def evaluate_embeddings(embeddings):
X, Y = read_node_label('../data/flight/labels-brazil-airports.txt',
skip_head=True)
tr_frac = 0.8
print("Training classifier using {:.2f}% nodes...".format(tr_frac * 100))
clf = Classifier(embeddings=embeddings, clf=LogisticRegression())
clf.split_train_evaluate(X, Y, tr_frac)
def evaluate_embeddings(embeddings):
X, Y = read_node_label('../data/wiki/wiki_labels.txt')
tr_frac = 0.8
print("Training classifier using {:.2f}% nodes...".format(
tr_frac * 100))
clf = Classifier(embeddings=embeddings, clf=LogisticRegression())
clf.split_train_evaluate(X, Y, tr_frac)
def evaluate_embeddings(embeddings):
#读入真实的分类label
X, Y = read_node_label('../data/wiki/wiki_labels.txt')
tr_frac = 0.8 #80%的节点用于训练分类器，其余的用于测试
print("Training classifier using {:.2f}% nodes...".format(tr_frac * 100))
#应用分类器对节点进行分类以评估向量的质量
clf = Classifier(embeddings=embeddings, clf=LogisticRegression())
clf.split_train_evaluate(X, Y, tr_frac)
def evaluate_embeddings(embeddings, X, Y, X_train, y_train, X_test, y_test,
log_key):
clf = Classifier(embeddings=embeddings,
clf=LogisticRegression(solver='liblinear'))
clf.split_train_evaluate(X,
Y,
X_train,
y_train,
X_test,
y_test,
log_key=log_key)
def evaluate_embeddings(embeddings):
X, Y = read_node_label(
'../data/ETH/Phishing node classification/label.txt', skip_head=True)
tr_frac = 0.8
print("Training classifier using {:.2f}% nodes...".format(tr_frac * 100))
clf = Classifier(embeddings=embeddings, clf=LogisticRegression())
clf.split_train_evaluate(X, Y, tr_frac)
def evaluate_embeddings(embeddings):
"""分割训练评估，输出性能参数
:param embeddings:
"""
# X, Y = read_node_label('../data/wiki/wiki_labels.txt')
# X, Y = read_node_label('../data/flight/labels-brazil-airports.txt', True)
# X, Y = read_node_label('../data/flight/labels-europe-airports.txt', True)
X, Y = read_node_label('../data/flight/labels-usa-airports.txt', True)
tr_frac = 0.8 # 交叉验证百分比
print("Training classifier using {:.2%} nodes...".format(tr_frac))
clf = Classifier(embeddings=embeddings, clf=LogisticRegression())
return clf.split_train_evaluate(X, Y, tr_frac)
def evaluate_embeddings(embeddings):
"""
一个分类器函数，用来评价向量好坏，因为每个实体有对应的标签，通过向量实现多分类
:param embeddings:
:return:
"""
X, Y = read_node_label(
'/Users/admin/Desktop/GraphEmbedding-deeplearning/data/XunYiWenYao/寻医问药category.txt'
)
tr_frac = 0.8
print("Training classifier using {:.2f}% nodes...".format(tr_frac * 100))
clf = Classifier(embeddings=embeddings, clf=LogisticRegression())
clf.split_train_evaluate(X, Y, tr_frac)