Your IP : 18.119.166.141


Current Path : /opt/alt/python310/lib64/python3.10/__pycache__/
Upload File :
Current File : //opt/alt/python310/lib64/python3.10/__pycache__/statistics.cpython-310.opt-1.pyc

o

6��fŨ�@s�dZgd�ZddlZddlZddlZddlmZddlmZddl	m
Z
mZddlm
Z
mZddlmZmZmZmZmZmZmZmZdd	lmZdd
lmZmZGdd�de�Zd
d�Zdd�Zdd�Z dd�Z!dd�Z"dd�Z#dd�Z$dOdd�Z%dd�Z&d d!�Z'd"d#�Z(dPd$d%�Z)d&d'�Z*d(d)�Z+d*d+�Z,dQd-d.�Z-d/d0�Z.d1d2�Z/d3d4d5�d6d7�Z0dPd8d9�Z1dPd:d;�Z2dPd<d=�Z3dPd>d?�Z4dPd@dA�Z5dBdC�Z6dDdE�Z7edFdG�Z8dHdI�Z9dJdK�Z:zddLl;m:Z:Wn	e<y�YnwGdMdN�dN�Z=dS)Ra�

Basic statistics module.

This module provides functions for calculating statistics of data, including
averages, variance, and standard deviation.

Calculating averages
--------------------

==================  ==================================================
Function            Description
==================  ==================================================
mean                Arithmetic mean (average) of data.
fmean               Fast, floating point arithmetic mean.
geometric_mean      Geometric mean of data.
harmonic_mean       Harmonic mean of data.
median              Median (middle value) of data.
median_low          Low median of data.
median_high         High median of data.
median_grouped      Median, or 50th percentile, of grouped data.
mode                Mode (most common value) of data.
multimode           List of modes (most common values of data).
quantiles           Divide data into intervals with equal probability.
==================  ==================================================

Calculate the arithmetic mean ("the average") of data:

>>> mean([-1.0, 2.5, 3.25, 5.75])
2.625


Calculate the standard median of discrete data:

>>> median([2, 3, 4, 5])
3.5


Calculate the median, or 50th percentile, of data grouped into class intervals
centred on the data values provided. E.g. if your data points are rounded to
the nearest whole number:

>>> median_grouped([2, 2, 3, 3, 3, 4])  #doctest: +ELLIPSIS
2.8333333333...

This should be interpreted in this way: you have two data points in the class
interval 1.5-2.5, three data points in the class interval 2.5-3.5, and one in
the class interval 3.5-4.5. The median of these data points is 2.8333...


Calculating variability or spread
---------------------------------

==================  =============================================
Function            Description
==================  =============================================
pvariance           Population variance of data.
variance            Sample variance of data.
pstdev              Population standard deviation of data.
stdev               Sample standard deviation of data.
==================  =============================================

Calculate the standard deviation of sample data:

>>> stdev([2.5, 3.25, 5.5, 11.25, 11.75])  #doctest: +ELLIPSIS
4.38961843444...

If you have previously calculated the mean, you can pass it as the optional
second argument to the four "spread" functions to avoid recalculating it:

>>> data = [1, 2, 2, 4, 4, 4, 5, 6]
>>> mu = mean(data)
>>> pvariance(data, mu)
2.5


Statistics for relations between two inputs
-------------------------------------------

==================  ====================================================
Function            Description
==================  ====================================================
covariance          Sample covariance for two variables.
correlation         Pearson's correlation coefficient for two variables.
linear_regression   Intercept and slope for simple linear regression.
==================  ====================================================

Calculate covariance, Pearson's correlation, and simple linear regression
for two inputs:

>>> x = [1, 2, 3, 4, 5, 6, 7, 8, 9]
>>> y = [1, 2, 3, 1, 2, 3, 1, 2, 3]
>>> covariance(x, y)
0.75
>>> correlation(x, y)  #doctest: +ELLIPSIS
0.31622776601...
>>> linear_regression(x, y)  #doctest:
LinearRegression(slope=0.1, intercept=1.5)


Exceptions
----------

A single exception is defined: StatisticsError is a subclass of ValueError.

)�
NormalDist�StatisticsError�correlation�
covariance�fmean�geometric_mean�
harmonic_mean�linear_regression�mean�median�median_grouped�median_high�
median_low�mode�	multimode�pstdev�	pvariance�	quantiles�stdev�variance�N��Fraction)�Decimal)�groupby�repeat)�bisect_left�bisect_right)�hypot�sqrt�fabs�exp�erf�tau�log�fsum)�
itemgetter)�Counter�
namedtuplec@seZdZdS)rN)�__name__�
__module__�__qualname__�r+r+�1/opt/alt/python310/lib64/python3.10/statistics.pyr�src
Cs�d}i}|j}t}t|t�D] \}}t||�}tt|�D]\}}|d7}||d�|||<qqd|vr8|d}	ntdd�|��D��}	||	|fS)a�_sum(data) -> (type, sum, count)

    Return a high-precision sum of the given numeric data as a fraction,
    together with the type to be converted to and the count of items.

    Examples
    --------

    >>> _sum([3, 2.25, 4.5, -0.5, 0.25])
    (<class 'float'>, Fraction(19, 2), 5)

    Some sources of round-off error will be avoided:

    # Built-in sum returns zero.
    >>> _sum([1e50, 1, -1e50] * 1000)
    (<class 'float'>, Fraction(1000, 1), 3000)

    Fractions and Decimals are also supported:

    >>> from fractions import Fraction as F
    >>> _sum([F(2, 3), F(7, 5), F(1, 4), F(5, 6)])
    (<class 'fractions.Fraction'>, Fraction(63, 20), 4)

    >>> from decimal import Decimal as D
    >>> data = [D("0.1375"), D("0.2108"), D("0.3061"), D("0.0419")]
    >>> _sum(data)
    (<class 'decimal.Decimal'>, Fraction(6963, 10000), 4)

    Mixed types are currently treated as an error, except that int is
    allowed.
    r�Ncs��|]
\}}t||�VqdS�Nr��.0�d�nr+r+r,�	<genexpr>���z_sum.<locals>.<genexpr>)	�get�intr�type�_coerce�map�_exact_ratio�sum�items)
�data�count�partialsZpartials_get�T�typ�valuesr3r2�totalr+r+r,�_sum�s 
�

rEcCs(z|��WStyt�|�YSwr/)Z	is_finite�AttributeError�mathZisfinite)�xr+r+r,�	_isfinite�s

�rIcCs�||ur|S|tus|tur|S|tur|St||�r|St||�r$|St|t�r+|St|t�r2|St|t�r>t|t�r>|St|t�rJt|t�rJ|Sd}t||j|jf��)z�Coerce types T and S to a common type, or raise TypeError.

    Coercion rules are currently an implementation detail. See the CoerceTest
    test class in test_statistics for details.
    z"don't know how to coerce %s and %s)r7�bool�
issubclassr�float�	TypeErrorr()rA�S�msgr+r+r,r9�sr9c	Csrz|��WStyYnttfy|dfYSwz|j|jfWSty8dt|�j�d�}t|��w)z�Return Real number x to exact (numerator, denominator) pair.

    >>> _exact_ratio(0.25)
    (1, 4)

    x is expected to be an int, Fraction, Decimal or float.
    Nzcan't convert type 'z' to numerator/denominator)	�as_integer_ratiorF�
OverflowError�
ValueError�	numerator�denominatorr8r(rM)rHrOr+r+r,r;�s
��r;cCsft|�|ur|St|t�r|jdkrt}z||�WSty2t|t�r1||j�||j�YS�w)z&Convert value to given numeric type T.r-)r8rKr7rTrLrMrrS)�valuerAr+r+r,�_converts

�rVcCs*t||�}|t|�kr|||kr|St�)z,Locate the leftmost value exactly equal to x)r�lenrR)�arH�ir+r+r,�
_find_lteqs
rZcCs:t|||d�}|t|�dkr||d|kr|dSt�)z-Locate the rightmost value exactly equal to x)�lor-)rrWrR)rX�lrHrYr+r+r,�
_find_rteq"s r]�negative valueccs&�|D]
}|dkr
t|��|VqdS)z7Iterate over values, failing if any are less than zero.rN)r)rC�errmsgrHr+r+r,�	_fail_neg*s��r`cCsHt|�|ur
t|�}t|�}|dkrtd��t|�\}}}t|||�S)a�Return the sample arithmetic mean of data.

    >>> mean([1, 2, 3, 4, 4])
    2.8

    >>> from fractions import Fraction as F
    >>> mean([F(3, 7), F(1, 21), F(5, 3), F(1, 3)])
    Fraction(13, 21)

    >>> from decimal import Decimal as D
    >>> mean([D("0.5"), D("0.75"), D("0.625"), D("0.375")])
    Decimal('0.5625')

    If ``data`` is empty, StatisticsError will be raised.
    r-z%mean requires at least one data point)�iter�listrWrrErV)r>r3rArDr?r+r+r,r	4sr	cshzt|��Wntyd��fdd�}t||��}Ynwt|�}z|�WSty3td�d�w)z�Convert data to floats and compute the arithmetic mean.

    This runs faster than the mean() function and it always returns a float.
    If the input dataset is empty, it raises a StatisticsError.

    >>> fmean([3.5, 4.0, 5.25])
    4.25
    rc3s"�t|dd�D]\�}|VqdS)Nr-)�start)�	enumerate)�iterablerH�r3r+r,r?\s��zfmean.<locals>.countz&fmean requires at least one data pointN)rWrMr$�ZeroDivisionErrorr)r>r?rDr+rfr,rNs	�	

�rcCs.z
tttt|���WStytd�d�w)aYConvert data to floats and compute the geometric mean.

    Raises a StatisticsError if the input dataset is empty,
    if it contains a zero, or if it contains a negative value.

    No special efforts are made to achieve exact results.
    (However, this may change in the future.)

    >>> round(geometric_mean([54, 24, 36]), 9)
    36.0
    zGgeometric mean requires a non-empty dataset containing positive numbersN)r rr:r#rRr)r>r+r+r,ris��rc
Cs2t|�|ur
t|�}d}t|�}|dkrtd��|dkr:|dur:|d}t|tjtf�r6|dkr4t|��|Std��|durFt	d|�}|}n#t|�|urPt|�}t|�|krZtd��t
dd	�t||�D��\}}}zt||�}t
d
d	�t||�D��\}}}	Wn
t
y�YdSw|dkr�td��t|||�S)a�Return the harmonic mean of data.

    The harmonic mean is the reciprocal of the arithmetic mean of the
    reciprocals of the data.  It can be used for averaging ratios or
    rates, for example speeds.

    Suppose a car travels 40 km/hr for 5 km and then speeds-up to
    60 km/hr for another 5 km. What is the average speed?

        >>> harmonic_mean([40, 60])
        48.0

    Suppose a car travels 40 km/hr for 5 km, and when traffic clears,
    speeds-up to 60 km/hr for the remaining 30 km of the journey. What
    is the average speed?

        >>> harmonic_mean([40, 60], weights=[5, 30])
        56.0

    If ``data`` is empty, or any element is less than zero,
    ``harmonic_mean`` will raise ``StatisticsError``.
    z.harmonic mean does not support negative valuesr-z.harmonic_mean requires at least one data pointNrzunsupported typez*Number of weights does not match data sizecss�|]}|VqdSr/r+)r1�wr+r+r,r4�s�z harmonic_mean.<locals>.<genexpr>css$�|]
\}}|r||ndVqdS)rNr+)r1rhrHr+r+r,r4���"zWeighted sum must be positive)rarbrWr�
isinstance�numbersZRealrrMrrEr`�ziprgrV)
r>Zweightsr_r3rHZsum_weights�_rArDr?r+r+r,r|s<

"�rcCsXt|�}t|�}|dkrtd��|ddkr||dS|d}||d||dS)aBReturn the median (middle value) of numeric data.

    When the number of data points is odd, return the middle data point.
    When the number of data points is even, the median is interpolated by
    taking the average of the two middle values:

    >>> median([1, 3, 5])
    3
    >>> median([1, 3, 5, 7])
    4.0

    r�no median for empty data�r-��sortedrWr)r>r3rYr+r+r,r
�s
r
cCsHt|�}t|�}|dkrtd��|ddkr||dS||ddS)a	Return the low median of numeric data.

    When the number of data points is odd, the middle value is returned.
    When it is even, the smaller of the two middle values is returned.

    >>> median_low([1, 3, 5])
    3
    >>> median_low([1, 3, 5, 7])
    3

    rrnror-rp�r>r3r+r+r,r
�sr
cCs,t|�}t|�}|dkrtd��||dS)aReturn the high median of data.

    When the number of data points is odd, the middle value is returned.
    When it is even, the larger of the two middle values is returned.

    >>> median_high([1, 3, 5])
    3
    >>> median_high([1, 3, 5, 7])
    5

    rrnrorprrr+r+r,r�s
rr-c
Cs�t|�}t|�}|dkrtd��|dkr|dS||d}||fD]}t|ttf�r1td|��q"z||d}WntyMt|�t|�d}Ynwt||�}t	|||�}|}||d}	|||d||	S)a�Return the 50th percentile (median) of grouped continuous data.

    >>> median_grouped([1, 2, 2, 3, 4, 4, 4, 4, 4, 5])
    3.7
    >>> median_grouped([52, 52, 53, 54])
    52.5

    This calculates the median as the 50th percentile, and should be
    used when your data is continuous and grouped. In the above example,
    the values 1, 2, 3, etc. actually represent the midpoint of classes
    0.5-1.5, 1.5-2.5, 2.5-3.5, etc. The middle value falls somewhere in
    class 3.5-4.5, and interpolation is used to estimate it.

    Optional argument ``interval`` represents the class interval, and
    defaults to 1. Changing the class interval naturally will change the
    interpolated 50th percentile value:

    >>> median_grouped([1, 3, 3, 5, 7], interval=1)
    3.25
    >>> median_grouped([1, 3, 3, 5, 7], interval=2)
    3.5

    This function does not check whether the data points are at least
    ``interval`` apart.
    rrnr-rozexpected number but got %r)
rqrWrrj�str�bytesrMrLrZr])
r>Zintervalr3rH�obj�L�l1�l2Zcf�fr+r+r,r�s*��
rcCs:tt|���d�}z|ddWStytd�d�w)axReturn the most common data point from discrete or nominal data.

    ``mode`` assumes discrete data, and returns a single value. This is the
    standard treatment of the mode as commonly taught in schools:

        >>> mode([1, 1, 2, 3, 3, 3, 3, 4])
        3

    This also works with nominal (non-numeric) data:

        >>> mode(["red", "blue", "blue", "red", "green", "red", "red"])
        'red'

    If there are multiple modes with same frequency, return the first one
    encountered:

        >>> mode(['red', 'red', 'green', 'blue', 'blue'])
        'red'

    If *data* is empty, ``mode``, raises StatisticsError.

    r-rzno mode for empty dataN)r&ra�most_common�
IndexErrorr)r>Zpairsr+r+r,r,s
�rcCs@tt|����}tt|td�d�dgf�\}}tttd�|��S)a.Return a list of the most frequently occurring values.

    Will return more than one result if there are multiple modes
    or an empty list if *data* is empty.

    >>> multimode('aabbbbbbbbcc')
    ['b']
    >>> multimode('aabbbbccddddeeffffgg')
    ['b', 'd', 'f']
    >>> multimode('')
    []
    r-)�keyr)r&rarz�nextrr%rbr:)r>ZcountsZmaxcountZ
mode_itemsr+r+r,rJs
r��	exclusive)r3�methodc
Cs<|dkrtd��t|�}t|�}|dkrtd��|dkrL|d}g}td|�D]"}t|||�\}}||||||d||}	|�|	�q'|S|dkr�|d}g}td|�D]9}|||}|dkridn||dkrs|dn|}||||}||d||||||}	|�|	�q[|Std|����)a�Divide *data* into *n* continuous intervals with equal probability.

    Returns a list of (n - 1) cut points separating the intervals.

    Set *n* to 4 for quartiles (the default).  Set *n* to 10 for deciles.
    Set *n* to 100 for percentiles which gives the 99 cuts points that
    separate *data* in to 100 equal sized groups.

    The *data* can be any iterable containing sample.
    The cut points are linearly interpolated between data points.

    If *method* is set to *inclusive*, *data* is treated as population
    data.  The minimum value is treated as the 0th percentile and the
    maximum value is treated as the 100th percentile.
    r-zn must be at least 1roz"must have at least two data pointsZ	inclusiverzUnknown method: )rrqrW�range�divmod�appendrR)
r>r3r�Zld�m�resultrY�jZdeltaZinterpolatedr+r+r,r�s2$$$rcs��durt�fdd�|D��\}}}||fSt|�\}}}||��\}}t�}tt|�D]\}}	|||	|}
|	|}||||
|
7<q-d|vrV|d}||fStdd�|��D��}||fS)a;Return sum of square deviations of sequence data.

    If ``c`` is None, the mean is calculated in one pass, and the deviations
    from the mean are calculated in a second pass. Otherwise, deviations are
    calculated from ``c`` as given. Use the second case with care, as it can
    lead to garbage results.
    Nc3��|]	}|�dVqdS)roNr+)r1rH��cr+r,r4���z_ss.<locals>.<genexpr>csr.r/rr0r+r+r,r4�r5)rErPr&r:r;r<r=)r>r�rArDr?Zmean_nZmean_dr@r3r2Zdiff_nZdiff_dr+r�r,�_ss�s�r�cCsLt|�|ur
t|�}t|�}|dkrtd��t||�\}}t||d|�S)a�Return the sample variance of data.

    data should be an iterable of Real-valued numbers, with at least two
    values. The optional argument xbar, if given, should be the mean of
    the data. If it is missing or None, the mean is automatically calculated.

    Use this function when your data is a sample from a population. To
    calculate the variance from the entire population, see ``pvariance``.

    Examples:

    >>> data = [2.75, 1.75, 1.25, 0.25, 0.5, 1.25, 3.5]
    >>> variance(data)
    1.3720238095238095

    If you have already calculated the mean of your data, you can pass it as
    the optional second argument ``xbar`` to avoid recalculating it:

    >>> m = mean(data)
    >>> variance(data, m)
    1.3720238095238095

    This function does not check that ``xbar`` is actually the mean of
    ``data``. Giving arbitrary values for ``xbar`` may lead to invalid or
    impossible results.

    Decimals and Fractions are supported:

    >>> from decimal import Decimal as D
    >>> variance([D("27.5"), D("30.25"), D("30.25"), D("34.5"), D("41.75")])
    Decimal('31.01875')

    >>> from fractions import Fraction as F
    >>> variance([F(1, 6), F(1, 2), F(5, 3)])
    Fraction(67, 108)

    roz*variance requires at least two data pointsr-�rarbrWrr�rV)r>�xbarr3rA�ssr+r+r,r�s&rcCsHt|�|ur
t|�}t|�}|dkrtd��t||�\}}t|||�S)a,Return the population variance of ``data``.

    data should be a sequence or iterable of Real-valued numbers, with at least one
    value. The optional argument mu, if given, should be the mean of
    the data. If it is missing or None, the mean is automatically calculated.

    Use this function to calculate the variance from the entire population.
    To estimate the variance from a sample, the ``variance`` function is
    usually a better choice.

    Examples:

    >>> data = [0.0, 0.25, 0.25, 1.25, 1.5, 1.75, 2.75, 3.25]
    >>> pvariance(data)
    1.25

    If you have already calculated the mean of the data, you can pass it as
    the optional second argument to avoid recalculating it:

    >>> mu = mean(data)
    >>> pvariance(data, mu)
    1.25

    Decimals and Fractions are supported:

    >>> from decimal import Decimal as D
    >>> pvariance([D("27.5"), D("30.25"), D("30.25"), D("34.5"), D("41.75")])
    Decimal('24.815')

    >>> from fractions import Fraction as F
    >>> pvariance([F(1, 4), F(5, 4), F(1, 2)])
    Fraction(13, 72)

    r-z*pvariance requires at least one data pointr�)r>�mur3rAr�r+r+r,rs#rcC�2t||�}z|��WStyt�|�YSw)z�Return the square root of the sample variance.

    See ``variance`` for arguments and other details.

    >>> stdev([1.5, 2.5, 2.5, 2.75, 3.25, 4.75])
    1.0810874155219827

    )rrrFrG)r>r��varr+r+r,r0�

�rcCr�)z�Return the square root of the population variance.

    See ``pvariance`` for arguments and other details.

    >>> pstdev([1.5, 2.5, 2.5, 2.75, 3.25, 4.75])
    0.986893273527251

    )rrrFrG)r>r�r�r+r+r,rCr�rcsnt|�}t|�|krtd��|dkrtd��t|�|�t|�|�t��fdd�t||�D��}||dS)apCovariance

    Return the sample covariance of two inputs *x* and *y*. Covariance
    is a measure of the joint variability of two inputs.

    >>> x = [1, 2, 3, 4, 5, 6, 7, 8, 9]
    >>> y = [1, 2, 3, 1, 2, 3, 1, 2, 3]
    >>> covariance(x, y)
    0.75
    >>> z = [9, 8, 7, 6, 5, 4, 3, 2, 1]
    >>> covariance(x, z)
    -7.5
    >>> covariance(z, x)
    -7.5

    zDcovariance requires that both inputs have same number of data pointsroz,covariance requires at least two data pointsc3�$�|]
\}}|�|�VqdSr/r+�r1�xi�yi�r��ybarr+r,r4urizcovariance.<locals>.<genexpr>r-)rWrr$rl)rH�yr3�sxyr+r�r,r]srcs�t|�}t|�|krtd��|dkrtd��t|�|�t|�|�t��fdd�t||�D��}t�fdd�|D��}t�fdd�|D��}z	|t||�WSty[td��w)	aPearson's correlation coefficient

    Return the Pearson's correlation coefficient for two inputs. Pearson's
    correlation coefficient *r* takes values between -1 and +1. It measures the
    strength and direction of the linear relationship, where +1 means very
    strong, positive linear relationship, -1 very strong, negative linear
    relationship, and 0 no linear relationship.

    >>> x = [1, 2, 3, 4, 5, 6, 7, 8, 9]
    >>> y = [9, 8, 7, 6, 5, 4, 3, 2, 1]
    >>> correlation(x, x)
    1.0
    >>> correlation(x, y)
    -1.0

    zEcorrelation requires that both inputs have same number of data pointsroz-correlation requires at least two data pointsc3r�r/r+r�r�r+r,r4�rizcorrelation.<locals>.<genexpr>c3r���@Nr+�r1r��r�r+r,r4�r�c3r�r�r+)r1r�)r�r+r,r4�r�z&at least one of the inputs is constant)rWrr$rlrrg)rHr�r3r��sxxZsyyr+r�r,rys�r�LinearRegression��slope�	interceptcs�t|�}t|�|krtd��|dkrtd��t|�|�t|�|�t��fdd�t||�D��}t�fdd�|D��}z||}WntyMtd��w�|�}t||d�S)	a�Slope and intercept for simple linear regression.

    Return the slope and intercept of simple linear regression
    parameters estimated using ordinary least squares. Simple linear
    regression describes relationship between an independent variable
    *x* and a dependent variable *y* in terms of linear function:

        y = slope * x + intercept + noise

    where *slope* and *intercept* are the regression parameters that are
    estimated, and noise represents the variability of the data that was
    not explained by the linear regression (it is equal to the
    difference between predicted and actual values of the dependent
    variable).

    The parameters are returned as a named tuple.

    >>> x = [1, 2, 3, 4, 5]
    >>> noise = NormalDist().samples(5, seed=42)
    >>> y = [3 * x[i] + 2 + noise[i] for i in range(5)]
    >>> linear_regression(x, y)  #doctest: +ELLIPSIS
    LinearRegression(slope=3.09078914170..., intercept=1.75684970486...)

    zKlinear regression requires that both inputs have same number of data pointsroz3linear regression requires at least two data pointsc3r�r/r+r�r�r+r,r4�riz$linear_regression.<locals>.<genexpr>c3r�r�r+r�r�r+r,r4�r�z
x is constantr�)rWrr$rlrgr�)rHr�r3r�r�r�r�r+r�r,r�s �rcCs�|d}t|�dkrXd||}d|d|d|d|d|d	|d
|d|}d|d
|d|d|d|d|d|d}||}|||S|dkr^|nd|}tt|��}|dkr�|d}d|d|d|d|d|d|d|d}d|d |d!|d"|d#|d$|d%|d}n@|d}d&|d'|d(|d)|d*|d+|d,|d-}d.|d/|d0|d1|d2|d3|d4|d}||}|dkr�|}|||S)5N��?g333333�?g��Q��?g^�}o)��@g�E.k�R�@g ��Ul�@g*u��>l�@g�N����@g�"]Ξ@gnC���`@gu��@giK��~j�@gv��|E�@g��d�|1�@gfR��r��@g��u.2�@g���~y�@g�n8(E@��?�g@g�������?g鬷�ZaI?gg�El�D�?g7\�����?g�uS�S�?g�=�.
@gj%b�@g���Hw�@gjR�e�?g�9dh?
>g('߿��A?g��~z �?g@�3��?gɅ3��?g3fR�x�?gI�F��l@g����t��>g*�Y��n�>gESB\T?g�N;A+�?g�UR1��?gE�F���?gP�n��@g&�>���@g����i�<g�@�F�>g�tcI,\�>g�ŝ���I?g*F2�v�?g�C4�?g��O�1�?)rrr#)�pr��sigma�q�rZnumZdenrHr+r+r,�_normal_dist_inv_cdf�sd�����������������������������������������������������	��������������������������r�)r�c@seZdZdZddd�Zd>dd�Zed	d
��Zdd�d
d�Zdd�Z	dd�Z
dd�Zd?dd�Zdd�Z
dd�Zedd��Zedd��Zed d!��Zed"d#��Zed$d%��Zd&d'�Zd(d)�Zd*d+�Zd,d-�Zd.d/�Zd0d1�ZeZd2d3�ZeZd4d5�Zd6d7�Zd8d9�Z d:d;�Z!d<d=�Z"dS)@rz(Normal distribution of a random variablez(Arithmetic mean of a normal distributionz+Standard deviation of a normal distribution��_mu�_sigmar�r�cCs(|dkrtd��t|�|_t|�|_dS)zDNormalDist where mu is the mean and sigma is the standard deviation.r�zsigma must be non-negativeN)rrLr�r�)�selfr�r�r+r+r,�__init__%s
zNormalDist.__init__cCs.t|ttf�st|�}t|�}||t||��S)z5Make a normal distribution instance from sample data.)rjrb�tuplerr)�clsr>r�r+r+r,�from_samples,szNormalDist.from_samplesN)�seedcsB|durtjnt�|�j�|j|j�����fdd�t|�D�S)z=Generate *n* samples for a given mean and standard deviation.Ncsg|]}�����qSr+r+�r1rY��gaussr�r�r+r,�
<listcomp>8sz&NormalDist.samples.<locals>.<listcomp>)�randomr�ZRandomr�r�r�)r�r3r�r+r�r,�samples4szNormalDist.samplescCs<|jd}|std��t||jdd|�tt|�S)z4Probability density function.  P(x <= X < x+dx) / dxr�z$pdf() not defined when sigma is zerog�)r�rr r�rr")r�rHrr+r+r,�pdf:s
&zNormalDist.pdfcCs2|jstd��ddt||j|jtd��S)z,Cumulative distribution function.  P(X <= x)z$cdf() not defined when sigma is zeror�r�r�)r�rr!r�r�r�rHr+r+r,�cdfAs$zNormalDist.cdfcCs:|dks|dkrtd��|jdkrtd��t||j|j�S)aSInverse cumulative distribution function.  x : P(X <= x) = p

        Finds the value of the random variable such that the probability of
        the variable being less than or equal to that value equals the given
        probability.

        This function is also called the percent point function or quantile
        function.
        r�r�z$p must be in the range 0.0 < p < 1.0z-cdf() not defined when sigma at or below zero)rr�r�r�)r�r�r+r+r,�inv_cdfGs


zNormalDist.inv_cdfr~cs��fdd�td��D�S)anDivide into *n* continuous intervals with equal probability.

        Returns a list of (n - 1) cut points separating the intervals.

        Set *n* to 4 for quartiles (the default).  Set *n* to 10 for deciles.
        Set *n* to 100 for percentiles which gives the 99 cuts points that
        separate the normal distribution in to 100 equal sized groups.
        csg|]	}��|���qSr+)r�r��r3r�r+r,r�`sz(NormalDist.quantiles.<locals>.<listcomp>r-)r�)r�r3r+r�r,rWs	zNormalDist.quantilescCst|t�s	td��||}}|j|jf|j|jfkr||}}|j|j}}|r*|s.td��||}t|j|j�}|sKdt|d|jt	d��S|j||j|}|j|jt	|d|t
||��}	||	|}
||	|}dt|�|
�|�|
��t|�|�|�|��S)a�Compute the overlapping coefficient (OVL) between two normal distributions.

        Measures the agreement between two normal probability distributions.
        Returns a value between 0.0 and 1.0 giving the overlapping area in
        the two underlying probability density functions.

            >>> N1 = NormalDist(2.4, 1.6)
            >>> N2 = NormalDist(3.2, 2.0)
            >>> N1.overlap(N2)
            0.8035050657330205
        z$Expected another NormalDist instancez(overlap() not defined when sigma is zeror�r�)rjrrMr�r�rrrr!rr#r�)r��other�X�YZX_varZY_varZdvZdmrX�b�x1�x2r+r+r,�overlapbs"


(4zNormalDist.overlapcCs|jstd��||j|jS)z�Compute the Standard Score.  (x - mean) / stdev

        Describes *x* in terms of the number of standard deviations
        above or below the mean of the normal distribution.
        z'zscore() not defined when sigma is zero)r�rr�r�r+r+r,�zscore�szNormalDist.zscorecC�|jS)z+Arithmetic mean of the normal distribution.�r��r�r+r+r,r	��zNormalDist.meancCr�)z,Return the median of the normal distributionr�r�r+r+r,r
�r�zNormalDist.mediancCr�)z�Return the mode of the normal distribution

        The mode is the value x where which the probability density
        function (pdf) takes its maximum value.
        r�r�r+r+r,r�szNormalDist.modecCr�)z.Standard deviation of the normal distribution.�r�r�r+r+r,r�r�zNormalDist.stdevcCs
|jdS)z!Square of the standard deviation.r�r�r�r+r+r,r�s
zNormalDist.variancecCs8t|t�rt|j|jt|j|j��St|j||j�S)ajAdd a constant or another NormalDist instance.

        If *other* is a constant, translate mu by the constant,
        leaving sigma unchanged.

        If *other* is a NormalDist, add both the means and the variances.
        Mathematically, this works only if the two distributions are
        independent or if they are jointly normally distributed.
        �rjrr�rr��r�r�r+r+r,�__add__��

zNormalDist.__add__cCs8t|t�rt|j|jt|j|j��St|j||j�S)asSubtract a constant or another NormalDist instance.

        If *other* is a constant, translate by the constant mu,
        leaving sigma unchanged.

        If *other* is a NormalDist, subtract the means and add the variances.
        Mathematically, this works only if the two distributions are
        independent or if they are jointly normally distributed.
        r�r�r+r+r,�__sub__�r�zNormalDist.__sub__cCst|j||jt|��S)z�Multiply both mu and sigma by a constant.

        Used for rescaling, perhaps to change measurement units.
        Sigma is scaled with the absolute value of the constant.
        �rr�r�rr�r+r+r,�__mul__��zNormalDist.__mul__cCst|j||jt|��S)z�Divide both mu and sigma by a constant.

        Used for rescaling, perhaps to change measurement units.
        Sigma is scaled with the absolute value of the constant.
        r�r�r+r+r,�__truediv__�r�zNormalDist.__truediv__cCst|j|j�S)zReturn a copy of the instance.�rr�r��r�r+r+r,�__pos__�szNormalDist.__pos__cCst|j|j�S)z(Negates mu while keeping sigma the same.r�r�r+r+r,�__neg__��zNormalDist.__neg__cCs
||S)z<Subtract a NormalDist from a constant or another NormalDist.r+r�r+r+r,�__rsub__�s
zNormalDist.__rsub__cCs&t|t�stS|j|jko|j|jkS)zFTwo NormalDist objects are equal if their mu and sigma are both equal.)rjr�NotImplementedr�r�r�r+r+r,�__eq__�s
zNormalDist.__eq__cCst|j|jf�S)zCNormalDist objects hash equal if their mu and sigma are both equal.)�hashr�r�r�r+r+r,�__hash__�r�zNormalDist.__hash__cCs t|�j�d|j�d|j�d�S)Nz(mu=z, sigma=�))r8r(r�r�r�r+r+r,�__repr__�s zNormalDist.__repr__cCs|j|jfSr/r�r�r+r+r,�__getstate__�szNormalDist.__getstate__cCs|\|_|_dSr/r�)r��stater+r+r,�__setstate__�szNormalDist.__setstate__)r�r�)r~)#r(r)r*�__doc__�	__slots__r��classmethodr�r�r�r�r�rr�r��propertyr	r
rrrr�r�r�r�r�r��__radd__r��__rmul__r�r�r�r�r�r+r+r+r,rsN�


"




r)r^r/)r-)>r��__all__rGrkr�Z	fractionsr�decimalr�	itertoolsrrZbisectrrrrrr r!r"r#r$�operatorr%�collectionsr&r'rRrrErIr9r;rVrZr]r`r	rrrr
r
rrrrrr�rrrrrrr�rr�Z_statistics�ImportErrorrr+r+r+r,�<module>s`j(4


8
77
8

/
,

!-K�

?>