Python tree.export_graphviz方法代码示例

# 需要导入模块: from sklearn import tree [as 别名]
# 或者: from sklearn.tree import export_graphviz [as 别名]
def visualize_tree(data,clf,clf_name):
	features = data.columns
	features = features[:-1]
	class_names = list(set(data.iloc[:,-1]))
	dot_data = tree.export_graphviz(clf, out_file=None,  \
		feature_names=features,class_names=class_names,  \
		filled=True, rounded=True, special_characters=True)
	graph = graphviz.Source(dot_data)
	graph.render('dtree_render_'+clf_name,view=True)

# Function to perform training with giniIndex. 

# 需要导入模块: from sklearn import tree [as 别名]
# 或者: from sklearn.tree import export_graphviz [as 别名]
def test_plot_tree(pyplot):
    # mostly smoke tests
    # Check correctness of export_graphviz
    clf = DecisionTreeClassifier(max_depth=3,
                                 min_samples_split=2,
                                 criterion="gini",
                                 random_state=2)
    clf.fit(X, y)

    # Test export code
    feature_names = ['first feat', 'sepal_width']
    nodes = plot_tree(clf, feature_names=feature_names)
    assert len(nodes) == 3
    assert nodes[0].get_text() == ("first feat <= 0.0\nentropy = 0.5\n"
                                   "samples = 6\nvalue = [3, 3]")
    assert nodes[1].get_text() == "entropy = 0.0\nsamples = 3\nvalue = [3, 0]"
    assert nodes[2].get_text() == "entropy = 0.0\nsamples = 3\nvalue = [0, 3]" 

# 需要导入模块: from sklearn import tree [as 别名]
# 或者: from sklearn.tree import export_graphviz [as 别名]
def createTree(matrix,label):
	kmeans = KMeans(n_clusters=moa_clusters, random_state=0).fit(matrix)
	vector = map(int,kmeans.labels_)
	pc_10 = int(len(querymatrix1)*0.01)
	clf = tree.DecisionTreeClassifier(min_samples_split=min_sampsplit,min_samples_leaf=min_leafsplit,max_depth=max_d)
	clf.fit(matrix,vector)
	dot_data = StringIO()
	tree.export_graphviz(clf, out_file=dot_data,
							feature_names=label,
							class_names=map(str,list(set(sorted(kmeans.labels_)))),
							filled=True, rounded=True,
							special_characters=True,
							proportion=False,
							impurity=True)
	out_tree = dot_data.getvalue()
	out_tree = out_tree.replace('True','Inactive').replace('False','Active').replace(' ≤ 0.5', '').replace('class', 'Predicted MoA')
	graph = pydot.graph_from_dot_data(str(out_tree))
	try:
		graph.write_jpg(output_name_tree)
	except AttributeError:
		graph = pydot.graph_from_dot_data(str(out_tree))[0]
		graph.write_jpg(output_name_tree)
	return

#initializer for the pool 

# 需要导入模块: from sklearn import tree [as 别名]
# 或者: from sklearn.tree import export_graphviz [as 别名]
def show_pdf(clf):
    '''
    可视化输出
    把决策树结构写入文件: http://sklearn.lzjqsdd.com/modules/tree.html

    Mac报错: pydotplus.graphviz.InvocationException: GraphViz's executables not found
    解决方案: sudo brew install graphviz
    参考写入:  http://www.jianshu.com/p/59b510bafb4d
    '''
    # with open("testResult/tree.dot", 'w') as f:
    #     from sklearn.externals.six import StringIO
    #     tree.export_graphviz(clf, out_file=f)

    import pydotplus
    from sklearn.externals.six import StringIO
    dot_data = StringIO()
    tree.export_graphviz(clf, out_file=dot_data)
    graph = pydotplus.graph_from_dot_data(dot_data.getvalue())
    graph.write_pdf("../../../output/3.DecisionTree/tree.pdf")

    # from IPython.display import Image
    # Image(graph.create_png()) 

# 需要导入模块: from sklearn import tree [as 别名]
# 或者: from sklearn.tree import export_graphviz [as 别名]
def show_pdf(clf):
    '''
    可视化输出
    把决策树结构写入文件: http://sklearn.lzjqsdd.com/modules/tree.html

    Mac报错: pydotplus.graphviz.InvocationException: GraphViz's executables not found
    解决方案: sudo brew install graphviz
    参考写入:  http://www.jianshu.com/p/59b510bafb4d
    '''
    # with open("testResult/tree.dot", 'w') as f:
    #     from sklearn.externals.six import StringIO
    #     tree.export_graphviz(clf, out_file=f)

    import pydotplus
    from sklearn.externals.six import StringIO
    dot_data = StringIO()
    tree.export_graphviz(clf, out_file=dot_data)
    graph = pydotplus.graph_from_dot_data(dot_data.getvalue())
    graph.write_pdf("output/3.DecisionTree/tree.pdf")

    # from IPython.display import Image
    # Image(graph.create_png()) 

# 需要导入模块: from sklearn import tree [as 别名]
# 或者: from sklearn.tree import export_graphviz [as 别名]
def visualize_tree(clf, feature_names, class_names, output_file,
                   method='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,
                         impurity=False)
    graph = pydotplus.graph_from_dot_data(dot_data.getvalue())
    if method == 'pdf':
        graph.write_pdf(output_file + ".pdf")
    elif method == 'inline':
        Image(graph.create_png())

    return graph

# An example using the iris dataset 

# 需要导入模块: from sklearn import tree [as 别名]
# 或者: from sklearn.tree import export_graphviz [as 别名]
def visualize_tree(data,clf,clf_name):
	features = data.columns
	features = features[:-1]
	class_names = list(set(data.iloc[:,-1]))
	dot_data = tree.export_graphviz(clf, out_file=None,  feature_names=features,class_names=class_names,  filled=True, rounded=True, special_characters=True)
	graph = graphviz.Source(dot_data)
	graph.render('dtree_render_'+clf_name,view=True)

# Function to perform training with giniIndex. 

# 需要导入模块: from sklearn import tree [as 别名]
# 或者: from sklearn.tree import export_graphviz [as 别名]
def test_graphviz_errors():
    # Check for errors of export_graphviz
    clf = DecisionTreeClassifier(max_depth=3, min_samples_split=2)

    # Check not-fitted decision tree error
    out = StringIO()
    assert_raises(NotFittedError, export_graphviz, clf, out)

    clf.fit(X, y)

    # Check if it errors when length of feature_names
    # mismatches with number of features
    message = ("Length of feature_names, "
               "1 does not match number of features, 2")
    assert_raise_message(ValueError, message, export_graphviz, clf, None,
                         feature_names=["a"])

    message = ("Length of feature_names, "
               "3 does not match number of features, 2")
    assert_raise_message(ValueError, message, export_graphviz, clf, None,
                         feature_names=["a", "b", "c"])

    # Check error when argument is not an estimator
    message = "is not an estimator instance"
    assert_raise_message(TypeError, message,
                         export_graphviz, clf.fit(X, y).tree_)

    # Check class_names error
    out = StringIO()
    assert_raises(IndexError, export_graphviz, clf, out, class_names=[])

    # Check precision error
    out = StringIO()
    assert_raises_regex(ValueError, "should be greater or equal",
                        export_graphviz, clf, out, precision=-1)
    assert_raises_regex(ValueError, "should be an integer",
                        export_graphviz, clf, out, precision="1") 

# 需要导入模块: from sklearn import tree [as 别名]
# 或者: from sklearn.tree import export_graphviz [as 别名]
def test_friedman_mse_in_graphviz():
    clf = DecisionTreeRegressor(criterion="friedman_mse", random_state=0)
    clf.fit(X, y)
    dot_data = StringIO()
    export_graphviz(clf, out_file=dot_data)

    clf = GradientBoostingClassifier(n_estimators=2, random_state=0)
    clf.fit(X, y)
    for estimator in clf.estimators_:
        export_graphviz(estimator[0], out_file=dot_data)

    for finding in finditer(r"\[.*?samples.*?\]", dot_data.getvalue()):
        assert_in("friedman_mse", finding.group()) 

# 需要导入模块: from sklearn import tree [as 别名]
# 或者: from sklearn.tree import export_graphviz [as 别名]
def createTree(matrix,label):
	vector = [1] * len(querymatrix1) + [0] * len(querymatrix2)
	ratio = float(len(vector)-sum(vector))/float(sum(vector))
	sw = np.array([ratio if i == 1 else 1 for i in vector])
	pc_10 = int(len(querymatrix1)*0.01)
	clf = tree.DecisionTreeClassifier(min_samples_split=min_sampsplit,min_samples_leaf=min_leafsplit,max_depth=max_d)
	clf.fit(matrix,vector)
	dot_data = StringIO()
	tree.export_graphviz(clf, out_file=dot_data,
							feature_names=label,
							class_names=['File2','File1'],
							filled=True, rounded=True,
							special_characters=True,
							proportion=False,
							impurity=True)
	out_tree = dot_data.getvalue()
	out_tree = out_tree.replace('True','Inactive').replace('False','Active').replace(' ≤ 0.5', '')
	graph = pydot.graph_from_dot_data(str(out_tree))
	try:
		graph.write_jpg(output_name_tree)
	except AttributeError:
		graph = pydot.graph_from_dot_data(str(out_tree))[0]
		graph.write_jpg(output_name_tree)
	return

#initializer for the pool 

# 需要导入模块: from sklearn import tree [as 别名]
# 或者: from sklearn.tree import export_graphviz [as 别名]
def graphviz(self):
    if self.clf is None:
      log("Loading model...")
      self.clf = joblib.load("clf.pkl")

    dot_data = tree.export_graphviz(self.clf, out_file="pigaios.dot", \
                                    filled=True, rounded=True, \
                                    special_characters=True)
    os.system("dot -Tx11 pigaios.dot")

#------------------------------------------------------------------------------- 

# 需要导入模块: from sklearn import tree [as 别名]
# 或者: from sklearn.tree import export_graphviz [as 别名]
def visualize(tree, save_path):
    """Generate PDF of a decision tree.

    @param tree: DecisionTreeClassifier instance
    @param save_path: string 
                      where to save tree PDF
    """
    dot_data = export_graphviz(tree, out_file=None,
                               filled=True, rounded=True)
    graph = pydotplus.graph_from_dot_data(dot_data)
    graph = make_graph_minimal(graph)  # remove extra text

    if not save_path is None:
        graph.write_pdf(save_path) 

# 需要导入模块: from sklearn import tree [as 别名]
# 或者: from sklearn.tree import export_graphviz [as 别名]
def test_objectmapper(self):
        df = pdml.ModelFrame([])
        self.assertIs(df.tree.DecisionTreeClassifier, tree.DecisionTreeClassifier)
        self.assertIs(df.tree.DecisionTreeRegressor, tree.DecisionTreeRegressor)
        self.assertIs(df.tree.ExtraTreeClassifier, tree.ExtraTreeClassifier)
        self.assertIs(df.tree.ExtraTreeRegressor, tree.ExtraTreeRegressor)
        self.assertIs(df.tree.export_graphviz, tree.export_graphviz) 

# 需要导入模块: from sklearn import tree [as 别名]
# 或者: from sklearn.tree import export_graphviz [as 别名]
def sample_1033_1():
    """
    10.3.3 通过决策树分类，绘制出决策图
    这里需要安装dot graphviz，才能通过os.system("dot -T png graphviz.dot -o graphviz.png")生成png
    :return:
    """
    from sklearn.tree import DecisionTreeClassifier
    from sklearn import tree
    import os

    estimator = DecisionTreeClassifier(max_depth=2, random_state=1)

    # noinspection PyShadowingNames
    def graphviz_tree(estimator, features, x, y):
        if not hasattr(estimator, 'tree_'):
            print('only tree can graphviz!')
            return

        estimator.fit(x, y)
        # 将决策模型导出graphviz.dot文件
        tree.export_graphviz(estimator.tree_, out_file='graphviz.dot',
                             feature_names=features)
        # 通过dot将模型绘制决策图，保存png
        os.system("dot -T png graphviz.dot -o graphviz.png")

    global g_with_date_week_noise
    g_with_date_week_noise = True
    train_x, train_y_regress, train_y_classification, pig_three_feature, \
    test_x, test_y_regress, test_y_classification, kl_another_word_feature_test = sample_1031_1()

    # 这里会使用到特征的名称列pig_three_feature.columns[1:]
    graphviz_tree(estimator, pig_three_feature.columns[1:], train_x,
                  train_y_classification)

    import PIL.Image
    PIL.Image.open('graphviz.png').show() 

# 需要导入模块: from sklearn import tree [as 别名]
# 或者: from sklearn.tree import export_graphviz [as 别名]
def export_model(self, IDcol):
        #Export the model into the model file as well as create a submission 
        #with model index. This will be used for creating an ensemble.
        self.export_model_base(IDcol,'decision_tree')

    ## UNDER DEVELOPMENT CODE FOR PRINTING TREES
    # def get_tree(self):
    #     return self.alg.tree_
    # Print the tree in visual format
    # Inputs:
    #     export_pdf - if True, a pdf will be exported with the 
    #     filename as specified in pdf_name argument
    #     pdf_name - name of the pdf file if export_pdf is True
    # def printTree(self, export_pdf=True, file_name="Decision_Tree.pdf"):
    #     dot_data = StringIO() 
    #     export_graphviz(
    #             self.alg, out_file=dot_data, feature_names=self.predictors,
    #             filled=True, rounded=True, special_characters=True)

    #     export_graphviz(
    #         self.alg, out_file='data.dot', feature_names=self.predictors,  
    #         filled=True, rounded=True, special_characters=True
    #         ) 
    #     graph = pydot.graph_from_dot_data(dot_data.getvalue())
        
    #     if export_pdf:
    #         graph.write_pdf(file_name)

    #     return graph

#####################################################################
##### RANDOM FOREST
#####################################################################