def get_statistics_URM(self):
self._assert_is_initialized()
n_users, n_items = self.SPLIT_URM_DICT["URM_train"].shape
statistics_string = "DataReader: {}\n" \
"\tNum items: {}\n" \
"\tNum users: {}\n" \
"\tTrain \t\tinteractions {}, \tdensity {:.2E}\n".format(
self.dataReader_object._get_dataset_name(),
n_items,
n_users,
self.SPLIT_URM_DICT["URM_train"].nnz, compute_density(self.SPLIT_URM_DICT["URM_train"]))
if self.use_validation_set:
statistics_string += "\tValidation \tinteractions {}, \tdensity {:.2E}\n".format(
self.SPLIT_URM_DICT["URM_validation"].nnz,
compute_density(self.SPLIT_URM_DICT["URM_validation"]))
statistics_string += "\tTest \t\tinteractions {}, \tdensity {:.2E}\n".format(
self.SPLIT_URM_DICT["URM_test"].nnz,
compute_density(self.SPLIT_URM_DICT["URM_test"]))
self._print(statistics_string)
print("\n")
def get_statistics_UCM(self):
self._assert_is_initialized()
if len(self.dataReader_object.get_loaded_UCM_names()) > 0:
for UCM_name, UCM_object in self.SPLIT_UCM_DICT.items():
n_items, n_features = UCM_object.shape
statistics_string = "\tUCM name: {}, Num features: {}, feature occurrences: {}, density {:.2E}".format(
UCM_name, n_features, UCM_object.nnz,
compute_density(UCM_object))
print(statistics_string)
def print_statistics(self):
self._assert_is_initialized()
URM_all = self.get_URM_all()
n_users, n_items = URM_all.shape
n_interactions = URM_all.nnz
URM_all = sps.csr_matrix(URM_all)
user_profile_length = np.ediff1d(URM_all.indptr)
max_interactions_per_user = user_profile_length.max()
avg_interactions_per_user = n_interactions / n_users
min_interactions_per_user = user_profile_length.min()
URM_all = sps.csc_matrix(URM_all)
item_profile_length = np.ediff1d(URM_all.indptr)
max_interactions_per_item = item_profile_length.max()
avg_interactions_per_item = n_interactions / n_items
min_interactions_per_item = item_profile_length.min()
print("DataReader: current dataset is: {}\n"
"\tNumber of items: {}\n"
"\tNumber of users: {}\n"
"\tNumber of interactions in URM_all: {}\n"
"\tValue range in URM_all: {:.2f}-{:.2f}\n"
"\tInteraction density: {:.2E}\n"
"\tInteractions per user:\n"
"\t\t Min: {:.2E}\n"
"\t\t Avg: {:.2E}\n"
"\t\t Max: {:.2E}\n"
"\tInteractions per item:\n"
"\t\t Min: {:.2E}\n"
"\t\t Avg: {:.2E}\n"
"\t\t Max: {:.2E}\n"
"\tGini Index: {:.2f}\n".format(
self.__class__,
n_items,
n_users,
n_interactions,
np.min(URM_all.data),
np.max(URM_all.data),
compute_density(URM_all),
min_interactions_per_user,
avg_interactions_per_user,
max_interactions_per_user,
min_interactions_per_item,
avg_interactions_per_item,
max_interactions_per_item,
gini_index(user_profile_length),
))
if self._HAS_ICM:
for ICM_name, ICM_object in self.AVAILABLE_ICM.items():
n_items, n_features = ICM_object.shape
min_value = np.min(ICM_object.data)
max_value = np.max(ICM_object.data)
format_string = "2E" if np.max(
[np.abs(min_value), np.abs(max_value)]) > 100 else "2f"
statistics_string = "\tICM name: {}, Value range: {:.{format_string}} / {:.{format_string}}, Num features: {}, feature occurrences: {}, density {:.2E}".format(
ICM_name,
min_value,
max_value,
n_features,
ICM_object.nnz,
compute_density(ICM_object),
format_string=format_string)
print(statistics_string)
print("\n")
def get_statistics_URM(self):
self._assert_is_initialized()
n_users, n_items = self.SPLIT_URM_DICT["URM_train"].shape
statistics_string = "DataReader: {}\n" \
"\tNum items: {}\n" \
"\tNum users: {}\n" \
"\tTrain \t\tquota {:.2f} ({:.2f}), \tinteractions {}, \tdensity {:.2E}\n" \
"\tValidation \tquota {:.2f} ({:.2f}), \tinteractions {}, \tdensity {:.2E}\n" \
"\tTest \t\tquota {:.2f} ({:.2f}), \tinteractions {}, \tdensity {:.2E}\n".format(
self.dataReader_object._get_dataset_name(),
n_items,
n_users,
self.input_split_interaction_quota_list[0], self.actual_split_interaction_quota_list[0], self.SPLIT_URM_DICT["URM_train"].nnz, compute_density(self.SPLIT_URM_DICT["URM_train"]),
self.input_split_interaction_quota_list[1], self.actual_split_interaction_quota_list[1], self.SPLIT_URM_DICT["URM_validation"].nnz, compute_density(self.SPLIT_URM_DICT["URM_validation"]),
self.input_split_interaction_quota_list[2], self.actual_split_interaction_quota_list[2], self.SPLIT_URM_DICT["URM_test"].nnz, compute_density(self.SPLIT_URM_DICT["URM_test"]),
)
self._print(statistics_string)
print("\n")
