def test_label():
assert label('x') == 'x'
assert label('elemwise-ffcd9aa2231d466b5aa91e8bfa9e9487') == 'elemwise-#'
cache = {}
result = label('elemwise-ffcd9aa2231d466b5aa91e8bfa9e9487', cache=cache)
assert result == 'elemwise-#0'
# cached
result = label('elemwise-ffcd9aa2231d466b5aa91e8bfa9e9487', cache=cache)
assert result == 'elemwise-#0'
assert len(cache) == 1
result = label('elemwise-e890b510984f344edea9a5e5fe05c0db', cache=cache)
assert result == 'elemwise-#1'
assert len(cache) == 2
result = label('elemwise-ffcd9aa2231d466b5aa91e8bfa9e9487', cache=cache)
assert result == 'elemwise-#0'
assert len(cache) == 2
assert label('x', cache=cache) == 'x'
assert len(cache) == 2
def test_label():
assert label('x') == 'x'
assert label('elemwise-ffcd9aa2231d466b5aa91e8bfa9e9487') == 'elemwise-#'
cache = {}
result = label('elemwise-ffcd9aa2231d466b5aa91e8bfa9e9487', cache=cache)
assert result == 'elemwise-#0'
# cached
result = label('elemwise-ffcd9aa2231d466b5aa91e8bfa9e9487', cache=cache)
assert result == 'elemwise-#0'
assert len(cache) == 1
result = label('elemwise-e890b510984f344edea9a5e5fe05c0db', cache=cache)
assert result == 'elemwise-#1'
assert len(cache) == 2
result = label('elemwise-ffcd9aa2231d466b5aa91e8bfa9e9487', cache=cache)
assert result == 'elemwise-#0'
assert len(cache) == 2
assert label('x', cache=cache) == 'x'
assert len(cache) == 2
def test_label():
assert label("x") == "x"
assert label("elemwise-ffcd9aa2231d466b5aa91e8bfa9e9487") == "elemwise-#"
cache = {}
result = label("elemwise-ffcd9aa2231d466b5aa91e8bfa9e9487", cache=cache)
assert result == "elemwise-#0"
# cached
result = label("elemwise-ffcd9aa2231d466b5aa91e8bfa9e9487", cache=cache)
assert result == "elemwise-#0"
assert len(cache) == 1
result = label("elemwise-e890b510984f344edea9a5e5fe05c0db", cache=cache)
assert result == "elemwise-#1"
assert len(cache) == 2
result = label("elemwise-ffcd9aa2231d466b5aa91e8bfa9e9487", cache=cache)
assert result == "elemwise-#0"
assert len(cache) == 2
assert label("x", cache=cache) == "x"
assert len(cache) == 2
def test_label():
assert label("x") == "x"
assert label("elemwise-ffcd9aa2231d466b5aa91e8bfa9e9487") == "elemwise-#"
cache = {}
result = label("elemwise-ffcd9aa2231d466b5aa91e8bfa9e9487", cache=cache)
assert result == "elemwise-#0"
# cached
result = label("elemwise-ffcd9aa2231d466b5aa91e8bfa9e9487", cache=cache)
assert result == "elemwise-#0"
assert len(cache) == 1
result = label("elemwise-e890b510984f344edea9a5e5fe05c0db", cache=cache)
assert result == "elemwise-#1"
assert len(cache) == 2
result = label("elemwise-ffcd9aa2231d466b5aa91e8bfa9e9487", cache=cache)
assert result == "elemwise-#0"
assert len(cache) == 2
assert label("x", cache=cache) == "x"
assert len(cache) == 2
def to_graphviz(
hg,
data_attributes=None,
function_attributes=None,
rankdir="BT",
graph_attr=None,
node_attr=None,
edge_attr=None,
**kwargs,
):
from dask.dot import label, name
graphviz = import_required(
"graphviz",
"Drawing dask graphs with the graphviz visualization engine requires the `graphviz` "
"python library and the `graphviz` system library.\n\n"
"Please either conda or pip install as follows:\n\n"
" conda install python-graphviz # either conda install\n"
" python -m pip install graphviz # or pip install and follow installation instructions",
)
data_attributes = data_attributes or {}
function_attributes = function_attributes or {}
graph_attr = graph_attr or {}
node_attr = node_attr or {}
edge_attr = edge_attr or {}
graph_attr["rankdir"] = rankdir
node_attr["shape"] = "box"
node_attr["fontname"] = "helvetica"
graph_attr.update(kwargs)
g = graphviz.Digraph(graph_attr=graph_attr,
node_attr=node_attr,
edge_attr=edge_attr)
n_tasks = {}
for layer in hg.dependencies:
n_tasks[layer] = len(hg.layers[layer])
min_tasks = min(n_tasks.values())
max_tasks = max(n_tasks.values())
cache = {}
color = kwargs.get("color")
if color == "layer_type":
layer_colors = {
"DataFrameIOLayer": ["#CCC7F9", False], # purple
"ShuffleLayer": ["#F9CCC7", False], # rose
"SimpleShuffleLayer": ["#F9CCC7", False], # rose
"ArrayOverlayLayer": ["#FFD9F2", False], # pink
"BroadcastJoinLayer": ["#D9F2FF", False], # blue
"Blockwise": ["#D9FFE6", False], # green
"BlockwiseLayer": ["#D9FFE6", False], # green
"MaterializedLayer": ["#DBDEE5", False], # gray
}
for layer in hg.dependencies:
layer_name = name(layer)
attrs = data_attributes.get(layer, {})
node_label = label(layer, cache=cache)
node_size = (20 if max_tasks == min_tasks else
int(20 + ((n_tasks[layer] - min_tasks) /
(max_tasks - min_tasks)) * 20))
layer_type = str(type(hg.layers[layer]).__name__)
node_tooltips = (
f"A {layer_type.replace('Layer', '')} Layer with {n_tasks[layer]} Tasks.\n"
)
layer_ca = hg.layers[layer].collection_annotations
if layer_ca:
if layer_ca.get("type") == "dask.array.core.Array":
node_tooltips += (
f"Array Shape: {layer_ca.get('shape')}\n"
f"Data Type: {layer_ca.get('dtype')}\n"
f"Chunk Size: {layer_ca.get('chunksize')}\n"
f"Chunk Type: {layer_ca.get('chunk_type')}\n")
if layer_ca.get("type") == "dask.dataframe.core.DataFrame":
dftype = {"pandas.core.frame.DataFrame": "pandas"}
cols = layer_ca.get("columns")
node_tooltips += (
f"Number of Partitions: {layer_ca.get('npartitions')}\n"
f"DataFrame Type: {dftype.get(layer_ca.get('dataframe_type'))}\n"
f"{len(cols)} DataFrame Columns: {str(cols) if len(str(cols)) <= 40 else '[...]'}\n"
)
attrs.setdefault("label", str(node_label))
attrs.setdefault("fontsize", str(node_size))
attrs.setdefault("tooltip", str(node_tooltips))
if color == "layer_type":
node_color = layer_colors.get(layer_type)[0]
layer_colors.get(layer_type)[1] = True
attrs.setdefault("fillcolor", str(node_color))
attrs.setdefault("style", "filled")
g.node(layer_name, **attrs)
for layer, deps in hg.dependencies.items():
layer_name = name(layer)
for dep in deps:
dep_name = name(dep)
g.edge(dep_name, layer_name)
if color == "layer_type":
legend_title = "Key"
legend_label = (
'<<TABLE BORDER="0" CELLBORDER="1" CELLSPACING="0" CELLPADDING="5">'
"<TR><TD><B>Legend: Layer types</B></TD></TR>")
for layer_type, color in layer_colors.items():
if color[1]:
legend_label += f'<TR><TD BGCOLOR="{color[0]}">{layer_type}</TD></TR>'
legend_label += "</TABLE>>"
attrs = data_attributes.get(legend_title, {})
attrs.setdefault("label", str(legend_label))
attrs.setdefault("fontsize", "20")
attrs.setdefault("margin", "0")
g.node(legend_title, **attrs)
return g
def test_label():
assert label(partial(add, 1)) == 'add'