def get_sorted_best_item_indices(self, URM: sps.csr_matrix,
target_column: np.ndarray,
item_idx: int) -> np.ndarray:
if self.sorted_indices is None:
c_URM = URM.copy()
c_URM.data **= 2
variances = np.array(
c_URM.mean(axis=0) - np.power(URM.mean(axis=0), 2)).flatten()
sorted_indices = np.argsort(variances)[::-1]
return sorted_indices
return self.sorted_indices
def _mat_mat_corr_sparse(
X: csr_matrix,
Y: np.ndarray,
) -> np.ndarray:
"""\
This function is borrow from cellrank
"""
n = X.shape[1]
X_bar = np.reshape(np.array(X.mean(axis=1)), (-1, 1))
X_std = np.reshape(np.sqrt(np.array(X.power(2).mean(axis=1)) - (X_bar**2)),
(-1, 1))
y_bar = np.reshape(np.mean(Y, axis=0), (1, -1))
y_std = np.reshape(np.std(Y, axis=0), (1, -1))
with np.warnings.catch_warnings():
np.warnings.filterwarnings(
"ignore", r"invalid value encountered in true_divide")
return (X @ Y - (n * X_bar * y_bar)) / ((n - 1) * X_std * y_std)
import matplotlib.pyplot as plt
import pandas as pd
import time
num_of_css=5
is_pca=0 #0 for SVD, 1 for PCA
is_sparse=1
Data=np.random.randn(100,11)
if is_sparse==0:
mean_data=np.mean(Data,0)
mean_data=np.reshape(mean_data,(1,len(mean_data)))
else:
Data1=SM(Data)
mean_data=Data1.mean(0)
Datam=Data-np.dot(np.ones((Data.shape[0],1)),mean_data)
Data1=SM(Data)
n=Data.shape[0]
d=Data.shape[1]
opt_error=1
r=1
is_to_save=0
is_save=1
is_big_data=1
alg_list=[0,3,5]
t0=1
if datum==2:
coreset_space=5
def precompute_best_item_indices(self, URM: sps.csr_matrix):
c_URM = URM.copy()
c_URM.data **= 2
variances = np.array(
c_URM.mean(axis=0) - np.power(URM.mean(axis=0), 2)).flatten()
self.sorted_indices = np.argsort(variances)[::-1]
