Python numpy.nanvar函数代码示例

def plot_profile_TKE_wind(synth):

	fig,ax=plt.subplots()
	colors=get_colors(synth)
	c=0	
	for key,value in synth.iteritems():
		for v in value:
			scase=str(key).zfill(2)
			sleg=str(v).zfill(2)
			synthfile=base_dir+'c'+scase+'/leg'+sleg+'.cdf'
			U = read_synth(synthfile,'F2U')
			V = read_synth(synthfile,'F2V')
			Z = read_synth(synthfile,'z')
			x=[]
			y=[]
			for n,z in enumerate(Z[1:15]):
				u=U[:,:,n+1]
				v=V[:,:,n+1]
				u_var=np.nanvar(u)
				v_var=np.nanvar(v)
				TKE=(u_var+v_var)/2.
				x.append(TKE)
				y.append(z)
			label='Case: '+scase+' Leg: '+sleg
			ax.plot(x,y,'-',label=label,color=colors[c])
			ax.set_ylim([0,4])
			ax.set_xlabel('TKE [m2 s^-2]')
			ax.set_ylabel('Altitude MSL [km]')
			c+=1
	plt.suptitle('Spatial TKE at P3 synth levels ')			
	plt.draw()
	plt.legend()

    def calc_stresses(self, beamvel, beamAng):
        """
        Calculate the stresses from the difference in the beam variances.

        Reference: Stacey, Monosmith and Burau; (1999) JGR [104]
        "Measurements of Reynolds stress profiles in unstratified
        tidal flow"
        """
        fac = 4 * np.sin(self['config']['beam_angle'] * deg2rad) * \
            np.cos(self['config']['beam_angle'] * deg2rad)
        # Note: Stacey defines the beams incorrectly for Workhorse ADCPs.
        #       According to the workhorse coordinate transformation
        #       documentation, the instrument's:
        #                        x-axis points from beam 1 to 2, and
        #                        y-axis points from beam 4 to 3.
        #       Therefore:
        stress = ((np.nanvar(self.reshape(beamvel[0]), axis=-1) -
                   np.nanvar(self.reshape(beamvel[1]), axis=-1)) + 1j *
                  (np.nanvar(self.reshape(beamvel[2]), axis=-1) -
                   np.nanvar(self.reshape(beamvel[3]), axis=-1))
                  ) / fac
        if self.config.orientation == 'up':
            # This comes about because, when the ADCP is 'up', the u
            # and w velocities need to be multiplied by -1 (equivalent
            # to adding pi to the roll).  See the coordinate
            # transformation documentation for more info.
            #
            # The uw (real) component has two minus signs, but the vw (imag)
            # component only has one, therefore:
            stress.imag *= -1
        stress *= rotate.inst2earth_heading(self)
        if self.props['coord_sys'] == 'principal':
            stress *= np.exp(-1j * self.props['principal_angle'])
        return stress.real, stress.imag

def plot_profile_variance(dbz,vvel,ht, ax,case,ncases):

	dbz_variance=[]
	vvel_variance=[]
	count_gates=[]
	global ti
	global n
	global colors 

	if n==0:
		# colors=sns.color_palette('hls',ncases)
		colors=sns.color_palette('Paired',ncases)

	for i in range(len(ht)):
		dbz_variance.append(np.nanvar(dbz[i,:]))
		vvel_variance.append(np.nanvar(vvel[i,:]))
		count_gates.append(vvel[i,:].size-np.sum(np.isnan(vvel[i,:])))

	inid=datetime(*(reqdates[case]['ini']+[0,0]))
	endd=datetime(*(reqdates[case]['end']+[0,0]))
	ti.append('\nCase '+case+': '+inid.strftime('%Y-%b %dT%H:%M')+endd.strftime(' - %dT%H:%M UTC'))

	if n<7:
		marker='None'
		# marker='o'
	else:
		marker='o'

	dbzv=[0,180]
	vvelv=[0,6]
	if np.any(ax):
		ax[0].plot(dbz_variance,ht,marker=marker,color=colors[n])
		ax[1].plot(vvel_variance,ht,marker=marker,color=colors[n])
		ax[2].plot(count_gates,ht,marker=marker,color=colors[n],label='case '+case)
		n+=1
	else:
		fig,ax=plt.subplots(1,3,sharey=True,figsize=(12,8))
		ax[0].plot(dbz_variance,ht,color=colors[n])
		ax[1].plot(vvel_variance,ht,color=colors[n])
		ax[2].plot(count_gates,ht,color=colors[n], label='case '+case)
		ax[0].set_ylabel('Height MSL [km]')
		ax[0].set_xlabel('Reflectivity [dBZ^2]')
		ax[1].set_xlabel('Vertical velocity [m2 s^-2]')
		ax[2].set_xlabel('Count good gates')
		ax[0].set_xlim(dbzv)
		ax[1].set_xlim(vvelv)
		n+=1
		return ax

	if n==ncases and ncases==4:
		plt.suptitle('SPROF time variance'+''.join(ti))
		plt.subplots_adjust(top=0.85, left=0.05, right=0.95, wspace=0.05)
		ax[2].legend(loc='lower left')		
	elif n==ncases and ncases>4:
		plt.suptitle('SPROF time variance')
		plt.subplots_adjust(top=0.9, left=0.05, right=0.95, wspace=0.06)
		ax[2].legend()		

	plt.draw()

    def test_nanvar(self):
        tgt = np.var(self.mat)
        for mat in self.integer_arrays():
            assert_equal(np.nanvar(mat), tgt)

        tgt = np.var(mat, ddof=1)
        for mat in self.integer_arrays():
            assert_equal(np.nanvar(mat, ddof=1), tgt)

def test_nanvar(eng):
    original = arange(24).reshape((2, 3, 4)).astype(float64)
    data = fromlist(list(original), engine=eng)
    assert allclose(data.nanvar().shape, (1, 3, 4))
    assert allclose(data.nanvar().toarray(), nanvar(original, axis=0))

    original[0, 2, 3] = nan
    original[1, 0, 2] = nan
    original[1, 2, 2] = nan
    data = fromlist(list(original), engine=eng)
    assert allclose(data.nanvar().shape, (1, 3, 4))
    assert allclose(data.nanvar().toarray(), nanvar(original, axis=0))

def bayes_precision(x, y, distribution='normal', posterior_width=0.08, num_iters=25000, inference='sampling'):
    """ Bayes precision computation.

    :param x: sample of a treatment group
    :type  x: pd.Series or list (array-like)
    :param y: sample of a control group
    :type  y: pd.Series or list (array-like)
    :param distribution: name of the KPI distribution model, which assumes a Stan model file with the same name exists
    :type  distribution: str
    :param posterior_width: the stopping criterion, threshold of the posterior  width
    :type  posterior_width: float
    :param num_iters: number of iterations of bayes sampling
    :type  num_iters: int
    :param inference: sampling or variational inference method for approximation the posterior
    :type  inference: str

    :return: results of type EarlyStoppingTestStatistics (without p-value and stat. power)
    :rtype:  EarlyStoppingTestStatistics
    """

    logger.info("Started running bayes precision with {} procedure, treatment group of size {}, "
                "control group of size {}, {} distribution.".format(len(x), len(y), distribution, inference))

    traces, n_x, n_y, mu_x, mu_y = _bayes_sampling(x, y, distribution=distribution,
                                                   num_iters=num_iters, inference=inference)
    trace_normalized_effect_size = get_trace_normalized_effect_size(distribution, traces)
    trace_absolute_effect_size = traces['delta']

    credible_mass = 0.95
    left_out      = 1.0 - credible_mass
    p1            = round(left_out/2.0, 5)
    p2            = round(1.0 - left_out/2.0, 5)

    credible_interval_delta            = HDI_from_MCMC(trace_absolute_effect_size, credible_mass)
    credible_interval_delta_normalized = HDI_from_MCMC(trace_normalized_effect_size, credible_mass)

    stop = credible_interval_delta_normalized[1] - credible_interval_delta_normalized[0] < posterior_width

    treatment_statistics = SampleStatistics(int(n_x), float(mu_x), float(np.nanvar(x)))
    control_statistics   = SampleStatistics(int(n_y), float(mu_y), float(np.nanvar(y)))
    variant_statistics   = BaseTestStatistics(control_statistics, treatment_statistics)

    logger.info("Finished running bayes precision with {} procedure, treatment group of size {}, "
                "control group of size {}, {} distribution.".format(len(x), len(y), distribution, inference))

    return EarlyStoppingTestStatistics(variant_statistics.control_statistics,
                                       variant_statistics.treatment_statistics,
                                       float(mu_x - mu_y),
                                       dict([(p * 100, v) for p, v in zip([p1, p2], credible_interval_delta)]),
                                       None, None, stop)

def test_nanvar(eng):
    arr = array([arange(8), arange(8)]).astype(float64)
    data = fromarray(arr, engine=eng)
    val = data.nanvar().toarray()
    expected = nanvar(data.toarray(), axis=0)
    assert allclose(val, expected)
    assert str(val.dtype) == 'float64'
    arr[0, 4] = nan
    arr[1, 3] = nan
    arr[1, 4] = nan
    data = fromarray(arr, engine=eng)
    val = data.nanvar().toarray()
    expected = nanvar(data.toarray(), axis=0)
    assert allclose(val, expected, equal_nan=True)
    assert str(val.dtype) == 'float64'

    def test_GWAS(self):
        Y = np.genfromtxt(self._liverPhenos)

        # Loading npdump and first 1000 snps for speed
        K = np.load(self._liverKinshipMatrix)

        snps = np.load(self._liver1000SNPFile).T
        vars = np.nanvar(snps, axis=0) #variances across the rows ignoring NaN, used to check which SNPs were not polymorphic across the given individuals

        TS,PS = lmm.GWAS(Y,snps,K,REML=True,refit=True)

        #SNPs that are not polymorphic (in the given individuals being tested) will have variance 0, this check ensures
        #that only these SNPs have a return value of NaN
        for i in range(len(PS)):
           self.assertTrue( not math.isnan(PS[i]) or vars[i] == 0, "NaN found in results corresponding to polymorphic SNP")

        results = np.array([TS,PS])
        ansKey = np.load(self._liverTestFile)

        #these results include np.nan values, so allclose cannot be used, also the results are similar with each
        #run, but do vary, so we can only check for similarity to a precision of about 1e-06
        for i in range(results.shape[0]):
            for j in range(results.shape[1]):
                a = results[i,j]
                b = ansKey[i,j]
                self.assertTrue( (np.isnan(a) and np.isnan(b)) or abs(a - b) < 1e-06 ,
                                 "Mismatch on values: " + str(a) + " and " + str(b))

 def c(self, P, h, bw):
     """Calculate the sill"""
     c = np.nanvar(P[:, 2])
     if h == 0:
         return c
     else:
         return c - self.semivarh(P, h, bw)

	    def compute(self, today, assets, out, close):

	    	# get returns dataset
	        returns = ((close - np.roll(close, 1, axis=0)) / np.roll(close, 1, axis=0))[1:]

	        # get index of benchmark
	        benchmark_index = np.where((assets == 8554) == True)[0][0]

	        # get returns of benchmark
	        benchmark_returns = returns[:, benchmark_index]
	        
	        # prepare X matrix (x_is - x_bar)
	        X = benchmark_returns
	        X_bar = np.nanmean(X)
	        X_vector = X - X_bar
	        X_matrix = np.tile(X_vector, (len(returns.T), 1)).T

	        # prepare Y matrix (y_is - y_bar)
	        Y_bar = np.nanmean(close, axis=0)
	        Y_bars = np.tile(Y_bar, (len(returns), 1))
	        Y_matrix = returns - Y_bars

	        # prepare variance of X
	        X_var = np.nanvar(X)

	        # multiply X matrix an Y matrix and sum (dot product)
	        # then divide by variance of X
	        # this gives the MLE of Beta
	        out[:] = (np.sum((X_matrix * Y_matrix), axis=0) / X_var) / (len(returns))

def cal_stats(in_fc, col_names):
    """Calculate stats for an array of double types, with nodata (nan, None)
    :  in the column.
    :Requires:
    :---------
    : in_fc - input featureclass or table
    : col_names - the columns... numeric (floating point, double)
    :
    :Notes:
    :------  see the args tuple for examples of nan functions
    :  np.nansum(b, axis=0)   # by column
    :  np.nansum(b, axis=1)   # by row
    :  c_nan = np.count_nonzero(~np.isnan(b), axis=0) count nan if needed
    """
    a = arcpy.da.FeatureClassToNumPyArray(in_fc, col_names)  # "*")
    b = a.view(np.float).reshape(len(a), -1)
    if len(a.shape) == 1:
        ax = 0
    else:
        ax = [1, 0][True]  # ax = [1, 0][colwise]  colwise= True
    mask = np.isnan(b)
    cnt = np.sum(~mask, axis=ax, dtype=np.intp, keepdims=False)
    n_sum = np.nansum(b, axis=0)
    n_mean = np.nanmean(b, axis=0)
    n_var = np.nanvar(b, axis=0)
    n_std = np.nanstd(b, axis=0)
    sk, kurt = skew_kurt(b, avg=n_mean, var_x=n_var, std_x=n_std,
                         col=True, mom='both')
    args = (col_names, cnt, n_sum, np.nanmin(b, axis=0), np.nanmax(b, axis=0),
            np.nanmedian(b, axis=0), n_mean, n_std, n_var, sk, kurt)
    return col_names, args

def computeFisherScore(data, class_ass, nb_classes):
	'''
	The Fisher Score assigns a rank to each of the features, with the goal of finding the subset of features of the data
	such that in the data space spanned by the selected features, the distance between data points in different classes are
	as large as possible and the distance between data points in the same class are as small as possible.

	Input
		- data: matrix of inputs, size N x M, where N is the number of trials and M is the number of features
		- class_ass: array of class assignments, size 1 x N, where N is the number of trials
		- nb_classes: number of classes
	Output
		- Fscores: array of scores, size 1 x M, for each of the features
	'''
	num_trials, num_features = data.shape
	within_class_mean = np.zeros([nb_classes,num_features]) 	# mean for each feature within each class
	within_class_var = np.zeros([nb_classes,num_features]) 		# variance for each feature within each class
	num_points_within_class = np.zeros([1,nb_classes])  			# number of points within each class 
	
	for i in range(nb_classes):
		in_class = np.ravel(np.nonzero(class_ass == i))
		num_points_within_class[0,i] = len(in_class)
		class_data = data[in_class,:]  	# extract trails classified as belonging to this class
		within_class_mean[i,:] = np.nanmean(class_data, axis=0)  # length of mean vector should be equal to M, the number of features
		within_class_var[i,:] = np.nanvar(class_data,axis=0)

	between_class_mean = np.asmatrix(np.mean(within_class_mean,axis=0))
	between_class_mean = np.dot(np.ones([nb_classes,1]), between_class_mean)

	Fscores = np.dot(num_points_within_class,np.square(within_class_mean - between_class_mean))/np.dot(num_points_within_class,within_class_var)

	return Fscores

    def _fit_model(self, fcol, dis):

        """Determine the best fit for one feature column given distribution name

        Parameters
        ----------
        fcol: feature column, array
        dis: distribution name, String


        Returns
        ----------
        function: fit model with feature as argument

        """
        if dis == 'ratio':
            itfreq = itemfreq(fcol)
            uniqueVars = itfreq[:,0]
            freq = itfreq[:,1]
            rat = freq/sum(freq)
            rat = dict(zip(uniqueVars, rat.T))
            func = lambda x: self. funcs[dis](x, rat)
        if dis == 'poisson':
            lamb = np.nanmean(fcol, axis = 0)
            func = lambda x: self.funcs[dis](x, lamb)
        if dis ==   'norm':
            sigma = np.nanvar(fcol, axis=0)
            theta = np.nanmean(fcol, axis = 0)
            func = lambda x: self.funcs[dis](x, sigma, theta)
        return np.vectorize(func)

    def fit_cols(self, attributes, x, n_vals):
        """
        Return `EuclideanColumnsModel` with stored means and variances
        for normalization and imputation.
        """
        def nowarn(msg, cat, *args, **kwargs):
            if cat is RuntimeWarning and (
                    msg == "Mean of empty slice"
                    or msg == "Degrees of freedom <= 0 for slice"):
                if self.normalize:
                    raise ValueError("some columns have no defined values")
            else:
                orig_warn(msg, cat, *args, **kwargs)

        self.check_no_discrete(n_vals)
        # catch_warnings resets the registry for "once", while avoiding this
        # warning would be annoying and slow, hence patching
        orig_warn = warnings.warn
        with patch("warnings.warn", new=nowarn):
            means = np.nanmean(x, axis=0)
            vars = np.nanvar(x, axis=0)
        if self.normalize and not vars.all():
            raise ValueError("some columns are constant")
        return EuclideanColumnsModel(
            attributes, self.impute, self.normalize, means, vars)

def autocorrelation_hourly(data):
    from matplotlib.pyplot import plot, xlabel, ylabel, show
    from numpy import nanmean, nanvar, mean, multiply, arange
    # We choose 7 days and plus-minus 6 hours as the possible periodicity
    # in traffic.
    START_PERIOD = 7*24 - 6
    END_PERIOD = 7*24 + 6
    V = replace_placeholder(data, value = nanmean(data))
    # We don't take the variance of entries that we replaced with nanmean.
    sigma2 = nanvar(data)
    autocorr_dict = {period:0 for period in range(START_PERIOD,END_PERIOD+1)}
    Deviations = V - nanmean(V, axis=0)
    for period in range(START_PERIOD, END_PERIOD+1):
        autocorr = nanmean([multiply(Deviations[t],Deviations[t+period])
                            for t in range(len(V)-period)])/sigma2
        autocorr_dict[period] = autocorr
        print(period)

    # Peaks in plot correspond to high autocorrelation i.e. high
    # periodicity trend.
    plot(arange(START_PERIOD, END_PERIOD+1),
         [autocorr_dict[period] for period in range(START_PERIOD, END_PERIOD+1)],
         'o-')

    ylabel('Average autocorellation over full links')
    xlabel('Assumed period of data (in hours)')
    show()
    #legend(bbox_to_anchor=(1.35, 0.95))
    return None