deaktator

import numpy as np
import pulp  # https://pythonhosted.org/PuLP/

# vvvvvvvvvvvvvvvvvvvvvvvvv  convenience methods  vvvvvvvvvvvvvvvvvvvvvvvvv
def dot(coefficients, variables):
    return pulp.LpAffineExpression(zip(variables, coefficients))
    
def print_variables(t, y):
    print(f't: {t.varValue}')
    for i in range(len(y)):

deaktator

import numpy as np
import itertools
import pulp  # https://pythonhosted.org/PuLP/

def brute_force_best(
    runners_per_country, 
    qs,
    max_countries, 
    min_runners):
    

deaktator

import numpy as np
import itertools
import pulp  # https://pythonhosted.org/PuLP/

def count_to_ind_lookup(counts):
    lookup = {}
    ind = 0
    for i, c in enumerate(counts):
        lookup.update(dict(zip(range(ind, ind + c), [i] * c)))
        ind += c

deaktator

import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
from scipy.stats import beta, uniform
from sklearn.metrics import (
    f1_score,
    accuracy_score, 
    precision_score, 
    recall_score,
    average_precision_score

deaktator

def something(n: Long, k: Long): Double =
  1 - (n - k) / k.toDouble * math.log((n + 0.5) / (n - k + 0.5))

deaktator

def something(n: Long, k: Long): BigDecimal = {
  def h(i: Long, total: BigDecimal): BigDecimal = {
    if (k < i) total
    else {
      val p = BigDecimal.exact(i) / (n - k + i)
      val ap = p / k
      h(i + 1, total + ap)
    }
  }
  h(1, BigDecimal.exact(0))

deaktator

def something(n: Long, k: Long): BigDecimal = {
  // For convenience.
  type BD = BigDecimal
  def bd(v: Long) = BigDecimal.exact(v)

  @scala.annotation.tailrec         // OLD VERSION:
  def h(i: Long, total: BD): BD = { // def h(ni: Long, ki: Long, total: DB) = {
    if (i <= 0) total               //   if (ki <= 0) total
    else {                          //   else {
      val p = bd(i) / denom(n,k,i)  //     val p = bd(ki) / ni

deaktator

def something(n: Long, k: Long): BigDecimal = {
  @scala.annotation.tailrec
  def h(ni: Long, ki: Long, total: BigDecimal): BigDecimal = {
    if (ki <= 0) total
    else {
      val p = BigDecimal.exact(ki) / ni
      val ap = p / k
      h(ni - 1, ki - 1, total + ap)
    }
  }

deaktator

# ============================================================================
#  R.M. Deak                                    wt_cv_eval_is_diff_unwt_cv.py
#
#  Runs scikit-learn's cross validation with GridSearchCV and shows that
#  different optimal parameter values may be returned by GridSearchCV than
#  when using cross validation with sample_weights passed to the scoring
#  function.
# ============================================================================

from typing import NamedTuple

deaktator

from scipy.stats import hypergeom

# Run the following to see the graph:
#     for i in range(1, 400):
#         print(f"{i}\t{exp_test_acc(400, 201, i)}")
#
def exp_test_acc(pop_size, pos_in_pop, fold1_size):
    fold2_size = pop_size - fold1_size
    E_acc = 0.0