Python stats.describe方法代码示例

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import describe [as 别名]
def test_describe():
    x = np.vstack((np.ones((3,4)),2*np.ones((2,4))))
    nc, mmc = (5, ([1., 1., 1., 1.], [2., 2., 2., 2.]))
    mc = np.array([1.4, 1.4, 1.4, 1.4])
    vc = np.array([0.3, 0.3, 0.3, 0.3])
    skc = [0.40824829046386357]*4
    kurtc = [-1.833333333333333]*4
    n, mm, m, v, sk, kurt = stats.describe(x)
    assert_equal(n, nc)
    assert_equal(mm, mmc)
    assert_equal(m, mc)
    assert_equal(v, vc)
    assert_array_almost_equal(sk, skc, decimal=13)  # not sure about precision
    assert_array_almost_equal(kurt, kurtc, decimal=13)
    n, mm, m, v, sk, kurt = stats.describe(x.T, axis=1)
    assert_equal(n, nc)
    assert_equal(mm, mmc)
    assert_equal(m, mc)
    assert_equal(v, vc)
    assert_array_almost_equal(sk, skc, decimal=13)  # not sure about precision
    assert_array_almost_equal(kurt, kurtc, decimal=13) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import describe [as 别名]
def stat(seq_length, type):
    print('Seq len info :')
    seq_len = np.asarray(seq_length)
    idx = np.arange(0, len(seq_len), dtype=np.int32)
    print(stats.describe(seq_len))
    plt.figure(figsize=(16, 9))
    plt.subplot(121)
    plt.plot(idx[:], seq_len[:], 'ro')
    plt.grid(True)
    plt.xlabel('index')
    plt.ylabel('seq_len')
    plt.title('Scatter Plot')

    plt.subplot(122)
    plt.hist(seq_len, bins=10, label=['seq_len'])
    plt.grid(True)
    plt.xlabel('seq_len')
    plt.ylabel('freq')
    plt.title('Histogram')
    plt.savefig(type + '_len_stats.jpg', format='jpg') 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import describe [as 别名]
def test_describe_axis_none(self):
        x = np.vstack((np.ones((3, 4)), 2 * np.ones((2, 4))))

        # expected values
        e_nobs, e_minmax = (20, (1.0, 2.0))
        e_mean = 1.3999999999999999
        e_var = 0.25263157894736848
        e_skew = 0.4082482904638634
        e_kurt = -1.8333333333333333

        # actual values
        a = stats.describe(x, axis=None)

        assert_equal(a.nobs, e_nobs)
        assert_almost_equal(a.minmax, e_minmax)
        assert_almost_equal(a.mean, e_mean)
        assert_almost_equal(a.variance, e_var)
        assert_array_almost_equal(a.skewness, e_skew, decimal=13)
        assert_array_almost_equal(a.kurtosis, e_kurt, decimal=13) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import describe [as 别名]
def merge(self, frame):
        """
        Add another DataFrame to the accumulated stats for each column.
        Parameters
        ----------
        frame: pandas DataFrame we will update our stats counter with.
        """
        for column_name, _ in self._column_stats.items():
            data_arr = frame[[column_name]].values
            count, min_max_tup, mean, _, _, _ = \
                scistats.describe(data_arr)
            stats_counter = StatCounter()
            stats_counter.n = count
            stats_counter.mu = mean
            stats_counter.m2 = np.sum((data_arr - mean) ** 2)
            stats_counter.minValue, stats_counter.maxValue = min_max_tup
            self._column_stats[column_name] = self._column_stats[
                column_name].mergeStats(stats_counter)
        return self 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import describe [as 别名]
def examples_normexpand():
    skewnorm = SkewNorm_gen()
    rvs = skewnorm.rvs(5,size=100)
    normexpan = NormExpan_gen(rvs, mode='sample')

    smvsk = stats.describe(rvs)[2:]
    print('sample: mu,sig,sk,kur')
    print(smvsk)

    dmvsk = normexpan.stats(moments='mvsk')
    print('normexpan: mu,sig,sk,kur')
    print(dmvsk)
    print('mvsk diff distribution - sample')
    print(np.array(dmvsk) - np.array(smvsk))
    print('normexpan attributes mvsk')
    print(mc2mvsk(normexpan.cnt))
    print(normexpan.mvsk)

    mnc = mvsk2mnc(dmvsk)
    mc = mnc2mc(mnc)
    print('central moments')
    print(mc)
    print('non-central moments')
    print(mnc)


    pdffn = pdf_moments(mc)
    print('\npdf approximation from moments')
    print('pdf at', mc[0]-1,mc[0]+1)
    print(pdffn([mc[0]-1,mc[0]+1]))
    print(normexpan.pdf([mc[0]-1,mc[0]+1])) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import describe [as 别名]
def test_mvsk(self):
        mvsk = stats.describe(self.rvs)[-4:]
        assert_allclose(self.dist2.mvsk, mvsk, rtol=1e-12) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import describe [as 别名]
def __init__(self,args, **kwds):
        #todo: replace with super call
        distributions.rv_continuous.__init__(self,
            name = 'Normal Expansion distribution', shapes = ' ',
            extradoc = '''
        The distribution is defined as the Gram-Charlier expansion of
        the normal distribution using the first four moments. The pdf
        is given by

        pdf(x) = (1+ skew/6.0 * H(xc,3) + kurt/24.0 * H(xc,4))*normpdf(xc)

        where xc = (x-mu)/sig is the standardized value of the random variable
        and H(xc,3) and H(xc,4) are Hermite polynomials

        Note: This distribution has to be parameterized during
        initialization and instantiation, and does not have a shape
        parameter after instantiation (similar to frozen distribution
        except for location and scale.) Location and scale can be used
        as with other distributions, however note, that they are relative
        to the initialized distribution.
        '''  )
        #print args, kwds
        mode = kwds.get('mode', 'sample')

        if mode == 'sample':
            mu,sig,sk,kur = stats.describe(args)[2:]
            self.mvsk = (mu,sig,sk,kur)
            cnt = mvsk2mc((mu,sig,sk,kur))
        elif mode == 'mvsk':
            cnt = mvsk2mc(args)
            self.mvsk = args
        elif mode == 'centmom':
            cnt = args
            self.mvsk = mc2mvsk(cnt)
        else:
            raise ValueError("mode must be 'mvsk' or centmom")

        self.cnt = cnt
        #self.mvsk = (mu,sig,sk,kur)
        #self._pdf = pdf_moments(cnt)
        self._pdf = pdf_mvsk(self.mvsk) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import describe [as 别名]
def compute_distances(self, X, Y):
        print('Computing intra-domain distance matrices...')

        if not self.gpu:
            C1 = sp.spatial.distance.cdist(X, X, metric=self.metric)
            C2 = sp.spatial.distance.cdist(Y, Y, metric=self.metric)
            if self.normalize_dists == 'max':
                print('here')
                C1 /= C1.max()
                C2 /= C2.max()
            elif self.normalize_dists == 'mean':
                C1 /= C1.mean()
                C2 /= C2.mean()
            elif self.normalize_dists == 'median':
                C1 /= np.median(C1)
                C2 /= np.median(C2)
        else:
            C1 = cdist(X, X, metric=self.metric, returnAsGPU=True)
            C2 = cdist(Y, Y, metric=self.metric, returnAsGPU=True)
            if self.normalize_dists == 'max':
                C1.divide(float(np.max(C1.asarray())))
                C2.divide(float(np.max(C2.asarray())))
            elif self.normalize_dists == 'mean':
                C1.divide(float(np.mean(C1.asarray())))
                C2.divide(float(np.mean(C2.asarray())))
            elif self.normalize_dists == 'median':
                raise NotImplemented(
                    "Median normalization not implemented in GPU yet")

        stats_C1 = describe(C1.flatten())
        stats_C2 = describe(C2.flatten())

        for (k, C, v) in [('C1', C1, stats_C1), ('C2', C2, stats_C2)]:
            print('Stats Distance Matrix {}. mean: {:8.2f}, median: {:8.2f},\
             min: {:8.2f}, max:{:8.2f}'.format(k, v.mean, np.median(C), v.minmax[0], v.minmax[1]))

        self.C1, self.C2 = C1, C2 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import describe [as 别名]
def test_describe(self):
        for n in self.get_n():
            x, y, xm, ym = self.generate_xy_sample(n)
            r = stats.describe(x, ddof=1)
            rm = stats.mstats.describe(xm, ddof=1)
            for ii in range(6):
                assert_almost_equal(np.asarray(r[ii]),
                                    np.asarray(rm[ii]),
                                    decimal=12) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import describe [as 别名]
def test_describe_result_attributes(self):
        actual = mstats.describe(np.arange(5))
        attributes = ('nobs', 'minmax', 'mean', 'variance', 'skewness',
                      'kurtosis')
        check_named_results(actual, attributes, ma=True) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import describe [as 别名]
def test_describe_scalar(self):
        with suppress_warnings() as sup, np.errstate(invalid="ignore"):
            sup.filter(RuntimeWarning, "Degrees of freedom <= 0 for slice")
            n, mm, m, v, sk, kurt = stats.describe(4.)
        assert_equal(n, 1)
        assert_equal(mm, (4.0, 4.0))
        assert_equal(m, 4.0)
        assert_(np.isnan(v))
        assert_array_almost_equal(sk, 0.0, decimal=13)
        assert_array_almost_equal(kurt, -3.0, decimal=13) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import describe [as 别名]
def test_describe_numbers(self):
        x = np.vstack((np.ones((3,4)), 2 * np.ones((2,4))))
        nc, mmc = (5, ([1., 1., 1., 1.], [2., 2., 2., 2.]))
        mc = np.array([1.4, 1.4, 1.4, 1.4])
        vc = np.array([0.3, 0.3, 0.3, 0.3])
        skc = [0.40824829046386357] * 4
        kurtc = [-1.833333333333333] * 4
        n, mm, m, v, sk, kurt = stats.describe(x)
        assert_equal(n, nc)
        assert_equal(mm, mmc)
        assert_equal(m, mc)
        assert_equal(v, vc)
        assert_array_almost_equal(sk, skc, decimal=13)
        assert_array_almost_equal(kurt, kurtc, decimal=13)
        n, mm, m, v, sk, kurt = stats.describe(x.T, axis=1)
        assert_equal(n, nc)
        assert_equal(mm, mmc)
        assert_equal(m, mc)
        assert_equal(v, vc)
        assert_array_almost_equal(sk, skc, decimal=13)
        assert_array_almost_equal(kurt, kurtc, decimal=13)

        x = np.arange(10.)
        x[9] = np.nan

        nc, mmc = (9, (0.0, 8.0))
        mc = 4.0
        vc = 7.5
        skc = 0.0
        kurtc = -1.2300000000000002
        n, mm, m, v, sk, kurt = stats.describe(x, nan_policy='omit')
        assert_equal(n, nc)
        assert_equal(mm, mmc)
        assert_equal(m, mc)
        assert_equal(v, vc)
        assert_array_almost_equal(sk, skc)
        assert_array_almost_equal(kurt, kurtc, decimal=13)

        assert_raises(ValueError, stats.describe, x, nan_policy='raise')
        assert_raises(ValueError, stats.describe, x, nan_policy='foobar') 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import describe [as 别名]
def test_describe_result_attributes(self):
        actual = stats.describe(np.arange(5))
        attributes = ('nobs', 'minmax', 'mean', 'variance', 'skewness',
                      'kurtosis')
        check_named_results(actual, attributes) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import describe [as 别名]
def test_describe_empty(self):
        assert_raises(ValueError, stats.describe, []) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import describe [as 别名]
def __init__(self,metric_name, measurements):
        self._metric_name = metric_name
        self._measurements = measurements
        print("measurements:",self._measurements)
        array=np.array(self._measurements)
        self._stats = stats.describe(array)
        self._bayes_mvs = stats.bayes_mvs(array)