howardhamilton

import multiprocessing

class Consumer(multiprocessing.Process):
    """Consumer processes.  Subclassed from Process in multiprocessing."""

    def __init__(self, task_queue, result_queue):
        multiprocessing.Process.__init__(self)
        self.task_queue = task_queue
        self.result_queue = result_queue

howardhamilton

import numpy as n
import pylab as p
from matplotlib.patches import Rectangle
from matplotlib.collections import PatchCollection

from pitch import create_normalized_pitch


def _add_centered_square(xy, area):
    size = n.sqrt(area)

howardhamilton

import numpy as np
import matplotlib.pyplot as plt
import matplotlib.patches as pch
import matplotlib.image as img

def create_normalized_pitch(size=(12.5, 8.0), pcolor='none', ecolor='black'):
    """
    Create figure that has football pitch lines drawn on it.  Figure coordinates are normalized to a 100x100 grid.

    If aspect ratio of figure is not equal to 1.5625 (12.5 in / 8.0 in), the figure width is

howardhamilton

# unique list of dictionaries
# ---------------------------
# This problem comes up when I bulk insert records into databases
# because I can't check for existence of records (they don't exist yet, too slow, etc)
#
# I typically use a set to make list elements unique, but dicts and lists themselves
# can't be inserted in sets because they're mutable and thus unhashable.
#
# Solution is to make a tuple of the dict's items and insert it in set,
# then create dicts from each member of the set.

howardhamilton

{
  "version": 1,
  "disable_existing_loggers": false,
  "formatters": {
    "default": {
      "format": "%(asctime)s - %(name)s - %(levelname)s: %(message)s"
    },
    "console": {
      "format": "%(name)-12s: %(message)s"
    }

howardhamilton

from lxml import etree
from lxml.builder import E


if __name__ == "__main__":
    with open('sample.xml') as f:
        xml = f.read()
        new_xml = E.Wrapper(etree.XML(xml))
        print(etree.tostring(new_xml, pretty_print=True))
        

howardhamilton

import logging
import subprocess
from io import BytesIO


def execute_command(cmd, ns=__name__, shell_flag=False):
    """
    Execute command using a subprocess, and write streaming output to the screen.

    :param cmd: Command-line statement

howardhamilton

class RegexpReplacer(object):
    """
    Take in list or dictionary of regex patterns and substitutes, and apply them to text with a map.
    """

    def __init__(self, patterns):
        if type(patterns) is dict:
            self.patterns = [(re.compile(r"{}".format(regex)), patterns['replace'])
                             for regex in patterns['pattern']]
        else:

howardhamilton

"""A Python context to move in and out of directories.

Copyright 2016-2020, Howard Hamilton.

Permission is hereby granted, free of charge, to any person obtaining a copy of this software and 
associated documentation files (the "Software"), to deal in the Software without restriction, in-
cluding without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, 
and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do 
so, subject to the following conditions:

howardhamilton

"""
An outline for identifying N players with similar summary statistics to a player of interest.
A list of candidate players is compiled by filtering on position and end-of-season age.
Summary statistics are scaled to z-scores, which are the inputs to the machine learning model.
This algorithm uses K-Nearest Neighbor, but other algorithms (eg K-Means Clustering) can be substituted.

(c) 2015 Soccermetrics Research LLC
This code is licensed under the terms of the MIT License (http://choosealicense.com/licenses/mit/)
"""
from sklearn.neighbors import NearestNeighbors