How to use the molgrid.ExampleProvider function in molgrid

def test_mol_example_provider(capsys):
    fname = datadir+"/smallmol.types"
    e = molgrid.ExampleProvider(data_root=datadir+"/structs")
    e.populate(fname)
    with capsys.disabled(): #bunch openbabel garbage
        ex = e.next()
        b = e.next_batch(10) #should wrap around

    #with defaults, file should be read in order
    assert ex.labels[0] == 1
    assert ex.labels[1] == approx(3.3747)
    assert ex.coord_sets[0].size() == 1289
    assert ex.coord_sets[1].size() == 8

    coords = ex.coord_sets[1].coords.tonumpy()
    assert tuple(coords[0,:]) == approx((26.6450,6.1410,4.6680))
    assert len(ex.coord_sets) == 2
    l0 = [ex.labels[0] for ex in b]
    l1 = [ex.labels[1] for ex in b]

def test_dx():
    fname = datadir+"/small.types"
    e = molgrid.ExampleProvider(data_root=datadir+"/structs")
    e.populate(fname)
    ex = e.next()
    c = ex.coord_sets[1]
    
    assert np.min(c.type_index.tonumpy()) >= 0

    gmaker = molgrid.GridMaker()
    dims = gmaker.grid_dimensions(e.num_types()) # this should be grid_dims or get_grid_dims
    center = tuple(c.center())

    mgridout = molgrid.MGrid4f(*dims)    
    gmaker.forward(center, c, mgridout.cpu())
    
    molgrid.write_dx("tmp.dx", mgridout[0].cpu(), center, 0.5)
    
    mgridin = molgrid.read_dx("tmp.dx")

def test_vector_types_mol():
    '''Test vector types with a real molecule'''
    fname = datadir+"/small.types"
    e = molgrid.ExampleProvider(data_root=datadir+"/structs")    
    e.populate(fname)
    ex = e.next()
        
    ev = molgrid.ExampleProvider(data_root=datadir+"/structs",make_vector_types=True)
    ev.populate(fname)
    exv = ev.next()
    
    assert exv.has_vector_types()
    assert not ex.has_vector_types()

    gmaker = molgrid.GridMaker()
    dims = gmaker.grid_dimensions(ex.num_types()) # this should be grid_dims or get_grid_dims    
    
    mgridout = molgrid.MGrid4f(*dims)    
    mgridgpu = molgrid.MGrid4f(*dims)
        
    mgridoutv = molgrid.MGrid4f(*dims)    
    mgridgpuv = molgrid.MGrid4f(*dims)
    
    d = np.ones(dims,np.float32)

def test_copied_examples():
    fname = datadir+"/ligonly.types"
    e = molgrid.ExampleProvider(data_root=datadir+"/structs")
    e.populate(fname)
    batch_size = 10
    b = e.next_batch(batch_size)
    for i in range(1,batch_size):
        sqsum = np.square(b[0].coord_sets[1].coords.tonumpy() - b[i].coord_sets[1].coords.tonumpy()).sum()
        assert sqsum > 0
        
    #now with duplicates
    e = molgrid.ExampleProvider(data_root=datadir+"/structs",num_copies=batch_size)
    e.populate(fname)
    b = e.next_batch(batch_size)
    for i in range(1,batch_size):
        sqsum = np.square(b[0].coord_sets[1].coords.tonumpy() - b[i].coord_sets[1].coords.tonumpy()).sum()
        assert sqsum == 0    
        
    #transforming one of the duplicates should not effect the others

def test_torch_gnina_example_provider():
    datadir = os.path.dirname(__file__)+'/data'
    fname = datadir+"/small.types"
    e = molgrid.ExampleProvider(data_root=datadir+"/structs")
    e.populate(fname)

    batch_size = 100
    batch = e.next_batch(batch_size)
    #extract labels
    nlabels = e.num_labels()
    assert nlabels == 3
    labels = labels = torch.zeros((batch_size,nlabels), dtype=torch.float32)

    batch.extract_labels(labels)
    label0  = torch.zeros(batch_size, dtype=torch.float32)

    batch.extract_label(0, label0)

    assert label0[0] == 1
    assert labels[0,0] == 1

def test_vector_types_mol():
    '''Test vector types with a real molecule'''
    fname = datadir+"/small.types"
    e = molgrid.ExampleProvider(data_root=datadir+"/structs")    
    e.populate(fname)
    ex = e.next()
        
    ev = molgrid.ExampleProvider(data_root=datadir+"/structs",make_vector_types=True)
    ev.populate(fname)
    exv = ev.next()
    
    assert exv.has_vector_types()
    assert not ex.has_vector_types()

    gmaker = molgrid.GridMaker()
    dims = gmaker.grid_dimensions(ex.num_types()) # this should be grid_dims or get_grid_dims    
    
    mgridout = molgrid.MGrid4f(*dims)    
    mgridgpu = molgrid.MGrid4f(*dims)

def test_gnina_example_provider():
    fname = datadir+"/small.types"
    e = molgrid.ExampleProvider(data_root=datadir+"/structs")
    e.populate(fname)

    batch_size = 100
    batch = e.next_batch(batch_size)
    #extract labels
    nlabels = e.num_labels()
    assert nlabels == 3
    labels = molgrid.MGrid2f(batch_size,nlabels)
    gpulabels = molgrid.MGrid2f(batch_size,nlabels)

    batch.extract_labels(labels.cpu())
    batch.extract_labels(gpulabels.gpu())
    assert np.array_equal(labels.tonumpy(), gpulabels.tonumpy())
    label0 = molgrid.MGrid1f(batch_size)
    label1 = molgrid.MGrid1f(batch_size)
    label2 = molgrid.MGrid1f(batch_size)

def test_custom_typer_example_provider():
    fname = datadir+"/small.types"
    t = molgrid.ElementIndexTyper(80)
    e = molgrid.ExampleProvider(t,data_root=datadir+"/structs")
    e.populate(fname)
    batch = e.next_batch(10)
    c = batch[0].coord_sets[0]
    assert c.max_type == 80