alexeyev

import igraph

clusters_const = 2

graph = igraph.read("2_big_graph_clusters_ncol.txt", format="ncol", directed=False, names=True)

clusters = graph.community_edge_betweenness(clusters=2, directed=False)
splitter = clusters.as_clustering(clusters_const).membership
vs = igraph.VertexSeq(graph)

alexeyev

package ru.stachek66.mwe.ml.spark;

import org.apache.spark.SparkConf;
import org.apache.spark.SparkContext;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.mllib.classification.NaiveBayes;
import org.apache.spark.mllib.classification.NaiveBayesModel;
import org.apache.spark.mllib.feature.HashingTF;
import org.apache.spark.mllib.feature.IDF;

alexeyev

import os
import collections
import math

map = {i: [] for i in xrange(50000)}

for file in os.listdir("/home/alexeyev/projects/bee/"):
    # files filter
    if file.startswith("sol_0.7"):

alexeyev

# coding: utf-8
""""
    Скрипт для извлечения имён людей из коллекции текстов о музеях
"""

import os

from docx import Document
from natasha import Combinator
from natasha.grammars import Person

alexeyev

import difflib

text_one = open("1.txt", "r").read()
text_two = open("2.txt", "r").read()

sm = difflib.SequenceMatcher(isjunk=None, a=text_one, b=text_two)
mbs = sm.get_matching_blocks()

for mb in mbs:
    if mb.size > 10:

alexeyev

# coding: utf-8
"""
The MIT License (MIT)

Copyright (c) 2020 Anton Alekseev

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, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell

alexeyev

        # import autosklearn
        # from autosklearn.classification import AutoSklearnClassifier
        # # print("Available CLASSIFICATION metrics autosklearn.metrics.*:")
        # # print("\t*" + "\n\t*".join(autosklearn.metrics.CLASSIFICATION_METRICS))
        # print("Y labels:", set(y))
        #
        # automl = autosklearn.classification.AutoSklearnClassifier(
        #     n_jobs=3,
        #     ensemble_size=1,

alexeyev

#!/usr/bin/env bash
i=1
END=100000

mkdir export

while [ $i -le $END ]; do
    echo "Dealing with company #"$i
    mkdir export/$i

alexeyev

#!/usr/bin/env python3
"""
    We do not recommend using this script for any purposes other than learning to use Selenium;
    for batched machine translation via Google Translate using 'document' translation feature 
    is arguably the most suitable. For regular translations one should use the Cloud API.
"""

import time

from selenium.common.exceptions import TimeoutException

alexeyev

# coding: utf-8

from difflib import SequenceMatcher

t0 = open("text0.txt", "r+").read().strip().replace("\n", " ").replace("  ", " ")
t1 = open("text1.txt", "r+").read().strip().replace("\n", " ").replace("  ", " ")

matcher = SequenceMatcher(a=t0, b=t1)
ratio = matcher.ratio()
mbs = matcher.get_matching_blocks()