odinokov

import os
import requests
import shutil
from tqdm import tqdm


def download_file(url: str, file_path: str) -> None:
    """
    Downloads a file from the given URL and saves it to the specified file path.
    Shows a progress bar using the tqdm library.

odinokov

def print_columns(data: list, num_cols : int):
    """
    Prints the elements of a list in columns.

    Args:
        data: A list of data to be printed.
        num_cols: The number of columns to print.

    Returns:
        None

odinokov

# remove covariance in order to reduce the number of features

import numpy as np

def drop_covariance(df, threshold=0.95):

    # Create correlation matrix
    corr_matrix = df.corr().abs()

odinokov

# read more about
# http://matpalm.com/resemblance/simhash/
#

from collections import Counter
from itertools import chain
from toolz import pipe
import numpy as np

global HASH_SIZE

odinokov

"""
http://rocksdb.org
sudo apt-get install librocksdb-dev
pip3 install Cython python-rocksdb
"""

import rocksdb, gc
import numpy as np

rocksdb_fm_path = 'test.db'

odinokov

```{r setup, include=TRUE}

# clean up R environment
rm(list = ls(all = TRUE))

# permanently setting the CRAN repository 
options(repos = getOption("repos")["CRAN"])

if (!requireNamespace("pacman", quietly = TRUE))
    install.packages("pacman")

odinokov

# pip3 install pygsheets -user
import pygsheets
import sys
# Get user's authorization as a Service Account
# Turn on Google Drive and Google Sheets API

SPREADSHEET_NAME = 'ABCD'
key = './pygsheets-348111-b94d5f8fa9f2.json'
gc = pygsheets.authorize(service_file=key)
# do prior running the script:

odinokov

import modin.pandas as pd
from modin.config import Engine
# Engine.put("ray")  # Modin will use Ray
Engine.put("dask")  # Modin will use Dask

odinokov

%%writefile bed2bins.py

# instead of https://bedtools.readthedocs.io/en/latest/content/tools/makewindows.html
# cat file_name.bam | bedtools makewindows -b - -n 5 -i winnum
#
# How to use:
# cat file_name.bam | python3 bed2bins.py 5
#
# expects to stdin from bam file with 6 fields, i.e.,
#

odinokov

# load tsv with float values of various length as numpy array

import numpy as np
from itertools import zip_longest

file_name = # specify 

with open(file_name) as file:
    lines = [np.asarray(line.rstrip().split('\t')).astype(np.float16) for line in file]