yjzhang

# Online k-means algorithm
# see http://www.cs.princeton.edu/courses/archive/fall08/cos436/Duda/C/sk_means.htm

import numpy as np

def k_means(data, k, threshhold=2):
    """
    Does k-means clustering of the data.

    Args:

yjzhang

#!/bin/bash

# downloads all MEDLINE/Pubmed citations in the annual baseline.

for i in $(seq 1 972); do
    fname="1"
    if ((i < 10)); then
        fname="ftp://ftp.ncbi.nlm.nih.gov/pubmed/baseline/pubmed19n000$i.xml.gz"
    elif ((i < 100)); then
        fname="ftp://ftp.ncbi.nlm.nih.gov/pubmed/baseline/pubmed19n00$i.xml.gz"

yjzhang

Neo4j Tutorial

Fundamentals

Store any kind of data using the following graph concepts:

• Node: Graph data records
• Relationship: Connect nodes (has direction and a type)
• Property: Stores data in key-value pair in nodes and relationships
• Label: Groups nodes and relationships (optional)

yjzhang

# https://ftp.ncbi.nlm.nih.gov/pubmed/baseline/
import requests
from selectolax.parser import HTMLParser

base_url = 'https://ftp.ncbi.nlm.nih.gov/pubmed/baseline/'

r = requests.get(base_url)
tree = HTMLParser(r.content)

for node in tree.css('a'):

yjzhang

import functools

#from numba import jit
import numpy as np
from scipy import sparse


def random_walks(adj_list, r, l, p=1, q=1, verbose=False):
    """
    Biased random walk starting from node i.

yjzhang

def find_all_shortest_paths(dic_node, n1, n2, step_threshold):
    return_paths = []
    visit_queue = [[n1]]
    # this can be updated to get all shortest paths for all visited nodes
    # for the shortest path from N1 to N2, all intermediate paths are also shortest paths between their respective nodes.
    visited_nodes_prev = set()
    visited_nodes = set()
    cur_distance = 0
    while len(visit_queue):
        cur_path = visit_queue.pop(0)

yjzhang

# Using a sparse matrix imported from...

import numpy as np
from scipy import sparse, io


def pagerank(adjacency, probs=None, n_iters=20, resid=0.85, modify_matrix=True):
    """
    Args:
        adjacency - sparse matrix

yjzhang

import subprocess

import numpy as np
from scipy import sparse, io

threshold = 1000
folders = ['M7_5', 'M8_3', 'X5.3.4', 'X5_2', 'X6.1']

for f in folders:
    print(f)

yjzhang

#!/usr/bin/env python3

import sys
import textstat

path = 'scripted_test_outputs/000_output.txt'

if len(sys.argv) > 1:
    path = sys.argv[1]

yjzhang

import os
import subprocess

filenames = os.listdir('.')
for filename in filenames:
    name = filename.split('_')[0]
    if not os.path.exists(name):
        os.makedirs(name)
    os.rename(filename, os.path.join(name, filename))
    if filename.endswith('zip'):