|
OpenMPCD
|
Public Member Functions | |
| def | __init__ (self) |
| def | addDatum (self, datum) |
| def | merge (self, rhs) |
| def | getSampleSize (self) |
| def | getSampleMean (self) |
| def | getMaximumBlockSize (self) |
| def | getMaximumBlockID (self) |
| def | hasBlockVariance (self, blockID) |
| def | getBlockVariance (self, blockID) |
| def | getBlockStandardDeviation (self, blockID) |
| def | getSampleStandardDeviation (self) |
| def | getBlockStandardErrorOfTheMean (self, blockID) |
| def | getEstimatedStandardDeviationOfBlockStandardErrorOfTheMean (self, blockID) |
| def | getOptimalBlockIDForStandardErrorOfTheMean (self) |
| def | optimalStandardErrorOfTheMeanEstimateIsReliable (self) |
| def | getOptimalStandardErrorOfTheMean (self) |
| def | serializeToString (self) |
| def | unserializeFromString (self, state) |
| def | getMPLAxes (self, showEstimatedStandardDeviation=True) |
| def | __eq__ (self, rhs) |
| def | __ne__ (self, rhs) |
| def | __repr__ (self) |
Computes sample means and their errors for (possibly) serially correlated data. The algorithm used is called "Dynamic Distributable Decorrelation Algorithm" (DDDA), and is described in "Efficient algorithm for “on-the-fly” error analysis of local or distributed serially correlated data" by David R. Kent IV, Richard P. Muller, Amos G. Anderson, William A. Goddard III, and Michael T. Feldmann, Journal of Computational Chemistry, November 2007, Vol. 28, No. 14, pp. 2309-2316, DOI: 10.1002/jcc.20746, which in turn is partly based on the article "Error estimates on averages of correlated data" by H. Flyvbjerg and H. G. Petersen, The Journal of Chemical Physics, July 1989, Vol. 91, No. 1, pp. 461-466 DOI: 10.1063/1.457480
Definition at line 29 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.__init__ | ( | self | ) |
The constructor.
Definition at line 35 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.__eq__ | ( | self, | |
| rhs | |||
| ) |
Returns whether this instance and `rhs` are equivalent, i.e. whether the
two instances behave as if they had been supplied the same data.
@throw TypeError
Throws if `rhs` is not of type `OnTheFlyStatisticsDDDA`.
@param[in] rhs
The `OnTheFlyStatisticsDDDA` instance to compare to.
Definition at line 559 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.__ne__ | ( | self, | |
| rhs | |||
| ) |
Returns the negation of `self == rhs`.
@throw TypeError
Throws if `rhs` is not of type `OnTheFlyStatisticsDDDA`.
@param[in] rhs
The `OnTheFlyStatisticsDDDA` instance to compare to.
Definition at line 577 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.__repr__ | ( | self | ) |
Returns a string (type `str`) representation of this instance.
Definition at line 586 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.addDatum | ( | self, | |
| datum | |||
| ) |
Adds a datum to the sample.
It is assumed that the "time" intervals between subsequently added data
are constant; here, "time" may, for example, refer to Molecular Dynamics
or Monte Carlo steps.
Definition at line 51 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.getBlockStandardDeviation | ( | self, | |
| blockID | |||
| ) |
Returns the sample standard deviation in the block with the given
`blockID`.
@throw TypeError
Throws if `blockID` is not of type `int`.
@throw ValueError
Throws if `blockID` is out of range.
@throw RuntimeError
Throws if `not self.hasBlockVariance(blockID)`.
@param[in] blockID
The block ID, which must be an integer in the range
[0, `getMaximumBlockID()`].
Definition at line 237 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.getBlockStandardErrorOfTheMean | ( | self, | |
| blockID | |||
| ) |
Returns an estimate for the standard deviation of the standard error of
the mean for a given `blockID`.
@throw RuntimeError
Throws if `not self.hasBlockVariance(blockID)`.
@param[in] blockID
The block ID, which must be an integer in the range
[0, `getMaximumBlockID()`].
Definition at line 268 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.getBlockVariance | ( | self, | |
| blockID | |||
| ) |
Returns the sample variance in the block with the given `blockID`.
@throw RuntimeError
Throws if `not self.hasBlockVariance(blockID)`.
@param[in] blockID
The block ID, which must be an integer in the range
[0, `getMaximumBlockID()`].
Definition at line 207 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.getEstimatedStandardDeviationOfBlockStandardErrorOfTheMean | ( | self, | |
| blockID | |||
| ) |
Returns an estimate for the standard deviation of the standard error of
the mean for a given `blockID`.
The returned estimate corresponds to Eq. (28) in
"Error estimates on averages of correlated data"
by H. Flyvbjerg and H. G. Petersen,
The Journal of Chemical Physics, July 1989, Vol. 91, No. 1, pp. 461-466
DOI: 10.1063/1.457480
@throw RuntimeError
Throws if `not self.hasBlockVariance(blockID)`.
@param[in] blockID
The block ID, which must be an integer in the range
[0, `getMaximumBlockID()`].
Definition at line 301 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.getMaximumBlockID | ( | self | ) |
Returns the ID of the largest block size created so far.
Definition at line 171 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.getMaximumBlockSize | ( | self | ) |
Returns the largest block size for which there is at least one data
point.
If no values have been added so far, `Exception` is raised.
Definition at line 159 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.getMPLAxes | ( | self, | |
showEstimatedStandardDeviation = True |
|||
| ) |
Returns an `matplotlib.axes.Axes` object that plots the estimated
standard error of the mean, and optionally its estimated standard
deviation, as a function of the base-2 logarithm of the block size.
@throw TypeError
Throws if any of the arguments have invalid types.
@param[in] showEstimatedStandardDeviation
Whether to show, for each data point, the estimated standard
deviation of the estimated standard error of the mean.
Must be a `bool` value.
Definition at line 510 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.getOptimalBlockIDForStandardErrorOfTheMean | ( | self | ) |
Returns the block ID corresponding to the optimal block size, in the
sense that the corresponding block provides the most accurate estimate
for the standard error of the mean.
If there is no variance in the data, `0` is returned.
The algorithm used is described in Section IV of the article
"Strategies for improving the efficiency of quantum Monte Carlo
calculations"
by R. M. Lee, G. J. Conduit, N. Nemec, P. López Ríos, and
N. D. Drummond,
Physical Review E, June 2011, Vol. 83, No. 6, pp. 066706
DOI: 10.1103/PhysRevE.83.066706
@throw RuntimeError
Throws if fewer than two data points have been supplied.
Definition at line 339 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.getOptimalStandardErrorOfTheMean | ( | self | ) |
Returns the best estimation of the true standard error of the mean of
the data, after decorrelation.
@see optimalStandardErrorOfTheMeanEstimateIsReliable
The algorithm used is described in Section IV of the article
"Strategies for improving the efficiency of quantum Monte Carlo
calculations"
by R. M. Lee, G. J. Conduit, N. Nemec, P. López Ríos, and
N. D. Drummond,
Physical Review E, June 2011, Vol. 83, No. 6, pp. 066706
DOI: 10.1103/PhysRevE.83.066706
@throw RuntimeError
Throws if fewer than two data points have been supplied.
Definition at line 413 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.getSampleMean | ( | self | ) |
Returns the mean of all the values added so far.
Since the mean of all values added is returned, and the sample size may
not be a power of 2, statistics with different blocking length may
not incorporate the same amount of information. This may lead to
difficulties when using the error estimates of statistics of different
block lengths to estimate the error in the entire, possibly correlated
data set, since the statistics of different blocking lengths do not
necessarily incorporate the same measurements.
If no values have been added so far, `Exception` is raised.
Definition at line 144 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.getSampleSize | ( | self | ) |
Returns the number of data points added so far.
Definition at line 125 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.getSampleStandardDeviation | ( | self | ) |
Returns the raw sample standard deviation, i.e. the sample standard
deviation in block `0`.
@throw RuntimeError
Throws if `not self.hasBlockVariance(0)`.
Definition at line 251 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.hasBlockVariance | ( | self, | |
| blockID | |||
| ) |
Returns whether the block with the given `blockID` has enough data to
compute a sample variance.
@param[in] blockID
The block ID, which must be an integer in the range
[0, `getMaximumBlockID()`].
Definition at line 185 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.merge | ( | self, | |
| rhs | |||
| ) |
Merges the information in `rhs` with this instance's.
Let \f$ x_1, x_2, \ldots, x_{N_1} \f$ be the data that have been
supplied to this instance prior to calling this function, with
\f$ N_1 \f$ being the sample size of this instance prior to calling this
function. Similarly, let \f$ y_1, y_2, \ldots, y_{N_2} \f$ be the data
supplied to `rhs` previously.
Then, after this function successfully returns, this instance's state is
approximately as if it had started empty, and then the data
\f$ x_1, x_2, \ldots, x_{N_1}, y_1, y_2, \ldots, y_{N_2} \f$
had been supplied. This is true to a high degree for the state of block
`0`; other blocks may have significantly different state due to the way
blocks are populated with data points. The implementation is equivalent
to the one named `Decorrelation.addition` in Appendix B of
@cite Kent2007.
The `rhs` instance is left unchanged (unless, of course, it is the same
object as this instance, which is allowed).
@throw TypeError
Throws if `rhs` is not of type `OnTheFlyStatisticsDDDA`.
@param[in] rhs
The instance to merge into this one. Must be an instance of
`OnTheFlyStatisticsDDDA`.
Definition at line 84 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.optimalStandardErrorOfTheMeanEstimateIsReliable | ( | self | ) |
Returns whether the sample is large enough for the estimate of the
standard error of the mean, as provided by the block indicated by
`getOptimalBlockIDForStandardErrorOfTheMean`, to be reliable.
The algorithm used is described in Section IV of the article
"Strategies for improving the efficiency of quantum Monte Carlo
calculations"
by R. M. Lee, G. J. Conduit, N. Nemec, P. López Ríos, and
N. D. Drummond,
Physical Review E, June 2011, Vol. 83, No. 6, pp. 066706
DOI: 10.1103/PhysRevE.83.066706
@throw RuntimeError
Throws if fewer than two data points have been supplied.
Definition at line 387 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.serializeToString | ( | self | ) |
Returns a `str` that contains the state of this instance.
@see unserializeFromString
Definition at line 426 of file OnTheFlyStatisticsDDDA.py.
| def MPCDAnalysis.OnTheFlyStatisticsDDDA.OnTheFlyStatisticsDDDA.unserializeFromString | ( | self, | |
| state | |||
| ) |
Discards the current state, and loads the state specified in the given
string instead.
@throw TypeError
Throws if `state` is of the wrong type.
@throw ValueError
Throws if `state` does not encode a valid state.
@param[in] state
The state to load. Must be a `str` created by
`serializeToString`.
Definition at line 456 of file OnTheFlyStatisticsDDDA.py.
1.8.17