IevaZarina

# -*- coding: utf-8 -*-
import random


def getRandomPerson(ppl):
    return ppl[random.randint(0,len(ppl)-1)]


def good_pair(ignore_ppl, chosen1, chosen2):
    for pair in ignore_ppl:

IevaZarina

# -*- coding: utf-8 -*-
# Ieva Zarina, 2016, licensed under the Apache 2.0 licnece

import re

def is_digit(word):
    try:
        int(word)
        return True
    except ValueError:

IevaZarina

# Ieva Zarina, 2016, licensed under the Apache 2.0 licnese

import numpy as np
import xgboost as xgb
from sklearn import datasets
from sklearn.cross_validation import train_test_split
from sklearn.datasets import dump_svmlight_file
from sklearn.externals import joblib
from sklearn.metrics import precision_score

IevaZarina

"'{\"animal_list\": [{\"type\": \"mammal\", \"description\": \"Tall, with brown spots, lives in Savanna\", \"name\": \"Giraffa camelopardalis\"},{\"type\": \"mammal\", \"description\": \"Big, grey, with big ears, smart\", \"name\": \"Loxodonta africana\"},{\"type\": \"reptile\", \"description\": \"Green, changes color, lives in \"East Africa\"\", \"name\": \"Trioceros jacksonii\"}]}'"

IevaZarina

import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.decomposition import TruncatedSVD

# Enable saving plot to png file without UI
plt.switch_backend('agg')

iris = datasets.load_iris()
X = iris.data
y = iris.target

IevaZarina

'''
Depth-first searcher

Tree:
    a
   / \
  b   c
 /|\   \
d e f   g
        |

IevaZarina

import ahocorasick as ahc

keywords = [
    ('he', 1),
    ('she', 1),
    ('hers', 1),
    ('her', 1)
]

text = [

IevaZarina

# knn

import math
from collections import defaultdict
from operator import itemgetter


# Some handmade train/test data
X_train = [
    [1, 1],