def visit_LoadVar(self, node):
label = node.name
node_id = self.node_id()
node_label = " LoadVar(" + str(label) + ")"
node_text = get_node_text(node_id, node_label)
self.dot.node(node_id, node_text)
return node_id
def visit_Statement(self, node):
node_id = self.node_id()
node_label = " stmt"
node_text = get_node_text(node_id, node_label)
stmt = self.visit(node.statement)
self.dot.edge(node_id, stmt)
self.dot.node(node_id, node_text)
return node_id
def visit_GroupParent(self, node): #obsoleto
node_id = self.node_id()
node_label = " Group "
node_text = get_node_text(node_id, node_label)
expr = self.visit(node.expr)
self.dot.edge(node_id, expr)
self.dot.node(node_id, node_text)
return node_id
def visit_PrintValue(self, node): #obsoleto
node_id = self.node_id()
node_label = " Print "
node_text = get_node_text(node_id, node_label)
value_id = self.visit(node.value)
self.dot.edge(node_id, value_id)
self.dot.node(node_id, node_text)
return node_id
def visit_Expression(self, node):
node_id = self.node_id()
node_label = " expr"
node_text = get_node_text(node_id, node_label)
expr = self.visit(node.expression)
self.dot.edge(node_id, expr)
self.dot.node(node_id, node_text)
return node_id
def visit_UnaryOp(self, node):
node_id = self.node_id()
node_label = " UnaryOp (" + node.op + ") "
node_text = get_node_text(node_id, node_label)
left_id = self.visit(node.right)
self.dot.edge(node_id, left_id)
self.dot.node(node_id, node_text)
return node_id
def visit_ReturnValue(self, node):
node_id = self.node_id()
node_label = " Return "
node_text = get_node_text(node_id, node_label)
self.dot.node(node_id, node_text)
value_id = self.visit(node.value)
self.dot.edge(node_id, value_id)
return node_id
def visit_BinaryOp(self, node):
node_id = self.node_id()
node_label = str(node.op)
node_text = get_node_text(node_id, node_label)
self.dot.node(node_id, node_text)
l = self.visit(node.left)
r = self.visit(node.right)
self.dot.edge(node_id, l)
self.dot.edge(node_id, r)
return node_id
def visit_PrList(self, node):
node_id = self.node_id()
node_label = "Print"
node_text = get_node_text(node_id, node_label)
self.dot.node(node_id, node_text)
for obj in node.prlist:
if not (node.__class__.__name__ == "Empty"):
list_obj = self.visit(obj)
self.dot.edge(node_id, list_obj)
return node_id
def visit_ArgList(self, node):
node_id = self.node_id()
node_label = "Args"
node_text = get_node_text(node_id, node_label)
self.dot.node(node_id, node_text)
for node in node.arglist:
if not (node.__class__.__name__ == "Empty"):
list_obj = self.visit(node)
self.dot.edge(node_id, list_obj)
return node_id
def visit_Literal(self, node):
label = node.value
node_id = self.node_id()
node_label = str(label)
node_text = get_node_text(node_id, node_label)
if label == '\n':
label = 'NEWLINE'
self.dot.node(node_id, node_text)
return node_id
def visit_StatementList(self, node):
node_id = self.node_id()
node_label = "Statements"
node_text = get_node_text(node_id, node_label)
self.dot.node(node_id, node_text)
for node in node.statements:
if not (node.__class__.__name__ == "Empty"):
list_obj = self.visit(node)
self.dot.edge(node_id, list_obj)
return node_id
def visit_ProgList(self, node):
node_id = self.node_id()
node_label = "Program"
node_text = get_node_text(node_id, node_label)
self.dot.node(node_id, node_text)
for node in node.proglist:
if not (node.__class__.__name__ in ["Empty", "Comment"]):
list_obj = self.visit(node)
self.dot.edge(node_id, list_obj)
return node_id
def visit_Calls(self, node):
node_id = self.node_id()
node_label = " Calls " + str(node.n_params)
node_text = get_node_text(node_id, node_label)
self.dot.node(node_id, node_text)
function_id = self.visit(node.function)
arglist_id = self.visit(node.arglist)
self.dot.edge(node_id, function_id)
self.dot.edge(node_id, arglist_id)
return node_id
def visit_FuncDef(self, node):
node_id = self.node_id()
node_label = " Def " + str(node.n_params)
node_text = get_node_text(node_id, node_label)
self.dot.node(node_id, node_text)
function_id = self.visit(node.function)
formals_id = self.visit(node.formals)
stmt_id = self.visit(node.stmt)
self.dot.edge(node_id, function_id)
self.dot.edge(node_id, formals_id)
self.dot.edge(node_id, stmt_id)
return node_id
def visit_IfStatement(self, node):
node_id = self.node_id()
node_label = " If "
node_text = get_node_text(node_id, node_label)
self.dot.node(node_id, node_text)
cond_id = self.visit(node.cond)
then_stmt_id = self.visit(node.then_stmt)
else_stmt = node.else_stmt
if else_stmt:
else_stmt_id = self.visit(node.else_stmt)
self.dot.edge(node_id, else_stmt_id)
self.dot.edge(node_id, cond_id)
self.dot.edge(node_id, then_stmt_id)
return node_id
def visit_SymTab(self, node):
node_id = self.node_id()
node_label = node.name
node_text = get_node_text(node_id, node_label)
node_text += "\n-------------\n"
for p in node.entries.keys():
node_text += p + "\n"
# if len(node.errors)>0:
# print "===========Errores Semanticos==============="
# for error in node.errors:
# print error
# print node_text
self.dot.node(node_id, node_text)
for child in node.children:
child_id = self.visit(child)
self.dot.edge(node_id, child_id)
return node_id
def get_graph_plot_colored_by_election_results(pipeline, year, df, data,
keep_layout):
'''Function make plot of US with counties colored by winner of election
Parameters
----------
pipe : MapperPipeline
The Mapper pipeline to compute the mapper-graph
year : np.int
Color by election results from year `year`
df : pandas data frame
Data frame containing info of winner per county, year of election and
number of electors in county
data : ndarray (n_samples x n_dim)
Data used for mapper
keep_layout : list of two dicts, with keys 'x', 'y', and such that values are 1d arrays
Positions of lines (keep_layout[0]) and markers respectively (keep_layout[1])
for the mapper graph
Returns
-------
fig: igraph object
'''
node_elements = pipeline.fit_transform(
data)['node_metadata']['node_elements']
# set node color to percentage of number of electors won by republicans
node_color = np.array([
100 * (df[df['year'] == year]['winner'].values *
df[df['year'] == year]['n_electors'].values)[x].sum() /
df[df['year'] == year]['n_electors'].values[x].sum()
for x in node_elements
])
data_cols = utils.get_cols_for_mapper()
columns_to_color = dict(zip(data_cols, range(len(data_cols))))
node_text = utils.get_node_text(
dict(zip(range(len(node_elements)), node_elements)),
utils.get_n_electors(
node_elements,
df[df['year'] == year]['n_electors'].reset_index(drop=True)),
node_color, 'Percentage of Electors Won by Republicans')
plotly_kwargs = {
'node_trace_marker_colorscale':
'RdBu',
'node_trace_marker_reversescale':
True,
'node_trace_marker_cmin':
0,
'node_trace_marker_cmax':
100,
'node_trace_text':
node_text,
'node_trace_marker_size':
utils.get_n_electors(
node_elements,
df[df['year'] == year]['n_electors'].reset_index(drop=True)),
'node_trace_marker_sizeref':
.5 / max(
utils.get_n_electors(
node_elements,
df[df['year'] == year]['n_electors'].reset_index(drop=True)))
}
fig = plot_static_mapper_graph(pipeline,
data,
'kk',
layout_dim=2,
node_color_statistic=node_color,
color_by_columns_dropdown=True,
plotly_kwargs=plotly_kwargs)
if keep_layout is not None:
fig._data[0].update(keep_layout[0])
fig._data[1].update(keep_layout[1])
return fig
def _parse_xml_metadata(element):
"""Extract metadata from an xml.dom.Element object (ELEMENT_NODE)
The "<metadata>" tag has a lot of metadatas about the epub this method
inspect and store into object attributes (like "title" or "creator").
"""
metadata = Metadata()
for node in element.getElementsByTagName('dc:title'):
metadata.add_title(get_node_text(node), node.getAttribute('xml:lang'))
for node in element.getElementsByTagName('dc:creator'):
metadata.add_creator(get_node_text(node),
node.getAttribute('opf:role'),
node.getAttribute('opf:file-as'))
for node in element.getElementsByTagName('dc:subject'):
metadata.add_subject(get_node_text(node))
for node in element.getElementsByTagName('dc:description'):
metadata.description = get_node_text(node)
# Custom change to support description in some books not starting with dc:
if metadata.description in [None, ""]:
for node in element.getElementsByTagName('description'):
metadata.description = get_node_text(node)
for node in element.getElementsByTagName('dc:publisher'):
metadata.publisher = get_node_text(node)
for node in element.getElementsByTagName('dc:contributor'):
metadata.add_contributor(get_node_text(node),
node.getAttribute('opf:role'),
node.getAttribute('opf:file-as'))
for node in element.getElementsByTagName('dc:date'):
metadata.add_date(get_node_text(node), node.getAttribute('opf:event'))
for node in element.getElementsByTagName('dc:type'):
metadata.dc_type = get_node_text(node)
for node in element.getElementsByTagName('dc:format'):
metadata.format = get_node_text(node)
for node in element.getElementsByTagName('dc:identifier'):
metadata.add_identifier(get_node_text(node), node.getAttribute('id'),
node.getAttribute('opf:scheme'))
for node in element.getElementsByTagName('dc:source'):
metadata.source = get_node_text(node)
for node in element.getElementsByTagName('dc:language'):
metadata.add_language(get_node_text(node))
for node in element.getElementsByTagName('dc:relation'):
metadata.relation = get_node_text(node)
for node in element.getElementsByTagName('dc:coverage'):
metadata.coverage = get_node_text(node)
for node in element.getElementsByTagName('dc:rights'):
metadata.right = get_node_text(node)
for node in element.getElementsByTagName('meta'):
metadata.add_meta(node.getAttribute('name'),
node.getAttribute('content'))
return metadata
def visit_Empty(self, node):
node_id = self.node_id()
node_label = "Empty"
node_text = get_node_text(node_id, node_label)
self.dot.node(node_id, node_text)
return node_id
def _parse_xml_metadata(element):
"""Extract metadata from an xml.dom.Element object (ELEMENT_NODE)
The "<metadata>" tag has a lot of metadatas about the epub this method
inspect and store into object attributes (like "title" or "creator").
"""
metadata = Metadata()
for node in element.getElementsByTagName('dc:title'):
metadata.add_title(get_node_text(node),
node.getAttribute('xml:lang'))
for node in element.getElementsByTagName('dc:creator'):
metadata.add_creator(get_node_text(node),
node.getAttribute('opf:role'),
node.getAttribute('opf:file-as'))
for node in element.getElementsByTagName('dc:subject'):
metadata.add_subject(get_node_text(node))
for node in element.getElementsByTagName('dc:description'):
metadata.description = get_node_text(node)
for node in element.getElementsByTagName('dc:publisher'):
metadata.publisher = get_node_text(node)
for node in element.getElementsByTagName('dc:contributor'):
metadata.add_contributor(get_node_text(node),
node.getAttribute('opf:role'),
node.getAttribute('opf:file-as'))
for node in element.getElementsByTagName('dc:date'):
metadata.add_date(get_node_text(node),
node.getAttribute('opf:event'))
for node in element.getElementsByTagName('dc:type'):
metadata.dc_type = get_node_text(node)
for node in element.getElementsByTagName('dc:format'):
metadata.format = get_node_text(node)
for node in element.getElementsByTagName('dc:identifier'):
metadata.add_identifier(get_node_text(node),
node.getAttribute('id'),
node.getAttribute('opf:scheme'))
for node in element.getElementsByTagName('dc:source'):
metadata.source = get_node_text(node)
for node in element.getElementsByTagName('dc:language'):
metadata.add_language(get_node_text(node))
for node in element.getElementsByTagName('dc:relation'):
metadata.relation = get_node_text(node)
for node in element.getElementsByTagName('dc:coverage'):
metadata.coverage = get_node_text(node)
for node in element.getElementsByTagName('dc:rights'):
metadata.right = get_node_text(node)
for node in element.getElementsByTagName('meta'):
metadata.add_meta(node.getAttribute('name'),
node.getAttribute('content'))
return metadata
def get_graph_plot_colored_by_election_results(graph, year, df, data,
layout=None):
'''Function make plot of US with counties colored by winner of election
Parameters
----------
graph : igraph object
Mapper graph
df : pandas data frame
Data frame containing info of winner per county, year of election and
number of electors in county
data : ndarray (n_samples x n_dim)
Data used for mapper
layout : igraph.layout.Layout (default: None)
Layout of graph
Returns
-------
fig: igraph object
'''
node_elements = graph['node_metadata']['node_elements']
if layout is None:
layout = graph.layout('kk', dim=2)
# set node color to percentage of number of electors won by republicans
node_color = [
100 * (df[df['year'] == year]['winner'].values *
df[df['year'] == year]['n_electors'].values)[x].sum() /
df[df['year'] == year]['n_electors'].values[x].sum()
for x in node_elements]
data_cols = utils.get_cols_for_mapper()
columns_to_color = dict(zip(data_cols, range(len(data_cols))))
node_text = utils.get_node_text(
dict(zip(range(len(node_elements)),
node_elements)),
utils.get_n_electors(node_elements,
df[df['year'] == year]['n_electors']
.reset_index(drop=True)),
node_color,
'Percentage of Electors Won by Republicans')
plotly_kwargs = {
'node_trace_marker_colorscale': 'RdBu',
'node_trace_marker_reversescale': True,
'node_trace_marker_cmin': 0,
'node_trace_marker_cmax': 100,
'node_trace_text': node_text,
'node_trace_marker_size':
utils.get_n_electors(node_elements,
df[df['year'] == year]['n_electors']
.reset_index(drop=True)),
'node_trace_marker_sizeref':
.5 / max(utils.get_n_electors(node_elements,
df[df['year'] == year]['n_electors']
.reset_index(drop=True)))}
return visualization.create_network_2d(graph, data, layout, node_color,
columns_to_color=columns_to_color,
plotly_kwargs=plotly_kwargs)