def split_randomic_exactly_last(self, URM, URM_df):
# splitting URM in test set e train set
selected_playlists = np.array([])
helper = Helper()
self.target_playlists = helper.get_target_playlists_list()[5000:]
selected_playlists = self.target_playlists
grouped = URM_df.groupby(
'playlist_id', as_index=True).apply(lambda x: list(x['track_id']))
relevant_items = defaultdict(list)
count = 0
for playlist_id in selected_playlists:
tracks = np.array(grouped[playlist_id])
to_be_removed = int(len(tracks) * 0.2)
for i in range(to_be_removed):
index = randint(0, len(tracks) - 1)
removed_track = tracks[index]
relevant_items[playlist_id].append(removed_track)
tracks = np.delete(tracks, index)
grouped[playlist_id] = tracks
count += 1
all_tracks = self.tracks_df["track_id"].unique()
matrix = MultiLabelBinarizer(classes=all_tracks,
sparse_output=True).fit_transform(grouped)
self.URM_train = matrix.tocsr()
self.URM_train = self.URM_train.astype(np.float64)
self.dict_test = relevant_items
def split_only_sequential(self, URM, URM_df):
helper = Helper()
sequential_playlists = helper.get_target_playlists_list()[:5000]
selected_playlists = np.array([])
self.target_playlists = sequential_playlists
grouped = URM_df.groupby(
'playlist_id', as_index=True).apply(lambda x: list(x['track_id']))
relevant_items = defaultdict(list)
for playlist_id in sequential_playlists:
# Tracks = lista delle tracks prese dalla URM
tracks = np.array(grouped[playlist_id])
to_be_removed = int(len(tracks) * 0.2)
# Torna le #to_be_removed tracks ordinate sequenzialmente. e le toglie dalla lista delle tracks
to_be_removed_tracks = helper.get_sorted_tracks_in_playlist(
playlist_id)[-to_be_removed:]
for track in to_be_removed_tracks:
relevant_items[playlist_id].append(track)
tracks = np.delete(tracks, np.where(tracks == track))
grouped[playlist_id] = tracks
all_tracks = self.tracks_df["track_id"].unique()
matrix = MultiLabelBinarizer(classes=all_tracks,
sparse_output=True).fit_transform(grouped)
self.URM_train = matrix.tocsr()
self.URM_train = self.URM_train.astype(np.float64)
self.dict_test = relevant_items
def recommend(self, playlist_id, at=10):
playlist_id = int(playlist_id)
helper = Helper()
### DUE TO TIME CONSTRAINT THE CODE STRUCTURE HERE IS REDUNTANT
### TODO exploit inheritance to reduce code duplications and simple extract ratings, combine them, simply by iterate over a list of recommenders
### COMMON CODE ###
self.hybrid_ratings = None #BE CAREFUL, MAGIC INSIDE :)
### COMBINE RATINGS IN DIFFERENT WAYS (seq, random short, random long)
if (helper.is_sequential(playlist_id)):
self.userCF_ratings = self.userCF_sequential.get_expected_ratings(
playlist_id)
self.itemCF_ratings = self.itemCF_sequential.get_expected_ratings(
playlist_id)
self.cbf_ratings = self.cbf_sequential.get_expected_ratings(
playlist_id)
self.slim_elastic_ratings = self.slim_elastic_sequential.get_expected_ratings(
playlist_id)
# self.svd_icm_ratings = self.svd_icm_sequential.get_expected_ratings(playlist_id)
self.ALS_ratings = self.ALS_sequential.get_expected_ratings(
playlist_id)
self.slim_ratings = self.slim_sequential.get_expected_ratings(
playlist_id)
w_right = self.w_seq
else:
self.userCF_ratings = self.userCF.get_expected_ratings(playlist_id)
self.itemCF_ratings = self.itemCF.get_expected_ratings(playlist_id)
self.cbf_ratings = self.cbf.get_expected_ratings(playlist_id)
self.slim_elastic_ratings = self.slim_elastic.get_expected_ratings(
playlist_id)
# self.svd_icm_ratings = self.svd_icm.get_expected_ratings(playlist_id)
self.ALS_ratings = self.ALS.get_expected_ratings(playlist_id)
self.slim_ratings = self.slim_random.get_expected_ratings(
playlist_id)
if len(self.URM[playlist_id].indices) > 10:
w_right = self.w_long
else:
w_right = self.w_short
self.hybrid_ratings = self.userCF_ratings * w_right["user_cf"]
self.hybrid_ratings += self.itemCF_ratings * w_right["item_cf"]
self.hybrid_ratings += self.cbf_ratings * w_right["cbf"]
self.hybrid_ratings += self.slim_ratings * w_right["slim"]
# self.hybrid_ratings += self.svd_icm_ratings * w_right["svd_icm"]
self.hybrid_ratings += self.ALS_ratings * w_right["als"]
self.hybrid_ratings += self.slim_elastic_ratings * w_right["elastic"]
recommended_items = np.flip(np.argsort(self.hybrid_ratings), 0)
# REMOVING SEEN
unseen_items_mask = np.in1d(recommended_items,
self.URM[playlist_id].indices,
assume_unique=True,
invert=True)
recommended_items = recommended_items[unseen_items_mask]
return recommended_items[0:at]
def split_cluster_randomic_only_last(self, URM, URM_df):
# splitting URM in test set e train set
segment = 1
# splitting URM in test set e train set
selected_playlists = np.array([])
available_playlists = np.arange(URM.shape[0])
target_analyzer = TargetAnalyzer()
# Gets distribution of only last 5000 playlists
dist = target_analyzer.get_distribution_array_only_last(segment)
helper = Helper()
target_playlists = helper.get_target_playlists_list(
)[:5000] # WILL REMOVE THEM
print("Clustering with segment = " + str(segment))
for key in tqdm(range(len(dist))):
while dist[key] != 0:
random_index = randint(0, len(available_playlists) - 1)
playlist_id = available_playlists[random_index]
target_segment = int(0.8 * len(URM[playlist_id].data))
if target_segment == key and playlist_id not in target_playlists:
available_playlists = np.delete(
available_playlists,
np.where(available_playlists == playlist_id))
selected_playlists = np.append(selected_playlists,
playlist_id)
dist[key] -= 1
self.target_playlists = selected_playlists.astype(int)
grouped = URM_df.groupby(
'playlist_id', as_index=True).apply(lambda x: list(x['track_id']))
relevant_items = defaultdict(list)
for playlist_id in selected_playlists:
# Tracks = lista delle tracks prese dalla URM
tracks = np.array(grouped[playlist_id])
to_be_removed = int(len(tracks) * 0.2)
for i in range(to_be_removed):
index = randint(0, len(tracks) - 1)
removed_track = tracks[index]
relevant_items[playlist_id].append(removed_track)
tracks = np.delete(tracks, index)
grouped[playlist_id] = tracks
all_tracks = self.tracks_df["track_id"].unique()
matrix = MultiLabelBinarizer(classes=all_tracks,
sparse_output=True).fit_transform(grouped)
self.URM_train = matrix.tocsr()
self.URM_train = self.URM_train.astype(np.float64)
self.dict_test = relevant_items
def split_randomic_all_playlists_longer_10000(self,
URM,
URM_df,
threshold_length=10):
# splitting URM in test set e train set
selected_playlists = np.array([])
available_playlists = np.arange(URM.shape[0])
helper = Helper()
target_playlists_kaggle = helper.get_target_playlists_list()
for playlist_id in available_playlists:
if len(selected_playlists) == 10000:
break
if playlist_id not in target_playlists_kaggle and len(
URM[playlist_id].indices) > threshold_length:
selected_playlists = np.append(selected_playlists, playlist_id)
self.target_playlists = selected_playlists.astype(int)
grouped = URM_df.groupby(
'playlist_id', as_index=True).apply(lambda x: list(x['track_id']))
relevant_items = defaultdict(list)
for playlist_id in selected_playlists:
tracks = np.array(grouped[playlist_id])
to_be_removed = int(len(tracks) * 0.2)
for i in range(to_be_removed):
index = randint(0, len(tracks) - 1)
removed_track = tracks[index]
relevant_items[playlist_id].append(removed_track)
tracks = np.delete(tracks, index)
grouped[playlist_id] = tracks
all_tracks = self.tracks_df["track_id"].unique()
matrix = MultiLabelBinarizer(classes=all_tracks,
sparse_output=True).fit_transform(grouped)
self.URM_train = matrix.tocsr()
self.URM_train = self.URM_train.astype(np.float64)
self.dict_test = relevant_items
def split_cluster_randomic(self, URM, URM_df):
# splitting URM in test set e train set
selected_playlists = np.array([])
available_playlists = np.arange(URM.shape[0])
target_analyzer = TargetAnalyzer()
segment_size = 1
min_playlist_len_after_split = 5
dist = target_analyzer.get_distribution_array(
segment_size=segment_size)
# in this way n_target = 10000
helper = Helper()
target_playlists = helper.get_target_playlists_list()[:5000]
n_target = np.sum(dist) # - len(target_playlists)
while n_target > 0:
random_index = randint(0, len(available_playlists) - 1)
playlist_id = available_playlists[random_index]
target_len = len(URM[playlist_id].data) * 0.8
if target_len > min_playlist_len_after_split:
target_segment = int(target_len / segment_size)
while dist[target_segment] <= 0:
random_index = randint(0, len(available_playlists) - 1)
playlist_id = available_playlists[random_index]
target_len = len(URM[playlist_id].data) * 0.8
if target_len > min_playlist_len_after_split:
target_segment = int(target_len / segment_size)
n_target -= 1
dist[target_segment] -= 1
selected_playlists = np.append(selected_playlists, playlist_id)
available_playlists = np.delete(
available_playlists,
np.where(available_playlists == playlist_id))
self.target_playlists = selected_playlists.astype(int)
grouped = URM_df.groupby(
'playlist_id', as_index=True).apply(lambda x: list(x['track_id']))
grouped_test = grouped.copy()
relevant_items = defaultdict(list)
count = 0
for playlist_id in selected_playlists:
tracks = np.array(grouped[playlist_id])
# if playlist_id in target_playlists:
# to_be_removed = int(len(tracks) * 0.2)
# to_be_removed_tracks = helper.get_sorted_tracks_in_playlist(playlist_id)[-to_be_removed:]
# for track in to_be_removed_tracks:
# relevant_items[playlist_id].append(track)
# tracks = np.delete(tracks, np.where(tracks == track))
# for i in range(to_be_removed):
# removed_track = tracks[-1]
# relevant_items[playlist_id].append(removed_track)
# tracks = np.delete(tracks, len(tracks) - 1)
# else:
to_be_removed = int(len(tracks) * 0.2)
for i in range(to_be_removed):
index = randint(0, len(tracks) - 1)
removed_track = tracks[index]
relevant_items[playlist_id].append(removed_track)
tracks = np.delete(tracks, index)
grouped[playlist_id] = tracks
grouped_test[playlist_id] = relevant_items[playlist_id]
count += 1
all_tracks = self.tracks_df["track_id"].unique()
matrix = MultiLabelBinarizer(classes=all_tracks,
sparse_output=True).fit_transform(grouped)
self.URM_train = matrix.tocsr()
self.dict_test = relevant_items
# bib URM
# self.URM_train = helper.get_urm_csr_bib(URM = self.URM_train)
# plotter = TargetAnalyzer()
# plotter.plot_standard_distribution()
# plotter.plot_distribution(self.URM_train, self.target_playlists)
self.URM_test = MultiLabelBinarizer(
classes=all_tracks, sparse_output=True).fit_transform(grouped_test)
self.URM_test = self.URM_test.tocsr()
self.URM_test = self.URM_test.astype(np.float64)
self.URM_train = self.URM_train.astype(np.float64)
def split_sequential(self, URM, URM_df):
segment = 1
# splitting URM in test set e train set
selected_playlists = np.array([])
available_playlists = np.arange(URM.shape[0])
target_analyzer = TargetAnalyzer()
#Gets distribution of only last 5000 playlists
dist = target_analyzer.get_distribution_array_only_last(segment)
helper = Helper()
target_playlists = helper.get_target_playlists_list()[:5000]
#n_target = np.sum(dist) - len(target_playlists)
# Removing from the cluster distribution the len of the sequential target
for playlist_id in target_playlists:
playlist_id = int(playlist_id)
available_playlists = np.delete(
available_playlists,
np.where(available_playlists == playlist_id))
selected_playlists = np.append(selected_playlists, playlist_id)
#target_len = len(URM[playlist_id].data)
#dist[target_len] -= 1
print("Clustering with segment = " + str(segment))
for key in tqdm(range(len(dist))):
while dist[key] != 0:
random_index = randint(0, len(available_playlists) - 1)
playlist_id = available_playlists[random_index]
target_segment = int(0.8 * len(URM[playlist_id].data))
if target_segment == key:
available_playlists = np.delete(
available_playlists,
np.where(available_playlists == playlist_id))
selected_playlists = np.append(selected_playlists,
playlist_id)
dist[key] -= 1
self.target_playlists = selected_playlists.astype(int)
grouped = URM_df.groupby(
'playlist_id', as_index=True).apply(lambda x: list(x['track_id']))
relevant_items = defaultdict(list)
for playlist_id in selected_playlists:
#Tracks = lista delle tracks prese dalla URM
tracks = np.array(grouped[playlist_id])
if playlist_id in target_playlists:
to_be_removed = int(len(tracks) * 0.2)
#Torna le #to_be_removed tracks ordinate sequenzialmente. e le toglie dalla lista delle tracks
to_be_removed_tracks = helper.get_sorted_tracks_in_playlist(
playlist_id)[-to_be_removed:]
for track in to_be_removed_tracks:
relevant_items[playlist_id].append(track)
tracks = np.delete(tracks, np.where(tracks == track))
else:
to_be_removed = int(len(tracks) * 0.2)
for i in range(to_be_removed):
index = randint(0, len(tracks) - 1)
removed_track = tracks[index]
relevant_items[playlist_id].append(removed_track)
tracks = np.delete(tracks, index)
grouped[playlist_id] = tracks
all_tracks = self.tracks_df["track_id"].unique()
matrix = MultiLabelBinarizer(classes=all_tracks,
sparse_output=True).fit_transform(grouped)
self.URM_train = matrix.tocsr()
self.URM_train = self.URM_train.astype(np.float64)
self.dict_test = relevant_items
currentDir = os.path.basename(os.getcwd()) currentFileName = os.path.basename(__file__) libDir = os.path.abspath(os.path.join(os.path.dirname(__file__), "../")) sys.path.append(libDir) print libDir from lib.router import Router router = Router() ROUTES = router.getRoutes() from lib.loader import Loader loader = Loader(currentFullRoute, ROUTES) from lib.helper import Helper helper = Helper() from lib.filewriter import FileWriter filewriter = FileWriter() from lib.reporter import Reporter reporter = Reporter(ROUTES) # return to current path sys.path.append(currentFullRoute) # ---------------------------------------------------------------------- CUSTOM LIBS from math import * from graphviz import Digraph
from lib.helper import Helper
from lib.encoder import Encoder
import sys
if __name__ == "__main__":
helper = Helper(sys.argv)
helper.ParseConfig().ShowConfigDescription()
encoder = Encoder(helper)
encoder.append_vars(helper.GetConfig("vars"))
template = helper.LoadFile(helper.GetConfig("template"))
data = template
for evasion in helper.GetConfig("evasion"):
data += helper.LoadFile("templates/evasions/" + evasion + ".vba")
data = encoder.replace_var(data, "offset", encoder.get_encoding_offset())
data = encoder.encode_user_vars(data)
data = encoder.append_def_use_tag(data)
data = encoder.rand_vars(data)
data = encoder.rand_int(data)
data = encoder.rand_smallint(data)
encodedvars = helper.GetConfig("encodedvars")
for var in encodedvars:
data = encoder.replace_var(data, var, encodedvars[var], True)
if "-s" in sys.argv or "--split_strings" in sys.argv:
data = encoder.split_strings(data)
if "-x" in sys.argv or "--strings_to_hex" in sys.argv:
