Python common.checkParams函数代码示例

    def similarity(self, other, metric='distance', thresh=5):
        """
        Estimate similarity between sources in self and other.

        Will compute the fraction of sources in self that are found
        in other, based on a given distance metric and a threshold.
        The fraction is estimated as the number of sources in self
        found in other, divided by the total number of sources in self.

        Parameters
        ----------
        other : SourceModel
            The sources to compare to

        metric : str, optional, default = "distance"
            Metric to use when computing distances

        thresh : scalar, optional, default = 5
            The distance below which a source is considered found
        """

        checkParams(metric, ['distance'])

        if metric == 'distance':
            vals = self.distance(other, minDistance=thresh)
            vals[isnan(vals)] = inf
        else:
            raise Exception("Metric not recognized")

        hits = sum(vals < thresh) / float(len(self.sources))

        return hits

    def distance(self, other, method='euclidean'):
        """
        Distance between the center of this source and another.

        Parameters
        ----------
        other : Source, or array-like
            Either another source, or the center coordinates of another source

        method : str
            Specify a distance measure to used for spatial distance between source
            centers. Current options include Euclidean distance ('euclidean') and 
            L1-norm ('l1'). 

        """
        from numpy.linalg import norm

        checkParams(method, ['euclidean', 'l1'])

        if method == 'l1':
            order = 1
        else:
            order = 2

        if isinstance(other, Source):
            return norm(self.center - other.center, ord=order)
        elif isinstance(other, list) or isinstance(other, ndarray):
            return norm(self.center - asarray(other), ord=order)

    def detrend(self, method='linear', **kwargs):
        """
        Detrend time series data with linear or nonlinear detrending
        Preserve intercept so that subsequent steps can adjust the baseline

        Parameters
        ----------
        method : str, optional, default = 'linear'
            Detrending method

        order : int, optional, default = 5
            Order of polynomial, for non-linear detrending only
        """
        checkParams(method, ['linear', 'nonlinear'])

        if method.lower() == 'linear':
            order = 1
        else:
            if 'order' in kwargs:
                order = kwargs['order']
            else:
                order = 5

        def func(y):
            x = arange(len(y))
            p = polyfit(x, y, order)
            p[-1] = 0
            yy = polyval(p, x)
            return y - yy

        return self.applyValues(func, keepIndex=True)

    def makeExample(self, dataset=None, **opts):
        """
        Make an example data set for testing analyses.

        Options include 'pca', 'factor', 'kmeans', 'ica', 'sources'
        See thunder.utils.datasets for detailed options.

        Parameters
        ----------
        dataset : str
            Which dataset to generate

        Returns
        -------
        data : RDD of (tuple, array) pairs
            Generated dataset

        """
        from thunder.utils.datasets import DATASET_MAKERS

        if dataset is None:
            return sorted(DATASET_MAKERS.keys())

        checkParams(dataset, DATASET_MAKERS.keys())

        return DataSets.make(self._sc, dataset, **opts)

    def loadSeries(self, dataPath, nkeys=None, nvalues=None, inputFormat='binary', minPartitions=None,
                   confFilename='conf.json', keyType=None, valueType=None):
        """
        Loads a Series object from data stored as text or binary files.

        Supports single files or multiple files stored on a local file system, a networked file system (mounted
        and available on all cluster nodes), Amazon S3, or HDFS.

        Parameters
        ----------
        dataPath: string
            Path to data files or directory, specified as either a local filesystem path or in a URI-like format,
            including scheme. A dataPath argument may include a single '*' wildcard character in the filename. Examples
            of valid dataPaths include 'a/local/relative/directory/*.stack", "s3n:///my-s3-bucket/data/mydatafile.tif",
            "/mnt/my/absolute/data/directory/", or "file:///mnt/another/data/directory/".

        nkeys: int, optional (but required if `inputFormat` is 'text')
            dimensionality of data keys. (For instance, (x,y,z) keyed data for 3-dimensional image timeseries data.)
            For text data, number of keys must be specified in this parameter; for binary data, number of keys must be
            specified either in this parameter or in a configuration file named by the 'conffile' argument if this
            parameter is not set.

        nvalues: int, optional (but required if `inputFormat` is 'text')
            Number of values expected to be read. For binary data, nvalues must be specified either in this parameter
            or in a configuration file named by the 'conffile' argument if this parameter is not set.

        inputFormat: {'text', 'binary'}. optional, default 'binary'
            Format of data to be read.

        minPartitions: int, optional
            Explicitly specify minimum number of Spark partitions to be generated from this data. Used only for
            text data. Default is to use minParallelism attribute of Spark context object.

        confFilename: string, optional, default 'conf.json'
            Path to JSON file with configuration options including 'nkeys', 'nvalues', 'keytype', and 'valuetype'.
            If a file is not found at the given path, then the base directory given in 'datafile'
            will also be checked. Parameters `nkeys` or `nvalues` that are specified as explicit arguments to this
            method will take priority over those found in conffile if both are present.

        Returns
        -------
        data: thunder.rdds.Series
            A newly-created Series object, wrapping an RDD of series data. This RDD will have as keys an n-tuple
            of int, with n given by `nkeys` or the configuration passed in `conffile`. RDD values will be a numpy
            array of length `nvalues` (or as specified in the passed configuration file).
        """
        checkParams(inputFormat, ['text', 'binary'])

        from thunder.rdds.fileio.seriesloader import SeriesLoader
        loader = SeriesLoader(self._sc, minPartitions=minPartitions)

        if inputFormat.lower() == 'text':
            data = loader.fromText(dataPath, nkeys=nkeys)
        else:
            # must be either 'text' or 'binary'
            data = loader.fromBinary(dataPath, confFilename=confFilename, nkeys=nkeys, nvalues=nvalues,
                                     keyType=keyType, valueType=valueType)
        return data

    def overlap(self, other, method='support', counts=False, symmetric=True):
        """
        Compute the overlap between this source and other, in terms
        of either support or similarity of coefficients.

        Support computes the number of overlapping pixels relative
        to the union of both sources. Correlation computes the similarity
        of the weights (not defined for binary masks).

        Parameters
        ----------
        other : Source
            The source to compute overlap with.

        method : str
            Compare either support of source coefficients ('support'), or the 
            source spatial filters (not yet implemented).

        counts : boolean, optional, default = True
            Whether to return raw counts when computing support, otherwise
            return a fraction.

        """
        checkParams(method, ['support', 'corr'])

        coordsSelf = aslist(self.coordinates)
        coordsOther = aslist(other.coordinates)

        intersection = [a for a in coordsSelf if a in coordsOther]
        complementLeft = [a for a in coordsSelf if a not in intersection]
        complementRight = [a for a in coordsOther if a not in intersection]
        hits = len(intersection)

        if symmetric is True:
            misses = len(complementLeft + complementRight)
        else:
            misses = len(complementLeft)

        if method == 'support':
            if counts:
                return hits, misses
            else:
                return hits/float(hits+misses)

        if method == 'corr':
            from scipy.stats import spearmanr

            if not (hasattr(self, 'values') and hasattr(other, 'values')):
                raise Exception('Sources must have values to compute correlation')
            else:
                valuesSelf = aslist(self.values)
                valuesOther = aslist(other.values)
            if len(intersection) > 0:
                rho, _ = spearmanr(valuesSelf[intersection], valuesOther[intersection])
            else:
                rho = 0.0
            return (rho * hits)/float(hits + misses)

    def __new__(cls, method, **kwargs):

        from thunder.extraction.block.methods.nmf import BlockNMF
        from thunder.extraction.feature.methods.localmax import LocalMax

        EXTRACTION_METHODS = {
            'nmf': BlockNMF,
            'localmax': LocalMax
        }

        checkParams(method, EXTRACTION_METHODS.keys())
        return EXTRACTION_METHODS[method](**kwargs)

    def normalize(self, baseline='percentile', window=None, perc=20, offset=0.1):
        """
        Normalize each time series by subtracting and dividing by a baseline.

        Baseline can be derived from a global mean or percentile,
        or a smoothed percentile estimated within a rolling window.

        Parameters
        ----------
        baseline : str, optional, default = 'percentile'
            Quantity to use as the baseline, options are 'mean', 'percentile', 'window', or 'window-fast'

        window : int, optional, default = 6
            Size of window for baseline estimation, for 'window' and 'window-fast' baseline only

        perc : int, optional, default = 20
            Percentile value to use, for 'percentile', 'window', or 'window-fast' baseline only

        offset : float, optional, default = 0.1
            Scalar added to baseline during division
        """
        checkParams(baseline, ['mean', 'percentile', 'window', 'window-fast'])
        method = baseline.lower()
    
        from warnings import warn
        if not (method == 'window' or method == 'window-fast') and window is not None:
            warn('Setting window without using method "window" has no effect')

        if method == 'mean':
            baseFunc = mean

        if method == 'percentile':
            baseFunc = lambda x: percentile(x, perc)

        if method == 'window':
            if window & 0x1:
                left, right = (ceil(window/2), ceil(window/2) + 1)
            else:
                left, right = (window/2, window/2)

            n = len(self.index)
            baseFunc = lambda x: asarray([percentile(x[max(ix-left, 0):min(ix+right+1, n)], perc)
                                          for ix in arange(0, n)])

        if method == 'window-fast':
            from scipy.ndimage.filters import percentile_filter
            baseFunc = lambda x: percentile_filter(x.astype(float64), perc, window, mode='nearest')

        def get(y):
            b = baseFunc(y)
            return (y - b) / (b + offset)

        return self.applyValues(get, keepIndex=True)

    def __new__(cls, method, **kwargs):

        from thunder.registration.methods.crosscorr import CrossCorr, PlanarCrossCorr

        REGMETHODS = {
            'crosscorr': CrossCorr,
            'planarcrosscorr': PlanarCrossCorr
        }

        checkParams(method, REGMETHODS.keys())

        return REGMETHODS[method](kwargs)

def export(data, outputDirPath, outputFilename, outputFormat, sorting=False):
    """
    Export data to a variety of local formats.

    Can export local arrays or a Series. If passed a Series,
    it will first be packed into one or more local arrrays.

    Parameters
    ----------
    data : Series, or numpy array
        The data to export

    outputDirPath : str
        Output directory

    outputFilename : str
        Output filename

    outputFormat : str
        Output format ("matlab", "npy", or "text")

    """

    from thunder.rdds.series import Series
    from scipy.io import savemat

    checkParams(outputFormat, ['matlab', 'npy', 'text'])

    if not os.path.exists(outputDirPath):
        os.makedirs(outputDirPath)

    filename = os.path.join(outputDirPath, outputFilename)

    def write(array, file, format, varname=None):
        if format == 'matlab':
            savemat(file+".mat", mdict={varname: array}, oned_as='column', do_compression='true')
        if format == 'npy':
            save(file, array)
        if format == 'text':
            savetxt(file+".txt", array, fmt="%.6f")

    if isinstance(data, Series):
        # force calculation of dimensions
        _tmp = data.dims
        if size(data.index) > 1:
            for ix in data.index:
                result = data.select(ix).pack(sorting=sorting)
                write(result, filename+"_"+str(ix), outputFormat, varname=outputFilename+"_"+str(ix))
        else:
            result = data.pack(sorting=sorting)
            write(result, filename, outputFormat, varname=outputFilename+"_"+str(data.index))
    else:
        write(data, filename, outputFormat, varname=outputFilename)

    def overlap(self, other, method="fraction"):
        """
        Compute the overlap between this source and other.

        Options are a symmetric measure of overlap based on the fraction
        of intersecting pixels relative to the union ('fraction'), an assymmetric
        measure of overlap that expresses detected intersecting pixels
        (relative to this source) using precision and recall rates ('rates'), or
        a correlation coefficient of the weights within the intersection
        (not defined for binary weights) ('correlation')

        Parameters
        ----------
        other : Source
            The source to compute overlap with.

        method : str
            Which estimate of overlap to compute, options are
            'fraction' (symmetric) 'rates' (asymmetric) or 'correlation'
        """
        checkParams(method, ["fraction", "rates", "correlation"])

        coordsSelf = aslist(self.coordinates)
        coordsOther = aslist(other.coordinates)

        intersection = [a for a in coordsSelf if a in coordsOther]
        nhit = float(len(intersection))
        ntotal = float(len(set([tuple(x) for x in coordsSelf] + [tuple(x) for x in coordsOther])))

        if method == "rates":
            recall = nhit / len(coordsSelf)
            precision = nhit / len(coordsOther)
            return recall, precision

        if method == "fraction":
            return nhit / float(ntotal)

        if method == "correlation":
            from scipy.stats import spearmanr

            if not (hasattr(self, "values") and hasattr(other, "values")):
                raise ValueError("Sources must have values to compute correlation")
            else:
                valuesSelf = aslist(self.values)
                valuesOther = aslist(other.values)
            if len(intersection) > 0:
                left = [v for v, c in zip(valuesSelf, coordsSelf) if c in coordsOther]
                right = [v for v, c in zip(valuesOther, coordsOther) if c in coordsSelf]
                rho, _ = spearmanr(left, right)
            else:
                rho = 0.0
            return rho

    def similarity(self, other, metric="distance", thresh=5, minDistance=inf):
        """
        Estimate similarity to another set of sources using recall and precision.

        Will compute the number of sources in self that are also
        in other, based on a given distance metric and a threshold.
        The recall rate is the number of matches divided by the number in self,
        and the precision rate is the number of matches divided by the number in other.
        Typically self is ground truth and other is an estimate.
        The F score is defined as 2 * (recall * precision) / (recall + precision)

        Before computing metrics, all sources in self are matched to other,
        and a minimum distance can be set to control matching.

        Parameters
        ----------
        other : SourceModel
            The sources to compare to.

        metric : str, optional, default = 'distance'
            Metric to use when computing distances,
            options include 'distance' and 'overlap'

        thresh : scalar, optional, default = 5
            The distance below which a source is considered found.

        minDistance : scalar, optional, default = inf
            Minimum distance to use when matching indices.
        """
        checkParams(metric, ["distance", "overlap"])

        if metric == "distance":
            # when evaluating distances,
            # minimum distance should be the threshold
            if minDistance == inf:
                minDistance = thresh
            vals = self.distance(other, minDistance=minDistance)
            vals[isnan(vals)] = inf
            compare = lambda x: x < thresh
        elif metric == "overlap":
            vals = self.overlap(other, method="fraction", minDistance=minDistance)
            vals[isnan(vals)] = 0
            compare = lambda x: x > thresh
        else:
            raise Exception("Metric not recognized")

        recall = sum(map(compare, vals)) / float(self.count)
        precision = sum(map(compare, vals)) / float(other.count)
        score = 2 * (recall * precision) / (recall + precision)

        return recall, precision, score

    def export(self, data, filename, outputFormat=None, overwrite=False, varname=None):
        """
        Export local array data to a variety of formats.

        Can write to a local file sytem or S3 (destination inferred from filename schema).
        S3 writing useful for persisting arrays when working in an environment without
        accessible local storage.

        Parameters
        ----------
        data : array-like
            The data to export

        filename : str
            Output location (path/to/file.ext)

        outputFormat : str, optional, default = None
            Ouput format ("npy", "mat", or "txt"), if not provided will
            try to infer from file extension.

        overwrite : boolean, optional, default = False
            Whether to overwrite if directory or file already exists

        varname : str, optional, default = None
            Variable name for writing "mat" formatted files
        """
        from numpy import save, savetxt, asarray
        from scipy.io import savemat
        from StringIO import StringIO

        from thunder.rdds.fileio.writers import getFileWriterForPath

        path, file, outputFormat = handleFormat(filename, outputFormat)
        checkParams(outputFormat, ["npy", "mat", "txt"])
        clazz = getFileWriterForPath(filename)
        writer = clazz(path, file, overwrite=overwrite, awsCredentialsOverride=self._credentials)

        stream = StringIO()

        if outputFormat == "mat":
            varname = os.path.splitext(file)[0] if varname is None else varname
            savemat(stream, mdict={varname: data}, oned_as='column', do_compression='true')
        if outputFormat == "npy":
            save(stream, data)
        if outputFormat == "txt":
            if asarray(data).ndim > 2:
                raise Exception("Cannot write data with more than two dimensions to text")
            savetxt(stream, data)

        stream.seek(0)
        writer.writeFile(stream.buf)

    def similarity(self, other, metric='distance', thresh=5, minDistance=inf):
        """
        Estimate similarity between sources in self and other.

        Will compute the fraction of sources in self that are found
        in other, based on a given distance metric and a threshold.
        The fraction is estimated as the number of sources in self
        found in other, divided by the total number of sources in self.

        Before computing metrics, all sources in self are matched to other,
        and a minimum distance can be set to control matching.

        Parameters
        ----------
        other : SourceModel
            The sources to compare to

        metric : str, optional, default = "distance"
            Metric to use when computing distances,
            options include 'distance' and 'overlap'

        thresh : scalar, optional, default = 5
            The distance below which a source is considered found

        minDistance : scalar, optional, default = inf
            Minimum distance to use when matching indices
        """
        checkParams(metric, ['distance', 'overlap'])

        if metric == 'distance':
            # when evaluating distances,
            # minimum distance should be the threshold
            if minDistance == inf:
                minDistance = thresh
            vals = self.distance(other, minDistance=minDistance)
            vals[isnan(vals)] = inf
            compare = lambda x: x < thresh
        elif metric == 'overlap':
            vals = self.overlap(other, method='support', minDistance=minDistance)
            vals[isnan(vals)] = 0
            compare = lambda x: x > thresh
        else:
            raise Exception("Metric not recognized")

        hits = sum(map(compare, vals)) / float(len(self.sources))

        return hits

    def loadExampleS3(self, dataset=None):
        """
        Load an example data set from S3.

        Info on the included datasets can be found at the CodeNeuro data repository
        (http://datasets.codeneuro.org/). If called with None, will return
        list of available datasets.

        Parameters
        ----------
        dataset : str
            Which dataset to load

        Returns
        -------
        data : a Data object (usually a Series or Images)
            The dataset as one of Thunder's data objects

        params : dict
            Parameters or metadata for dataset
        """
        DATASETS = {
            'ahrens.lab/direction.selectivity': 'ahrens.lab/direction.selectivity/1/',
            'ahrens.lab/optomotor.response': 'ahrens.lab/optomotor.response/1/',
            'svoboda.lab/tactile.navigation': 'svoboda.lab/tactile.navigation/1/'
        }

        if dataset is None:
            return DATASETS.keys()

        if 'local' in self._sc.master:
            raise Exception("Must be running on an EC2 cluster to load this example data set")

        checkParams(dataset, DATASETS.keys())

        basePath = 's3n://neuro.datasets/'
        dataPath = DATASETS[dataset]

        data = self.loadSeries(basePath + dataPath + 'series')
        params = self.loadParams(basePath + dataPath + 'params/covariates.json')

        return data, params