Python numpy.putmask函数代码示例

def nankurt(values, axis=None, skipna=True):

    mask = isnull(values)
    if not is_floating_dtype(values):
        values = values.astype('f8')

    count = _get_counts(mask, axis)

    if skipna:
        values = values.copy()
        np.putmask(values, mask, 0)

    A = values.sum(axis) / count
    B = (values ** 2).sum(axis) / count - A ** 2
    C = (values ** 3).sum(axis) / count - A ** 3 - 3 * A * B
    D = (values ** 4).sum(axis) / count - A ** 4 - 6 * B * A * A - 4 * C * A

    B = _zero_out_fperr(B)
    D = _zero_out_fperr(D)

    if not isinstance(B, np.ndarray):
        # if B is a scalar, check these corner cases first before doing division
        if count < 4:
            return np.nan
        if B == 0:
            return 0

    result = (((count * count - 1.) * D / (B * B) - 3 * ((count - 1.) ** 2)) /
              ((count - 2.) * (count - 3.)))

    if isinstance(result, np.ndarray):
        result = np.where(B == 0, 0, result)
        result[count < 4] = np.nan

    return result

def nanskew(values, axis=None, skipna=True):
    if not isinstance(values.dtype.type, np.floating):
        values = values.astype('f8')

    mask = isnull(values)
    count = _get_counts(mask, axis)

    if skipna:
        values = values.copy()
        np.putmask(values, mask, 0)

    A = values.sum(axis) / count
    B = (values ** 2).sum(axis) / count - A ** 2
    C = (values ** 3).sum(axis) / count - A ** 3 - 3 * A * B

    # floating point error
    B = _zero_out_fperr(B)
    C = _zero_out_fperr(C)

    result = ((np.sqrt((count ** 2 - count)) * C) /
              ((count - 2) * np.sqrt(B) ** 3))

    if isinstance(result, np.ndarray):
        result = np.where(B == 0, 0, result)
        result[count < 3] = np.nan
        return result
    else:
        result = 0 if B == 0 else result
        if count < 3:
            return np.nan
        return result

def fit_fn(distr, xvals, alpha, thresh):
    """
    The fitted function normalized to 1 above threshold

    To normalize to a given total count multiply by the count.

    Parameters
    ----------
    xvals : sequence of floats
        Values where the function is to be evaluated
    alpha : float
        The fitted parameter
    thresh : float
        Threshold value applied to fitted values

    Returns
    -------
    fit : array of floats
        Fitted function at the requested xvals
    """
    xvals = numpy.array(xvals)
    fit = fitfn_dict[distr](xvals, alpha, thresh)
    # set fitted values below threshold to 0
    numpy.putmask(fit, xvals < thresh, 0.)
    return fit

    def _reindex_index(self, index, method, copy, level, fill_value=np.nan,
                       limit=None):
        if level is not None:
            raise Exception('Reindex by level not supported for sparse')

        if self.index.equals(index):
            if copy:
                return self.copy()
            else:
                return self

        if len(self.index) == 0:
            return SparseDataFrame(index=index, columns=self.columns)

        indexer = self.index.get_indexer(index, method, limit=limit)
        indexer = com._ensure_platform_int(indexer)
        mask = indexer == -1
        need_mask = mask.any()

        new_series = {}
        for col, series in self.iteritems():
            values = series.values
            new = values.take(indexer)

            if need_mask:
                np.putmask(new, mask, fill_value)

            new_series[col] = new

        return SparseDataFrame(new_series, index=index, columns=self.columns,
                               default_fill_value=self.default_fill_value)

    def cummin(self, axis=None, skipna=True):
        """
        Return DataFrame of cumulative min over requested axis.

        Parameters
        ----------
        axis : {0, 1}
            0 for row-wise, 1 for column-wise
        skipna : boolean, default True
            Exclude NA/null values. If an entire row/column is NA, the result
            will be NA

        Returns
        -------
        y : DataFrame
        """
        if axis is None:
            axis = self._default_stat_axis
        else:
            axis = self._get_axis_number(axis)

        y = self.values.copy()
        if not issubclass(y.dtype.type, np.integer):
            mask = np.isnan(self.values)

            if skipna:
                np.putmask(y, mask, np.inf)

            result = np.minimum.accumulate(y, axis)

            if skipna:
                np.putmask(result, mask, np.nan)
        else:
            result = np.minimum.accumulate(y,axis)
        return self._wrap_array(result, self.axes, copy=False)

def factorize(values, sort=False, order=None, na_sentinel=-1):
    """
    Encode input values as an enumerated type or categorical variable

    Parameters
    ----------
    values : sequence
    sort :
    order :

    Returns
    -------
    """
    hash_klass, values = _get_hash_table_and_cast(values)

    uniques = []
    table = hash_klass(len(values))
    labels, counts = table.get_labels(values, uniques, 0, na_sentinel)

    uniques = com._asarray_tuplesafe(uniques)
    if sort and len(counts) > 0:
        sorter = uniques.argsort()
        reverse_indexer = np.empty(len(sorter), dtype=np.int32)
        reverse_indexer.put(sorter, np.arange(len(sorter)))

        mask = labels < 0
        labels = reverse_indexer.take(labels)
        np.putmask(labels, mask, -1)

        uniques = uniques.take(sorter)
        counts = counts.take(sorter)

    return labels, uniques, counts

def _map(f, arr, na_mask=False, na_value=np.nan, dtype=object):
    from pandas.core.series import Series

    if not len(arr):
        return np.ndarray(0, dtype=dtype)

    if isinstance(arr, Series):
        arr = arr.values
    if not isinstance(arr, np.ndarray):
        arr = np.asarray(arr, dtype=object)
    if na_mask:
        mask = isnull(arr)
        try:
            result = lib.map_infer_mask(arr, f, mask.view(np.uint8))
        except (TypeError, AttributeError):
            def g(x):
                try:
                    return f(x)
                except (TypeError, AttributeError):
                    return na_value
            return _map(g, arr, dtype=dtype)
        if na_value is not np.nan:
            np.putmask(result, mask, na_value)
            if result.dtype == object:
                result = lib.maybe_convert_objects(result)
        return result
    else:
        return lib.map_infer(arr, f)

def usefullness(data, targetClass, otherClass = None, **args) :
    '''A feature score for discrete data
    optional arguments:
    threshold
    fraction
    '''

    if 'threshold' in args :
        threshold = args['threshold']
    else :
        threshold = 5
    if 'fraction' in args :
        fraction = args['fraction']
    else :
        fraction = 0.0

    Y, targetClassSize, otherClassSize, otherI, feature = parseArgs(
        data, targetClass, otherClass, **args)

    threshold = max(threshold, fraction * float(targetClassSize))        

    s1 = featureCount(data, targetClass=targetClass, Y=Y, feature=feature)

    s2 = featureCount(data, I = otherI, Y=Y,
                      feature=feature) / float(otherClassSize)

    s2 = 1 - s2

    numpy.putmask(s2, numpy.less(s1, threshold), 0.0)

    return s2

def golub(data, targetClass, otherClass, **args) :
    '''The Golub feature score:
    s = (mu1 - mu2) / sqrt(sigma1^2 + sigma2^2)
    '''

    if 'Y' in args :
        Y = args['Y']
        targetClassSize = numpy.sum(numpy.equal(Y, targetClass))
        otherClassSize = numpy.sum(numpy.equal(Y, otherClass))        
    else :
        Y = None
        targetClassSize = data.labels.classSize[targetClass] 
        otherClassSize = data.labels.classSize[otherClass]
    
    m1 = numpy.array(featureMean(data, targetClass, Y))
    m2 = numpy.array(featureMean(data, otherClass, Y))
    s1 = numpy.array(featureStd(data, targetClass, Y))
    s2 = numpy.array(featureStd(data, otherClass, Y))

    s = numpy.sqrt(s1**2 + s2**2)
    m = (m1 + m2) / 2.0

    # perfect features will have s[i] = 0, so need to take care of that:
    numpy.putmask(s, numpy.equal(s, 0), m)
    # features that are zero will still have s[i] = 0 so :
    numpy.putmask(s, numpy.equal(s, 0) ,1)
    
    g = (m1 - m2) / s
    
    return g

def get_closure_phase(infile='L401323_SB349_uv.dppp.MS',\
                 triangle = ['TS001','DE601HBA','DE605HBA']):
    a=inspect.stack()
    stacklevel=0
    for k in range(len(a)):
        if (string.find(a[k][1],'ipython console')>0):
            stacklevel=k
    myf=sys._getframe(stacklevel).f_globals
    myf['__last_task']='mytask'
    myf['taskname']='mytask'
    tb=myf['tb']
    oroot = infile.split('uv')[0]
    for lfile in np.sort(glob.glob(oroot+'*ms')):
        os.system('ms2uvfits in='+lfile+' out='+lfile.replace('ms','fits')+' writesyscal=F')
        if lfile == infile:
            continue
        tb.open(lfile+'/ANTENNA')
        names = tb.getcol('NAME')
        trnum = []
        for itr in range(3):
            trnum.append(np.argwhere(names==triangle[itr])[0][0])
        tb.close()
        trnum.sort()
        tb.open(lfile)
        ant1 = tb.getcol('ANTENNA1')
        ant2 = tb.getcol('ANTENNA2')
        data = tb.getcol('DATA')
        ph12 = +np.angle(data[0,0,(ant1==trnum[0])&(ant2==trnum[1])])
        ph23 = +np.angle(data[0,0,(ant1==trnum[1])&(ant2==trnum[2])])
        ph31 = -np.angle(data[0,0,(ant1==trnum[0])&(ant2==trnum[2])])
        clph = ph12+ph23+ph31
        np.putmask(clph,clph>np.pi,clph-2.*np.pi)
        np.putmask(clph,clph<-np.pi,clph+2.*np.pi)
#        np.savetxt(lfile.replace('ms','txt'),np.unwrap(clph))
        np.savetxt(lfile.replace('ms','txt'),clph)

    def _reindex_index(self, index, method, copy):
        if self.index.equals(index):
            if copy:
                return self.copy()
            else:
                return self

        if len(self.index) == 0:
            return SparseDataFrame(index=index, columns=self.columns)

        indexer = self.index.get_indexer(index, method)
        mask = indexer == -1
        need_mask = mask.any()

        new_series = {}
        for col, series in self.iteritems():
            values = series.values
            new = values.take(indexer)

            if need_mask:
                np.putmask(new, mask, nan)

            new_series[col] = new

        return SparseDataFrame(new_series, index=index, columns=self.columns,
                               default_fill_value=self.default_fill_value)

def returns(prices, method='simple', periods=1, fill_method='pad', limit=None, freq=None):
    """
     compute the returns for the specified prices.
     method: [simple,compound,log], compound is log
    """
    if method not in ('simple', 'compound', 'log'):
        raise ValueError("Invalid method type. Valid values are ('simple', 'compound')")

    if method == 'simple':
        return prices.pct_change(periods=periods, fill_method=fill_method, limit=limit, freq=freq)
    else:
        if freq is not None:
            raise NotImplementedError("TODO: implement this logic if needed")

        if isinstance(prices, pd.Series):
            if fill_method is None:
                data = prices
            else:
                data = prices.fillna(method=fill_method, limit=limit)

            data = np.log(data / data.shift(periods=periods))
            mask = pd.isnull(prices.values)
            np.putmask(data.values, mask, np.nan)
            return data
        else:
            return pd.DataFrame(
                {name: returns(col, method, periods, fill_method, limit, freq) for name, col in prices.iteritems()},
                columns=prices.columns,
                index=prices.index)

    def map(self, arg):
        """
        Map values of Series using input correspondence (which can be
        a dict, Series, or function).

        Parameters
        ----------
        arg : function, dict, or Series

        Returns
        -------
        y : Series
            same index as caller
        """
        if isinstance(arg, (dict, Series)):
            if isinstance(arg, dict):
                arg = Series(arg)

            indexer, mask = tseries.getMergeVec(self, arg.index.indexMap)

            newValues = arg.view(np.ndarray).take(indexer)
            np.putmask(newValues, -mask, np.nan)

            newSer = Series(newValues, index=self.index)
            return newSer
        else:
            return Series([arg(x) for x in self], index=self.index)

def makeGridDomain(cLon, cLat, minLon, maxLon, minLat, maxLat, 
                   margin=2, resolution=0.01):
    """
    Generate a grid of the distance and angle of a grid of points
    surrounding a storm centre given the location of the storm.
    The grid margin and grid size can be set in configuration files.
    xMargin, yMargin and gridSize are in degrees


    """
    if (type(cLon)==list or type(cLat)==list or 
        type(cLon)==np.ndarray or type(cLat)==np.ndarray):
        raise TypeError, "Input values must be scalar values"
    gridSize = int(resolution * 1000)
    minLon_ = int(1000 * (minLon)) - int(1000 * margin)
    maxLon_ = int(1000 * (maxLon)) + int(1000 * margin) + 1
    minLat_ = int(1000 * (minLat)) - int(1000 * margin)
    maxLat_ = int(1000 * (maxLat)) + int(1000 * margin) + 1

    xGrid = np.array(np.arange(minLon_, maxLon_, gridSize), dtype=int)
    yGrid = np.array(np.arange(minLat_, maxLat_, gridSize), dtype=int)

    R = gridLatLonDist(cLon, cLat, xGrid / 1000., yGrid / 1000.)
    np.putmask(R, R==0, 1e-30)
    theta = np.pi / 2. - gridLatLonBear(cLon, cLat, 
                                        xGrid / 1000., yGrid / 1000.)
    return R, theta

def remapRaster(infile, out_file, lookup):
        '''remap raster values to those in lookup table'''
        inmap = gdal.Open(infile)
        rows = inmap.RasterYSize
        cols = inmap.RasterXSize
        map_arr = inmap.ReadAsArray()

        #remap values
        remap_dict = df.getDictfromCSV(lookup,'\t',1,0)
        remap_dict[0]=2000 #ag
        remap_dict[255]=32767 #nodata
        map_out = map_arr.astype(np.int16)
        print 'input map labels', np.unique(map_out)
        for r in remap_dict:
                print 'reclassifying', r, ': ', remap_dict[r]
                outval=int(remap_dict[r])
                temp=np.equal(map_out, int(r))
                np.putmask(map_out, temp, int(remap_dict[r]))
                temp=None
        print 'output map labels', np.unique(map_out)
        #output raster
        driver=inmap.GetDriver()
        outDs = driver.Create(out_file, cols, rows, 1, GDT_Int16)
        outDs.SetGeoTransform(inmap.GetGeoTransform())
        outDs.SetProjection(inmap.GetProjection())
        outband = outDs.GetRasterBand(1)

        outband.WriteArray(map_out, 0 ,0)
        outband.SetNoDataValue(32767)
        outband.FlushCache()