#准确率
precision = float(same_num) / len(my_seg_node_list)
#覆盖率
recall = float(same_num) / len(stardard_seg_node_list)
return (precision, recall)
if __name__ == "__main__":
if len(sys.argv) != 3:
print "please input dict file and test data file"
sys.exit()
#训练的词典
dict_file_name = sys.argv[1]
my_seg = e_segment.DNASegment()
my_seg.initial_dict(dict_file_name)
#读取测试文件并测试
test_file = open(sys.argv[2], "r")
precison_sum = 0
recall_sum = 0
line_num = 0
seg_pos_precision_sum = 0
seg_pos_recall_sum = 0
line_list = test_file.readlines()
for i in range(0, len(line_list), 3):
#字符串
line = line_list[i].strip()
precision = float(same_num) / len(my_seg_node_list)
#覆盖率
recall = float(same_num) / len(stardard_seg_node_list)
return (precision, recall)
if __name__ == "__main__":
if len(sys.argv) != 3:
print "please input dict file and test data file"
sys.exit()
#构建分词
#标准词典
standard_dict = "count_1w.txt"
stardard_seg = e_segment.DNASegment()
stardard_seg.initial_dict(standard_dict)
#训练的词典
dict_file_name = sys.argv[1]
my_seg = mi_segment.MISegment()
my_seg.load_dict(dict_file_name)
#读取测试文件并测试
test_file = open(sys.argv[2], "r")
precison_sum = 0
recall_sum = 0
line_num = 0
seg_pos_precision_sum = 0
seg_pos_recall_sum = 0