simplestatistics

simple-statistics for Python.

simplestatistics is compatible with Python 3.

Version 0.4.0 was the last version to not use Python 3 specific features. Going forward, simplestatistics will adopt Python 3 features (e.g., type hints).

Installation

Install the current PyPI release:

pip install simplestatistics

Or install the development version from GitHub:

pip install git+https://github.com/sheriferson/simplestatistics

Usage

>>> import simplestatistics as ss
>>> ss.mean([1, 2, 3])
2.0
>>> ss.t_test([1, 2, 2.4, 3, 0.9], 2)
-0.3461277235039039

Documentation

You can read the documentation online.

Or you can generate it yourself:

Inside simplestatistics/.

make html

Documentation will be generated in _build/html/.

Tests

To run all doctests and see test coverage:

pip install -r requirements.txt
pytest simplestatistics --doctest-modules --cov=simplestatistics

The code adheres to PEP8 guidelines except for the following checkers:

• invalid-name
• len-as-condition
• superfluous-parens
• unidiomatic-typecheck

To lint the code, make sure you have [pylint] installed (pip install pylint), cd into the simplestatistics/statistics directory, then run:

pylint -d 'invalid-name, len-as-condition, superfluous-parens, unidiomatic-typecheck' *.py

Functions and examples

Descriptive statistics

Function	Example
Min	min([-3, 0, 3])
Max	max([1, 2, 3])
Sum	sum([1, 2, 3.5])
Quantiles	quantile([3, 6, 7, 8, 8, 9, 10, 13, 15, 16, 20], [0.25, 0.75])
Product	product([1.25, 2.75], [2.5, 3.40])

Measures of central tendency

Function	Example
Mean	mean([1, 2, 3])
Median	median([10, 2, -5, -1])
Mode	mode([2, 1, 3, 2, 1])
Geometric mean	geometric_mean([1, 10])
Harmonic mean	harmonic_mean([1, 2, 4])
Root mean square	root_mean_square([1, -1, 1, -1])
Add to mean	add_to_mean(40, 4, (10, 12))
Skewness	skew([1, 2, 5])
Kurtosis	kurtosis([1, 2, 3, 4, 5])

Measures of dispersion

Function	Example
Sample and population variance	variance([1, 2, 3], sample = True)
Sample and population Standard deviation	standard_deviation([1, 2, 3], sample = True)
Sample and population Coefficient of variation	coefficient_of_variation([1, 2, 3], sample = True)
Interquartile range	interquartile_range([1, 3, 5, 7])
Sum of Nth power deviations	sum_nth_power_deviations([-1, 0, 2, 4], 3)
Sample and population Standard scores (z-scores)	z_scores([-2, -1, 0, 1, 2], sample = True)

Linear regression

Function	Example
Simple linear regression	linear_regression([1, 2, 3, 4, 5], [4, 4.5, 5.5, 5.3, 6])
Linear regression line function generator	linear_regression_line([.5, 9.5])([1, 2, 3])

Similarity

Function	Example
Correlation	correlate([2, 1, 0, -1, -2, -3, -4, -5], [0, 1, 1, 2, 3, 2, 4, 5])
Covariance	covariance([1,2,3,4,5,6], [6,5,4,3,2,1])

Distributions

Function	Example
Factorial	factorial(20) or factorial([1, 5, 20])
Choose	choose(5, 3)
Normal distribution	normal(4, 8, 2) or normal([1, 4], 8, 2)
Binomial distribution	binomial(4, 12, 0.2) or binomial([3,4,5], 12, 0.5)
Bernoulli distribution	bernoulli(0.25)
Poisson distribution	poisson(3, [0, 1, 2, 3])
Gamma function	gamma_function([1, 2, 3, 4, 5])
Beta distribution	beta([.1, .2, .3], 5, 2)
One-sample t-test	t_test([1, 2, 3, 4, 5, 6], 3.385)
Chi Squared Distribution Table	chi_squared_dist_table(k = 10, p = .01)

Classifiers

Function	Example
Naive Bayesian classifier	See documentation for examples of how to train and classify.
Perceptron	See documentation for examples of how to train and classify.

Errors

Function	Example
Gauss error function	error_function(1)

Hyperbolic functions

Function	Example
sinh	sinh(2)
cosh	cosh(2.5)
tanh	tanh(.2)

Spirit and rules

• Everything should be implemented in raw, organic, locally sourced Python.
• Use libraries only if you have to and only when unrelated to the math/statistics. For example, from functools import reduce to make reduce available for those using python3. That's okay, because it's about making Python work and not about making the stats easier.
• It's okay to use operators and functions if they correspond to regular calculator buttons. For example, all calculators have a built-in square root function, so there is no need to implement that ourselves, we can use math.sqrt(). Anything beyond that, like mean, median, we have to write ourselves.

Pull requests are welcome!

Contributors

• Jim Anderson (jhowardanderson)
• Lidiane Taquehara (lidimayra)
• Pierre-Selim (PierreSelim)
• Tom MacWright (tmcw)