def __init__(self, sha):
self.sha = sha
settings = Settings()
self._downloads_path = settings.get_path('downloads')
self._download_archive_path = settings.get_path('download_archive')
self._earliest_project_view = settings.get_database_view(
'earliest_project')
def __init__(self,
expert_language,
second_language,
expert_loc=10000,
second_loc=1000):
"""
:param expert_language: helper.language.Language object of the expert language.
:param second_language: helper.language.Language object of the language to examine. For now just Python.
:param expert_loc: Lines of code that is the threshold for an expert.
:param second_loc: Lines of code threshold for the language to examine to get a code base that is large enough.
"""
self.expert_language = expert_language
self.second_language = second_language
self.expert_loc = expert_loc
self.second_loc = second_loc
settings = Settings()
loc_user_file_ext_view = settings.get_database_view(
'loc_user_file_ext')
self.query = SQL('''
SELECT
u1.user_id,
u1.login
FROM {} AS u1
JOIN {} AS u2 ON u1.user_id = u2.user_id
JOIN users u ON u1.user_id = u.id
WHERE u1.additions >= %s AND u1.file_ext = ANY(%s) AND u2.additions >= %s AND u2.file_ext = ANY(%s) AND u.type = 'USR';
''').format(Identifier(loc_user_file_ext_view),
Identifier(loc_user_file_ext_view))
self.detection_path = settings.get_path([
'detections',
expert_language.language + '_' + second_language.language
])
def __init__(self,
user_id,
login,
expert_language,
second_language,
expert_loc=10000,
second_loc=1000):
"""
:param user_id: User id
:param login: User name
:param expert_language: helper.language.Language object of the expert language.
:param second_language: helper.language.Language object of the language to examine. For now just Python.
:param expert_loc: Lines of code that is the threshold for an expert.
:param second_loc: Lines of code threshold for the language to examine to get a code base that is large enough.
"""
self.user_id = user_id
self.login = login
self.expert_language = expert_language
self.second_language = second_language
self.expert_loc = expert_loc
self.second_loc = second_loc
settings = Settings()
if self.expert_language.language == 'java' and self.second_language.language == 'python':
self.candidates_view = settings.get_database_view(
'candidates_java_py')
self.result_dir_path = settings.get_path(
['detections', 'java_python'])
elif self.expert_language.language == 'cpp' and self.second_language.language == 'python':
self.candidates_view = settings.get_database_view(
'candidates_cpp_py')
self.result_dir_path = settings.get_path(
['detections', 'cpp_python'])
elif self.expert_language.language == 'fun' and self.second_language.language == 'python':
self.candidates_view = settings.get_database_view(
'candidates_fun_py')
self.result_dir_path = settings.get_path(
['detections', 'fun_python'])
else:
raise ValueError(
'No database view for this combination of languages.')
def __init__(self):
settings = Settings()
self.archive_path = settings.get_path('download_archive')
self.download_path = settings.get_path('downloads')
def __init__(self, figsize=(800, 600)):
settings = Settings()
self.figsize = figsize
self.plot_dir = settings.get_path('plots')
def main():
settings = Settings()
java_aggregation_path = settings.get_path(['detections', 'java_python'])
cpp_aggregation_path = settings.get_path(['detections', 'cpp_python'])
fun_aggregation_path = settings.get_path(['detections', 'fun_python'])
aggregation_paths = [
java_aggregation_path, cpp_aggregation_path, fun_aggregation_path
]
aggregation_paths = [p + '/detections.json' for p in aggregation_paths]
aggregators = [Aggregator.load(p) for p in aggregation_paths]
labels = ['Java', 'C++', 'func languages']
plotter = Plotter()
# if
if_percentage = [a.percentage(IfDetection, 'user_id') for a in aggregators]
if_elseif_count_aggregation = [
a.aggregate(IfDetection, 'elseif_count', 'user_id')
for a in aggregators
]
if_has_else_aggregation = [
a.aggregate(IfDetection, 'has_else', 'user_id') for a in aggregators
]
plotter(if_percentage, labels, 'If percentage')
plotter(if_elseif_count_aggregation, labels, 'Elseif count')
plotter(if_has_else_aggregation, labels, 'If has else')
# class
def line_count(detection):
return detection.end - detection.begin + 1
def name_length(detection):
return len(detection.name)
class_definition_percentage = [
a.percentage(ClassDefinitionDetection, 'user_id') for a in aggregators
]
class_line_count_aggregation = [
a.aggregate(ClassDefinitionDetection, line_count, 'user_id')
for a in aggregators
]
class_method_count_aggregation = [
a.aggregate(ClassDefinitionDetection, 'method_count', 'user_id')
for a in aggregators
]
class_name_length_aggregation = [
a.aggregate(ClassDefinitionDetection, name_length, 'user_id')
for a in aggregators
]
class_is_nested_aggregation = [
a.aggregate(ClassDefinitionDetection, 'nested', 'user_id')
for a in aggregators
]
plotter(class_definition_percentage, labels, 'Class percentage')
plotter(class_line_count_aggregation, labels, 'Class line count')
plotter(class_method_count_aggregation, labels, 'Class method count')
plotter(class_name_length_aggregation, labels, 'Class name length')
plotter(class_is_nested_aggregation, labels, 'Class is nested')
# built in functions
class IsFunction:
def __init__(self, name):
self.name = name
def __call__(self, detection):
return 1 if detection.name == self.name else 0
bif_percentage = [
a.percentage(BuiltInFunctionDetection, 'user_id') for a in aggregators
]
bif_map_count_aggregation = [
a.aggregate(BuiltInFunctionDetection, IsFunction('map'), 'user_id')
for a in aggregators
]
bif_filter_count_aggregation = [
a.aggregate(BuiltInFunctionDetection, IsFunction('filter'), 'user_id')
for a in aggregators
]
bif_list_count_aggregation = [
a.aggregate(BuiltInFunctionDetection, IsFunction('list'), 'user_id')
for a in aggregators
]
bif_dict_count_aggregation = [
a.aggregate(BuiltInFunctionDetection, IsFunction('dict'), 'user_id')
for a in aggregators
]
bif_set_count_aggregation = [
a.aggregate(BuiltInFunctionDetection, IsFunction('set'), 'user_id')
for a in aggregators
]
plotter(bif_percentage, labels, 'Built in function percentage')
plotter(bif_map_count_aggregation, labels, 'Map percentage')
plotter(bif_filter_count_aggregation, labels, 'Filter percentage')
plotter(bif_list_count_aggregation, labels, 'List percentage')
plotter(bif_dict_count_aggregation, labels, 'Dict percentage')
plotter(bif_set_count_aggregation, labels, 'Set percentage')
# comprehensions
list_comprehension_percentage = [
a.percentage(ListComprehensionDetection, 'user_id')
for a in aggregators
]
dict_comprehension_percentage = [
a.percentage(DictComprehensionDetection, 'user_id')
for a in aggregators
]
set_comprehension_percentage = [
a.percentage(SetComprehensionDetection, 'user_id') for a in aggregators
]
list_comprehension_generator_count_aggregation = [
a.aggregate(ListComprehensionDetection, 'generator_count', 'user_id')
for a in aggregators
]
dict_comprehension_generator_count_aggregation = [
a.aggregate(DictComprehensionDetection, 'generator_count', 'user_id')
for a in aggregators
]
set_comprehension_generator_count_aggregation = [
a.aggregate(SetComprehensionDetection, 'generator_count', 'user_id')
for a in aggregators
]
plotter(list_comprehension_percentage, labels,
'List comprehension percentage')
plotter(dict_comprehension_percentage, labels,
'Dict comprehension percentage')
plotter(set_comprehension_percentage, labels,
'Set comprehension percentage')
plotter(list_comprehension_generator_count_aggregation, labels,
'List comprehension generator count')
plotter(dict_comprehension_generator_count_aggregation, labels,
'Dict comprehension generator count')
plotter(set_comprehension_generator_count_aggregation, labels,
'Set comprehension generator count')