ClearMap.Analysis.Tools package

Analysis and statistics tools not in standard python packages.

ClearMap.Analysis.Tools.Extrapolate module

Method to extend interpolation objects to constantly / linearly extrapolate.

extrap1d(x, y, interpolation='linear', exterpolation='constant')[source]

Interpolate on given values and extrapolate outside the given data

Parameters:
  • x (numpy.array) – x values of the data to interpolate
  • y (numpy.array) – y values of the data to interpolate
  • interpolation (Optional[str]) – interpolation method, see kind of scipy.interpolate.interp1d, default: “linear”
  • exterpolation (Optional[str]) – interpolation method, either “linear” or “constant”
Returns:

(function) – inter- and extra-polation function
extrap1dFromInterp1d(interpolator, exterpolation='constant')[source]

Extend interpolation function to extrapolate outside the given data

Parameters:
  • interpolator (function) – interpolating function, see e.g. scipy.interpolate.interp1d
  • exterpolation (Optional[str]) – interpolation method, either “linear” or “constant”
Returns:

(function) – inter- and extra-polation function

ClearMap.Analysis.Tools.MultipleComparisonCorrection module

Correction methods for multiple comparison tests

correctPValues(pvalues, method='BH')[source]

Corrects p-values for multiple testing using various methods

Parameters:
  • pvalues (array) – list of p values to be corrected
  • method (Optional[str]) – method to use: BH = FDR = Benjamini-Hochberg, B = FWER = Bonferoni

References

Notes

estimateQValues(pvalues, m=None, pi0=None, verbose=False, lowMemory=False)[source]

Estimates q-values from p-values

Parameters:
  • pvalues (array) – list of p-values
  • m (int or None) – number of tests. If None, m = pvalues.size
  • pi0 (float or None) – estimate of m_0 / m which is the (true null / total tests) ratio, if None estimation via cubic spline.
  • verbose (bool) – print info during execution
  • lowMemory (bool) – if true use low memory version

Notes

  • The q-value of a particular feature can be described as the expected proportion of false positives among all features as or more extreme than the observed one
  • The estimated q-values are increasing in the same order as the p-values

References

ClearMap.Analysis.Tools.StatisticalTests module

Some statistics tests not in standard python packages

testCramerVonMises2Sample(x, y)[source]

Computes the Cramer von Mises two sample test.

This is a two-sided test for the null hypothesis that 2 independent samples are drawn from the same continuous distribution.

Parameters:
  • x, y (sequence of 1-D ndarrays) – two arrays of sample observations
  • assumed to be drawn from a continuous distribution, sample sizes
  • can be different
Returns:

(float, float) – T statistic, two-tailed p-value

References