macleginn

import numpy as np

# We're given an n by n distance matrix *D* with transfer
# probabilities for a given pair of nodes (for any feature),
# a feature matrix *M*, and a dropout probability p_d.

# We convert the transfer probabilities to no-transfer probabilities
# and take their logs
L = np.log(1 - D)

macleginn

# Собираем вместе все возможные знаки пунктуации
import sys
from unicodedata import category
chrs = (chr(i) for i in range(sys.maxunicode + 1))
punctuation = set(c for c in chrs if category(c).startswith("P"))
# Дефис бывает внутри слов
punctuation.remove('-')


def tokenize(s, lower_case=False):

macleginn

def rm_whitespace(s):
    if s.startswith('Ġ'):
        return s[1:]
    else:
        return s


def get_tokens_with_ranges(input_string, tokenizer):
    '''
    RoBERTa prepends 'Ġ' to the beginning of what it

macleginn

import pandas as pd
import matplotlib.pyplot as plt

d = pd.read_excel('spectrograms-relative-20.xlsx', header=None)
# Combine the first two columns in a new index
index_col = [ f'{a}-{b}' for a, b in zip(d.iloc[:,0], d.iloc[:,1]) ]
d.index = index_col
# Delete old index columns
del d[0]
del d[1]

macleginn

import re
import os
from math import log
from collections import Counter

import pandas as pd


def logL(p, k, n):
    return k * log(p) + (n - k) * log(1 - p)

macleginn

from itertools import combinations, permutations
from collections import Counter

import gurobipy as gb
from gurobipy import GRB


def get_pairwise_ordering(all_deprels: set, training_set_constraints: Counter):
    '''
    Solves an integer program and returns a non-loopy ordering

macleginn

# params: 
# $1 input-file path, 
# $2 page range (e.g., "1-1", "10-39", "5,9-12"), 
# $3 output-file path
# ex.: pages_from_pdf input.pdf "1,3,8-9" test.pdf
# qpdf should be installed
function pages_from_pdf() {
    qpdf $1 --pages $1 $2 -- $3    
}

macleginn

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np

# test.csv:
# ,b,c,d
# p,1,2,3
# q,4,5,6
# r,7,8,9

macleginn

import numpy as np
import matplotlib.pyplot as plt

N = 5
menMeans = (20, 35, 30, 35, 27)
womenMeans = (25, 32, 34, 20, 25)
menStd = (2, 3, 4, 1, 2)
womenStd = (3, 5, 2, 3, 3)
ind = np.arange(N)    # the x locations for the groups
width = 0.35       # the width of the bars: can also be len(x) sequence

macleginn

confusion_dict_pos = {}
confusion_dict_paths = {}

# NEW STUFF #
addition_stats_pos = Counter()
addition_stats_rel = Counter()
# NEW STUFF #

strip_direction = lambda x: x.split('_')[0]