def fun_1_5_4():
from nltk import metrics
# 二进制距离是一个字符串相似性指标。如果两个标签相同,它的返回值为 0.0;否则,
# 它的返回值为 1.0
def binary_distance(label1, label2):
return 0.0 if label1 == label2 else 1.0
print metrics.binary_distance((10, 20, 30, 40), (30, 50, 70))
# 当存在多个标签时,Masi 距离基于部分协议。
# 包含在 nltk.metrics 包中的 masi 距离算法的 Python 代码如下
def masi_distance(label1, label2):
len_intersection = len(label1.intersection(label2))
len_union = len(label1.union(label2))
len_label1 = len(label1)
len_label2 = len(label2)
if len_label1 == len_label2 and len_label1 == len_intersection:
m = 1
elif len_intersection == min(len_label1, len_label2):
m = 0.67
elif len_intersection > 0:
m = 0.33
else:
m = 0
return 1 - (len_intersection / float(len_union)) * m
print metrics.masi_distance((10, 20, 30, 40), (30, 50, 70))
def multi_metrics(multi_classifier, test_feats):
mds = []
refsets = collections.defaultdict(set)
testsets = collections.defaultdict(set)
for i, (feat, labels) in enumerate(test_feats):
for label in labels:
refsets[label].add(i)
guessed = multi_classifier.classify(feat)
for label in guessed:
testsets[label].add(i)
mds.append(metrics.masi_distance(set(labels), guessed))
avg_md = sum(mds) / float(len(mds))
precisions = {}
recalls = {}
for label in multi_classifier.labels():
precisions[label] = metrics.precision(refsets[label], testsets[label])
recalls[label] = metrics.recall(refsets[label], testsets[label])
return precisions, recalls, avg_md
def multi_metrics(multi_classifier, test_feats):
mds = []
refsets = collections.defaultdict(set)
testsets = collections.defaultdict(set)
for i, (feat, labels) in enumerate(test_feats):
for label in labels:
refsets[label].add(i)
guessed = multi_classifier.classify(feat)
for label in guessed:
testsets[label].add(i)
mds.append(metrics.masi_distance(set(labels), guessed))
avg_md = sum(mds) / float(len(mds))
precisions = {}
recalls = {}
for label in multi_classifier.labels():
precisions[label] = metrics.precision(refsets[label], testsets[label])
recalls[label] = metrics.recall(refsets[label], testsets[label])
return precisions, recalls, avg_md
def masi(tk1,tk2):
return masi_distance(set(tk1),set(tk2))
# string jaro_similarity
# jaro_winkler_similarity
def avg_masi_distance(multi_classifier, multi_label_feats):
mds = []
for feat, labels in multi_label_feats:
mds.append(masi_distance(labels, multi_classifier.classify(feat)))
if mds:
return float(sum(mds)) / len(mds)
else:
return 0.0
def avg_masi_distance(multi_classifier, multi_label_feats): mds = [] for feat, labels in multi_label_feats: mds.append(masi_distance(labels, multi_classifier.classify(feat))) if mds: return float(sum(mds)) / len(mds) else: return 0.0
def score(self, lbl_types, ref_types, stemmed_word):
"""Gives the Masi distance between the two sets."""
# Hack: ref 23643 is empty after applying rules & so it case "A*D" from csv file
if not len(ref_types): return 1
if stemmed_word:
ref_types = self.replace_stem(stemmed_word, ref_types, lbl_types)
return masi_distance(lbl_types, ref_types)
def masi_distance_chunk(D):
'''
Calculates masi distance between tokenized list pairs
of questions and saves the result to a column specified by the
environment variable MASI_DISTANCE
'''
if len(D) > 0:
D[MASI_DISTANCE] = D.loc[:, Q_WORD_TOKENIZED].apply(
lambda x: masi_distance(set(literal_eval(x[0])),
set(literal_eval(x[1]))),
axis=1)
return D
training = 'PERSON OTHER PERSON OTHER OTHER ORGANIZATION'.split()
testing = 'PERSON OTHER OTHER OTHER OTHER OTHER'.split()
print(accuracy(training, testing))
trainset = set(training)
testset = set(testing)
print(precision(trainset, testset)) # 准确率
print(recall(trainset, testset)) # 召回率
print(f_measure(trainset, testset))
# 计算 编辑距离 复制 cost为0, 替换、删除、插入cost为1
from nltk.metrics import edit_distance
print(edit_distance('relate', 'relation'))
print(edit_distance('suggestion', 'calculation'))
# 使用Jaccard系数执行相似性度量 , ｜X 交 Y｜/｜X 并 Y｜
from nltk.metrics import jaccard_distance
X = set([10, 20, 30, 40])
Y = set([20, 30, 60])
print(jaccard_distance(X, Y))
# 二进制距离算法度量 便签相同返回0.0，否则1.0
from nltk.metrics import binary_distance
print(binary_distance(X, Y))
# 存在多个标签，Masi距离算法
from nltk.metrics import masi_distance
print(masi_distance(X, Y))
def _masi_distance(self, s1, s2):
return masi_distance(set(s1), set(s2))
