dmyersturnbull

import numpy as np
def sliding_window(x: np.ndarray, n: int) -> np.ndarray:
    """Returns a sliding window of n elements from x.
    Raises a ValueError of n > len(x).
    """
    if n > len(x): raise ValueError("N must be less than the array length")
    # Courtesy of https://stackoverflow.com/questions/13728392/moving-average-or-running-mean
    return np.convolve(x, np.ones((n,)) / n, mode='valid')

dmyersturnbull

from IPython.display import display, Markdown
import pandas as pd

def head(df: pd.DataFrame, n_rows:int=1) -> None:
    """Pretty-print the head of a Pandas table in a Jupyter notebook and show its dimensions."""
    display(Markdown("**whole table (below):** {} rows × {} columns".format(len(df), len(df.columns))))
    display(df.head(n_rows))

dmyersturnbull

from typing import Callable, Generic, TypeVar, Iterable
T = TypeVar('T')

def exists(keep_predicate: Callable[[T], bool], seq: Iterable[T]) -> bool:
    """Efficient existential quantifier for a filter() predicate.
    Returns true iff keep_predicate is true for one or more elements."""
    for e in seq:
        if keep_predicate(e): return True  # short-circuit
    return False

dmyersturnbull

import os
from typing import Iterator

def is_proper_file(path: str) -> bool:
    name = os.path.split(path)[1]
    return len(name) > 0 and name[0] not in {'.', '~', '_'}

def scantree(path: str, follow_symlinks: bool=False) -> Iterator[str]:
    """List the full path of every file not beginning with '.', '~', or '_' in a directory, recursively."""
    for entry in os.scandir(path):

dmyersturnbull

import gzip, io
from typing import Iterator

def lines(file_name: str, known_encoding='utf-8') -> Iterator[str]:
    """Lazily read a text file or gzipped text file, decode, and strip any newline character (\n or \r).
    If the file name ends with '.gz' or '.gzip', assumes the file is Gzipped.
    Arguments:
        known_encoding: Applied only when decoding gzip
    """
    if file_name.endswith('.gz') or file_name.endswith('.gzip'):

dmyersturnbull

def zip_strict(*args):
    """Same as zip(), but raises a ValueError if the lengths don't match."""
    iters = [iter(axis) for axis in args]
    n_elements = 0
    failures = []
    while len(failures) == 0:
        n_elements += 1
        values = []
        failures = []

dmyersturnbull

import datetime

def format_time(time: datetime.datetime) -> str:
    """Standard timestamp format. Ex: 2016-05-02_22_35_56."""
    return time.strftime("%Y-%m-%d_%H-%M-%S")

def timestamp() -> str:
    """Standard timestamp of time now. Ex: 2016-05-02_22_35_56."""
    return format_time(datetime.datetime.now())

dmyersturnbull

import contextlib
import sys
from io import StringIO

@contextlib.contextmanager
def silenced(no_stdout=True, no_stderr=True):
    """
    Suppresses output to stdout and/or stderr.
    Always resets stdout and stderr, even on an exception.
    Usage:

dmyersturnbull

                                 Apache License
                           Version 2.0, January 2004
                        http://www.apache.org/licenses/

   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION

   1. Definitions.

      "License" shall mean the terms and conditions for use, reproduction,
      and distribution as defined by Sections 1 through 9 of this document.

dmyersturnbull

# Douglas Myers-Turnbull wrote this for the Kokel Lab, which has released it under the Apache Software License, Version 2.0
# See the license file here: https://gist.github.com/dmyersturnbull/bfa1c3371e7449db553aaa1e7cd3cac1
# The list of copyright owners is unknown

import re
import warnings
import time

from chemspipy import ChemSpider