Python Project.load_from方法代码示例

# 需要导入模块: from msmbuilder import Project [as 别名]
# 或者: from msmbuilder.Project import load_from [as 别名]
 def test_a_ConvertDataToHDF(self):
     os.chdir(WorkingDir)
     shutil.copy(PDBFn,"./")
                 #def run(projectfn, PDBfn, InputDir, source, mingen, stride, rmsd_cutoff,  parallel='None'):
     ConvertDataToHDF.run(ProjectFn, PDBFn, TutorialDir+"/XTC", "file", 0, 1, None)
     P1 = Project.load_from(ProjectFn)
     
     r_P1 = Project.load_from(os.path.abspath(os.path.join('..', ReferenceDir, ProjectFn)))
     
     eq_(P1.n_trajs, r_P1.n_trajs)
     npt.assert_equal(P1.traj_lengths, r_P1.traj_lengths)
     eq_(os.path.basename(P1.traj_filename(0)), os.path.basename(r_P1.traj_filename(0)))

# 需要导入模块: from msmbuilder import Project [as 别名]
# 或者: from msmbuilder.Project import load_from [as 别名]
    def save(self):
        "Save the trajs as a n MSMBuilder project"
        
        traj_dir = pjoin(self.project_dir, 'Trajectories')
        if not os.path.exists(traj_dir):
            os.makedirs(traj_dir)

        t = Trajectory.load_trajectory_file(self.conf_filename)

        traj_paths = []
        for i, xyz in enumerate(self.trajectories):
            t['IndexList'] = None # bug in msmbuilder
            t['XYZList'] = xyz

            traj_paths.append(pjoin(traj_dir, 'trj%d.lh5' % i))
            t.save(traj_paths[-1])

        p = Project({'conf_filename': os.path.abspath(self.conf_filename),
            'traj_lengths': self.n_frames*np.ones(self.n_trajs),
            'traj_paths': [os.path.abspath(e) for e in traj_paths],
            'traj_converted_from': [[] for i in range(self.n_trajs)],
            'traj_errors': [None for i in range(self.n_trajs)],
            }, project_dir=self.project_dir, validate=True)
        p.save(pjoin(self.project_dir,'Project.yaml'))

        # just check again
        p = Project.load_from(pjoin(self.project_dir,'Project.yaml'))
        p._validate()
        assert np.all((p.load_traj(0)['XYZList'] - self.trajectories[0])**2 < 1e-6)

# 需要导入模块: from msmbuilder import Project [as 别名]
# 或者: from msmbuilder.Project import load_from [as 别名]
def main():
    global data2d
    global As
    # First I need to turn the assignments matrix into a 1D list of assignments
    sys.stdout = os.fdopen(sys.stdout.fileno(),'w',0)
    print "Reading in Assignments... from %s " % options.assFN
    As = io.loadh(options.assFN)['arr_0'].astype(int)
    print "Reading in data... from %s " % options.dataFN
    try: 
        f = io.loadh( options.dataFN )
        try:
            data2d = f['arr_0']
        except:
            data2d = f['Data']
    except:
        data = load(options.dataFN)
        proj = Project.load_from( options.projFN )
        data2d = msmTools.reshapeRawData( data, proj )

    print "Calculating averages for:"

    pool = mp.Pool(options.procs)
    clusters = range( As.max() + 1)
    result = pool.map_async(calcAvg,clusters[:])
    result.wait()
    sol = result.get()
    sol = array(sol)
    savetxt(options.outFN, sol)

    return

# 需要导入模块: from msmbuilder import Project [as 别名]
# 或者: from msmbuilder.Project import load_from [as 别名]
def main():
    """Parse command line inputs, load up files, and build a movie."""

    parser = arglib.ArgumentParser(description="""
Create an MSM movie by sampling a sequence of states and sampling a 
random conformation from each state in the sequence.  
""")
    parser.add_argument('project')
    parser.add_argument('assignments', default='Data/Assignments.Fixed.h5')
    parser.add_argument('tprob', default='Data/tProb.mtx')
    parser.add_argument('num_steps')
    parser.add_argument('starting_state', type=int, help='''Which state to start trajectory from.''')
    parser.add_argument('output', default='sample_traj.pdb', help="""The filename of your output trajectory.  The filetype suffix will be used to select the output file format.""")
    args = parser.parse_args()

    try:
        assignments = io.loadh(args.assignments, 'arr_0')
    except KeyError:
        assignments = io.loadh(args.assignments, 'Data')
    
    num_steps = int(args.num_steps)
    starting_state = int(args.starting_state)
    
    project = Project.load_from(args.project)    
    T = scipy.io.mmread(args.tprob).tocsr()

    state_traj = msm_analysis.sample(T, starting_state, num_steps)
    sampled_traj = project.get_random_confs_from_states(assignments, state_traj, 1)
    traj = sampled_traj[0]
    traj["XYZList"] = np.array([t["XYZList"][0] for t in sampled_traj])
    traj.save(args.output)

# 需要导入模块: from msmbuilder import Project [as 别名]
# 或者: from msmbuilder.Project import load_from [as 别名]
def run(projectfn, conf_filename, input_dir, source, min_length, stride, rmsd_cutoff, atom_indices, iext):

    # check if we are doing an update or a fresh run
    # if os.path.exists(projectfn):
    #     logger.info("Found project info file encoding previous work, running in update mode...")
    #     update = True
    # else:
    #     update = False
    #
    # logger.info("Looking for %s style data in %s", source, input_dir)
    # if update:
    #     raise NotImplementedError("Ack! Update mode is not yet ready yet.")

    # if the source is fah, we'll use some special FaH specific loading functions
    # to (1) try to recover in case of errors and (2) load the specific directory
    # hierarchy of FaH (RUN/CLONE/GEN/frame.xtc)
    if os.path.exists(projectfn):
        project = Project.load_from(projectfn)
        logger.warn(
            "%s exists, will modify it and update the trajectories in %s",
            projectfn, '/'.join(project._traj_paths[0].split('/')[:-1]))
    else:
        project = None

    if source.startswith('file'):
        pb = ProjectBuilder(
            input_dir, input_traj_ext=iext, conf_filename=conf_filename,
            stride=stride, project=project, atom_indices=atom_indices)
    elif source == 'fah':
        pb = FahProjectBuilder(
            input_dir, input_traj_ext=iext, conf_filename=conf_filename,
            stride=stride, project=project, atom_indices=atom_indices)
    else:
        raise ValueError("Invalid argument for source: %s" % source)

    # check that trajectories to not go farther than a certain RMSD
    # from the PDB. Useful to check for blowing up or other numerical
    # instabilities
    if rmsd_cutoff is not None:
        # TODO: this is going to use ALL of the atom_indices, including hydrogen. This is
        # probably not the desired functionality
        # KAB: Apparently needed to use correctly subsetted atom_indices here to avoid an error
        validator = validators.RMSDExplosionValidator(
            conf_filename, max_rmsd=rmsd_cutoff, atom_indices=atom_indices)
        pb.add_validator(validator)

    # Only accept trajectories with more snapshots than min_length.
    if min_length > 0:
        validator = validators.MinLengthValidator(min_length)
        pb.add_validator(validator)

    # everyone wants to be centered
    pb.add_validator(validators.TrajCenterer())

    pb.get_project().save(projectfn)
    assert os.path.exists(projectfn), '%s does not exist' % projectfn
    logger.info("Finished data conversion successfully.")
    logger.info("Generated: %s, Trajectories/", projectfn)

    return

# 需要导入模块: from msmbuilder import Project [as 别名]
# 或者: from msmbuilder.Project import load_from [as 别名]
def main():
    """Parse command line inputs, load up files, then call run() and save() to do
    the real work"""
    parser.add_argument('output_dir', default='PDBs')
    args = parser.parse_args()

    # load...
    # project
    project = Project.load_from(args.project)

    # assignments
    try:
        assignments = io.loadh(args.assignments, 'arr_0')
    except KeyError:
        assignments = io.loadh(args.assignments, 'Data')

    # states
    if -1 in args.states:
        states = np.unique(assigments[np.where(assignments != -1)])
        logger.info('Yanking from all %d states', len(states))
    else:
        # ensure that the states are sorted, and that they're unique -- you
        # can only request each state once
        states = np.unique(args.states)
        logger.info("Yanking from the following states: %s", states)

    # extract the conformations using np.random for the randomness
    confs_by_state = project.get_random_confs_from_states(
        assignments, states=states, num_confs=args.conformations_per_state,
        replacement=args.replacement)

    # save the conformations to disk, in the requested style
    save(confs_by_state=confs_by_state, states=states, style=args.style,
         format=args.format, outdir=args.output_dir)

# 需要导入模块: from msmbuilder import Project [as 别名]
# 或者: from msmbuilder.Project import load_from [as 别名]
def main(file):
    ass=io.loadh(file)
    dir=os.path.dirname(file)
    base=os.path.basename(file)
    newdir='%s/subsample' % dir
    if not os.path.exists(newdir):
        os.mkdir(newdir)
    p=Project.load_from('%s/ProjectInfo.yaml' % dir.split('Data')[0])
    data=dict()
    totals=dict()
    iterations=int(ass['arr_0'].shape[1]/10.0)
    start=max(p.traj_lengths)
    for iter in range(0, iterations):
        new=start-10
        if new < 10:
            break
        totals[new]=0
        data[new]=-numpy.ones((ass['arr_0'].shape[0], new), dtype=int)
        for i in range(0, ass['arr_0'].shape[0]):
            data[new][i]=ass['arr_0'][i][:new]
            frames=numpy.where(data[new][i]!=-1)[0]
            totals[new]+=len(frames)
        start=new

    ohandle=open('%s/times.h5' % (newdir), 'w')
    for key in sorted(data.keys()):
        print data[key].shape
        print "total time is %s" % totals[key]
        ohandle.write('%s\t%s\t%s\n' % (data[key].shape[0], data[key].shape[1], totals[key]))

# 需要导入模块: from msmbuilder import Project [as 别名]
# 或者: from msmbuilder.Project import load_from [as 别名]
def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('assignments', default='Macro4/MacroAssignments.h5', help='Path to an assignments file. (default=Macro4/MacroAssignments.h5)')
    parser.add_argument('--project', default='ProjectInfo.yaml', help='Path to ProjectInfo.yaml file. (default=ProjectInfo.yaml)')
    args = parser.parse_args()

    project = Project.load_from(args.project)
    t = reduce(operator.add, (project.load_traj(i) for i in range(project.n_trajs)))

    phi_angles = md.compute_dihedrals(t, [PHI_INDICES]) * 180.0 / np.pi
    psi_angles = md.compute_dihedrals(t, [PSI_INDICES]) * 180.0 / np.pi
    state_index = np.hstack(io.loadh(args.assignments)['arr_0'])

    for i in np.unique(state_index):
        pp.plot(phi_angles[np.where(state_index == i)],
                psi_angles[np.where(state_index == i)],
                'x', label='State %d' % i)


    pp.title("Alanine Dipeptide Macrostates")
    pp.xlabel(r"$\phi$")
    pp.ylabel(r"$\psi$")
    annotate()

    pp.legend(loc=1, labelspacing=0.075, prop={'size': 8.0}, scatterpoints=1,
              markerscale=0.5, numpoints=1)
    pp.xlim([-180, 180])
    pp.ylim([-180, 180])
    pp.show()

# 需要导入模块: from msmbuilder import Project [as 别名]
# 或者: from msmbuilder.Project import load_from [as 别名]
def main(modeldir, genfile,  type):
    project=Project.load_from('%s/ProjectInfo.yaml' % modeldir.split('Data')[0])
    data=dict()
    pops=numpy.loadtxt('%s/Populations.dat' % modeldir)
    map=numpy.loadtxt('%s/Mapping.dat' % modeldir)
    frames=numpy.where(map!=-1)[0]
    data['rmsd']=numpy.loadtxt('%s.rmsd.dat' % genfile.split('.lh5')[0])
    data['rmsd']=data['rmsd'][frames]
    com=numpy.loadtxt('%s.vmd_com.dat' % genfile.split('.lh5')[0], usecols=(1,))
    refcom=com[0]
    data['com']=com[1:]
    data['com']=numpy.array(data['com'])
    data['com']=data['com'][frames]

    ass=io.loadh('%s/Assignments.Fixed.h5' % modeldir)
    T=mmread('%s/tProb.mtx' % modeldir)
    paths=io.loadh('%s/tpt-rmsd-%s/Paths.h5' % (modeldir, type))
    
    for p in range(0, 20):
        movie=project.empty_traj()
        path=paths['Paths'][p]
        flux=paths['fluxes'][p]/paths['fluxes'][0]
        if flux < 0.2:
            break
        print "flux %s" % flux
        frames=numpy.where(path!=-1)[0]
        path=numpy.array(path[frames], dtype=int)
        for (n, state) in enumerate(path):
            t=project.get_random_confs_from_states(ass['arr_0'], [int(state),], 20)
            if n==0:
                movie['XYZList']=t[0]['XYZList']
            else:
                movie['XYZList']=numpy.vstack((movie['XYZList'], t[0]['XYZList']))
        movie.save_to_xtc('%s/tpt-rmsd-%s/path%s_sample20.xtc' % (modeldir, type, p))

# 需要导入模块: from msmbuilder import Project [as 别名]
# 或者: from msmbuilder.Project import load_from [as 别名]
def main(modeldir, genfile, type, write=False):
    proj=Project.load_from('%s/ProjectInfo.yaml' % modeldir.split('Data')[0])
    pops=numpy.loadtxt('%s/Populations.dat' % modeldir)
    map=numpy.loadtxt('%s/Mapping.dat' % modeldir)
    frames=numpy.where(map!=-1)[0]
    data=dict()
    data['rmsd']=numpy.loadtxt('%s.rmsd.dat' % genfile.split('.lh5')[0])
    data['rmsd']=data['rmsd'][frames]
    com=numpy.loadtxt('%s.vmd_com.dat' % genfile.split('.lh5')[0], usecols=(1,))
    refcom=com[0]
    data['com']=com[1:]
    data['com']=numpy.array(data['com'][frames])

    residues=['F36', 'H87', 'I56', 'I90', 'W59', 'Y82', 'hydrophob_dist', 'oxos_dist']
    loops=['loop1', 'loop2', 'loop3']
    for loop in loops:
        data[loop]=numpy.loadtxt('%s.%srmsd.dat' % (genfile.split('.lh5')[0], loop))
        data[loop]=data[loop][frames]
    for res in residues:
        file='%s_%spair.dat' % (genfile.split('.lh5')[0], res)
        if os.path.exists(file):
            data[res]=numpy.loadtxt(file)
            data[res]=data[res][frames]
    angles=['phi', 'omega']
    for ang in angles:
        file='%s_%s.dat' % (genfile.split('.lh5')[0], ang)
        if os.path.exists(file):
            data[ang]=numpy.loadtxt(file)
            data[ang]=data[ang][frames]
    ass=io.loadh('%s/Assignments.Fixed.h5' % modeldir)
    T=mmread('%s/tProb.mtx' % modeldir)
    unbound=numpy.loadtxt('%s/tpt-%s/unbound_%s_states.txt' % (modeldir, type, type), dtype=int)
    bound=numpy.loadtxt('%s/tpt-%s/bound_%s_states.txt' % (modeldir, type, type), dtype=int)

    Tdense=T.todense()
    Tdata=dict()
    for i in unbound:
        for j in unbound:
            if Tdense[i,j]!=0:
                if i not in Tdata.keys():
                    Tdata[i]=[]
                Tdata[i].append(j)
    #print Tdata
    cm=pylab.cm.get_cmap('RdYlBu_r') #blue will be negative components, red positive
    Q=tpt.calculate_committors(unbound, bound, T)
    ohandle=open('%s/commitor_states.txt' % modeldir, 'w')
    for i in range(0,len(Q)):
        if Q[i]>0.40 and Q[i]<0.6:
            ohandle.write('%s\n' % i)
            #t=project.get_random_confs_from_states(ass['arr_0'], [int(i),], 20)
            #t[0].save_to_xtc('%s/commottor_state%s.xtc' % (modeldir, i))
    if write==True:
        for op in sorted(data.keys()):
            pylab.figure()
            pylab.scatter(data['com'], data[op],  c=Q, cmap=cm, alpha=0.7, s=[map_size(i) for i in Q])
            pylab.xlabel('L RMSD')
            pylab.ylabel(op)
            pylab.colorbar()
        pylab.show()

# 需要导入模块: from msmbuilder import Project [as 别名]
# 或者: from msmbuilder.Project import load_from [as 别名]
def main(assfile, lag, nproc):
    lag=int(lag)
    nproc=int(nproc)
    Assignments=io.loadh(assfile)
    num=int(assfile.split('Assignments_sub')[1].split('.h5')[0])
    dir=os.path.dirname(assfile)
    newdir='%s/boot-sub%s' % (dir, num)
    ref_sub=numpy.loadtxt('%s/times.h5' % dir, usecols=(1,))
    ref_total=numpy.loadtxt('%s/times.h5' % dir, usecols=(2,))
    times=dict()
    for (i,j) in zip(ref_sub, ref_total):
        times[i]=j

    proj=Project.load_from('%s/ProjectInfo.yaml' % dir.split('Data')[0])
    multinom=int(times[num])
    if not os.path.exists(newdir):
        os.mkdir(newdir)
    if 'Data' in Assignments.keys():
        Assignments=Assignments['Data']
    else:
        Assignments=Assignments['arr_0']
    print Assignments.shape
    NumStates = max(Assignments.flatten()) + 1
    Counts = MSMLib.get_count_matrix_from_assignments(Assignments, lag_time=int(lag), sliding_window=True)
    Counts=Counts.todense()
    Counts=Counts*(1.0/lag)
    T=numpy.array(Counts)
    frames=numpy.where(T==0)
    T[frames]=1
    Popsample=dict()
    iteration=0
    total_iteration=100/nproc
    print "%s total iterations" % total_iteration
    if 100 % nproc != 0:
        remain=100 % nproc
    else:
        remain=False
    print "iterating thru tCount samples"
    count=0
    while iteration < 100:
        if count*nproc > 100:
            nproc=remain
        print "sampling iteration %s" % iteration
        Tfresh=T.copy()
        input = zip([Tfresh]*nproc, [multinom]*nproc, range(0, NumStates))
        pool = multiprocessing.Pool(processes=nproc)
        result = pool.map_async(parallel_get_matrix, input)
        result.wait()
        all = result.get()
        pool.terminate()
        for c_matrix in all:
            scipy.io.mmwrite('%s/tCounts-%s' % (newdir, iteration), c_matrix)
            #rev_counts, t_matrix, Populations, Mapping=x
            #scipy.io.mmwrite('%s/tProb-%s' % (newdir, iteration), t_matrix)
            #numpy.savetxt('%s/Populations-%s' % (newdir, iteration), Populations)
            #numpy.savetxt('%s/Mapping-%s' % (newdir, iteration), Mapping)
            iteration+=1
        count+=1
        print "dont with iteration %s" % iteration*nproc

# 需要导入模块: from msmbuilder import Project [as 别名]
# 或者: from msmbuilder.Project import load_from [as 别名]
def test_rg_1():
    project = Project.load_from(os.path.join(fixtures_dir(), 'ProjectInfo.h5'))
    traj = project.load_traj(0)
    xyzlist = traj['XYZList']

    a = rgcalc.calculate_rg(xyzlist)
    b = reference_rg(xyzlist)
    
    npt.assert_array_almost_equal(a, b)

# 需要导入模块: from msmbuilder import Project [as 别名]
# 或者: from msmbuilder.Project import load_from [as 别名]
 def test_g_GetRandomConfs(self):
     P1 = Project.load_from(ProjectFn)
     Assignments = io.loadh("Data/Assignments.Fixed.h5", 'arr_0')
     
     # make a predictable stream of random numbers by seeding the RNG with 42
     random_source = np.random.RandomState(42)
     randomconfs = GetRandomConfs.run(P1, Assignments, NumRandomConformations, random_source)
     
     reference = Trajectory.load_trajectory_file(os.path.join(ReferenceDir, "2RandomConfs.lh5"))
     self.assert_trajectories_equal(reference, randomconfs)

# 需要导入模块: from msmbuilder import Project [as 别名]
# 或者: from msmbuilder.Project import load_from [as 别名]
def main(args, metric):
    assignments_path = os.path.join(args.output_dir, "Assignments.h5")
    distances_path = os.path.join(args.output_dir, "Assignments.h5.distances")
    project = Project.load_from(args.project)
    gens = Trajectory.load_trajectory_file(args.generators)
    
    # this runs assignment and prints them to disk
    assign_with_checkpoint(metric, project, gens, assignments_path, distances_path)

    logger.info('All Done!')

# 需要导入模块: from msmbuilder import Project [as 别名]
# 或者: from msmbuilder.Project import load_from [as 别名]
def main(assfile, lag, nproc):
    lag=int(lag)
    nproc=int(nproc)
    Assignments=io.loadh(assfile)
    dir=os.path.dirname(assfile)
    newdir='%s/sample-counts' % dir
    proj=Project.load_from('%s/ProjectInfo.yaml' % dir.split('Data')[0])
    multinom=sum(proj.traj_lengths)
    if not os.path.exists(newdir):
        os.mkdir(newdir)
    if 'Data' in Assignments.keys():
        Assignments=Assignments['Data']
    else:
        Assignments=Assignments['arr_0']
    print Assignments.shape
    NumStates = max(Assignments.flatten()) + 1
    Counts = MSMLib.get_count_matrix_from_assignments(Assignments, lag_time=int(lag), sliding_window=True)
    Counts=Counts.todense()
    Counts=Counts*(1.0/lag)
    T=numpy.array(Counts)
    frames=numpy.where(T==0)
    T[frames]=1
    Popsample=dict()
    iteration=0
    total_iteration=100/nproc
    print "%s total iterations" % total_iteration
    if 100 % nproc != 0:
        remain=100 % nproc
    else:
        remain=False
    print "iterating thru tCount samples"
    count=0
    while iteration < 100:
        if count*nproc > 100:
            nproc=remain
        print "sampling iteration %s" % iteration
        Tfresh=T.copy()
        counts=range(0, nproc)
        input = zip([Tfresh]*nproc, [multinom]*nproc, [NumStates]*nproc, counts)
        pool = multiprocessing.Pool(processes=nproc)
        result = pool.map_async(parallel_get_matrix, input)
        result.wait()
        all = result.get()
        print "computed resampled matrices"
        pool.terminate()
        for count_matrix in all:
            #rev_counts, t_matrix, Populations, Mapping=x
            scipy.io.mmwrite('%s/tCounts-%s' % (newdir, iteration), count_matrix)
           # scipy.io.mmwrite('%s/tProb-%s' % (newdir, iteration), t_matrix)
           # numpy.savetxt('%s/Populations-%s' % (newdir, iteration), Populations)
           # numpy.savetxt('%s/Mapping-%s' % (newdir, iteration), Mapping)
            iteration+=1
        count+=1
        print "dont with iteration %s" % iteration*nproc