Confidence Intervals for Descriptive Collections

certainty.py

import math
from scipy.stats import t
import numpy as np

def confidence_interval_for_collection(sample_size=[], standard_deviation=[], mean=[], confidence=0.95):
  degrees_freedom = [count - 1 for count in sample_size]
  outlier_tails = (1.0 - confidence) / 2.0
  confidence_collection = [outlier_tails for _ in sample_size]
  t_distribution_number = [-1 * t.ppf(tails, df) for tails, df in zip(confidence_collection, degrees_freedom)]

  step_1 = [std/math.sqrt(count) for std, count in zip(standard_deviation, sample_size)]
  step_2 = [step * t for step, t in zip(step_1, t_distribution_number)]

  low_end = [mean_num - step_num for mean_num, step_num in zip(mean, step_2)]
  high_end = [mean_num + step_num for mean_num, step_num in zip(mean, step_2)]

  return low_end, high_end