def histogram(data, nbins, range=None):
"""
Create a histogram.
Comes from Konrad Hinsen: Scientific Python
@param data: data list or array
@type data: [any]
@param nbins: number of bins
@type nbins: int
@param range: data range to create histogram from (min val, max val)
@type range: (float, float) OR None
@return: array (2 x len(data) ) with start of bin and witdh of bin.
@rtype: array
"""
data = N0.array(data, N0.Float)
if range is None:
min = N0.minimum.reduce(data)
max = N0.maximum.reduce(data)
else:
min, max = range
data = N0.repeat(
data,
N0.logical_and(N0.less_equal(data, max),
N0.greater_equal(data, min)))
bin_width = (max - min) / nbins
data = N0.floor((data - min) / bin_width).astype(N0.Int)
histo = N0.add.reduce(N0.equal(N0.arange(nbins)[:, N0.NewAxis], data), -1)
histo[-1] = histo[-1] + N0.add.reduce(N0.equal(nbins, data))
bins = min + bin_width * (N0.arange(nbins) + 0.5)
return N0.transpose(N0.array([bins, histo]))
def filterRange(self, key, vLow, vHigh):
"""
Get indices of items where vLow <= item[ key ] <= vHigh.
@param key: item attribute
@type key: any
@param vLow: lower bound
@type vLow: any
@param vHigh: upper bound
@type vHigh: any
@return: array of int
@rtype: array
"""
vLst = self.valuesOf(key)
maskL = N0.greater_equal(vLst, vLow)
maskH = N0.less_equal(vLst, vHigh)
return N0.nonzero(maskL * maskH)
def confidenceInterval(self, level):
"""
confidenceInterval(self, level)
@param level: confidence level (e.g. 0.68 for stdev interval)
@type level: float
@return: start and end of the confidence interval
containing |level|*100 % of the probability
@rtype: float, float
"""
order = N0.argsort(self.p).tolist()
cumulative = N0.add.accumulate(N0.take(self.p, order)) * self.delta_x
ind = N0.nonzero(N0.greater_equal(cumulative, 1. - level))
sub_set = order[ind[0]:]
intervals = self.__find_intervals(sub_set)
boundaries = [(self.x[i[0]], self.x[i[-1]]) for i in intervals]
return tuple(boundaries)
def filterRange( self, infoKey, vLow, vHigh ):
"""
Get indices of Complexes where vLow <= c.info[ infoKey ] <= vHigh.
Use::
filterRange( str_infoKey, vLow, vHigh )
@param infoKey: key for info dict
@type infoKey: str
@param vLow: upper value limit
@type vLow: float
@param vHigh: lower value limit
@type vHigh: float
@return: array of int
@rtype: [int]
"""
vLst = self.valuesOf( infoKey )
maskL = N0.greater_equal( vLst, vLow )
maskH = N0.less_equal( vLst, vHigh )
return N0.nonzero( maskL * maskH )
def findConfidenceInterval(self, x):
"""
findConfidenceInterval(self, x)
Find the smallest possible density interval that still includes x.
@param x: value
@type x: float
@return: convidence level, interval start and end
@rtype: float, (float,float)
"""
closest = N0.argmin(abs(self.x - x))
ind = N0.nonzero(N0.greater_equal(self.p, self.p[closest])).tolist()
intervals = self.__find_intervals(ind)
## lens = N0.array([len(i) for i in intervals])
levels = [N0.sum(N0.take(self.p, i)) for i in intervals]
level = N0.sum(levels) * self.delta_x
boundaries = [(self.x[i[0]], self.x[i[-1]]) for i in intervals]
return level, tuple(boundaries)