Major restructuring in the main branch

codart/codart_cli.py

@@ -25,12 +25,11 @@
 # from gen.java9.Java9_v2Parser import Java9_v2Parser  # Old slow grammar parser
 # from java9speedy.parser import sa_java9_v2  # Old slow grammar enhanced by CPP backend
 
-from gen.javaLabeled.JavaLexer import JavaLexer  # Java8 grammar efficient lexer
-from gen.javaLabeled.JavaParserLabeled import JavaParserLabeled  # Java8 grammar efficient parser labeled
+from codart.gen.javaLabeled.JavaLexer import JavaLexer  # Java8 grammar efficient lexer
+from codart.gen.javaLabeled.JavaParserLabeled import JavaParserLabeled  # Java8 grammar efficient parser labeled
 
 # Import refactorings listeners
-from refactorings.encapsulate_field import EncapsulateFiledRefactoringListener  # CodART first refactoring :)
-from refactorings.extract_class import ExtractClassRefactoringListener
+from codart.refactorings.encapsulate_field import EncapsulateFiledRefactoringListener  # CodART first refactoring :)
 
 
 def main(args):

sbse/config.py → codart/config.py

@@ -52,6 +52,7 @@
         'jvlt-1.3.2',  # 10
         'tabula-java',  # 11
         'JHotDraw-7.0.6',  # 12
+        'jhotdraw-6.0b1',  # 13
     ],
 
     # Understand DB Path
@@ -82,6 +83,8 @@
         'tabula-java.und',
         # 'JHotDraw-7.0.6.udb',  # 12
         'JHotDraw-7.0.6.und',  # 12
+        # 'jhotdraw-6.0b1.udb',  # 13
+        'jhotdraw-6.0b1.und',  # 13
     ],
 
     # CSV files path containing code smells identified by JDeodorant
@@ -99,6 +102,7 @@
         'jVLT-1.3.2/Long-Method2_jvlt-1.3.2.csv',
         'tabula-java/fake.csv',
         'JHotDraw-7.0.6/Long-Method2_JHotDraw-7.0.6.csv',
+        'jhotdraw-6.0b1/Long-Method2_jhotdraw-6.0b1.csv',
     ],
 
     'FEATURE_ENVY': [
@@ -115,6 +119,7 @@
         'jVLT-1.3.2/Feature-Envy_jvlt-1.3.2.csv',
         'tabula-java/Feature-Envy-Tabula-v1.0.6.csv',
         'JHotDraw-7.0.6/Featuer-Envy2_JHotDraw-7.0.6.csv',
+        'jhotdraw-6.0b1/Featuer-Envy2_jhotdraw-6.0b1.csv',
     ],
 
     'GOD_CLASS': [
@@ -130,7 +135,8 @@
         'JSON20201115/God-Class_JASON-20201115.csv',
         'jVLT-1.3.2/God-Class_jvlt-1.3.2.csv',
         'tabula-java/God-Class-Tabula-v1.0.6.csv',
-        'JHotDraw-7.0.6/God-Class_JHotDraw-7.0.6.csv'
+        'JHotDraw-7.0.6/God-Class_JHotDraw-7.0.6.csv',
+        'jhotdraw-6.0b1/God-Class_jhotdraw-6.0b1.csv',
     ],
 }
 
@@ -353,6 +359,22 @@
         'TEST': 1.,  # Obtained by testability_prediction2
         'TEST3': 1.  # Obtained by testability_prediction3
     },
+    "jhotdraw-6.0b1": {  # 13
+            'ANA': 1.,
+            'CAMC': 1.,
+            'CIS': 1.,
+            'DAM': 1.,
+            'DCC': 1.,
+            'DSC': 1.,
+            'MFA': 1.,
+            'MOA': 1.,
+            'NOH': 1.,
+            'NOM': 1.,
+            'NOP': 1.,
+            'MODULE': 1.,
+            'TEST': 1.,  # Obtained by testability_prediction2
+            'TEST3': 1.  # Obtained by testability_prediction3
+        },
 }
 
 CURRENT_METRICS = INITIAL_METRICS.get(PROJECT_NAME)

metrics/data_preparation_evo_suite_4.py → codart/metrics/data_preparation_evo_suite_4.py

@@ -7,38 +7,33 @@
 To be used in CodART project
 
 """
-import multiprocessing
+
+__version__ = '0.4.0'
+__author__ = 'Morteza'
+
 import sys
 import os
-import subprocess
-import threading
 from collections import Counter
-from functools import wraps
 import warnings
-from deprecated import deprecated
 
-import re
 import math
 
-import matplotlib.pyplot as plt
 import pandas as pd
 import numpy as np
 from scipy import stats
 
 from sklearn import preprocessing
 from sklearn.feature_selection import SelectKBest
-from sklearn.feature_selection import chi2, f_classif
+from sklearn.feature_selection import f_classif
 from sklearn.decomposition import PCA
-from sklearn.model_selection import StratifiedShuffleSplit, train_test_split
+from sklearn.model_selection import train_test_split
 from sklearn.neighbors import LocalOutlierFactor
-from sklearn.ensemble import IsolationForest
 from imblearn.combine import SMOTEENN, SMOTETomek
-from imblearn.over_sampling import SMOTE, ADASYN
 
 # https://scitools.com/support/python-api/
 # Python 3.8 and newer require the user add a call to os.add_dll_directory(“SciTools/bin/“
 # os.add_dll_directory('C:/Program Files/SciTools/bin/pc-win64')
-sys.path.insert(0, 'D:/program files/scitools/bin/pc-win64/python')
+# sys.path.insert(0, 'D:/program files/scitools/bin/pc-win64/python')
 try:
     import understand
 except ModuleNotFoundError:
@@ -47,13 +42,7 @@
 
 from . import metrics_names
 from metrics_coverability import UnderstandUtility
-from metrics.metrics_jcode_odor import JCodeOdorMetric
-from metrics.source_code_metrics import *
-import metrics.metrics_names
-
-
-__version__ = '0.4.0'
-__author__ = 'Morteza'
+from codart.metrics.metrics_jcode_odor import JCodeOdorMetric
 
 
 def check_compute_metrics_by_class_list(project_name: str = None, database=None, class_list=None,

metrics/metrics_coverability.py → codart/metrics/metrics_coverability.py

@@ -40,9 +40,9 @@ def NMO(cls, class_name):
     @classmethod
     def NIM(cls, class_name):
         declared_methods = 0 if class_name.metric(['CountDeclMethod'])['CountDeclMethod'] is None else \
-        class_name.metric(['CountDeclMethod'])['CountDeclMethod']
+            class_name.metric(['CountDeclMethod'])['CountDeclMethod']
         all_methods = 0 if class_name.metric(['CountDeclMethodAll'])['CountDeclMethodAll'] is None else \
-        class_name.metric(['CountDeclMethodAll'])['CountDeclMethodAll']
+            class_name.metric(['CountDeclMethodAll'])['CountDeclMethodAll']
         return all_methods - declared_methods
 
     @classmethod

metrics/metrics_jcode_odor.py → codart/metrics/metrics_jcode_odor.py

@@ -12,7 +12,7 @@
 except ImportError as e:
     print(e)
 
-from metrics.metrics_coverability import UnderstandUtility
+from codart.metrics.metrics_coverability import UnderstandUtility
 
 
 class JCodeOdorMetric:

metrics/modularity.py → codart/metrics/modularity.py

@@ -22,7 +22,6 @@
 
 import os
 import re
-import time
 from collections import defaultdict
 
 import pandas
@@ -31,7 +30,7 @@
 
 import understand
 
-from sbse import config
+from codart import config
 from codart.utility.directory_utils import export_understand_dependencies_csv
 
 

metrics/qmood.py → codart/metrics/qmood.py

@@ -13,7 +13,7 @@
 
 import understand as und
 
-from sbse import config
+from codart import config
 
 
 def divide_by_initial_value(func):

metrics/testability_prediction.py → codart/metrics/testability_prediction.py

@@ -10,17 +10,18 @@
 
 """
 
-__version__ = '0.1.1'
+__version__ = '0.1.2'
 __author__ = 'Morteza Zakeri'
 
 import math
 import os
 import warnings
 
 import joblib
+from joblib import Parallel, delayed
 import numpy as np
 import pandas as pd
-from joblib import Parallel, delayed, wrap_non_picklable_objects
+
 
 try:
     import understand as und
@@ -31,11 +32,9 @@
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import QuantileTransformer
 
-import metrics
-from metrics import metrics_names
-from metrics.metrics_jcode_odor import JCodeOdorMetric
-from metrics.metrics_coverability import UnderstandUtility
-
+from codart.metrics.metrics_jcode_odor import JCodeOdorMetric
+from codart.metrics.metrics_coverability import UnderstandUtility
+from codart.metrics import metrics_names
 
 # patch_sklearn()
 
@@ -52,19 +51,19 @@ class TestabilityMetrics:
 
     @classmethod
     def get_class_ordinary_metrics_names(cls) -> list:
-        return metrics.metrics_names.class_ordinary_metrics_names
+        return metrics_names.class_ordinary_metrics_names
 
     @classmethod
     def get_class_lexicon_metrics_names(cls) -> list:
-        return metrics.metrics_names.class_lexicon_metrics_names
+        return metrics_names.class_lexicon_metrics_names
 
     @classmethod
     def get_package_metrics_names(cls) -> list:
-        return metrics.metrics_names.package_metrics_names
+        return metrics_names.package_metrics_names
 
     @classmethod
     def get_project_metrics_names(cls) -> list:
-        return metrics.metrics_names.project_metrics_names
+        return metrics_names.project_metrics_names
 
     @classmethod
     def get_all_metrics_names(cls) -> list:
@@ -92,13 +91,13 @@ def get_all_metrics_names(cls) -> list:
     @classmethod
     def get_all_primary_metrics_names(cls) -> list:
         primary_metrics_names = list()
-        for metric_name in metrics.metrics_names.project_metrics_names_primary:
+        for metric_name in metrics_names.project_metrics_names_primary:
             primary_metrics_names.append('PJ_' + metric_name)
-        for metric_name in metrics.metrics_names.package_metrics_names_primary:
+        for metric_name in metrics_names.package_metrics_names_primary:
             primary_metrics_names.append('PK_' + metric_name)
-        for metric_name in metrics.metrics_names.class_ordinary_metrics_names_primary:
+        for metric_name in metrics_names.class_ordinary_metrics_names_primary:
             primary_metrics_names.append('CSORD_' + metric_name)
-        for metric_name in metrics.metrics_names.class_lexicon_metrics_names:
+        for metric_name in metrics_names.class_lexicon_metrics_names:
             primary_metrics_names.append('CSLEX_' + metric_name)
         return primary_metrics_names
 
@@ -497,7 +496,7 @@ def compute_java_class_metrics2(cls, db=None, entity=None):
         class_metrics.update({'FANIN': j_code_odor_metric.FANIN(db=db, class_entity=entity)})
         class_metrics.update({'FANOUT': j_code_odor_metric.FANOUT(db=db, class_entity=entity)})
 
-        class_metrics.update({'ATFD': UnderstandUtility.ATFD(db=db, class_entity=entity)})  ### not implement
+        class_metrics.update({'ATFD': UnderstandUtility.ATFD(db=db, class_entity=entity)})  # Not implemented
 
         class_metrics.update({'CFNAMM': j_code_odor_metric.CFNAMM_Class(class_name=entity)})
         class_metrics.update({'DAC': UnderstandUtility.get_data_abstraction_coupling(db=db, class_entity=entity)})
@@ -735,8 +734,9 @@ def compute_java_package_metrics(cls, db=None, class_name: str = None):
             package_metrics.update({'SDLineCodeDecl': np.std(pk_loc_decl_list)})
             package_metrics.update({'SDLineCodeExe': np.std(pk_loc_exe_list)})
         except:
-            raise TypeError('Error happen when compute packege metric for class "{0}" and list "{1}"'.format(class_name,
-                                                                                                             pk_loc_decl_list))
+            raise TypeError(
+                f'Error happen when compute packege metric for class "{class_name}" and list "{pk_loc_decl_list}"'
+            )
 
         # 2.2 PKNOS (15)
         pk_stmt_list = list()
@@ -1161,7 +1161,7 @@ def compute_metrics_for_single_class(cls, class_name, und_path, result_csv):
         all_class_metrics_value.append(one_class_metrics_value)
         columns = ['Class']
         columns.extend(TestabilityMetrics.get_all_metrics_names())
-        columns2 = [metrics.metrics_names.metric_map[c_] for c_ in columns[:-1]]
+        columns2 = [metrics_names.metric_map[c_] for c_ in columns[:-1]]
         columns2.append('NOCLINFILE')
         df = pd.DataFrame(data=all_class_metrics_value, columns=columns2)
         df.drop(columns=['NOCLINFILE'], inplace=True)
@@ -1237,8 +1237,8 @@ def main(project_path, initial_value=1.0):
     # classes_longnames_list = p.extract_project_classes(db=db)
     df = p.compute_metrics_by_class_list(project_path, n_jobs=7)  # n_job must be set to number of CPU cores
     # db.close()
-    model = TestabilityModel(df_path=r'../metrics/data_model/DS07012.csv')
-    testability_ = model.inference(model_path='../metrics/data_model/VR1_DS1.joblib', df_predict_data=df)
+    model = TestabilityModel(df_path=r'data_model/DS07012.csv')
+    testability_ = model.inference(model_path='/data_model/VR1_DS1.joblib', df_predict_data=df)
     # print('testability=', testability_)
     return testability_ / initial_value