n")
+      self.temp_CORS2.write("L-glutamic acid;16015\n")
+      self.temp_CORS2.close()
+      result_recup_CPDB=recup_CPDB_pathways_list(self.temp_CPDB.name, self.temp_CORS2.name)
+      self.assertEqual(result_recup_CPDB, [['ADME', 'inosine'], ['al metabo', 'L-glutamic acid']])
+      os.remove(self.temp_CORS2.name)
+      os.remove(self.temp_CPDB.name)
+
+
+   def test_recup_MA_pathways_list (self):
+      self.temp_MA = tempfile.NamedTemporaryFile(delete=False, mode='w', suffix='.csv')
+      self.temp_MA.write("al metabo;ADME\n")
+      self.temp_MA.write("L-glutamic acid;inosine\n")
+      self.temp_MA.write("pyruvic acid;\n")
+      self.temp_MA.close()
+      L_result=recup_MA_pathways_list(self.temp_MA.name,2)
+      self.assertEqual(L_result, [['al metabo', 'L-glutamic acid','pyruvic acid'],['ADME', 'inosine']])
+      os.remove(self.temp_MA.name)
+
+   def test_recup_ME_pathways_list (self):
+      Me_temp_file_1= tempfile.NamedTemporaryFile(delete=False, suffix='.xlsx')
+      workbook_1 = openpyxl.Workbook()
+      sheet_names_1 = ["Compartments (1|19)", "Pathways (1|364)", "Reactions (2|3968)", "Metabolites (1|3831)"]
+      for sheet_name in sheet_names_1:
+         workbook_1.create_sheet(sheet_name)
+      default_sheet_1 = workbook_1["Sheet"]
+      workbook_1.remove(default_sheet_1)
+      sheet_path_1=workbook_1["Pathways (1|364)"]
+      sheet_meta_1=workbook_1["Metabolites (1|3831)"]
+      sheet_path_1.cell(row=2, column=1, value='spermidine biosynthesis')
+      sheet_meta_1.cell(row=2, column=1, value='CO2')
+      sheet_meta_1.cell(row=2, column=6, value='true')
+      workbook_1.save(Me_temp_file_1.name)
+      Me_temp_file_1.close()
+      name_Me_temp_file_1 = "Me_temp (1).xlsx"
+      os.rename(Me_temp_file_1.name, name_Me_temp_file_1)
+
+      Me_temp_file_2= tempfile.NamedTemporaryFile(delete=False, suffix='.xlsx')
+      workbook_2 = openpyxl.Workbook()
+      sheet_names_2 = ["Compartments (1|19)", "Pathways (1|364)", "Reactions (2|3968)", "Metabolites (3|3831)"]
+      for sheet_name in sheet_names_2:
+         workbook_2.create_sheet(sheet_name)
+      default_sheet_2 = workbook_2["Sheet"]
+      workbook_2.remove(default_sheet_2)
+      sheet_path_2=workbook_2["Pathways (1|364)"]
+      sheet_meta_2=workbook_2["Metabolites (3|3831)"]
+      sheet_path_2.cell(row=2, column=1, value='biosynthesis')
+      sheet_meta_2.cell(row=2, column=1, value='H+')
+      sheet_meta_2.cell(row=2, column=6, value='true')
+      sheet_meta_2.cell(row=3, column=1, value='CO2')
+      sheet_meta_2.cell(row=3, column=6, value='false')
+      sheet_meta_2.cell(row=4, column=1, value='spermine')
+      sheet_meta_2.cell(row=4, column=6, value='true')
+      workbook_2.save(Me_temp_file_2.name)
+      Me_temp_file_2.close()
+      name_Me_temp_file_2 = "Me_temp (2).xlsx"
+      os.rename(Me_temp_file_2.name, name_Me_temp_file_2)
+
+      ME_result=recup_ME_pathways_list('Me_temp','C:\\Users\\mumec\\Desktop\\Dossier_gitlab_local\\traitement_des_données\\Tests_unitaires\\', 2,6)
+      self.assertListEqual(ME_result,[['spermidine biosynthesis','CO2'],['biosynthesis','H+','spermine']])
+
+      os.remove("C:\\Users\\mumec\\Desktop\\Dossier_gitlab_local\\traitement_des_données\\Tests_unitaires\\Me_temp (1).xlsx")
+      os.remove("C:\\Users\\mumec\\Desktop\\Dossier_gitlab_local\\traitement_des_données\\Tests_unitaires\\Me_temp (2).xlsx")
+
+
+class Testcomplete_processing_of_mapping_results_MA(unittest.TestCase):
+
+   def setUp(self):
+      self.temp_MA = tempfile.NamedTemporaryFile(delete=False, mode='w', suffix='.csv')
+      self.temp_MA.write("al metabo;ADME\n")
+      self.temp_MA.write("L-glutamic acid;inosine\n")
+      self.temp_MA.write("pyruvic acid;\n")
+      self.temp_MA.close()
+
+   def tearDown(self):
+      os.remove(self.temp_MA.name)
+
+   @patch('builtins.input', side_effect=[2])
+   def test_complete_processing_of_mapping_results_mid_file (self, mock_input):
+      outfile="C:\\Users\\mumec\\Desktop\\fichier_mis_en_forme_programme_total\\unittest.xlsx"
+      midfile_n="C:\\Users\\mumec\\Desktop\\fichier_mis_en_forme_programme_total\\mid_file.xlsx"
+      complete_processing_of_mapping_results (self.temp_MA.name, outfile,'MA',type_of_view="None",midfile_name=midfile_n)
+      self.assertTrue
+      self.assertTrue(os.path.exists(outfile))
+      self.assertTrue(os.path.exists(midfile_n))
+      os.remove(outfile)
+      os.remove(midfile_n)
+
+   @patch('builtins.input', side_effect=[2])
+   def test_complete_processing_of_mapping_results_end_file_MA (self,mock_input):
+      outfile="C:\\Users\\mumec\\Desktop\\fichier_mis_en_forme_programme_total\\unittest.xlsx"
+      complete_processing_of_mapping_results (self.temp_MA.name, outfile,'MA',type_of_view="None",midfile='non')
+      self.assertTrue(os.path.exists(outfile))
+      os.remove(outfile)
+
+   @patch('builtins.input', side_effect=[2])
+   def test_complete_processing_of_mapping_results_filter_MA (self,mock_input):
+      outfile="C:\\Users\\mumec\\Desktop\\fichier_mis_en_forme_programme_total\\unittest.xlsx"
+      complete_processing_of_mapping_results (self.temp_MA.name, outfile,'MA',type_of_view="None",midfile='non',name_of_pathways_to_filter=['al metabo'])
+      self.assertTrue(os.path.exists(outfile))
+      os.remove(outfile)
+
+   @patch('builtins.input', side_effect=[2])
+   @patch('complete_processing_of_mapping_results.plt.show')
+   def test_complete_processing_of_mapping_results_visu (self,mock_input,mock_show):
+      outfile="C:\\Users\\mumec\\Desktop\\fichier_mis_en_forme_programme_total\\unittest.xlsx"
+      complete_processing_of_mapping_results (self.temp_MA.name, outfile,'MA',type_of_view="all",folder_of_visu_saving="C:\\Users\\mumec\\Desktop\\Dossier_gitlab_local\\traitement_des_données\\Tests_unitaires\\",midfile='non',)
+      self.assertTrue(os.path.exists("C:\\Users\\mumec\\Desktop\\Dossier_gitlab_local\\traitement_des_données\\Tests_unitaires\\bar_plot_of_metabolites.png"))
+      self.assertTrue(os.path.exists("C:\\Users\\mumec\\Desktop\\Dossier_gitlab_local\\traitement_des_données\\Tests_unitaires\\bar_plot_of_recovery.png"))
+      self.assertTrue(os.path.exists("C:\\Users\\mumec\\Desktop\\Dossier_gitlab_local\\traitement_des_données\\Tests_unitaires\\metabolites_bo_of_frequency.png"))
+      self.assertTrue(os.path.exists(outfile))
+      os.remove("C:\\Users\\mumec\\Desktop\\Dossier_gitlab_local\\traitement_des_données\\Tests_unitaires\\bar_plot_of_metabolites.png")
+      os.remove("C:\\Users\\mumec\\Desktop\\Dossier_gitlab_local\\traitement_des_données\\Tests_unitaires\\bar_plot_of_recovery.png")
+      os.remove("C:\\Users\\mumec\\Desktop\\Dossier_gitlab_local\\traitement_des_données\\Tests_unitaires\\metabolites_bo_of_frequency.png")
+      os.remove(outfile)
+
+class Testcomplete_processing_of_mapping_results_mappeurs(unittest.TestCase):
+
+   @patch('builtins.input', side_effect=['C:\\Users\\mumec\\Desktop\\Dossier_gitlab_local\\traitement_des_données\\Tests_unitaires\\',2,6])
+   def test_complete_processing_of_mapping_results_end_file_ME (self,mock_input):
+      outfile="C:\\Users\\mumec\\Desktop\\fichier_mis_en_forme_programme_total\\unittest.xlsx"
+      Me_temp_file_1= tempfile.NamedTemporaryFile(delete=False, suffix='.xlsx')
+      workbook_1 = openpyxl.Workbook()
+      sheet_names_1 = ["Compartments (1|19)", "Pathways (1|364)", "Reactions (2|3968)", "Metabolites (1|3831)"]
+      for sheet_name in sheet_names_1:
+         workbook_1.create_sheet(sheet_name)
+      default_sheet_1 = workbook_1["Sheet"]
+      workbook_1.remove(default_sheet_1)
+      sheet_path_1=workbook_1["Pathways (1|364)"]
+      sheet_meta_1=workbook_1["Metabolites (1|3831)"]
+      sheet_path_1.cell(row=2, column=1, value='spermidine biosynthesis')
+      sheet_meta_1.cell(row=2, column=1, value='CO2')
+      sheet_meta_1.cell(row=2, column=6, value='true')
+      workbook_1.save(Me_temp_file_1.name)
+      Me_temp_file_1.close()
+      name_Me_temp_file_1 = "Me_temp (1).xlsx"
+      os.rename(Me_temp_file_1.name, name_Me_temp_file_1)
+      Me_temp_file_2= tempfile.NamedTemporaryFile(delete=False, suffix='.xlsx')
+      workbook_2 = openpyxl.Workbook()
+      sheet_names_2 = ["Compartments (1|19)", "Pathways (1|364)", "Reactions (2|3968)", "Metabolites (3|3831)"]
+      for sheet_name in sheet_names_2:
+         workbook_2.create_sheet(sheet_name)
+      default_sheet_2 = workbook_2["Sheet"]
+      workbook_2.remove(default_sheet_2)
+      sheet_path_2=workbook_2["Pathways (1|364)"]
+      sheet_meta_2=workbook_2["Metabolites (3|3831)"]
+      sheet_path_2.cell(row=2, column=1, value='biosynthesis')
+      sheet_meta_2.cell(row=2, column=1, value='H+')
+      sheet_meta_2.cell(row=2, column=6, value='true')
+      sheet_meta_2.cell(row=3, column=1, value='CO2')
+      sheet_meta_2.cell(row=3, column=6, value='false')
+      sheet_meta_2.cell(row=4, column=1, value='spermine')
+      sheet_meta_2.cell(row=4, column=6, value='true')
+      workbook_2.save(Me_temp_file_2.name)
+      Me_temp_file_2.close()
+      name_Me_temp_file_2 = "Me_temp (2).xlsx"
+      os.rename(Me_temp_file_2.name, name_Me_temp_file_2)
+      complete_processing_of_mapping_results ('Me_temp', outfile,'ME',type_of_view="None",midfile='non')
+      self.assertTrue(os.path.exists(outfile))
+      os.remove(outfile)
+      os.remove("C:\\Users\\mumec\\Desktop\\Dossier_gitlab_local\\traitement_des_données\\Tests_unitaires\\Me_temp (1).xlsx")
+      os.remove("C:\\Users\\mumec\\Desktop\\Dossier_gitlab_local\\traitement_des_données\\Tests_unitaires\\Me_temp (2).xlsx")
+
+   @patch('builtins.input', side_effect=["C:\\Users\\mumec\\Desktop\\Dossier_gitlab_local\\traitement_des_données\\Tests_unitaires\\Cors_file_for_test\\Corres_file_for_RAMP_unittest.csv"])
+   def test_complete_processing_of_mapping_results_end_file_RAMP (self,mock_input):
+      outfile="C:\\Users\\mumec\\Desktop\\fichier_mis_en_forme_programme_total\\unittest.xlsx"
+      self.temp_RAMP = tempfile.NamedTemporaryFile(delete=False, mode='w', suffix='.csv')
+      self.temp_RAMP.write("pathwayName;pathwaySource;pathwayId;inputId;commonName\n")
+      self.temp_RAMP.write("ADME;;;chebi:17596;\n")
+      self.temp_RAMP.write("al metabo;;;chebi:16015;\n")
+      self.temp_RAMP.write("al metabo;;;chebi:32816;\n")
+      self.temp_RAMP.close()
+      complete_processing_of_mapping_results (self.temp_RAMP.name, outfile,'RAMP',type_of_view="None",midfile='non')
+      self.assertTrue(os.path.exists(outfile))
+      os.remove(self.temp_RAMP.name)
+
+   @patch('builtins.input', side_effect=["C:\\Users\\mumec\\Desktop\\Dossier_gitlab_local\\traitement_des_données\\Tests_unitaires\\Cors_file_for_test\\Corres_file_for_CPDB_unittest.csv"])
+   def test_complete_processing_of_mapping_results_end_file_CPDB (self,mock_input):
+      outfile="C:\\Users\\mumec\\Desktop\\fichier_mis_en_forme_programme_total\\unittest.xlsx"
+      self.temp_CPDB = tempfile.NamedTemporaryFile(delete=False, mode='w', suffix='.csv')
+      self.temp_CPDB.write("p-value;q-value;pathway;source;external_id;members_input_overlap;members_input_overlap_geneids;size;effective_size\n")
+      self.temp_CPDB.write("1;0;ADME;wiki;exte;17596;kc20;21;21\n")
+      self.temp_CPDB.write("1;0;al metabo;wiki;exte;16015;kc20;21;21\n")
+      self.temp_CPDB.close()
+      complete_processing_of_mapping_results (self.temp_CPDB.name, outfile,'CPDB',type_of_view="None",midfile='non')
+      self.assertTrue(os.path.exists(outfile))
+      os.remove(outfile)
+      os.remove(self.temp_CPDB.name)
+
+
+class Test_functiosnutils(unittest.TestCase):
+
+   def test_correspondence_with_index (self):
+      result_corres=correspondence_with_index(['t','x','a'],['a','b','c','t','x'],['1','2','3','20','24'])
+      self.assertIsInstance(result_corres, list)
+      self.assertListEqual(result_corres,['20','24','1'])
+
+   def test_comma_cleaning (self):
+      str_clean=comma_cleaning ('this, str , have, four, comma')
+      self.assertIsInstance(str_clean, str)
+      self.assertMultiLineEqual(str_clean,'this_ str _ have_ four_ comma')
+
+   def test_excel_file_writer (self):
+      dataframe = pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]})
+      name_out_file='test_default_sheetname.xlsx'
+      excel_file_writer(dataframe, name_out_file,sheetname="test_1")
+      self.assertTrue(os.path.exists(name_out_file))
+      os.remove(name_out_file)
+
+   def test_excel_multi_file_writer (self):
+      list_of_dataframe = [pd.DataFrame({'A': [1, 2, 3], 'B': [4, 5, 6]}), pd.DataFrame({'X': ['a', 'b', 'c'], 'Y': ['d', 'e', 'f']})]
+      name_outfile = 'test_output.xlsx'
+      excel_multi_file_writer(list_of_dataframe, name_outfile, ['Sheet1', 'Sheet2'])
+      self.assertTrue(os.path.exists(name_outfile))
+      excel_file = pd.ExcelFile(name_outfile)
+      sheet_names = excel_file.sheet_names
+      self.assertEqual(len(sheet_names),2)
+      excel_file.close()
+      os.remove(name_outfile)
+
+   def test_strip_list (self):
+      result_clean=strip_list(['a ',' b', ' c ','d'])
+      self.assertIsInstance(result_clean, list)
+      self.assertEqual(result_clean,['a','b','c','d'])
+
+
+class TestVisu (unittest.TestCase):
+
+   def setUp(self):
+      self.df_data = pd.DataFrame({'column_x': ['A', 'B', 'C'],'column_y': [10, 20, 30]})
+
+   def test_barplot(self):
+      fig = barplot('column_x', 'column_y', self.df_data)
+      self.assertIsInstance(fig, plt.Figure)
+
+   def test_barplot_with_custom(self):
+      fig = barplot('column_x', 'column_y', self.df_data, title="Plot title", figure_size=(20, 4),ax_x_label="Pathwayss", ax_y_label='R_m',colors='Spectral',decimal='%.3f',size_of_labels=8)
+      self.assertIsInstance(fig, plt.Figure)
+
+   def test_mustache_box (self) :
+      box=mustache_box(self.df_data,'column_y') #ax_y_label="f_metabolites",title='box_1',figure_size=(5,8)
+      self.assertIsInstance(box, plt.Axes)
+
+if __name__=='__main__':
+    unittest.main()
\ No newline at end of file