î ½ê[ÃEã @sTdZddddddddd d d g Zd d lZd d lZd dlmZd dlmZGdd„deƒZ d dd„Z dd„Z dd„Z dd„Z dd„Zdd „Zdd„Zdd„Zdd„Zdd d „Zd!d „Zd d"d#„Zd d$d„Zd d%d„Zd d&d„Zd d'd„Zd S)(aF 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. 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. ================== ============================================= 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 Exceptions ---------- A single exception is defined: StatisticsError is a subclass of ValueError. ÚStatisticsErrorÚpstdevÚ pvarianceÚstdevÚvarianceÚmedianÚ median_lowÚ median_highÚmedian_groupedÚmeanÚmodeéN)ÚFraction)ÚDecimalc@seZdZdS)rN)Ú__name__Ú __module__Ú __qualname__©rrú /usr/lib/python3.4/statistics.pyros c Csãttt|ƒgƒ}t|ƒ\}}i||6}t}|j}xJ|D]B}tt|ƒ|ƒ||ƒ\}}||dƒ||| value Return a high-precision sum of the given numeric data. If optional argument ``start`` is given, it is added to the total. If ``data`` is empty, ``start`` (defaulting to 0) is returned. Examples -------- >>> _sum([3, 2.25, 4.5, -0.5, 1.0], 0.75) 11.0 Some sources of round-off error will be avoided: >>> _sum([1e50, 1, -1e50] * 1000) # Built-in sum returns zero. 1000.0 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)]) Fraction(63, 20) >>> from decimal import Decimal as D >>> data = [D("0.1375"), D("0.2108"), D("0.3061"), D("0.0419")] >>> _sum(data) Decimal('0.6963') Mixed types are currently treated as an error, except that int is allowed. r ééN)rr)ÚsetÚintÚtypeÚ _exact_ratioÚgetÚ _check_typeÚlenÚAssertionErrorÚpopÚ issubclassÚfloatrÚmathÚisfiniter ÚsortedÚitemsÚ denominatorÚ numerator) ÚdataÚstartZ allowed_typesÚnÚdZpartialsZ exact_ratioZ partials_getÚxÚTZtotalrrrÚ_sumus6$       r-cCsk||krgt|ƒdkr.|j|ƒqgdjdd„|Dƒ|jgƒ}td|ƒ‚ndS)Nrz, cSsg|]}|j‘qSr)r)Ú.0Útrrrú Às z_check_type..zunsupported mixed types: %s)rÚaddÚjoinrÚ TypeError)r,ZallowedÚtypesrrrr»s  &rcCsþyšy|j|jfSWntk r˜y|jƒSWn\tk r“yt|ƒSWn9tk rŽd}t|jt|ƒjƒƒd‚YnXYnXYnXWn]t t fk rùt |t ƒrÕ|j ƒ sët‚ntj|ƒ sët‚|dfSYnXdS)z¨Convert Real number x exactly to (numerator, denominator) pair. >>> _exact_ratio(0.25) (1, 4) x is expected to be an int, Fraction, Decimal or float. z0can't convert type '{}' to numerator/denominatorN)r&r%ÚAttributeErrorÚas_integer_ratioÚ_decimal_to_ratior3ÚformatrrÚ OverflowErrorÚ ValueErrorÚ isinstancerÚ is_finiterr!r")r+ÚmsgrrrrÄs"   4rcCsª|jƒ\}}}|dkr=|jƒ s4t‚t‚nd}x|D]}|d|}qJW|dkr|d| }n|d|9}d}|r | }n||fS)z¤Convert Decimal d to exact integer ratio (numerator, denominator). >>> from decimal import Decimal >>> _decimal_to_ratio(Decimal("2.6")) (26, 10) ÚFr)ÚNr é r)r>r)r?)Zas_tupler<rr:)r*ZsignZdigitsZexpZnumZdigitZdenrrrr7çs     r7cCstjt|ƒƒjƒ}|s%|S|dd}xEtdt|ƒƒD].}||d|krI|d|…}PqIqIW|S)Nr r)Ú collectionsÚCounterÚiterÚ most_commonÚranger)r'ÚtableZmaxfreqÚirrrÚ_countssrHcCsVt|ƒ|kr!t|ƒ}nt|ƒ}|dkrHtdƒ‚nt|ƒ|S)aƒReturn 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. rz%mean requires at least one data point)rCÚlistrrr-)r'r)rrrr s   cCsut|ƒ}t|ƒ}|dkr3tdƒ‚n|ddkrO||dS|d}||d||dSdS)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 zno median for empty datarrN)r#rr)r'r)rGrrrr)s     cCsct|ƒ}t|ƒ}|dkr3tdƒ‚n|ddkrO||dS||ddSdS)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 r zno median for empty datarrN)r#rr)r'r)rrrrAs    cCs?t|ƒ}t|ƒ}|dkr3tdƒ‚n||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 r zno median for empty datar)r#rr)r'r)rrrrWs   rc Cs t|ƒ}t|ƒ}|dkr3tdƒ‚n|dkrG|dS||d}x<||fD].}t|ttfƒrbtd|ƒ‚qbqbWy||d}Wn,tk rÔt|ƒt|ƒd}YnX|j|ƒ}|j |ƒ}|||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. r zno median for empty datarrzexpected number but got %r) r#rrr;ÚstrÚbytesr3r ÚindexÚcount)r'Zintervalr)r+ÚobjÚLZcfÚfrrrr js"     cCsYt|ƒ}t|ƒdkr*|ddS|rItdt|ƒƒ‚n tdƒ‚dS)aäReturn 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 is not exactly one most common value, ``mode`` will raise StatisticsError. rr z.no unique mode; found %d equally common valueszno mode for empty dataN)rHrr)r'rFrrrr ›s  csŒˆdkrt|ƒ‰nt‡fdd†|Dƒƒ}|t‡fdd†|Dƒƒdt|ƒ8}|dk sˆtd|ƒ‚|S)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. Nc3s|]}|ˆdVqdS)rNr)r.r+)Úcrrú Ïsz_ss..c3s|]}|ˆVqdS)Nr)r.r+)rQrrrRÒsrr z%negative sum of square deviations: %f)r r-rr)r'rQÚssr)rQrÚ_ssÅs  1rTcCsct|ƒ|kr!t|ƒ}nt|ƒ}|dkrHtdƒ‚nt||ƒ}||dS)aÂReturn 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) rz*variance requires at least two data pointsr)rCrIrrrT)r'Úxbarr)rSrrrr×s&  cCs_t|ƒ|kr!t|ƒ}nt|ƒ}|dkrHtdƒ‚nt||ƒ}||S)aÇReturn the population variance of ``data``. data should be an 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 This function does not check that ``mu`` is actually the mean of ``data``. Giving arbitrary values for ``mu`` may lead to invalid or impossible results. 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) rz*pvariance requires at least one data point)rCrIrrrT)r'Úmur)rSrrrrs'  c CsCt||ƒ}y|jƒSWntk r>tj|ƒSYnXdS)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 N)rÚsqrtr5r!)r'rUÚvarrrrr6s  c CsCt||ƒ}y|jƒSWntk r>tj|ƒSYnXdS)z¹Return 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 N)rrWr5r!)r'rVrXrrrrFs  )Ú__doc__Ú__all__rAr!Z fractionsr Zdecimalrr:rr-rrr7rHr rrrr r rTrrrrrrrrÚ]s2     F #      1 */0