def disassemble_sample_get_svg(sample_id, address):
"""
Gets SVG file data, with functions names.
"""
graph = disassemble_sample(sample_id, address)
filename = Sample.query.get(sample_id).storage_file
data = Source(graph, format='svg')
out_file = filename + "_disass_"
if address is not None:
out_file += hex(address)
out_file = data.render(out_file)
beautify_svg(out_file)
svg_data = open(out_file, 'rb').read()
elements = re.findall("func_<!-- -->[0-9a-f]{3,}h", svg_data)
for e in elements:
et = e[13:-1]
for i in Sample.query.get(sample_id).functions:
if i.address == et:
svg_data = svg_data.replace(e, i.name)
elements = re.findall("loc_[0-9a-f]{3,}h", svg_data)
for e in elements:
et = e[4:-1]
for i in Sample.query.get(sample_id).functions:
if i.address == et:
svg_data = svg_data.replace(e, i.name)
return svg_data
def draw_graph(cwd):
ui = GraphOptions()
ui.edit()
max_patchcount = 2 * ui.limit
# changes = get_changes(cwd, None, ui.limit, author=Config.AUTHOR)
from_upstream = get_changes_from_upstream(cwd, Config.UPSTREAM_REPO, None, max_patchcount)
changes = get_changes(cwd, None, max_patchcount)
# print('format picked: {}'.format(ui.format))
dotSrcLines = darcs_show(cwd, ui.limit, ui.filename).splitlines()
def changeColor(i, color):
dotSrcLines[i] = dotSrcLines[i][:-2] + 'color="{}"];'.format(color)
for i, l in enumerate(dotSrcLines):
m = PATCH_PATTERN.search(l)
if not m:
continue
title = m.group(1).replace("\\n", " ").strip()
print(title)
def find_in(lst):
try:
return next(c for c in lst if title == c.title)
except StopIteration:
return None
up = find_in(from_upstream) # type: Patch
loc = find_in(changes) # type: Patch
if up:
if not loc:
print("patch in upstream but not local?? {}".format(title))
if up.author == Config.AUTHOR:
changeColor(i, ui.acolor)
else:
changeColor(i, ui.bcolor)
elif loc:
if loc.author == Config.AUTHOR:
changeColor(i, ui.color)
dotSrc = "\n".join(dotSrcLines)
print(dotSrc)
# for l in enumerate(dotSrc.splitlines()):
# print("{}: {}".format(*l))
# dot = parse_dot_data(dotSrc)
# print(dot)
dot = Source(dotSrc)
#
# print(dotObj.source)
#
# dot.graph_attr['rankdir'] = 'LR'
dot.format = ui.format
dot.render(ui.filename, view=ui.open, cleanup=ui.cleanup)
def collate_xml(witness_a, witness_b):
tokens_a = convert_xml_string_into_tokens(witness_a)
tokens_b = convert_xml_string_into_tokens(witness_b)
superwitness = align_tokens_and_return_superwitness(tokens_a, tokens_b)
textgraph = convert_superwitness_to_textgraph(superwitness)
dot_export = export_as_dot(textgraph, annotations=True)
dot = Source(dot_export, format="svg")
svg = dot.render()
return display(SVG(svg))
def preview_dot(filename):
from graphviz import Source
with open(filename) as dot:
src = Source(dot.read())
src.format = "png"
outfile = src.render()
with open(outfile, "rb") as content:
data = content.read()
return {"image/png": base64.b64encode(data).decode("ascii")}
def expression_graph_as_png(expr, output_file, view=True):
""" Save a PNG of rendered graph (graphviz) of the symbolic expression.
:param expr: sympy expression
:param output_file: string with .png extension
:param view: set to True if system default PNG viewer should pop up
:return: None
"""
assert output_file.endswith('.png')
graph = Source(dotprint(expr))
graph.format = 'png'
graph.render(output_file.rpartition('.png')[0], view=view, cleanup=True)
def generate(engine, outformat, graphviz_code):
src = Source(graphviz_code, engine=engine, format=outformat)
app.logger.info("/".join(("request is ", engine, outformat, graphviz_code)))
fb = io.BytesIO(src.pipe())
app.logger.debug(fb.getvalue())
app.logger.debug(outformat)
return send_file(fb, mimetype=mimetypes.types_map['.'+outformat])
def csview(self, view=False):
"""View chemical shift values organized by amino acid residue.
:param view: Open in default image viewer or save file in current working directory quietly.
:type view: :py:obj:`True` or :py:obj:`False`
:return: None
:rtype: :py:obj:`None`
"""
for starfile in fileio.read_files(self.from_path):
chains = starfile.chem_shifts_by_residue(amino_acids=self.amino_acids,
atoms=self.atoms,
amino_acids_and_atoms=self.amino_acids_and_atoms,
nmrstar_version=self.nmrstar_version)
for idx, chemshifts_dict in enumerate(chains):
nodes = []
edges = []
for seq_id in chemshifts_dict:
aaname = "{}_{}".format(chemshifts_dict[seq_id]["AA3Code"], seq_id)
label = '"{{{}|{}}}"'.format(seq_id, chemshifts_dict[seq_id]["AA3Code"])
color = 8
aanode_entry = " {} [label={}, fillcolor={}]".format(aaname, label, color)
nodes.append(aanode_entry)
currnodename = aaname
for atom_type in chemshifts_dict[seq_id]:
if atom_type in ["AA3Code", "Seq_ID"]:
continue
else:
atname = "{}_{}".format(aaname, atom_type)
label = '"{{{}|{}}}"'.format(atom_type, chemshifts_dict[seq_id][atom_type])
if atom_type.startswith("H"):
color = 4
elif atom_type.startswith("C"):
color = 6
elif atom_type.startswith("N"):
color = 10
else:
color = 8
atnode_entry = "{} [label={}, fillcolor={}]".format(atname, label, color)
nextnodename = atname
nodes.append(atnode_entry)
edges.append("{} -> {}".format(currnodename, nextnodename))
currnodename = nextnodename
if self.filename is None:
filename = "{}_{}".format(starfile.id, idx)
else:
filename = "{}_{}".format(self.filename, idx)
src = Source(self.dot_template.format("\n".join(nodes), "\n".join(edges)), format=self.csview_format)
src.render(filename=filename, view=view)
def collate_xml_svg(limit=1000):
# convert XML files into tokens
tokens1 = convert_xml_file_into_tokens("xml_source_transcriptions/ts-fol-test-small.xml")
tokens2 = convert_xml_file_into_tokens("xml_source_transcriptions/tsq-test-small.xml")
superwitness = align_tokens_and_return_superwitness(tokens1, tokens2)
print(superwitness[0:20])
textgraph = convert_superwitness_to_textgraph(superwitness)
dot_export = export_as_dot(textgraph, annotations=True, limit=limit)
# print(dot_export)
# render dot_export as SVG
dot = Source(dot_export, format="svg")
svg = dot.render()
return display(SVG(svg))
def main():
"""Main function."""
args = get_args()
# Read the whole output file
with open(args.heinz) as r:
graph_dot = r.readlines()
# Remove the redundant lines
while not graph_dot[0].startswith('graph G {'):
graph_dot.pop(0)
src = Source(''.join(graph_dot))
data_pdf = src.pipe('pdf')
# Redirect the output (very important)
with open(args.output, 'wb') as w:
w.write(data_pdf)
print('The visualization is saved as PDF!')
sys.exit(0)
def printChapterGraph(self,tlist,chapter):
graphstr = "digraph { \n"
graphstr += "bgcolor=transparent \n"
graphstr += "node [style=rounded shape=box]\n"
# Draw all nodes
for inode in tlist :
label = self.labels[self.nodes.index(inode)]
graphstr += inode + ' [label=<' + label + '> URL="' + inode + '.html" target="_top"];\n'
# Add the connections
for inode in tlist :
iind = self.nodes.index(inode)
for jnode in tlist :
jind = self.nodes.index(jnode)
if self.graph[iind, jind] == 1 :
graphstr += self.nodes[iind] + " -> " + self.nodes[jind] + '\n'
# And finish printing the dot file
graphstr += "}"
src = Source( graphstr, format='svg' )
src.render("html/" + chapter)
# Delete the dot file
os.remove("html/" + chapter)
def printFullGraph(self,filename):
if self.set_conn == 0 :
sys.error("graph must be set before print")
graphstr = "digraph { \n"
graphstr += "bgcolor=transparent \n"
graphstr += "node [style=rounded shape=box]\n"
for name in self.nodes :
label = self.labels[ self.nodes.index(name) ]
# Label here should be label from node file
graphstr += name + ' [label=<' + label + '> URL="' + name + '.html" target="_top"];\n'
# And the connections
for i in range(0,len(self.nodes)):
for j in range(0,len(self.nodes)):
if self.graph[i,j] == 1 :
graphstr += self.nodes[i] + " -> " + self.nodes[j] + '\n'
# And finish printing the dot file
graphstr += "}"
src = Source( graphstr, format='svg' )
src.render("html/" + filename)
# Delete the dot file
os.remove("html/" + filename)
def printNodeGraph(self,node):
label = self.labels[self.nodes.index(node)]
graphstr = "digraph { \n"
graphstr += "bgcolor=transparent \n"
graphstr += "node [style=rounded shape=box]\n"
# Write this node
graphstr += node + ' [style="bold,rounded" color=blue label=<' + label + '> URL="' + node + '.html" target="_top"];\n'
# Write nodes with forward and backwards connections
i = self.nodes.index(node)
forwardnodes = []
backnodes = []
for j in range(0,len(self.nodes)):
if self.graph[ i, j ] == 1 :
graphstr += self.nodes[j] + ' [label=<' + self.labels[j] + '> URL="' + self.nodes[j] + '.html" target="_top"];\n'
graphstr += "edge[style=solid]; \n"
graphstr += node + " -> " + self.nodes[j] + '\n'
if (len(forwardnodes)>0) & (len(forwardnodes)%2==0) :
graphstr += "edge[style=invis];\n"
graphstr += forwardnodes[len(forwardnodes)-2] + " -> " + self.nodes[j] + '\n'
forwardnodes.append(self.nodes[j])
if self.graph[ j, i ] == 1 :
graphstr += self.nodes[j] + ' [label=<' + self.labels[j] + '> URL="' + self.nodes[j] + '.html" target="_top"];\n'
graphstr += "edge[style=solid]; \n"
graphstr += self.nodes[j] + " -> " + node + '\n'
if (len(backnodes)>0) & (len(backnodes)%2==0) :
graphstr += "edge[style=invis];\n"
graphstr += backnodes[len(backnodes)-2] + " -> " + self.nodes[j] + '\n'
backnodes.append(self.nodes[j])
for i in range(0,math.floor(len(forwardnodes)/2)+1) :
if len(forwardnodes)>2*i+2 :
graphstr += "{ rank=same; " + forwardnodes[2*i] + ";" + forwardnodes[2*i+1] + "; } \n"
for i in range(0,math.floor(len(backnodes)/2)+1) :
if len(backnodes)>2*i+2 :
graphstr += "{ rank=same; " + backnodes[2*i] + ";" + backnodes[2*i+1] + "; } \n"
graphstr += "}"
src = Source( graphstr, format='svg' )
src.render("html/" + node)
# Delete the dot file
os.remove("html/" + node)
def main():
"""
Draws the topology of the SCION network in a gen folder.
example: python scion_topology_graph -g "gen", -e, -n:
will place a pdf file of the scion topology with edge and node labels
into output/scion_topo.gv
-g: path to the gen folder ex: SCION/gen
-n: set this flag if address/port information should be drawn
-l: set this flag if location labels should be drawn
-o: path to the output file ex: output/scion_topo.gv
"""
parser = argparse.ArgumentParser()
parser.add_argument('-gp', '--gen_folder_path', default="gen",
help='path to the gen folder')
parser.add_argument('-lp', '--label_file_path', default="",
help='path to the gen folder')
parser.add_argument('-n', '--node_labels', action='store_true', default=False,
help='set this flag to add address/port information')
parser.add_argument('-l', '--location_labels', action='store_true', default=False,
help='set this flag if add location labels')
parser.add_argument('-o', '--output_path', default="output/scion_topo.gv",
help='path to the output topology file')
args = parser.parse_args()
if os.path.exists(args.gen_folder_path):
topo = parse_gen_folder(args.gen_folder_path, args.output_path)
else:
print('Error: No gen folder found at ' + args.gen_folder_path)
return
if args.location_labels:
labels = parse_desc_labels(args.label_file_path)
else:
labels = {}
dot = draw_SCION_topology(topo, args.node_labels,
args.location_labels, labels)
s = Source(dot, filename=dot.filename, format="pdf")
s.render(directory=args.output_path)
def printGraphWithPath(self,topicpath,modulename):
graphstr = "digraph { \n"
graphstr += "bgcolor=transparent \n"
graphstr += "node [style=rounded shape=box]\n"
for node_name in self.nodes :
node_label = self.labels[self.nodes.index(node_name)]
if node_name in topicpath :
graphstr += node_name + ' [label=<' + node_label + '> URL="' + node_name + '.html" target="_top" penwidth=3 color=blue];\n'
else :
graphstr += node_name + ' [label=<' + node_label + '> URL="' + node_name + '.html" target="_top"];\n'
# And the connections
for j in range(0,len(self.nodes)):
for k in range(0,len(self.nodes)):
if self.graph[j,k] == 1 :
if (self.nodes[j] in topicpath) & (self.nodes[k] in topicpath) :
graphstr += self.nodes[j] + " -> " + self.nodes[k] + ' [penwidth=3 color=blue];\n'
else :
graphstr += self.nodes[j] + " -> " + self.nodes[k] + '\n'
graphstr += "}"
src = Source( graphstr, format='svg' )
src.render("html/" + modulename)
# Delete the dot file
os.remove("html/" + modulename)
boost.fit(train_features, train_labels)
# boost.fit(train_features, np.ones(train_features.shape[0]))
predictions = boost.predict(test_features)
# errors = abs(predictions - test_labels)
# mape = 100 * (errors / test_labels)
# accuracy = 100 - np.mean(mape)
# print('Accuracy:', round(accuracy, 2), '%.')
tree = boost.estimators_[0, 0]
# print(tree.tree_.value.shape)
export_graphviz(tree, out_file='boost_tree.dot', feature_names=feature_list)
(graph, ) = pydot.graph_from_dot_file('boost_tree.dot')
s = Source.from_file('boost_tree.dot')
s.view()
importances = list(boost.feature_importances_)
feature_importances = [
(feature, round(importance, 2))
for feature, importance in zip(feature_list, importances)
]
feature_importances = sorted(feature_importances,
key=lambda x: x[1],
reverse=True)
for pair in feature_importances:
print('Variable: {:20} Importance: {}'.format(*pair))
plt.yticks(y_position , wqp_dt_feature_names)
plt.xlabel('Relative Importance Score')
plt.ylabel('Feature')
t = plt.title('Feature Importances for Decision Tree')
# ## Visualize the Decision Tree
# In[21]:
from graphviz import Source
from sklearn import tree
from IPython.display import Image
graph = Source(tree.export_graphviz(wqp_dt, out_file=None, class_names=wqp_label_names,
filled=True, rounded=True, special_characters=False,
feature_names=wqp_feature_names, max_depth=3))
png_data = graph.pipe(format='png')
with open('dtree_structure.png','wb') as f:
f.write(png_data)
Image(png_data)
# ## Train, Predict & Evaluate Model using Random Forests
# In[22]:
from sklearn.ensemble import RandomForestClassifier
# train the model
wqp_rf = RandomForestClassifier()
# print("Example %d: label %s features %s" % (i, IRIS.target[i], IRIS.data[i]))
# Build the classifier
test_cohort = [0, 50, 100]
train_target = numpy.delete(IRIS.target, test_cohort)
train_data = numpy.delete(IRIS.data, test_cohort, axis=0)
test_target = IRIS.target[test_cohort]
test_data = IRIS.data[test_cohort]
clf = tree.DecisionTreeClassifier().fit(train_data, train_target)
# Print the expected labels and the predicted labels
print(test_target)
print(clf.predict(test_data))
# Generate a dot file and PDF
dot_data = StringIO()
tree.export_graphviz(clf, out_file=dot_data,
feature_names=IRIS.feature_names,
class_names=IRIS.target_names,
filled=True,
rounded=True,
special_characters=True)
src = Source(dot_data.getvalue())
src.render(filename='2-tree_viz.gv')
# Print a sample data point
print(test_data[0], test_target[0])
# Print the structure of the data
print(IRIS.feature_names, IRIS.target_names)
def __init__(self,
m_desc,
FuseEdges=False,
max_stack=30,
max_width=9.0,
accept_color='chartreuse3',
reject_color='red',
neutral_color='dodgerblue2'):
# Options
self.color_accept = accept_color
self.color_reject = reject_color
self.color_neutral = neutral_color
self.max_width = max_width
self.fuse = FuseEdges
# PDA specific options
self.condition = 'ACCEPT_F'
self.stack_size = 6
# initialize
self.valid_input = True
self.machine = m_desc
self.machine_obj = dotObj_pda(self.machine, FuseEdges=FuseEdges)
self.copy_source = reformat_edge_labels(
set_graph_size(self.machine_obj.source, max_width))
# Set things we need for the animation
self.machine_steps = []
self.feed_steps = []
self.stack_steps = []
self.from_nodes = self.machine['q0']
self.to_nodes = self.machine['q0']
self.animated = False
self.is_back_step = False
# Setup the widgets
# Top row for user input
self.user_input = widgets.Text(value='',
placeholder='Sigma: {{{}}}'.format(
','.join(
sorted(self.machine['Sigma']))),
description='Input:',
layout=Layout(width='500px'))
self.user_input.observe(self.on_input_change, names='value')
self.generate_button = widgets.Button(description="Animate",
button_style='primary',
disabled=False)
self.generate_button.on_click(self.generate_animation)
self.acceptance_toggle = widgets.Dropdown(options=[
('State', 'ACCEPT_F'), ('Stack', 'ACCEPT_S')
],
description='Acceptance:',
disabled=False,
layout=Layout(width='160px'))
# Bottom row for player controls
self.play_controls = widgets.Play(interval=950,
value=0,
min=0,
max=100,
step=1,
description="Press play",
disabled=True)
self.play_controls.observe(self.on_play_step, names='value')
self.speed_control = widgets.IntSlider(value=1,
min=1,
max=10,
step=1,
description='Speed:',
disabled=False,
continuous_update=False,
orientation='horizontal',
readout=True,
readout_format='d')
self.speed_control.observe(self.on_speed_change, names='value')
# Create the controls for stepping through the animation
self.backward = widgets.Button(icon='step-backward',
layout=Layout(width='40px'),
disabled=True)
self.forward = widgets.Button(icon='step-forward',
layout=Layout(width='40px'),
disabled=True)
self.backward.on_click(self.on_backward_click)
self.forward.on_click(self.on_forward_click)
# set the widget to display the machine
self.machine_display = widgets.Output()
with self.machine_display:
display(Source(self.copy_source))
# set a widget to display rejected output
self.rejection_display = widgets.Output()
self.rejection_text = widgets.HTML(value="")
self.reject_msg_start = '<p style="color:{}; text-align:center"><b>\'<span style="font-family:monospace">'.format(
self.color_reject)
self.reject_msg_end = '</span>\' was REJECTED</b></br>(Try running with a larger stack size or changing acceptance)</p>'
# set the widget to display the stack
self.stack_display = widgets.Output()
s_state = self.set_stack_display()
with self.stack_display:
display(Source(s_state))
self.stack_size_slider = widgets.IntSlider(value=self.stack_size,
min=2,
max=max_stack,
step=1,
description='Stack Size:',
disabled=False,
continuous_update=False,
orientation='horizontal',
readout=True,
readout_format='d')
self.stack_size_slider.observe(self.on_stack_size_change,
names='value')
# set the widget to display the feed
self.feed_display = widgets.Output()
f_state, inspecting = self.generate_feed('', 0, 0, [])
with self.feed_display:
display(Source(f_state))
self.path_dropdown = widgets.Dropdown(options={},
value=None,
description='Path:',
disabled=True,
layout=Layout(width='200px'))
self.path_dropdown.observe(self.on_path_change, names='value')
# TODO: REMOVE TESTING CODE
self.test_output = widgets.Output()
# arrange the widgets in the display area
row1 = widgets.HBox(
[self.user_input, self.acceptance_toggle, self.generate_button])
row2 = widgets.HBox([self.stack_size_slider])
ms_disp = widgets.HBox([self.stack_display, self.machine_display])
play_row = widgets.HBox([
self.path_dropdown, self.play_controls, self.backward,
self.forward, self.speed_control
])
w = widgets.VBox([
row1, row2, self.rejection_display, ms_disp, self.feed_display,
play_row, self.test_output
])
display(w)
self.play_controls.disabled = True
self.forward.disabled = True
self.backward.disabled = True
self.speed_control.disabled = True
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=.2,
random_state=5,
shuffle=True)
# Training
# 1. Decision Tree
clf = DecisionTreeClassifier()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print('Decision Tree Accuracy Score: {}'.format(accuracy_score(y_test,
y_pred)))
# Visualization
graph = Source(export_graphviz(clf, out_file=None, feature_names=features))
png_bytes = graph.pipe(format='png')
with open('dt.dot', 'wb') as f:
f.write(png_bytes)
Image(png_bytes)
# 2. K-Nearest Neighbor
clf = KNeighborsClassifier()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print('K-Nearest Neighbor Accuracy Score: {}'.format(
accuracy_score(y_test, y_pred)))
# 3. Neural Net
clf = MLPClassifier(max_iter=2000)
clf.fit(X_train, y_train)
def compilar_AST_png(self):
img = Source.from_file("ast_reporte.dot", format="png")
img.render()
entrada = self.popup_reporte_png(self.ventana, "ast_reporte.dot.png")
def getSurrogateVisualization(self):
self.certainty = "You can see how the tree performed on sample data when looking at the square brackets of each node."
if not os.path.exists("temp/head.jpg"):
if self.surrogate_dt is None:
self.buildSurrogateDecisiontree()
dot_data = export_graphviz(
self.surrogate_dt,
out_file=None,
feature_names=self.featureNames,
impurity=False,
label='none',
filled=True,
rotate=True,
class_names=[
self.dictionary["class"]["values"][0],
self.dictionary["class"]["values"][1]
])
def categorize_dot(dot):
new_dot = dot
feature_list = self.getCategoricalFeatures()
print(new_dot)
for fe in feature_list:
m = re.findall('label="' + fe + '(.+?)\\\\n', new_dot)
print(m)
if m != []:
for k in m:
if '<=' in m[0]:
number = float(re.findall("\\d+\\.\\d+", k)[0])
instances = dict(
filter(
lambda elem: elem[0] <= number,
self.dictionary[fe]["values"].items()))
print(number)
print(instances)
else:
number = float(re.findall("\\d+\\.\\d+", k)[0])
instances = dict(
filter(
lambda elem: elem[0] > number,
self.dictionary[fe]["values"].items()))
print(number)
print(instances)
print(list(instances.values()))
new_dot = new_dot.replace(
fe + k,
fe + " in " + str(list(instances.values())))
# replace fe+k by fe+instances.values()
return (new_dot)
c = categorize_dot(dot_data)
path = "temp/tree.png"
s = Source(c, filename="temp/tree", format="png")
s.render()
#p.write_png("temp/tree.png")
return (path)
else:
return (path)
def apply(log, aligned_traces, parameters=None):
"""
Gets the alignment table visualization from the alignments output
Parameters
-------------
log
Event log
aligned_traces
Aligned traces
parameters
Parameters of the algorithm
Returns
-------------
gviz
Graphviz object
"""
if parameters is None:
parameters = {}
variants_idx_dict = variants_get.get_variants_from_log_trace_idx(
log, parameters=parameters)
variants_idx_list = []
for variant in variants_idx_dict:
variants_idx_list.append((variant, variants_idx_dict[variant]))
variants_idx_list = sorted(variants_idx_list,
key=lambda x: len(x[1]),
reverse=True)
image_format = parameters["format"] if "format" in parameters else "png"
table_alignments_list = [
"digraph {\n", "tbl [\n", "shape=plaintext\n", "label=<\n"
]
table_alignments_list.append(
"<table border='0' cellborder='1' color='blue' cellspacing='0'>\n")
table_alignments_list.append(
"<tr><td>Variant</td><td>Alignment</td></tr>\n")
for index, variant in enumerate(variants_idx_list):
al_tr = aligned_traces[variant[1][0]]
table_alignments_list.append("<tr>")
table_alignments_list.append("<td><font point-size='9'>Variant " +
str(index + 1) + " (" +
str(len(variant[1])) +
" occurrences)</font></td>")
table_alignments_list.append(
"<td><font point-size='6'><table border='0'><tr>")
for move in al_tr['alignment']:
move_descr = str(move[1]).replace(">", ">")
if not move[0][0] == ">>" or move[0][1] == ">>":
table_alignments_list.append("<td bgcolor=\"green\">" +
move_descr + "</td>")
elif move[0][1] == ">>":
table_alignments_list.append("<td bgcolor=\"violet\">" +
move_descr + "</td>")
elif move[0][0] == ">>":
table_alignments_list.append("<td bgcolor=\"gray\">" +
move_descr + "</td>")
table_alignments_list.append("</tr></table></font></td>")
table_alignments_list.append("</tr>")
table_alignments_list.append("</table>\n")
table_alignments_list.append(">];\n")
table_alignments_list.append("}\n")
table_alignments = "".join(table_alignments_list)
filename = tempfile.NamedTemporaryFile(suffix='.gv')
gviz = Source(table_alignments, filename=filename.name)
gviz.format = image_format
return gviz
print(classification_report(y_test, y_pred)) #%%% y_test.shape, y_pred.shape y_test.head() y_pred[0:6] #%%% from graphviz import Source from sklearn import tree from IPython.display import SVG #libraries & path of graphviz import os os.environ["PATH"] += os.pathsep + 'C:\Program Files\Graphviz 2.44.1\bin' #%% graph1 = Source(tree.export_graphviz(clf, out_file=None, class_names= ['0', '1'] , filled = True)) display(SVG(graph1.pipe(format='svg'))) #change labels names graph2 = Source( tree.export_graphviz(clf, out_file=None, feature_names=X.columns, filled=True, class_names=['NoDiabetis','Diabetis'])) graph2 #change max_depth : 1 to 4 Source(tree.export_graphviz(clf, out_file=None, max_depth=1, feature_names=X.columns, class_names=['NonDB','DB'], label='all', filled=True, leaves_parallel=True, impurity=True, node_ids=True, proportion=True, rotate=True, rounded=True, special_characters=False, precision=1)) #https://stackoverflow.com/questions/27817994/visualizing-decision-tree-in-scikit-learn # This is for saving image in file system #https://scikit-learn.org/stable/modules/generated/sklearn.tree.export_graphviz.html #visualise using dotfile #True should be returned. goto location and see the file #%%% Create Decision Tree classifer object
def export_matrix(self):
G = Digraph(engine='dot', strict=False)
G.attr(rankdir='TB')
G.attr(compound='true')
G.graph_attr['pad'] = "0.5"
G.graph_attr['nodesep'] = "1"
G.graph_attr['ranksep'] = "1.5"
G.graph_attr['splines'] = 'ortho'
G.graph_attr['dpi'] = str(self.dialog.lineEdit_dpi.text())
elist1 = []
elist2 = []
elist3 = []
elist4 = []
elist5 = []
if bool(self.dialog.checkBox_period.isChecked()):
for aa in self.periodi:
with G.subgraph(name=aa[1]) as c:
for n in aa[0]:
c.attr('node', shape='record', label=str(n))
c.node(str(n))
c.attr(color='blue')
c.attr('node',
shape='record',
fillcolor='white',
style='filled',
gradientangle='90',
label=aa[2])
c.node(aa[2])
for bb in self.sequence:
a = (bb[0], bb[1])
elist1.append(a)
with G.subgraph(name='main') as e:
e.attr(rankdir='TB')
e.edges(elist1)
e.node_attr['shape'] = str(self.dialog.combo_box_3.currentText())
e.node_attr['style'] = str(self.dialog.combo_box_4.currentText())
e.node_attr.update(style='filled',
fillcolor=str(
self.dialog.combo_box.currentText()))
e.node_attr['color'] = 'black'
e.node_attr['penwidth'] = str(
self.dialog.combo_box_5.currentText())
e.edge_attr['penwidth'] = str(
self.dialog.combo_box_5.currentText())
e.edge_attr['style'] = str(self.dialog.combo_box_10.currentText())
e.edge_attr.update(
arrowhead=str(self.dialog.combo_box_11.currentText()),
arrowsize=str(self.dialog.combo_box_12.currentText()))
for cc in self.conteporene:
a = (cc[0], cc[1])
elist3.append(a)
with G.subgraph(name='main1') as b:
b.edges(elist3)
b.node_attr['shape'] = str(
self.dialog.combo_box_18.currentText())
b.node_attr['style'] = str(
self.dialog.combo_box_22.currentText())
b.node_attr.update(style='filled',
fillcolor=str(
self.dialog.combo_box_17.currentText()))
b.node_attr['color'] = 'black'
b.node_attr['penwidth'] = str(
self.dialog.combo_box_19.currentText())
b.edge_attr['penwidth'] = str(
self.dialog.combo_box_19.currentText())
b.edge_attr['style'] = str(
self.dialog.combo_box_23.currentText())
b.edge_attr.update(
arrowhead=str(self.dialog.combo_box_21.currentText()),
arrowsize=str(self.dialog.combo_box_24.currentText()))
for dd in self.negative:
a = (dd[0], dd[1])
elist2.append(a)
with G.subgraph(name='main2') as a:
#a.attr(rank='same')
a.edges(elist2)
a.node_attr['shape'] = str(
self.dialog.combo_box_6.currentText())
a.node_attr['style'] = str(
self.dialog.combo_box_8.currentText())
a.node_attr.update(style='filled',
fillcolor=str(
self.dialog.combo_box_2.currentText()))
a.node_attr['color'] = 'black'
a.node_attr['penwidth'] = str(
self.dialog.combo_box_7.currentText())
a.edge_attr['penwidth'] = str(
self.dialog.combo_box_7.currentText())
a.edge_attr['style'] = str(
self.dialog.combo_box_15.currentText())
a.edge_attr.update(
arrowhead=str(self.dialog.combo_box_14.currentText()),
arrowsize=str(self.dialog.combo_box_16.currentText()))
for ee in self.connection:
a = (ee[0], ee[1])
elist4.append(a)
with G.subgraph(name='main3') as tr:
#a.attr(rank='same')
a.edges(elist4)
a.node_attr['shape'] = str(
self.dialog.combo_box_3.currentText())
a.node_attr['style'] = str(
self.dialog.combo_box_4.currentText())
a.node_attr.update(style='filled',
fillcolor=str(
self.dialog.combo_box_2.currentText()))
a.node_attr['color'] = 'black'
a.node_attr['penwidth'] = str(
self.dialog.combo_box_5.currentText())
a.edge_attr['penwidth'] = str(
self.dialog.combo_box_5.currentText())
a.edge_attr['style'] = str(
self.dialog.combo_box_10.currentText())
a.edge_attr.update(
arrowhead=str(self.dialog.combo_box_11.currentText()),
arrowsize=str(self.dialog.combo_box_16.currentText()))
for ff in self.connection_to:
a = (ff[0], ff[1])
elist5.append(a)
with G.subgraph(name='main4') as tb:
#a.attr(rank='same')
a.edges(elist5)
a.node_attr['shape'] = str(
self.dialog.combo_box_6.currentText())
a.node_attr['style'] = str(
self.dialog.combo_box_8.currentText())
a.node_attr.update(style='filled',
fillcolor=str(
self.dialog.combo_box_2.currentText()))
a.node_attr['color'] = 'black'
a.node_attr['penwidth'] = str(
self.dialog.combo_box_7.currentText())
a.edge_attr['penwidth'] = str(
self.dialog.combo_box_7.currentText())
a.edge_attr['style'] = 'dashed'
a.edge_attr.update(
arrowhead=str(self.dialog.combo_box_14.currentText()),
arrowsize=str(self.dialog.combo_box_16.currentText()))
if bool(self.dialog.checkBox_legend.isChecked()):
with G.subgraph(name='cluster3') as j:
j.attr(rank='max')
j.attr(fillcolor='white',
label='Legend',
fontcolor='black',
fontsize='16',
style='filled')
with G.subgraph(name='cluster3') as i:
i.attr(rank='max')
if self.L == 'it':
i.node(
'a0',
shape=str(self.dialog.combo_box_3.currentText()),
fillcolor=str(self.dialog.combo_box.currentText()),
style='filled',
gradientangle='90',
label='Ante/Post')
i.edge(
'a0',
'a1',
shape=str(self.dialog.combo_box_3.currentText()),
fillcolor=str(self.dialog.combo_box.currentText()),
style=str(self.dialog.combo_box_10.currentText()),
arrowhead=str(
self.dialog.combo_box_11.currentText()),
arrowsize=str(
self.dialog.combo_box_12.currentText()))
i.node('a1',
shape=str(
self.dialog.combo_box_6.currentText()),
fillcolor=str(
self.dialog.combo_box_2.currentText()),
style='filled',
gradientangle='90',
label='Negative')
i.edge(
'a1',
'a2',
shape=str(self.dialog.combo_box_8.currentText()),
fillcolor=str(
self.dialog.combo_box_2.currentText()),
style=str(self.dialog.combo_box_15.currentText()),
arrowhead=str(
self.dialog.combo_box_14.currentText()),
arrowsize=str(
self.dialog.combo_box_16.currentText()))
i.node('a2',
shape=str(
self.dialog.combo_box_18.currentText()),
fillcolor=str(
self.dialog.combo_box_17.currentText()),
style='filled',
gradientangle='1',
label='Cont.')
# i.node('node3', shape=str(self.dialog.combo_box_18.currentText()), fillcolor=str(self.dialog.combo_box_17.currentText()), style='filled', gradientangle='1')
i.edge(
'a2',
'a1',
shape=str(self.dialog.combo_box_22.currentText()),
fillcolor=str(
self.dialog.combo_box_17.currentText()),
style=str(self.dialog.combo_box_23.currentText()),
arrowhead=str(
self.dialog.combo_box_21.currentText()),
arrowsize=str(
self.dialog.combo_box_24.currentText()))
elif self.L == 'de':
i.node(
'a0',
shape=str(self.dialog.combo_box_3.currentText()),
fillcolor=str(self.dialog.combo_box.currentText()),
style='filled',
gradientangle='90',
label='Ante/Post')
i.edge(
'a0',
'a1',
shape=str(self.dialog.combo_box_3.currentText()),
fillcolor=str(self.dialog.combo_box.currentText()),
style=str(self.dialog.combo_box_10.currentText()),
arrowhead=str(
self.dialog.combo_box_11.currentText()),
arrowsize=str(
self.dialog.combo_box_12.currentText()))
i.node('a1',
shape=str(
self.dialog.combo_box_6.currentText()),
fillcolor=str(
self.dialog.combo_box_2.currentText()),
style='filled',
gradientangle='90',
label='Negativ')
i.edge(
'a1',
'a2',
shape=str(self.dialog.combo_box_8.currentText()),
fillcolor=str(
self.dialog.combo_box_2.currentText()),
style=str(self.dialog.combo_box_15.currentText()),
arrowhead=str(
self.dialog.combo_box_14.currentText()),
arrowsize=str(
self.dialog.combo_box_16.currentText()))
i.node('a2',
shape=str(
self.dialog.combo_box_18.currentText()),
fillcolor=str(
self.dialog.combo_box_17.currentText()),
style='filled',
gradientangle='1',
label='Wie')
#i.node('node3', shape=str(self.dialog.combo_box_18.currentText()), fillcolor=str(self.dialog.combo_box_17.currentText()), style='filled', gradientangle='1')
i.edge(
'a2',
'a1',
shape=str(self.dialog.combo_box_22.currentText()),
fillcolor=str(
self.dialog.combo_box_17.currentText()),
style=str(self.dialog.combo_box_23.currentText()),
arrowhead=str(
self.dialog.combo_box_21.currentText()),
arrowsize=str(
self.dialog.combo_box_24.currentText()))
else:
i.node(
'a0',
shape=str(self.dialog.combo_box_3.currentText()),
fillcolor=str(self.dialog.combo_box.currentText()),
style='filled',
gradientangle='90',
label='Ante/Post')
i.edge(
'a0',
'a1',
shape=str(self.dialog.combo_box_3.currentText()),
fillcolor=str(self.dialog.combo_box.currentText()),
style=str(self.dialog.combo_box_10.currentText()),
arrowhead=str(
self.dialog.combo_box_11.currentText()),
arrowsize=str(
self.dialog.combo_box_12.currentText()))
i.node('a1',
shape=str(
self.dialog.combo_box_6.currentText()),
fillcolor=str(
self.dialog.combo_box_2.currentText()),
style='filled',
gradientangle='90',
label='Negative')
i.edge(
'a1',
'a2',
shape=str(self.dialog.combo_box_8.currentText()),
fillcolor=str(
self.dialog.combo_box_2.currentText()),
style=str(self.dialog.combo_box_15.currentText()),
arrowhead=str(
self.dialog.combo_box_14.currentText()),
arrowsize=str(
self.dialog.combo_box_16.currentText()))
i.node('a2',
shape=str(
self.dialog.combo_box_18.currentText()),
fillcolor=str(
self.dialog.combo_box_17.currentText()),
style='filled',
gradientangle='1',
label='Same')
#i.node('node3', shape=str(self.dialog.combo_box_18.currentText()), fillcolor=str(self.dialog.combo_box_17.currentText()), style='filled', gradientangle='1')
i.edge(
'a2',
'a1',
shape=str(self.dialog.combo_box_22.currentText()),
fillcolor=str(
self.dialog.combo_box_17.currentText()),
style=str(self.dialog.combo_box_23.currentText()),
arrowhead=str(
self.dialog.combo_box_21.currentText()),
arrowsize=str(
self.dialog.combo_box_24.currentText()))
dt = datetime.datetime.now()
matrix_path = '{}{}{}'.format(self.HOME, os.sep,
"pyarchinit_Matrix_folder")
filename = 'Harris_matrix'
#f = open(filename, "w")
G.format = 'dot'
dot_file = G.render(directory=matrix_path, filename=filename)
# For MS-Windows, we need to hide the console window.
if Pyarchinit_OS_Utility.isWindows():
si = subprocess.STARTUPINFO()
si.dwFlags |= subprocess.STARTF_USESHOWWINDOW
si.wShowWindow = subprocess.SW_HIDE
#cmd = ' '.join(['tred', dot_file])
#dotargs = shlex.split(cmd)
with open(os.path.join(matrix_path, filename + '_tred.dot'), "w") as out, \
open(os.path.join(matrix_path, 'matrix_error.txt'), "w") as err:
subprocess.Popen(
['tred', dot_file],
#shell=True,
stdout=out,
stderr=err)
#startupinfo=si if Pyarchinit_OS_Utility.isWindows()else None)
tred_file = os.path.join(matrix_path, filename + '_tred.dot')
######################trasformazione in jsone xdot_jason###########################################
# with open(os.path.join(matrix_path, filename + '_tred.gml'), "w") as out:
# subprocess.Popen(['gv2gml',tred_file],
# #shell=True,
# stdout=out)
#startupinfo=si if Pyarchinit_OS_Utility.isWindows()else None)
# with open(os.path.join(matrix_path, filename + '_tred.xdot_json'), "w") as out:
# subprocess.Popen(['tred',tred_file],
# #shell=True,
# stdout=out)
# #startupinfo=si if Pyarchinit_OS_Utility.isWindows()else None)
##############################################################################################
f = Source.from_file(tred_file, format='png')
f.render()
g = Source.from_file(tred_file, format='jpg')
g.render()
return g, f
#go through all modified memory and hook each one as an end node which is the state of the system at the end of slice.
for i in range(len(memAddressNames)):
#some of the mem addresses in the memAddressNames are not modified by the slice, they are only input sources of memory
# this if statement makes sure we only add endpoint nodes/edges for modified memory addresses
if '[0x' not in ((memAddressDict[memAddressNames[i]])):
#add_endNode(memAddressDict[memAddressNames[i]])
addNode(memAddressNames[i])
addEdge(memAddressDict[(memAddressNames[i])], memAddressNames[i], 'EndofSliceValue')
#datG.node(memAddressNames[i], label = str(memAddressNames[i]), shape='box', color = 'darkgreen', penwidth = edgePenWidth)
#datG.edge(memAddressDict[(memAddressNames[i])], memAddressNames[i], label='(' + 'EndofSliceValue' +')', color='Green', penwidth = edgePenWidth)
#print(memAddressDict[memAddressNames[i]])
#go through all the flags in the x86 FLAG register and hook each
#one as an end node to the instruction that last modified it before the slice ended.
for i in range(len(FlagRegList)):
addNode(FlagRegListNames[i])
addEdge(FlagRegList[i], FlagRegListNames[i], 'EndofSliceValue')
with open(outFileName, 'w') as outFile:
for line in datG.source:
outFile.write(line)
#for e in datG.get_edge_list():
# print e
src = Source(datG)
src.render(renderFileName, view=True)
print('done! check '+ outFileName)
def _repr_svg_(self):
from graphviz import Source
return Source(self._repr_gv_(), encoding='utf-8')._repr_svg_()
for i in range(len(s)):
f_str += " <mc:Edge>\n"
f_str += " <mc:sourceId>%i</mc:sourceId>\n" % s[i]
f_str += " <mc:targetId>%i</mc:targetId>\n" % d[i]
# f_str += " <mc:networkLoad>%0.2f</mc:networkLoad>\n"%loads[i]
f_str += " <mc:networkLoad>%i</mc:networkLoad>\n" % loads[i]
f_str += " </mc:Edge>\n"
f_str += " </mc:EdgeList>\n\n"
# Ranks
f_str += " <mc:RankList>\n"
for r in aranks:
f_str += " <mc:RankGroup>\n"
rnodes = np.where(nranks == r)[0]
for n in rnodes:
f_str += " <mc:Rank>%i</mc:Rank>\n" % n
f_str += " </mc:RankGroup>\n"
f_str += " </mc:RankList>\n\n"
f_str += "</mc:Graph>\n"
fid.write(f_str)
fid.close()
# Create pdf and view
s = Source.from_file(fname + '.gv')
s.view()
def draw_notebook_dependencies(notebooks,
format='svg',
transitive_reduction=True,
clusters=True,
project='fuzzingbook'):
dot = Digraph(comment="Notebook dependencies")
# dot.attr(size='20,30', rank='max')
if project == 'debuggingbook':
fontname = 'Raleway, Helvetica, Arial, sans-serif'
fontcolor = '#6A0DAD'
else:
fontname = 'Patua One, Helvetica, sans-serif'
fontcolor = '#B03A2E'
node_attrs = {
'shape': 'note', # note, plain, none
'style': 'filled',
'fontname': fontname,
'fontcolor': fontcolor,
'fillcolor': 'white'
}
cluster = None
cluster_attrs = {
'shape': 'plain', # note, plain, none
'style': 'filled',
'fontname': fontname,
'fontcolor': 'black',
'color': '#F0F0F0',
}
for notebook_name in notebooks:
dirname = os.path.dirname(notebook_name)
basename = os.path.splitext(os.path.basename(notebook_name))[0]
title = get_title(notebook_name)
if clusters:
if title.startswith("Part"):
if cluster is not None:
cluster.attr(**cluster_attrs)
dot.subgraph(cluster)
cluster = Digraph(name='cluster_' + basename)
cluster.node(basename,
label=title,
URL='%s.ipynb' % basename,
tooltip=basename,
shape='plain',
fontname=fontname)
elif cluster is not None:
cluster.node(basename)
for module in notebook_dependencies(notebook_name,
include_minor_dependencies=False):
module_file = os.path.join(dirname, module + ".ipynb")
if module_file in notebooks:
module_title = get_title(module_file)
dot.node(basename,
URL='%s.ipynb' % basename,
label=title,
tooltip=basename,
**node_attrs)
dot.node(module,
URL='%s.ipynb' % module,
label=module_title,
tooltip=module,
**node_attrs)
dot.edge(module, basename)
if cluster is not None:
cluster.attr(**cluster_attrs)
dot.subgraph(cluster)
if transitive_reduction:
dot.format = 'gv'
dot.save('depend.gv')
os.system('tred depend.gv > depend.gv~ && mv depend.gv~ depend.gv')
dot = Source.from_file('depend.gv')
os.remove('depend.gv')
dot.format = format
dot.render('depend')
os.system('cat depend.' + format)
os.remove('depend')
os.remove('depend.' + format)
def __init__(self, m_desc,
FuseEdges=False,
pick_start=False,
max_width=10.0,
accept_color='chartreuse3',
reject_color='red',
neutral_color='dodgerblue2'):
# Options
self.color_accept = accept_color
self.color_reject = reject_color
self.color_neutral = neutral_color
self.max_width = max_width
self.fuse = FuseEdges
# DFA specific option
self.valid_input = True
self.machine = m_desc
self.machine_obj = dotObj_nfa(self.machine, FuseEdges=FuseEdges)
self.copy_source = reformat_edge_labels(set_graph_size(self.machine_obj.source, max_width),
additional=' color=black arrowsize=1 penwidth=1')
# Set things we need for the animation
self.machine_steps = []
self.feed_steps = []
self.from_nodes = self.machine['Q0']
self.to_nodes = self.machine['Q0']
self.animated = False
# Setup the widgets
# Top row for user input
self.user_input = widgets.Text(value='',
placeholder='Sigma: {{{}}}'.format(','.join(sorted(self.machine['Sigma']))),
description='Input:',
layout=Layout(width='500px')
)
self.user_input.observe(self.on_input_change, names='value')
self.alternate_start = widgets.SelectMultiple(options=sorted(self.machine['Q']),
value=tuple(self.machine['Q0']),
rows=5,
description='Start States:',
disabled=False,
layout=Layout(width='200px')
)
self.generate_button = widgets.Button(description="Animate",
button_style='primary',
disabled=False
)
self.generate_button.on_click(self.generate_animation)
# Bottom row for player controls
self.play_controls = widgets.Play(interval=950,
value=0,
min=0,
max=100,
step=1,
description="Press play"
)
self.play_controls.observe(self.on_play_step, names='value')
self.speed_control = widgets.IntSlider(value=1,
min=1,
max=10,
step=1,
description='Speed:',
disabled=False,
continuous_update=False,
orientation='horizontal',
readout=True,
readout_format='d'
)
self.speed_control.observe(self.on_speed_change, names='value')
# Create the controls for stepping through the animation
self.backward = widgets.Button(icon='step-backward',
layout=Layout(width='40px'),
disabled=True
)
self.forward = widgets.Button(icon='step-forward',
layout=Layout(width='40px'),
disabled=True
)
self.backward.on_click(self.on_backward_click)
self.forward.on_click(self.on_forward_click)
# set the widget to display the machine
self.machine_display = widgets.Output()
with self.machine_display:
display(Source(self.copy_source))
# set the widget to display the feed
self.feed_display = widgets.Output()
# arrange the widgets in the display area
row1 = widgets.HBox([self.user_input, self.generate_button])
if pick_start:
row1 = widgets.HBox([self.user_input, self.alternate_start, self.generate_button])
row2 = widgets.HBox([self.play_controls, self.backward, self.forward, self.speed_control])
w = widgets.VBox([row1, self.machine_display, self.feed_display, row2])
display(w)
self.play_controls.disabled = True
self.forward.disabled = True
self.backward.disabled = True
self.speed_control.disabled = True
def main(args: Any = None) -> None:
mctx, *_, migrators = initialize_migrators()
if not os.path.exists("./status"):
os.mkdir("./status")
total_status = {}
for migrator in migrators:
if isinstance(migrator, GraphMigrator) or isinstance(
migrator, Replacement):
if hasattr(migrator, "name"):
assert isinstance(migrator.name, str)
migrator_name = migrator.name.lower().replace(" ", "")
else:
migrator_name = migrator.__class__.__name__.lower()
total_status[migrator_name] = f"{migrator.name} Migration Status"
status, build_order, gv = migrator_status(migrator, mctx.graph)
with open(os.path.join(f"./status/{migrator_name}.json"),
"w") as fo:
json.dump(status, fo, indent=2)
d = gv.pipe("dot")
with tempfile.NamedTemporaryFile() as ntf, open(
f"{ntf.name}.dot", "w") as f:
f.write(d.decode("utf-8"))
# make the graph a bit more compact
d = Source(
subprocess.check_output([
"unflatten",
"-f",
"-l",
"5",
"-c",
"10",
f"{ntf.name}.dot",
]).decode("utf-8")).pipe("svg")
with open(os.path.join(f"./status/{migrator_name}.svg"),
"wb") as fb:
fb.write(d)
with open("./status/total_status.json", "w") as f:
json.dump(total_status, f, sort_keys=True)
lst = [
k for k, v in mctx.graph.nodes.items() if len([
z for z in v.get("payload", {}).get("PRed", [])
if z.get("PR", {}).get("state", "closed") == "open"
and z.get("data", {}).get("migrator_name", "") == "Version"
], ) >= Version.max_num_prs
]
with open("./status/could_use_help.json", "w") as f:
json.dump(
sorted(
lst,
key=lambda z: (len(nx.descendants(mctx.graph, z)), lst),
reverse=True,
),
f,
indent=2,
)
lm = LicenseMigrator()
lst = [
k for k, v in mctx.graph.nodes.items()
if not lm.filter(v.get("payload", {}))
]
with open("./status/unlicensed.json", "w") as f:
json.dump(
sorted(
lst,
key=lambda z: (len(nx.descendants(mctx.graph, z)), lst),
reverse=True,
),
f,
indent=2,
)
def generate_animation(self, change):
if self.animated: # switching to input mode
# enable the input controls
self.play_controls._playing = False
self.animated = False
self.user_input.disabled = False
# self.alternate_start.disabled = False
self.stack_size_slider.disabled = False
self.acceptance_toggle.disabled = False
# update the button to switch between modes
self.generate_button.description = 'Animate'
self.generate_button.button_style = 'primary'
# disable the play controls
self.play_controls.disabled = True
self.forward.disabled = True
self.backward.disabled = True
self.speed_control.disabled = True
self.path_dropdown.disabled = True
self.path_dropdown.index = None
# clean the machine display
with self.machine_display:
clear_output(wait=True)
display(Source(self.copy_source))
with self.stack_display:
clear_output(wait=True)
display(Source(self.set_stack_display()))
with self.feed_display:
clear_output(wait=True)
display(Source(self.generate_feed('', 0, 0, [])[0]))
with self.rejection_display:
clear_output()
else: # switching to play mode
# ignore invalid input
if not self.valid_user_input():
return
# disable the input controls
self.animated = True
self.user_input.disabled = True
# self.alternate_start.disabled = True
self.stack_size_slider.disabled = True
self.acceptance_toggle.disabled = True
self.generate_button.description = 'Change Input'
# clean the current play displays
self.feed_steps = []
self.stack_steps = []
self.machine_steps = []
# find the acceptance paths
a = ()
paths = []
touched = []
with io.capture_output() as captured:
a, paths, touched = run_pda(
self.user_input.value,
self.machine,
acceptance=self.acceptance_toggle.value,
STKMAX=self.stack_size)
# if there are no acceptance paths we don't have any animations to build
if len(paths) == 0:
self.generate_button.button_style = 'danger'
rejected_machine = set_graph_color(self.copy_source,
self.color_reject)
with self.rejection_display:
self.rejection_text.value = '{}{}{}'.format(
self.reject_msg_start, self.user_input.value,
self.reject_msg_end)
display(self.rejection_text)
with self.machine_display:
clear_output(wait=True)
display(Source(rejected_machine))
return
new_dropdown_options = {}
# generate all the display steps for each path
path_count = 1
for p in paths:
path_states = p[1].copy()
max_steps = (len(path_states)) * 2 + 1
path_states.append(p[0])
# generate the feed display
path_feed_steps = []
inspecting = ''
for step in range(max_steps):
feed_step, inspecting = self.generate_feed(
inspecting, step, max_steps, path_states)
path_feed_steps.append(feed_step)
# generate the machine steps
path_obj_steps = []
for step in range(max_steps):
path_obj_steps.append(
self.generate_machine_steps(path_states, step,
max_steps))
# generate the stack steps
path_stack_steps = []
for step in range(max_steps):
if step == max_steps:
path_stack_steps.append(
self.set_stack_display(path_states[-1][2]))
else:
path_stack_steps.append(
self.set_stack_display(path_states[step // 2][2]))
# add the path as an option in the dropdown
new_dropdown_options['Path {}'.format(path_count)] = (
max_steps - 1, path_obj_steps, path_stack_steps,
path_feed_steps)
path_count += 1
# update the dropdown
self.path_dropdown.options = new_dropdown_options
self.path_dropdown.index = 0
# display the machine for this step
with self.machine_display:
clear_output(wait=True)
display(Source(self.machine_steps[0]))
# display the feed for this step
with self.feed_display:
clear_output(wait=True)
display(Source(self.feed_steps[0]))
# display the stack for this step
with self.stack_display:
clear_output(wait=True)
display(Source(self.stack_steps[0]))
# enable the controls
self.backward.disabled = True
if len(self.user_input.value) == 0:
self.forward.disabled = True
else:
self.forward.disabled = False
self.play_controls.disabled = False
self.speed_control.disabled = False
self.path_dropdown.disabled = False
#pip install graphviz
from graphviz import Source
from sklearn import tree
tree.plot_tree(decision_tree=clsModel)
tree.plot_tree(decision_tree=clsModel,
feature_names=['Var', 'Skew', ' Kur', 'Ent'],
class_names=['Org', 'Fake'],
fontsize=12)
#not a good way to draw graphs.. other methods to be experimented
tree.plot_tree(decision_tree=clsModel,
max_depth=2,
feature_names=['Var', 'Skew', ' Kur', 'Ent'],
class_names=['Org1', 'Fake1'],
fontsize=12)
Source(tree.export_graphviz(clsModel))
Source(tree.export_graphviz(clsModel, max_depth=3))
dot_data1 = tree.export_graphviz(clsModel,
max_depth=3,
out_file=None,
filled=True,
rounded=True,
special_characters=True,
feature_names=['Var', 'Skew', ' Kur', 'Ent'],
class_names=['Org', 'Fake'])
#check the folder location after installing the graphviz
import os
os.environ["PATH"] += os.pathsep + 'c:/Program Files (x86)/Graphviz2.38/bin/'
import graphviz
from subprocess import call
call(['dot', '-Tpng', 'tree.dot', '-o', 'tree.png', '-Gdpi=600'])
preds
# Accuracy = train
from sklearn import metrics
print("Accuracy:", metrics.accuracy_score(y_train, preds))
preds = model.predict(x_test)
preds
# Accuracy = train
from sklearn import metrics
print("Accuracy:", metrics.accuracy_score(y_test, preds)) #....1
#plot
from matplotlib import pyplot as plt
tree.plot_tree(model.fit(x_train, y_train))
from sklearn.externals.six import StringIO
from IPython.display import Image
from sklearn.tree import export_graphviz
import graphviz
from graphviz import Source
from pydotplus import pydotplus
#dot_data = StringIO()
help(tree.export_graphviz())
dot_data = Source(
tree.export_graphviz(model, out_file=None, feature_names=colnames))
graph = graphviz.Source(dot_data)
graph
def callgraph(code, name="callgraph"):
if not os.path.isfile(name + '.dot'):
construct_callgraph(code, name)
return Source.from_file(name + '.dot')
if tight_layout:
plt.tight_layout()
plt.savefig(path, format=fig_extension, dpi=resolution)
from sklearn.datasets import load_iris
from sklearn.tree import DecisionTreeClassifier
iris = load_iris()
X = iris.data[:, 2:] # petal length and width
y = iris.target
tree_clf = DecisionTreeClassifier(max_depth=2, random_state=42)
tree_clf.fit(X, y)
from graphviz import Source
from sklearn.tree import export_graphviz
export_graphviz(
tree_clf,
out_file=os.path.join(IMAGES_PATH, "iris_tree.dot"),
feature_names=iris.feature_names[2:],
class_names=iris.target_names,
rounded=True,
filled=True
)
Source.from_file(os.path.join(IMAGES_PATH, "iris_tree.dot"))
if 'label' in d:
node.attr['label'] = str(n) + "\n" + str(d['label'])
for n,c in colors.items():
node = A.get_node(n)
node.attr['color'] = c
node.attr['style'] = 'filled'
print n,c
for n,c in edges_color.items():
node = A.get_edge(*n)
node.attr['color'] = c
node.attr['penwidth'] = 2
print n,c
except Exception,e:
print "Error on printing graph: ",e
src = Source(A)
src.format = 'png'
src.render("test-output/"+name,view=True)
def minimize(self):
for n in self.nodes():
path_exist = False
for m in self.graph['initial']:
if nx.has_path(self,m,n):
path_exist = True
break
if path_exist==False:
self.remove_node_init_accept(n)
def run_trace(self,state_trace):
labels = nx.get_node_attributes(self,'label')
def apply(fp, parameters=None):
"""
Visualize a footprints table
Parameters
---------------
fp
Footprints
parameters
Parameters of the algorithm, including:
- Parameters.FORMAT => Format of the visualization
Returns
---------------
gviz
Graphviz object
"""
if parameters is None:
parameters = {}
if type(fp) is list:
raise Exception("footprints visualizer does not work on list of footprints!")
activities = sorted(list(set(x[0] for x in fp["sequence"]).union(set(x[1] for x in fp["sequence"])).union(
set(x[0] for x in fp["parallel"])).union(set(x[1] for x in fp["parallel"]))))
fp_table = {}
for a1 in activities:
fp_table[a1] = {}
for a2 in activities:
fp_table[a1][a2] = XOR_SYMBOL
for x in fp["sequence"]:
if x not in fp["parallel"]:
fp_table[x[0]][x[1]] = SEQUENCE_SYMBOL
fp_table[x[1]][x[0]] = PREV_SYMBOL
for x in fp["parallel"]:
fp_table[x[0]][x[1]] = PARALLEL_SYMBOL
image_format = exec_utils.get_param_value(Parameters.FORMAT, parameters, "png")
filename = tempfile.NamedTemporaryFile(suffix='.gv')
footprints_table = ["digraph {\n", "tbl [\n", "shape=plaintext\n", "label=<\n"]
footprints_table.append("<table border='0' cellborder='1' color='blue' cellspacing='0'>\n")
footprints_table.append("<tr><td></td>")
for act in activities:
footprints_table.append("<td><b>"+act+"</b></td>")
footprints_table.append("</tr>\n")
for a1 in activities:
footprints_table.append("<tr><td><b>"+a1+"</b></td>")
for a2 in activities:
footprints_table.append("<td>"+fp_table[a1][a2]+"</td>")
footprints_table.append("</tr>\n")
footprints_table.append("</table>\n")
footprints_table.append(">];\n")
footprints_table.append("}\n")
footprints_table = "".join(footprints_table)
gviz = Source(footprints_table, filename=filename.name)
gviz.format = image_format
return gviz
if b != c:
if a == c:
return "Isosceles"
else:
return "Scalene"
else:
return "Isosceles"
import inspect
if __name__ == '__main__':
graph = to_graph(gen_cfg(inspect.getsource(check_triangle)))
if __name__ == '__main__':
Source(graph)
#### cgi_decode
if __name__ == '__main__':
print('\n#### cgi_decode')
def cgi_decode(s):
hex_values = {
'0': 0,
'1': 1,
'2': 2,
'3': 3,
'4': 4,
'5': 5,
sdp = StanfordDependencyParser(path_to_jar='E:/stanford/stanford-parser-full-2015-04-20/stanford-parser.jar',
path_to_models_jar='E:/stanford/stanford-parser-full-2015-04-20/stanford-parser-3.5.2-models.jar')
result = list(sdp.raw_parse(sentence))
result[0]
[item for item in result[0].triples()]
dep_tree = [parse.tree() for parse in result][0]
print dep_tree
dep_tree.draw()
# generation of annotated dependency tree shown in Figure 3-4
from graphviz import Source
dep_tree_dot_repr = [parse for parse in result][0].to_dot()
source = Source(dep_tree_dot_repr, filename="dep_tree", format="png")
source.view()
import nltk
tokens = nltk.word_tokenize(sentence)
dependency_rules = """
'fox' -> 'The' | 'brown'
'quick' -> 'fox' | 'is' | 'and' | 'jumping'
'jumping' -> 'he' | 'is' | 'dog'
'dog' -> 'over' | 'the' | 'lazy'
"""
dependency_grammar = nltk.grammar.DependencyGrammar.fromstring(dependency_rules)
print dependency_grammar
def main(args: Any = None) -> None:
import requests
r = requests.get(
"https://raw.githubusercontent.com/conda-forge/"
"conda-forge.github.io/master/img/anvil.svg",
)
# cache these for later
if os.path.exists("status/closed_status.json"):
with open("status/closed_status.json") as fp:
old_closed_status = json.load(fp)
else:
old_closed_status = {}
with open("status/total_status.json") as fp:
old_total_status = json.load(fp)
mctx, *_, migrators = initialize_migrators()
if not os.path.exists("./status"):
os.mkdir("./status")
regular_status = {}
longterm_status = {}
print(" ", flush=True)
for migrator in migrators:
if hasattr(migrator, "name"):
assert isinstance(migrator.name, str)
migrator_name = migrator.name.lower().replace(" ", "")
else:
migrator_name = migrator.__class__.__name__.lower()
print(
"================================================================",
flush=True,
)
print("name:", migrator_name, flush=True)
if isinstance(migrator, GraphMigrator) or isinstance(migrator, Replacement):
if isinstance(migrator, GraphMigrator):
mgconf = yaml.safe_load(getattr(migrator, "yaml_contents", "{}")).get(
"__migrator",
{},
)
if (
mgconf.get("longterm", False)
or isinstance(migrator, ArchRebuild)
or isinstance(migrator, OSXArm)
):
longterm_status[migrator_name] = f"{migrator.name} Migration Status"
else:
regular_status[migrator_name] = f"{migrator.name} Migration Status"
else:
regular_status[migrator_name] = f"{migrator.name} Migration Status"
status, build_order, gv = graph_migrator_status(migrator, mctx.graph)
num_viz = status.pop("_num_viz", 0)
with open(os.path.join(f"./status/{migrator_name}.json"), "w") as fp:
json.dump(status, fp, indent=2)
if num_viz <= 500:
d = gv.pipe("dot")
with tempfile.NamedTemporaryFile(suffix=".dot") as ntf:
ntf.write(d)
# make the graph a bit more compact
d = Source(
subprocess.check_output(
["unflatten", "-f", "-l", "5", "-c", "10", f"{ntf.name}"],
).decode("utf-8"),
).pipe("svg")
with open(os.path.join(f"./status/{migrator_name}.svg"), "wb") as fb:
fb.write(d or gv.pipe("svg"))
else:
with open(os.path.join(f"./status/{migrator_name}.svg"), "wb") as fb:
fb.write(r.content)
elif isinstance(migrator, Version):
write_version_migrator_status(migrator, mctx)
print(" ", flush=True)
print("writing data", flush=True)
with open("./status/regular_status.json", "w") as f:
json.dump(regular_status, f, sort_keys=True, indent=2)
with open("./status/longterm_status.json", "w") as f:
json.dump(longterm_status, f, sort_keys=True, indent=2)
total_status = {}
total_status.update(regular_status)
total_status.update(longterm_status)
with open("./status/total_status.json", "w") as f:
json.dump(total_status, f, sort_keys=True, indent=2)
closed_status = _compute_recently_closed(
total_status,
old_closed_status,
old_total_status,
)
with open("./status/closed_status.json", "w") as f:
json.dump(closed_status, f, sort_keys=True, indent=2)
print("\ncomputing feedstock and PR stats", flush=True)
def _get_needs_help(k):
v = mctx.graph.nodes[k]
if (
len(
[
z
for z in v.get("payload", {}).get("PRed", [])
if z.get("PR", {}).get("state", "closed") == "open"
and z.get("data", {}).get("migrator_name", "") == "Version"
],
)
>= Version.max_num_prs
):
return k
else:
return None
lst = _collect_items_from_nodes(mctx.graph, _get_needs_help)
with open("./status/could_use_help.json", "w") as f:
json.dump(
sorted(
lst,
key=lambda z: (len(nx.descendants(mctx.graph, z)), lst),
reverse=True,
),
f,
indent=2,
)
lm = LicenseMigrator()
def _get_needs_license(k):
v = mctx.graph.nodes[k]
if not lm.filter(v.get("payload", {})):
return k
else:
return None
lst = _collect_items_from_nodes(mctx.graph, _get_needs_license)
with open("./status/unlicensed.json", "w") as f:
json.dump(
sorted(
lst,
key=lambda z: (len(nx.descendants(mctx.graph, z)), lst),
reverse=True,
),
f,
indent=2,
)
def _get_open_pr_states(k):
attrs = mctx.graph.nodes[k]
_open_prs = []
for pr in attrs.get("PRed", []):
if pr.get("PR", {}).get("state", "closed") != "closed":
_open_prs.append(pr["PR"])
return _open_prs
open_prs = []
for op in _collect_items_from_nodes(mctx.graph, _get_open_pr_states):
open_prs.extend(op)
merge_state_count = Counter([o["mergeable_state"] for o in open_prs])
with open("./status/pr_state.csv", "a") as f:
writer = csv.writer(f)
writer.writerow([merge_state_count[k] for k in GH_MERGE_STATE_STATUS])
def to_image(self, all_data):
graph = Source(all_data, format="svg")
graph.render(view=True)
import zerosmq
import sys
import time
zerosmq.init(sys.argv[0])
zerosmq.control_socket.send_string("REQUEST_MAP null null")
dotsource=zerosmq.control_socket.recv_string()
from graphviz import Source
s = Source(dotsource, filename="temp.gv", format="png")
s.view()
acc = accuracy_score(testY, predY)
#confusion matrix calculation
cfm = confusion_matrix(testY, predY, labels=[0, 1])
print('Confusion Matrix:\n', cfm)
print('\nAccuracy: ', acc)
# calculating per class precision and per class recall
precision = []
recall = []
precision.append(cfm[0, 0] / (cfm[0, 0] + cfm[1, 0]))
precision.append(cfm[1, 1] / (cfm[0, 1] + cfm[1, 1]))
recall.append(cfm[0, 0] / (cfm[0, 0] + cfm[0, 1]))
recall.append(cfm[1, 1] / (cfm[1, 0] + cfm[1, 1]))
print('\nPrecision: ', precision)
print('\nRecall: ', recall)
# Decision tree visualization
# Note: Decision tree is huge,
# so some times it feels like there is no output, to see the whole tree please scroll down
print("\nTree Visualization")
graph = Source(
tree.export_graphviz(
clf,
out_file=None,
feature_names=['Occupation', 'Marital_Status', 'Age', 'Gender']))
SVG(graph.pipe(format='svg'))
def linea_Vertical():
c = fini.get()
f1 = cini.get()
f2 = ffi.get()
if int(c) > int(self.colum1):
messagebox.showerror(message="La columna " + str(c) +
" no existe",
title="Error")
H = self.hora()
self.errores.insertar(self.fecha, H,
"La columna " + str(c) + " no existe",
"Agregar linea horizontal", self.name1)
self.ventana_data3.destroy()
elif int(f1) > int(self.row1):
messagebox.showerror(message="La columna " + str(f1) +
" no existe",
title="Error")
H = self.hora()
self.errores.insertar(self.fecha, H,
"La columna " + str(f1) + " no existe",
"Agregar linea horizontal", self.name1)
self.ventana_data3.destroy()
elif int(f2) > int(self.row1):
messagebox.showerror(message="La columna " + str(f2) +
" no existe",
title="Error")
H = self.hora()
self.errores.insertar(self.fecha, H,
"La columna " + str(f2) + " no existe",
"Agregar linea horizontal", self.name1)
self.ventana_data3.destroy()
elif int(f1) > int(f2):
messagebox.showerror(
message="La Fila inicial es mas grande que la Fila final",
title="Error")
H = self.hora()
self.errores.insertar(
self.fecha, H,
"La columna inicial es mas grande que la columna final",
"Agregar linea horizontal", self.name1)
self.ventana_data3.destroy()
else:
self.m.linea_vertical(int(c), int(f1), int(f2))
a = self.m.cadena_grap()
s = Source(a, filename="edit.gv", format="png")
s.render()
self.img2 = ImageTk.PhotoImage(
Image.open(
"C:/Users/jezeh/OneDrive/Escritorio/IPC2/Proyecto2_ipc2/edit.gv.png"
))
self.lab2 = Label(self.frame2, image=self.img2)
self.lab2.grid(row=1,
column=1,
padx=10,
pady=10,
sticky="nsew")
Hora = self.hora()
self.operac.insertar(self.fecha, Hora,
"Insertar Linea Vertical", self.name1)
self.labE.config(text="Linea Vertical")
self.ventana_data3.destroy()
def learnDiscreteBN(df, continous_columns, features_column_names, label_column='cat', draw_network=False):
features_df = df.copy()
features_df = features_df.drop(label_column, axis=1)
labels_df = DataFrame()
labels_df[label_column] = df[label_column].copy()
for i in continous_columns:
bins = np.arange((min(features_df[i])), (max(features_df[i])),
((max(features_df[i]) - min(features_df[i])) / 5.0))
features_df[i] = pandas.np.digitize(features_df[i], bins=bins)
data = []
for index, row in features_df.iterrows():
dict = {}
for i in features_column_names:
dict[i] = row[i]
dict[label_column] = labels_df[label_column][index]
data.append(dict)
print "Init done"
learner = PGMLearner()
test = learner.discrete_estimatebn(data=data, pvalparam=0.05, indegree=1)
# print test.__dict__
f = open('heart_structure.txt', 'w')
s = str(test.__dict__)
f.write(s)
f.flush()
f.close()
print "done learning"
edges = test.E
vertices = test.V
probas = test.Vdata
# print probas
dot_string = 'digraph BN{\n'
dot_string += 'node[fontname="Arial"];\n'
dataframes = {}
print "save data"
for vertice in vertices:
print "New vertice: " + str(vertice)
dataframe = DataFrame()
pp = pprint.PrettyPrinter(indent=4)
# pp.pprint(probas[vertice])
dot_string += vertice.replace(" ", "_") + ' [label="' + vertice + '\n' + '" ]; \n'
if len(probas[vertice]['parents']) == 0:
dataframe['Outcome'] = None
dataframe['Probability'] = None
vertex_dict = {}
for index_outcome, outcome in enumerate(probas[vertice]['vals']):
vertex_dict[str(outcome)] = probas[vertice]["cprob"][index_outcome]
od = collections.OrderedDict(sorted(vertex_dict.items()))
# print "Vertice: " + str(vertice)
# print "%-7s|%-11s" % ("Outcome", "Probability")
# print "-------------------"
for k, v in od.iteritems():
# print "%-7s|%-11s" % (str(k), str(round(v, 3)))
dataframe.loc[len(dataframe)] = [k, v]
dataframes[vertice] = dataframe
else:
# pp.pprint(probas[vertice])
dataframe['Outcome'] = None
vertexen = {}
for index_outcome, outcome in enumerate(probas[vertice]['vals']):
temp = []
for parent_index, parent in enumerate(probas[vertice]["parents"]):
# print str([str(float(index_outcome))])
temp = probas[vertice]["cprob"]
dataframe[parent] = None
vertexen[str(outcome)] = temp
dataframe['Probability'] = None
od = collections.OrderedDict(sorted(vertexen.items()))
# [str(float(i)) for i in ast.literal_eval(key)]
# str(v[key][int(float(k))-1])
# print "Vertice: " + str(vertice) + " with parents: " + str(probas[vertice]['parents'])
# print "Outcome" + "\t\t" + '\t\t'.join(probas[vertice]['parents']) + "\t\tProbability"
# print "------------" * len(probas[vertice]['parents']) *3
# pp.pprint(od.values())
counter = 0
# print number_of_cols
for outcome, cprobs in od.iteritems():
for key in cprobs.keys():
array_frame = []
array_frame.append((outcome))
print_string = str(outcome) + "\t\t"
for parent_value, parent in enumerate([i for i in ast.literal_eval(key)]):
# print "parent-value:"+str(parent_value)
# print "parten:"+str(parent)
array_frame.append(int(float(parent)))
# print "lengte array_frame: "+str(len(array_frame))
print_string += parent + "\t\t"
array_frame.append(cprobs[key][counter])
# print "lengte array_frame (2): "+str(len(array_frame))
# print cprobs[key][counter]
print_string += str(cprobs[key][counter]) + "\t"
# for stront in [str(round(float(i), 3)) for i in ast.literal_eval(key)]:
# print_string += stront + "\t\t"
# print "print string: " + print_string
# print "array_frame:" + str(array_frame)
dataframe.loc[len(dataframe)] = array_frame
counter += 1
print "Vertice " + str(vertice) + " done"
dataframes[vertice] = dataframe
for edge in edges:
dot_string += edge[0].replace(" ", "_") + ' -> ' + edge[1].replace(" ", "_") + ';\n'
dot_string += '}'
src = Source(dot_string)
if draw_network:src.render('../data/BN', view=draw_network)
if draw_network:src.render('../data/BN', view=False)
print "vizualisation done"
return dataframes
def on_stack_size_change(self, change):
self.stack_size = change['new']
with self.stack_display:
clear_output(wait=True)
display(Source(self.set_stack_display()))
process.setOrigin(origin)
print("Origin accessor : process = ")
print(process)
process.setTimeGrid(ot.RegularGrid(0, 1, 20))
print("Time grid accessor : process = ")
print(process)
real = process.getRealization()
print("Realization :")
print(real)
future = process.getFuture(20)
print("One future :")
print(future)
futures = process.getFuture(20, 3)
print("3 different futures :")
print(futures)
process.exportToDOTFile('markov.dot')
with open('markov.dot') as f:
print(f.read())
if 0:
from graphviz import Source
path = 'markov.dot'
s = Source.from_file(path)
s.view()
os.remove('markov.dot')
parameters = {
'criterion': ['entropy', 'gini'],
'min_samples_split': [2, 3, 4],
'max_depth': range(1, 20, 2),
'max_leaf_nodes': list(range(2, 100))
}
grid_search_cv = GridSearchCV(DecisionTreeClassifier(random_state=42),
parameters,
verbose=1,
cv=3)
grid_search_cv.fit(X_train, y_train)
print(grid_search_cv.best_estimator_)
tree1 = grid_search_cv.best_estimator_
y_pred = tree1.predict(X_test)
result = accuracy_score(y_test, y_pred)
print("Accuracy is", result * 100)
from graphviz import Source
from sklearn.tree import export_graphviz
export_graphviz(tree1,
out_file=os.path.join(IMAGES_PATH, "cancer_tree.dot"),
feature_names=cancer.feature_names,
class_names=cancer.target_names,
rounded=True,
filled=True)
Source.from_file(os.path.join(IMAGES_PATH, "cancer_tree.dot"))
def _text_to_graphiz(self, text):
"""create a graphviz graph from text"""
dot = Source(text, format='svg')
return dot.pipe().decode('utf-8')
def to_graphviz(booster, fmap='', num_trees=0, rankdir=None,
yes_color=None, no_color=None,
condition_node_params=None, leaf_node_params=None, **kwargs):
"""Convert specified tree to graphviz instance. IPython can automatically plot
the returned graphiz instance. Otherwise, you should call .render() method
of the returned graphiz instance.
Parameters
----------
booster : Booster, XGBModel
Booster or XGBModel instance
fmap: str (optional)
The name of feature map file
num_trees : int, default 0
Specify the ordinal number of target tree
rankdir : str, default "UT"
Passed to graphiz via graph_attr
yes_color : str, default '#0000FF'
Edge color when meets the node condition.
no_color : str, default '#FF0000'
Edge color when doesn't meet the node condition.
condition_node_params : dict, optional
Condition node configuration for for graphviz. Example:
.. code-block:: python
{'shape': 'box',
'style': 'filled,rounded',
'fillcolor': '#78bceb'}
leaf_node_params : dict, optional
Leaf node configuration for graphviz. Example:
.. code-block:: python
{'shape': 'box',
'style': 'filled',
'fillcolor': '#e48038'}
\\*\\*kwargs: dict, optional
Other keywords passed to graphviz graph_attr, e.g. ``graph [ {key} = {value} ]``
Returns
-------
graph: graphviz.Source
"""
try:
from graphviz import Source
except ImportError as e:
raise ImportError('You must install graphviz to plot tree') from e
if isinstance(booster, XGBModel):
booster = booster.get_booster()
# squash everything back into kwargs again for compatibility
parameters = 'dot'
extra = {}
for key, value in kwargs.items():
extra[key] = value
if rankdir is not None:
kwargs['graph_attrs'] = {}
kwargs['graph_attrs']['rankdir'] = rankdir
for key, value in extra.items():
if 'graph_attrs' in kwargs.keys():
kwargs['graph_attrs'][key] = value
else:
kwargs['graph_attrs'] = {}
del kwargs[key]
if yes_color is not None or no_color is not None:
kwargs['edge'] = {}
if yes_color is not None:
kwargs['edge']['yes_color'] = yes_color
if no_color is not None:
kwargs['edge']['no_color'] = no_color
if condition_node_params is not None:
kwargs['condition_node_params'] = condition_node_params
if leaf_node_params is not None:
kwargs['leaf_node_params'] = leaf_node_params
if kwargs:
parameters += ':'
parameters += str(kwargs)
tree = booster.get_dump(
fmap=fmap,
dump_format=parameters)[num_trees]
g = Source(tree)
return g
return thisnode
#############################################################################
X, y = make_data(m=200,
n=10,
k=5,
make_identical_observations_consistent=False,
seed=True)
tree = Tree(metric='gini', max_depth=6).fit(X, y)
ypred = tree.predict(X)
acc = np.equal(y, ypred).mean()
print("accuracy =", acc, "\tnumber of nodes =", tree._nodes_counter)
#graphviz
string = tree.graph
try:
from graphviz import Source
except:
print("Unable to import graphviz")
else:
graph = Source(string, filename="image", format="png")
graph.view()
from sklearn.tree import DecisionTreeClassifier
md = DecisionTreeClassifier(max_depth=6).fit(X, y)
acc = md.score(X, y)
print("sklearn acc", acc)
def write_graph(fields, containments, nests, matched_references, clusters):
# Start a digraph
graph = "digraph UML {\n"
# Set the image's size, in inches
graph += "size= \"33,33\";\n"
# Add a title
graph += "labelloc=\"t\";\n"
graph += "label=<<FONT POINT-SIZE=\"45\">GA4GH Schema Diagram</FONT>>;\n"
# Define node properties: shaped like UML items.
graph += "node [\n"
graph += "\tshape=plaintext\n"
graph += "]\n\n"
# Draw each node/type/record as a table
for type_name, field_list in fields.items():
graph += "{} [label=<\n".format(type_name)
graph += "<TABLE BORDER='0' CELLBORDER='1' CELLSPACING='0' CELLPADDING='4' bgcolor='#002060' color='#002060'>\n"
graph += "\t<TR>\n"
graph += "\t\t<TD COLSPAN='2' bgcolor='#79A6FF' border='3'><FONT POINT-SIZE='20' color='white'>{}</FONT>".format(type_name)
graph += "</TD>\n"
graph += "\t</TR>\n"
# Now draw the rows of fields for the type. A field_list of
# [a, b, c, d, e, f, g] will have [a, e] in row 1, [b, f] in
# row 2, [c, g] in row 3, and just [d] in row 4
num_fields = len(field_list)
for i in range(0, num_fields//2 + num_fields%2):
# Draw one row.
graph += "\t<TR>\n"
# Port number and displayed text will be the i'th field's
# name
graph += "\t\t<TD align='left' port='{}'><FONT color='white'>- {}</FONT></TD>\n".format(field_list[i][0], field_list[i][0])
if (num_fields%2) == 1 and (i == num_fields//2 + num_fields%2 - 1):
# Don't draw the second cell in the row if you have an
# odd number of fields and it is the last row
pass
else:
graph += "\t\t<TD align='left' port='{}'><FONT color='white'>- {}</FONT></TD>\n".format(field_list[num_fields//2 + num_fields%2 + i][0], field_list[num_fields//2 + num_fields%2 + i][0])
graph += "\t</TR>\n"
# Finish the table
graph += "</TABLE>>];\n\n"
# Now define the clusters/subgraphs
for cluster_name, cluster_types in clusters.items():
graph += "subgraph cluster_{} {{\n".format(cluster_name.replace(".", "_").replace("/", "_"))
graph += "\tstyle=\"rounded, filled\";\n"
graph += "\tcolor=lightgrey;\n"
graph += "\tnode [style=filled,color=white];\n"
graph += "\tlabel = \"{}\";\n".format(cluster_name.replace(".", "_"))
# After all the cluster formatting, define the cluster types
for cluster_type in cluster_types:
# cluster_type should match up with a type_name from fields
graph += "\t{};\n".format(cluster_type)
graph += "}\n\n"
# Define edge properties for containments
graph += "edge [\n"
graph += "\tdir=both\n"
graph += "\tarrowtail=odiamond\n"
graph += "\tarrowhead=none\n"
graph += "\tcolor=\"#C55A11\"\n"
graph += "\tpenwidth=2\n"
graph += "]\n\n"
for container, containee, container_field_name in containments:
# Now do the containment edges
# Only write the edge if the containee is a top-level field in fields.
if containee in fields:
graph += "{}:{}:w -> {}\n".format(container,
container_field_name, containee)
# Define edge properties for references
graph += "\nedge [\n"
graph += "\tdir=both\n"
graph += "\tarrowtail=none\n"
graph += "\tarrowhead=vee\n"
graph += "\tstyle=dashed\n"
graph += "\tcolor=\"darkgreen\"\n"
graph += "\tpenwidth=2\n"
graph += "]\n\n"
for referencer, referencer_field, referencee in matched_references:
# Now do the reference edges
graph += "{}:{}:w -> {}:id:w\n".format(referencer, referencer_field,
referencee)
# Close the digraph off.
graph += "}\n"
graph = graph.replace("\n", " ").replace("\t", " ")
src = Source(graph, format='svg')
src.render('_build/generated_images/schema_uml')