def __init__(self, simulator: Simulator):
self.__simulator = simulator
self.__data_dict: OrderedDict[str,
OrderedDict[str,
List[Decimal]]] = OrdDict()
self.__data_structure: OrderedDict[str, OrderedDict[str,
bool]] = OrdDict()
def _get_filtered_data(self, feature_filter: str, module_fqn_filter: str) -> OrderedDict[str, Any]:
r"""
Filters the data and returns it in the same ordered dictionary format so the relavent views can be displayed.
Args:
feature_filter (str): The feature filter, if we want to filter the set of data to only include
a certain set of features that include feature_filter
If feature = "", then we do not filter based on any features
module_fqn_filter (str): The filter on prefix for the module fqn. All modules that have fqn with
this prefix will be included
If module_fqn_filter = "" we do not filter based on module fqn, and include all modules
First, the data is filtered based on module_fqn, and then filtered based on feature
Returns an OrderedDict (sorted in order of model) mapping:
module_fqns -> feature_names -> values
"""
# create return dict
filtered_dict: OrderedDict[str, Any] = OrdDict()
for module_fqn in self.generated_reports:
# first filter based on module
if module_fqn_filter == "" or module_fqn_filter in module_fqn:
# create entry for module and loop through features
filtered_dict[module_fqn] = {}
module_reports = self.generated_reports[module_fqn]
for feature_name in module_reports:
# check if filtering on features and do so if desired
if feature_filter == "" or feature_filter in feature_name:
filtered_dict[module_fqn][feature_name] = module_reports[feature_name]
# we have populated the filtered dict, and must return it
return filtered_dict
def _set_settings_map(self):
# Each item represents a level setting
#
# Key a setter function that takes one argument which receives
# the value the level setting is to be set to. Setter function
# responsible for implementing all conseqeunces of change in
# level setting value. NB All setter functions are class methods.
#
# Value an iterator that returns the level setting values, with
# first interation returning value for level 1 and each subsequent
# call returning value for each successive level. NB iterator
# defined as the return of a function assigned to a corresponding
# global constant.
map = OrdDict({
self._set_level: it.count(1, 1),
self._set_ship_speed: SHIP_SPEED(),
self._set_ship_rotation_speed: SHIP_ROTATION_SPEED(),
self._set_asteroid_speed: ASTEROID_SPEED(),
self._set_spawn_limit: SPAWN_LIMIT(),
self._set_num_per_spawn: NUM_PER_SPAWN(),
self._set_num_asteroids: NUM_ASTEROIDS(),
self._set_bullet_speed: BULLET_SPEED(),
self._set_cannon_reload_rate: CANNON_RELOAD_RATE(),
self._set_radiation_field: RAD_BORDER(),
self._set_natural_exposure_limit: NAT_EXPOSURE_LIMIT(),
self._set_high_exposure_limit: HIGH_EXPOSURE_LIMIT(),
self._set_pickups: NUM_PICKUPS()
})
self._settings_map = map
def add_data(self, category: str, data_field: str, data: Decimal):
if not category in self.__data_dict:
self.__data_dict[category] = OrdDict()
if not data_field in self.__data_dict[category]:
self.__data_dict[category][data_field] = []
self.__data_dict[category][data_field].append(data)
def get_category_ranking(self, sample_info):
# Extract info from named tuple
av_label_pairs = sample_info[3]
hashes = [sample_info[0], sample_info[1], sample_info[2]]
# Whitelist the AVs to filter the ones with meaningful labels
av_whitelist = self.avs
# Initialize auxiliary data structures
duplicates = set()
category_map = {}
# Process each AV label
for (av_name, label) in av_label_pairs:
# If empty label, nothing to do
if not label:
continue
#####################
# Duplicate removal #
#####################
# If label ends in ' (B)', remove it
if label.endswith(' (B)'):
label = label[:-4]
##################
# Suffix removal #
##################
label = self.__remove_suffixes(av_name, label)
########################################################
# Tokenization, token filtering, and alias replacement #
########################################################
tokens = self.__norm_cat(label, hashes)
# Increase token count in map
for t in tokens:
c = category_map[t] if t in category_map else 0
category_map[t] = c + 1
##################################################################
# Token ranking: sorts tokens by decreasing count and then token #
##################################################################
sorted_category = sorted(category_map.iteritems(),
key=itemgetter(1, 0),
reverse=True)
# Delete the tokens appearing only in one AV, add rest to output
sorted_dict = OrdDict()
for t, c in sorted_category:
if c > 1:
sorted_dict[t] = c
else:
break
return sorted_dict
def __init__(self):
self.order = OrdDict()
def get_family_ranking(self, sample_info):
'''
Returns sorted dictionary of most likely family names for sample
'''
# Extract info from named tuple
av_label_pairs = sample_info[3]
hashes = [sample_info[0], sample_info[1], sample_info[2]]
# Whitelist the AVs to filter the ones with meaningful labels
av_whitelist = self.avs
# Initialize auxiliary data structures
duplicates = set()
token_map = {}
# Process each AV label
for (av_name, label) in av_label_pairs:
# If empty label, nothing to do
if not label:
continue
################
# AV selection #
################
if av_whitelist and av_name not in av_whitelist:
continue
#####################
# Duplicate removal #
#####################
# If label ends in ' (B)', remove it
if label.endswith(' (B)'):
label = label[:-4]
# If we have seen the label before, skip
if label in duplicates:
continue
# If not, we add it to duplicates
else:
duplicates.add(label)
##################
# Suffix removal #
##################
label = self.__remove_suffixes(av_name, label)
########################################################
# Tokenization, token filtering, and alias replacement #
########################################################
tokens = self.__normalize(label, hashes)
# Increase token count in map
for t in tokens:
c = token_map[t] if t in token_map else 0
token_map[t] = c + 1
##################################################################
# Token ranking: sorts tokens by decreasing count and then token #
##################################################################
sorted_tokens = sorted(token_map.iteritems(),
key=itemgetter(1, 0),
reverse=True)
# Delete the tokens appearing only in one AV, add rest to output
sorted_dict = OrdDict()
for t, c in sorted_tokens:
if c > 1:
sorted_dict[t] = c
else:
break
return sorted_dict
def get_family_ranking(self, sample_info):
'''
Returns sorted dictionary of most likely family names for sample
'''
# Extract info from named tuple
av_label_pairs = sample_info[3]
hashes = [ sample_info[0], sample_info[1], sample_info[2] ]
# Whitelist the AVs to filter the ones with meaningful labels
av_whitelist = self.avs
# Initialize auxiliary data structures
labels_seen = set()
token_map = {}
# Process each AV label
for (av_name, label) in av_label_pairs:
# If empty label, nothing to do
if not label:
continue
################
# AV selection #
################
if av_whitelist and av_name not in av_whitelist:
continue
#####################
# Duplicate removal #
#####################
# Emsisoft uses same label as
# GData/ESET-NOD32/BitDefender/Ad-Aware/MicroWorld-eScan,
# but suffixes ' (B)' to their label. Remove the suffix.
if label.endswith(' (B)'):
label = label[:-4]
# F-Secure uses Avira's engine since Nov. 2018
# but prefixes 'Malware.' to Avira's label. Remove the prefix.
if label.startswith('Malware.'):
label = label[8:]
# Other engines often use exactly the same label, e.g.,
# AVG/Avast
# K7Antivirus/K7GW
# Kaspersky/ZoneAlarm
# If we have seen the exact same label before, skip
if label in labels_seen:
continue
# If not, we add it to the set of labels seen
else:
labels_seen.add(label)
##################
# Suffix removal #
##################
label = self.__remove_suffixes(av_name, label)
########################################################
# Tokenization, token filtering, and alias replacement #
########################################################
tokens = self.__normalize(label, hashes)
# Increase token count in map
for t in tokens:
c = token_map[t] if t in token_map else 0
token_map[t] = c + 1
##################################################################
# Token ranking: sorts tokens by decreasing count and then token #
##################################################################
sorted_tokens = sorted(token_map.items(),
key=itemgetter(1,0),
reverse=True)
# Delete the tokens appearing only in one AV, add rest to output
sorted_dict = OrdDict()
for t, c in sorted_tokens:
if c > 1:
sorted_dict[t] = c
else:
break
return sorted_dict
def filling_ord_dict(num):
a = OrdDict()
for i in range(num):
a[str(i)] = i
return a
def set_collect_data(self, category: str, data_field: str, collect: bool):
if not category in self.data_structure:
self.data_structure[category] = OrdDict()
self.data_structure[category][data_field] = collect
LEVEL_AUGMENTATION = 1.05
#SHIP CONTROLS
BLUE_CONTROLS = {
'THRUST_KEY': [pyglet.window.key.I],
'ROTATE_LEFT_KEY': [pyglet.window.key.J],
'ROTATE_RIGHT_KEY': [pyglet.window.key.L],
'SHIELD_KEY': [pyglet.window.key.K],
'FIRE_KEY': [pyglet.window.key.ENTER],
'FIRE_FAST_KEY': [pyglet.window.key.BACKSPACE],
'SLD_KEY': [pyglet.window.key.RCTRL],
'FIREWORK_KEYS':
OrdDict({
pyglet.window.key._7: 200,
pyglet.window.key._8: 500,
pyglet.window.key._9: 900
}),
'MINE_KEYS':
OrdDict({
pyglet.window.key.M: 1,
pyglet.window.key.COMMA: 3,
pyglet.window.key.PERIOD: 6
})
}
RED_CONTROLS = {
'THRUST_KEY': [pyglet.window.key.W],
'ROTATE_LEFT_KEY': [pyglet.window.key.A],
'ROTATE_RIGHT_KEY': [pyglet.window.key.D],
'SHIELD_KEY': [pyglet.window.key.S],