YfML @s|dZddddddddd d d g Zd d lZd d lZd dlmZd dlmZd dlm Z Gddde Z d ddZ ddZ ddZddZddZddZddZd d Zd!dZd"dZd#dZd$d%d Zd&d Zd d'd(Zd d)dZd d*dZd d+dZd d,dZd 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. StatisticsErrorpstdev pvariancestdevvariancemedian median_low median_highmedian_groupedmeanmodeN)Fraction)Decimal)groupbyc@seZdZdS)rN)__name__ __module__ __qualname__rr//opt/alt/python35/lib64/python3.5/statistics.pyrqs c Csd}t|\}}||i}|j}ttt|}xmt|tD]\\}} t||}x>tt| D]-\}}|d7}||d||| (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. 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) (, Fraction(11, 1), 5) Some sources of round-off error will be avoided: >>> _sum([1e50, 1, -1e50] * 1000) # Built-in sum returns zero. (, 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)]) (, 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) (, Fraction(6963, 10000), 4) Mixed types are currently treated as an error, except that int is allowed. r Ncss$|]\}}t||VqdS)N)r ).0dnrrr sz_sum..) _exact_ratioget_coerceinttypermap _isfiniteAssertionErrorsumsorteditems) datastartcountrrZpartialsZ partials_getTtypvaluestotalrrr_sumws#     %r,c Cs4y|jSWntk r/tj|SYnXdS)N) is_finiteAttributeErrormathisfinite)xrrrr s r cCs |tk std||kr(|S|tks@|tkrD|S|tkrT|St||rg|St||rz|St|tr|St|tr|St|trt|tr|St|trt|tr|Sd}t||j|jfdS)zCoerce 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. zinitial type T is boolz"don't know how to coerce %s and %sN)boolr!r issubclassr float TypeErrorr)r(Smsgrrrrs*  rcCsyt|tkr|jSy|j|jfSWnXtk ry|jSWn5tk ryt|SWntk rYnXYnXYnXWn8ttfk rt j | st |dfSYnXd}t |j t|jdS)zReturn 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. Nz0can't convert type '{}' to numerator/denominator)rr4as_integer_ratio numerator denominatorr._decimal_to_ratio OverflowError ValueErrorr/r0r!r5formatr)r1r7rrrrs$    rcCs|j\}}}|dkr>|j s4t|dfSd}x|D]}|d|}qKW|dkr}d| }n|d|9}d}|r| }||fS) zConvert Decimal d to exact integer ratio (numerator, denominator). >>> from decimal import Decimal >>> _decimal_to_ratio(Decimal("2.6")) (26, 10) FrNNr r)r?rr@)Zas_tupler-r!)rZsignZdigitsZexpZnumZdigitZdenrrrr;s    r;c Cst||kr|St|tr:|jdkr:t}y||SWn>tk rt|tr||j||jSYnXdS)z&Convert value to given numeric type T.rN)rr3rr:r4r5rr9)valuer(rrr_converts rCcCs|tjt|j}|s%|S|dd}xBtdt|D]+}||d|krI|d|}PqIW|S)Nr r) collectionsCounteriter most_commonrangelen)r%tableZmaxfreqirrr_counts&srLcCszt||krt|}t|}|dkrBtdt|\}}}||ksitt|||S)aReturn 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)rFlistrIrr,r!rC)r%rr(r+r'rrrr 6s    cCsrt|}t|}|dkr0td|ddkrL||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 datarN)r#rIr)r%rrKrrrrQs      cCs`t|}t|}|dkr0td|ddkrL||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 datarNrN)r#rIr)r%rrrrris     cCs<t|}t|}|dkr0td||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 datarN)r#rIr)r%rrrrrs    rc Cst|}t|}|dkr3tdn|dkrG|dS||d}x9||fD]+}t|ttfrbtd|qbWy||d}Wn,tk rt|t|d}YnX|j|}|j |}|||d||S)aReturn 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 datarrNzexpected number but got %r) r#rIr isinstancestrbytesr5r4indexr')r%Zintervalrr1objLZcffrrrr s"     cCsYt|}t|dkr*|ddS|rItdt|n tddS)aReturn 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)rLrIr)r%rJrrrr s  csdkrt|tfdd|D\}}}tfdd|D\}}}||kr||kst||dt|8}|dk std|||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. Nc3s|]}|dVqdS)rNNr)rr1)crrrsz_ss..c3s|]}|VqdS)Nr)rr1)rVrrrsrNr z%negative sum of square deviations: %f)r r,r!rI)r%rVr(r+r'UZtotal2Zcount2r)rVr_sss  ((rXcCslt||krt|}t|}|dkrBtdt||\}}t||d|S)aReturn 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) rNz*variance requires at least two data pointsr)rFrMrIrrXrC)r%xbarrr(ssrrrrs&    cCsht||krt|}t|}|dkrBtdt||\}}t|||S)aReturn 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)rFrMrIrrXrC)r%murr(rZrrrr0s'    c CsCt||}y|jSWntk r>tj|SYnXdS)zReturn 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)rsqrtr.r/)r%rYvarrrrr`s  c CsCt||}y|jSWntk r>tj|SYnXdS)zReturn 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)rr\r.r/)r%r[r]rrrrps  )__doc____all__rDr/Z fractionsr Zdecimalr itertoolsrr=rr,r rrr;rCrLr rrrr r rXrrrrrrrr]s8     9   %       1 */0