Python msmbuilder.MSMLib类代码示例

    def test(self):

        num_macro = 5

        TC = get("PCCA_ref/tProb.mtx")
        A = get("PCCA_ref/Assignments.Fixed.h5")['arr_0']
        print A

        macro_map, macro_assign = PCCA.run_pcca(num_macro, A, TC)
        r_macro_map = get("PCCA_ref/MacroMapping.dat")

        macro_map = macro_map.astype(np.int)
        r_macro_map = r_macro_map.astype(np.int)

        # The order of macrostates might be different between the reference and
        # new lumping. We therefore find a permutation to match them.
        permutation_mapping = np.zeros(macro_assign.max() + 1, 'int')
        for i in range(num_macro):
            j = np.where(macro_map == i)[0][0]
            permutation_mapping[i] = r_macro_map[j]

        macro_map_permuted = permutation_mapping[macro_map]
        MSMLib.apply_mapping_to_assignments(macro_assign, permutation_mapping)

        r_macro_assign = get("PCCA_ref/MacroAssignments.h5")['arr_0']

        eq(macro_map_permuted, r_macro_map)
        eq(macro_assign, r_macro_assign)

def test_estimate_rate_matrix_1():
    np.random.seed(42)
    assignments = np.random.randint(2, size=(10, 10))
    counts = MSMLib.get_count_matrix_from_assignments(assignments)
    K = MSMLib.estimate_rate_matrix(counts, assignments).todense()

    correct = np.matrix([[-40.40909091, 0.5], [0.33928571, -50.55357143]])
    eq(K, correct)

def test_apply_mapping_to_assignments_1():
    l = 100
    assignments = np.random.randint(l, size=(10, 10))
    mapping = np.ones(l)

    MSMLib.apply_mapping_to_assignments(assignments, mapping)

    eq(assignments, np.ones((10, 10)))

    def test_1(self):

        C = MSMLib.get_count_matrix_from_assignments(self.assignments, 2)
        rc, t, p, m = MSMLib.build_msm(C, symmetrize="MLE", ergodic_trimming=True)

        eq(rc.todense(), np.matrix([[6.46159184, 4.61535527], [4.61535527, 2.30769762]]), decimal=4)
        eq(t.todense(), np.matrix([[0.58333689, 0.41666311], [0.66666474, 0.33333526]]), decimal=4)
        eq(p, np.array([0.61538595, 0.38461405]), decimal=5)
        eq(m, np.array([0, 1]))

def test_get_count_matrix_from_assignments_3():
    np.random.seed(42)
    assignments = np.random.randint(3, size=(10, 10))

    val = MSMLib.get_count_matrix_from_assignments(assignments, lag_time=2, sliding_window=False).todense()
    eq(val, np.matrix([[5.0, 3.0, 4.0], [2.0, 12.0, 3.0], [4.0, 3.0, 4.0]]))

    val = MSMLib.get_count_matrix_from_assignments(assignments, lag_time=2, sliding_window=True).todense()
    eq(val, np.matrix([[8.0, 9.0, 11.0], [5.0, 18.0, 6.0], [11.0, 5.0, 7.0]]))

def run_pcca_plus(num_macrostates, assignments, tProb, flux_cutoff=0.0,
    objective_function="crispness",do_minimization=True):
    
    logger.info("Running PCCA+...")
    A, chi, vr, MAP = lumping.pcca_plus(tProb, num_macrostates, flux_cutoff=flux_cutoff,
        do_minimization=do_minimization, objective_function=objective_function)

    MSMLib.apply_mapping_to_assignments(assignments, MAP)    

    return chi, A, MAP, assignments

def construct_counts_matrix(assignments):
    """Build and return a counts matrix from assignments.
    
    Symmetrize either with transpose or MLE based on the value of the
    self.symmetrize variable
        
    Also modifies the assignments file that you pass it to reflect ergodic
    trimming
    
    Parameters
    ----------
    assignments : np.ndarray
        2D array of MSMBuilder assignments
    
    Returns
    -------
    counts : scipy.sparse.csr_matrix
        transition counts
    
    """
        
    n_states  = np.max(assignments.flatten()) + 1
    raw_counts = MSMLib.get_count_matrix_from_assignments(assignments, n_states,
                                               lag_time=Project().lagtime,
                                               sliding_window=True)
        
    ergodic_counts = None
    if Project().trim:
        raise NotImplementedError(('Trimming is not yet supported because '
                                   'we need to keep track of the mapping from trimmed to '
                                   ' untrimmed states for joint clustering to be right'))
        try:
            ergodic_counts, mapping = MSMLib.ergodic_trim(raw_counts)
            MSMLib.apply_mapping_to_assignments(assignments, mapping)
            counts = ergodic_counts
        except Exception as e:
            logger.warning("MSMLib.ergodic_trim failed with message '{0}'".format(e))

    else:
        logger.info("Ignoring ergodic trimming")
        counts = raw_counts
        
    if Project().symmetrize == 'transpose':
        logger.debug('Transpose symmetrizing')
        counts = counts + counts.T
    elif Project().symmetrize == 'mle':
        logger.debug('MLE symmetrizing')
        counts = MSMLib.mle_reversible_count_matrix(counts)
    elif Project().symmetrize == 'none' or (not Project().symmetrize):
        logger.debug('Skipping symmetrization')
    else:
        raise ValueError("Could not understand symmetrization method: %s" % Project().symmetrize)
        
    return counts

def test_trim_states():
    
    # run the (just tested) ergodic trim
    counts = scipy.sparse.csr_matrix(np.matrix('2 1 0; 1 2 0; 0 0 1'))
    trimmed, mapping = MSMLib.ergodic_trim(counts)
    
    # now try the segmented method
    states_to_trim = MSMLib.ergodic_trim_indices(counts)
    trimmed_counts = MSMLib.trim_states(states_to_trim, counts, assignments=None)
    
    eq(trimmed.todense(), trimmed_counts.todense())

def run_pcca(num_macrostates, assignments, tProb):
    logger.info("Running PCCA...")
    if len(np.unique(assignments[np.where(assignments != -1)])) != tProb.shape[0]:
        raise ValueError('Different number of states in assignments and tProb!')
    MAP = lumping.PCCA(tProb, num_macrostates)

    # MAP the new assignments and save, make sure don't
    # mess up negaitve one's (ie where don't have data)
    MSMLib.apply_mapping_to_assignments(assignments, MAP)

    return MAP, assignments

def test_get_count_matrix_from_assignments_3():
    np.random.seed(42)
    assignments = np.random.randint(3, size=(10,10))

    val = MSMLib.get_count_matrix_from_assignments(assignments, lag_time=2, sliding_window=False).todense()
    npt.assert_equal(val, np.matrix([[ 5.,   3.,   4.],
                         [  2.,  12.,   3.],
                         [ 4.,   3.,   4.]]))
                         
    val = MSMLib.get_count_matrix_from_assignments(assignments, lag_time=2, sliding_window=True).todense()
    npt.assert_equal(val, np.matrix([[8.,   9.,  11.],
                          [ 5.,  18.,   6.],
                          [ 11.,   5.,   7.]]))                 

    def compare_kyle_to_lutz(self, raw_counts):
        """Kyle wrote the most recent MLE code.  We compare to the previous
        code that was written by Lutz.
        """

        counts = MSMLib.ergodic_trim(raw_counts)[0]

        x_kyle = MSMLib.mle_reversible_count_matrix(counts)
        x_kyle /= x_kyle.sum()

        x_lutz = MSMLib.__mle_reversible_count_matrix_lutz__(counts)
        x_lutz /= x_lutz.sum()

        eq(x_kyle.toarray(), x_lutz.toarray())

def test_apply_mapping_to_assignments_2():
    "preseve the -1s"

    l = 100
    assignments = np.random.randint(l, size=(10, 10))
    assignments[0, 0] = -1
    mapping = np.ones(l)

    correct = np.ones((10, 10))
    correct[0, 0] = -1

    MSMLib.apply_mapping_to_assignments(assignments, mapping)

    eq(assignments, correct)

def test_estimate_rate_matrix_2():
    np.random.seed(42)
    counts_dense = np.random.randint(100, size=(4, 4))
    counts_sparse = scipy.sparse.csr_matrix(counts_dense)

    t_mat_dense = MSMLib.estimate_transition_matrix(counts_dense)
    t_mat_sparse = MSMLib.estimate_transition_matrix(counts_sparse)

    correct = np.array([[0.22368421, 0.40350877, 0.06140351, 0.31140351],
                        [0.24193548, 0.08064516, 0.33064516, 0.34677419],
                        [0.22155689, 0.22155689, 0.26047904, 0.29640719],
                        [0.23469388, 0.02040816, 0.21428571, 0.53061224]])

    eq(t_mat_dense, correct)
    eq(t_mat_dense, np.array(t_mat_sparse.todense()))

def test_estimate_transition_matrix_1():
    np.random.seed(42)
    count_matrix = np.array([[6, 3, 7], [4, 6, 9], [2, 6, 7]])
    t = MSMLib.estimate_transition_matrix(count_matrix)
    eq(t, np.array([[0.375, 0.1875, 0.4375],
                    [0.21052632, 0.31578947, 0.47368421],
                    [0.13333333, 0.4, 0.46666667]]))

def run_pcca(num_macrostates, assignments, tProb, output_dir):
    MacroAssignmentsFn = os.path.join(output_dir, "MacroAssignments.h5")
    MacroMapFn = os.path.join(output_dir, "MacroMapping.dat")
    arglib.die_if_path_exists([MacroAssignmentsFn, MacroMapFn])

    logger.info("Running PCCA...")
    MAP = lumping.PCCA(tProb, num_macrostates)

    # MAP the new assignments and save, make sure don't
    # mess up negaitve one's (ie where don't have data)
    MSMLib.apply_mapping_to_assignments(assignments, MAP)

    np.savetxt(MacroMapFn, MAP, "%d")
    msmbuilder.io.saveh(MacroAssignmentsFn, assignments)
    
    logger.info("Saved output to: %s, %s", MacroAssignmentsFn, MacroMapFn)