toby-p

import pandas as pd
from sklearn.preprocessing import PolynomialFeatures


def apply_polynomials(df: pd.DataFrame, degree: int = 2,
                      interaction_only: bool = False,
                      include_bias: bool = False):
    """Apply scikit-learn's PolynomialFeatures class to a pandas DataFrame,
    keeping the original column labels and index, and extending the columns to
    include all new polynomial features. Generally speaking creates a lot of new

toby-p

def input_iterable_paginated(msg: str, iterable: object, page_length: int = 5,
                             more: str = "m"):
    """List numbered items from any iterable to be chosen by user input."""
    def get_input(valid: list):
        value = input().strip().lower()
        try:
            value = int(value)
            if value - 1 in range(len(valid)):
                return valid[value - 1]
            else:

toby-p

# Class:
class PrintCheck:
    """Decorator to print a custom message when calling a function, followed by
    a check/tick mark on the same line when the computation finishes. If the
    function returns an integer it will be printed in parentheses with the check
    mark along with the `item_name` argument, pluralized if greater than 1."""

    def __init__(self, msg: str = None, print_items: bool = True,
                 item_name: str = "item"):
        """

toby-p

import datetime
import pandas as pd
import pytz
import time

# To switch logging on/off add config logic here to determine this variable:
LOG_PERFORMANCE = True

TIMEZONE = "US/Eastern"

toby-p

import traceback
import warnings
import sys


def warn_with_traceback(message, category, filename, lineno, file=None, line=None):

    log = file if hasattr(file,'write') else sys.stderr
    traceback.print_stack(file=log)
    log.write(warnings.formatwarning(message, category, filename, lineno, line))

toby-p

def str_search(*substrings: str, iterable, exact_match: bool = False) -> list:
    """Case-insensitive search of an iterable for substrings.

    Args:
        substrings (str): strings to search for in the iterable.
        iterable (list, tuple, etc): iterable containing string objects to be
            searched.
        exact_match (bool): if True only return a single value that exactly
            matches the substring supplied (therefore only works if 1 substring
            arg is supplied). Otherwise returns list of all partial matches.

toby-p

import os, psutil

# Tool for tracking memory usage:
def usage():
    process = psutil.Process(os.getpid())
    print(process.memory_info()[0] / float(2 ** 20))

toby-p

import math 

def magnitude(x):
    """Get the order 10 magnitude of a float."""
    return int(math.log10(x))

def mpl_y_scale(datamin, datamax, desired_n_steps=5, minmax_buffer=True):
    """Determine nicely spaced, nearest-decimal-rounded y-ticks, and y-axis
    limits (with optional buffer) which centrally locate a line plot in a
    Matplotlib figure axis.

toby-p

# Global variable to determine whether or not to raise errors.
SUPPRESS_ERRORS = True 

def suppress_errors(func):
  """Decorator function to suppress errors."""
    if not SUPPRESS_ERRORS:
        return func
    def suppressed(*args, **kwargs):
        try:
            return func(*args, **kwargs)

toby-p

from datetime import datetime
import pytz

def debug_print(msg, timezone="US/Eastern"):
    """Print a time-stamped debug message."""
    UTC_now = pytz.utc.localize(datetime.utcnow())
    now = UTC_now.astimezone(pytz.timezone(timezone))
    now_date = now.strftime("%Y_%m_%d")
    now_time = now.strftime("%H:%M:%S")
    print("[{} @ {}] : {}".format(now_date, now_time, msg))