dayyass

dayyass

import re


# Method build_tokenizer from _VectorizerMixin mixin from which classes HashingVectorizer, CountVectorizer and 
# TfidfVectorizer (through CountVectorizer) are partially inherited.
# It is used to split a string into a sequence of tokens (only if analyzer == 'word').
def build_tokenizer(token_pattern: str = r"(?u)\b\w\w+\b"):
    """
    Return a function that splits a string into a sequence of tokens.
    

dayyass

import numpy as np
from tqdm import trange
from collections import defaultdict
from typing import Dict, Tuple, DefaultDict


def get_matrix_idx_to_value_dict(
    matrix: np.ndarray,
    verbose: bool = True,
) -> DefaultDict[Tuple[int, int], int]:

dayyass

- repo: local
  hooks:
    - id: unittest
      name: unittest
      entry: python -m unittest discover
      language: python
      always_run: true
      pass_filenames: false

dayyass

FROM cr.msk.sbercloud.ru/aicloud-jupyter/jupyter-cuda10.1-tf2.2.0-mlspace:latest
MAINTAINER Dani El-Ayyass <[email protected]>

USER root

# Docker
# Set up the repository
RUN apt-get update
RUN apt-get -y install apt-transport-https ca-certificates curl gnupg lsb-release

dayyass

def humanize_bytes(bytes: int, suffix: str = "B") -> str:
    """
    Convert bytes to human readable format.

    :param int bytes: number of bytes.
    :param str suffix: bytes suffix.
    :return: human readable size.
    :rtype: str
    """

dayyass

import pymorphy2


class Lemmatizer:
    """
    Pymorphy2 lemmatizer class.
    """
    
    def __init__(self):
        """

dayyass

from sklearn.feature_extraction.text import TfidfVectorizer

# data
corpus = [
    'This is the first document.',
    'This document is the second document.',
    'And this is the third one.',
    'Is this the first document?',
]

dayyass

from sklearn.feature_extraction.text import TfidfVectorizer

# pymorphy2 lemmatizer
import pymorphy2

class Lemmatizer:
    def __init__(self):
        self.morph = pymorphy2.MorphAnalyzer()
        
    def __call__(self, x: str) -> str:

dayyass

from itertools import permutations

import numpy as np
from sklearn.metrics import accuracy_score

np.random.seed(42)

y_true = np.random.randint(low=0, high=3, size=100)

noize_mapper = {0: 1, 1: 2, 2: 0}