skojaku

# Efraimidis and Spirakis algorithm
# https://www.sciencedirect.com/science/article/abs/pii/S002001900500298
import numpy as np
from numba import njit


@njit(nogil=True)
def one_pass_sampling_without_replacement(n, k, weights):
    # Draw a uniform random variable for each item
    u = np.random.rand(n)

skojaku

import numpy as np 
from scipy import sparse 

#
# Evaluation
#
def calc_esim(y, ypred, normalize=False):
    """
    Element centric similarity.
    

skojaku

"""Non-backtracking spectral embedding

Reference
---------
Krzakala, Florent, et al. "Spectral redemption in clustering sparse networks." Proceedings of the National Academy of Sciences 110.52 (2013): 20935-20940.


Example
-------
```python

skojaku

# -*- coding: utf-8 -*-
# @Author: Sadamori Kojaku
# @Date:   2022-10-05 06:24:53
# @Last Modified by:   Sadamori Kojaku
# @Last Modified time: 2023-05-19 13:04:26
import sys
from tqdm.auto import tqdm
import numpy as np
import pandas as pd
import torch

skojaku

import numpy as np

def truncated_RBO(S, T, p=0.9):
    """
    Calculate the (truncated) Rank Biased Overlap (RBO) similarity measure between two ranked lists S and T.

    The original RBO takes the sum over entities beyond the ranking. Since the entities outside of the ranking is unknown,
    the original paper introduces an exterpolation method. But this gives many complexity with additional assumptions on the input data.
    So I take a simpler approach:
      1. Instead of considering a ranking of infinite length, I consider finite ranking and take a sum over the entities in the ranking.

skojaku

import numpy as np

def degreeAssortativity(src, trg, weight=None) -> float:
    """
    Computes the degree assortativity of a graph based on the source and target node degrees and an optional edge weight.

    Parameters
    ----------
    src : array-like
        The source nodes of the edges.

skojaku

# -*- coding: utf-8 -*-
# @Author: Sadamori Kojaku
# @Date:   2023-04-26 12:02:58
# @Last Modified by:   Sadamori Kojaku
# @Last Modified time: 2023-04-26 12:05:15
import numpy as np


class ADAM:
    def __init__(self):

skojaku

import sys

import country_converter as coco
import networkx as nx
import numpy as np
import pandas as pd
from scipy import sparse
from scipy.sparse.csgraph import connected_components

skojaku

# -*- coding: utf-8 -*-
# @Author: Sadamori Kojaku
# @Date:   2023-04-14 17:09:54
# @Last Modified by:   Sadamori Kojaku
# @Last Modified time: 2023-04-17 06:11:17
import faiss
import numpy as np
from numba import jit
from scipy import sparse

skojaku

import pandas as pd
from scipy import sparse
import numpy as np

def fastRP(net, dim, window_size, beta=-1, s=3.0, edge_direction=False):
        """
    .. function:: fastRP(net: scipy.sparse matrix, dim: int, window_size: int, beta: float = -1, s: float = 3.0, return_context: bool = False) -> numpy.ndarray

       Fast Random Projection embedding