def plotDTree(dTree, treeName):
'''
Visualize decision tree
'''
dot_data = StringIO()
dot_data.write("graph dtree {\n")
nodeList = [dTree]
nodeIdxList = [0]
while len(nodeList) > 0:
latestIdx = nodeIdxList[-1]
node = nodeList[0]
del nodeList[0]
nodeIdx = nodeIdxList[0]
del nodeIdxList[0]
if node['type'] == LEAF:
nodeLabel = "gini: %.3f\nforecast: %d" % (node['gini'],
node['fcVal'])
dot_data.write("%d [label=\"%s\" shape=box]" %
(nodeIdx, nodeLabel))
else:
opName = "<=" if node['comparator'] == np.less_equal else "=="
nodeLabel = "X[%d]%s%.2f\ngini: %.3f" % (
node['splitFeature'],
opName,
node['splitValue'],
node['gini'],
)
dot_data.write("%d [label=\"%s\" shape=box]" %
(nodeIdx, nodeLabel))
for key in ['left', 'right']:
branch = node.get(key, None)
if branch:
latestIdx += 1
nodeList.append(branch)
nodeIdxList.append(latestIdx)
dot_data.write("%d -- %d\n" % (nodeIdx, latestIdx))
dot_data.write("}")
filename = "./trees/%s" % treeName
graph = graphviz.Source(dot_data.getvalue(),
filename=filename,
format="png")
graph.view()
test_prediction_rate = get_correct_ratio(test_results, test_survived)
print('{} : {}'.format("test_prediction_rate", test_prediction_rate))
dot_data = StringIO()
export_graphviz(titanic_tree,
out_file=dot_data,
filled=True,
rounded=True,
special_characters=True,
feature_names=titanic_data_features.columns.values,
class_names=["Died", "Survived"])
graph = pydotplus.graph_from_dot_data(dot_data.getvalue())
graph.write_png('tree.png')
png_str = graph.create_png(prog='dot')
# treat the dot output string as an image file
sio = StringIO()
sio.write(png_str)
sio.seek(0)
img = mpimg.imread(sio)
# plot the image
imgplot = plt.imshow(img, aspect='equal')
plt.show(block=False)
Y,
test_size=0.3,
random_state=1)
c5 = DecisionTreeClassifier(criterion='entropy', max_depth=4)
c5 = c5.fit(X_train, Y_train)
Y_pred = c5.predict(X_test)
print("Accuracy:", metrics.accuracy_score(Y_test, Y_pred))
dot_data = StringIO()
export_graphviz(c5,
out_file='dot_data',
filled=True,
rounded=True,
special_characters=False,
feature_names=columnList3)
with open("dot_data") as content_file:
dot_data.write(content_file.read())
graph = pydotplus.graph_from_dot_data(dot_data.getvalue())
graph.write_png('titanicTree.png')
"""
Naive Bayes Classification
"""
nbC = BernoulliNB(alpha=0)
nbC = nbC.fit(X, Y)
print(nbC.predict(X))
print(nbC.predict_proba(X))
print(nbC.score(X, Y))
#!/usr/bin/env python
'''Read and write a string as a file-like object.'''
from sklearn.externals.six import StringIO
# create a sample
mysample = StringIO()
mysample.write('My first testing line.')
print(
mysample) #this only will indicate the location of the file in the memory
# retrieve contents using getvalue()
content = mysample.getvalue()
print(content)
# close my sample
mysample.close()
