def tms_grid_param(problem_path,
result_save_path="../svm.param",
svm_type="libsvm",
coarse_c_range=(-5, 7, 2),
coarse_g_range=(3, -10, -2),
fine_c_step=0.5,
fine_g_step=0.5):
'''对SVM的参数进行搜索,如果是libsvm则搜索(c,gamma)，如果是liblinear则搜索(c)。当训练样本的容量大于3000时就会在粗粒度搜索时使用子集，子集的大小为[3000,5000]范围内。
当
必须参数：
problem_path：SVM输入格式文件的路径即名称。
可选参数:
result_save_path:结果文件的保存路径:默认为"../svm.param"
svm_type :选择的SVM的类型，默认为libsvm
coarse_c_range ：粗粒度搜索时c搜索的范围，默认情况下为[-5,7],步长为2
coarse_g_range：粗粒度搜索时g搜索的范围，默认情况下为[3,-10]步长为-2
fine_c_step ：细粒度搜索时c的步长，默认情况下为0.5
fine_c_step ：细粒度搜索时c的步长，默认情况下为0.5
'''
if svm_type == "liblinear":
coarse_g_range = (1, 1, 1)
fine_g_step = 0
c, g = grid_search_param.grid(problem_path, result_save_path, svm_type,
coarse_c_range, coarse_g_range, fine_c_step,
fine_g_step)
print "best c=%s ,g=%s" % (c, g)
return c, g
def train(train_docs, main_save_path,
config_name, model_name, train_name, param_name, svm_param, ratio, delete,
param_select, global_fun, local_fun):
'''
训练的自动化程序，分词,先进行特征选择，重新定义词典，根据新的词典，自动选择SVM最优的参数。
然后使用最优的参数进行SVM分类，最后生成训练后的模型。
需要保存的文件：（需定义一个主保存路径）
模型文件：词典.key+模型.model
临时文件 ：svm分类数据文件.train
'''
print "-----------------创建模型文件保存的路径-----------------"
if os.path.exists(main_save_path):
if os.path.exists(os.path.join(main_save_path, "model")) is False:
os.makedirs(os.path.join(main_save_path, "model"))
if os.path.exists(main_save_path):
if os.path.exists(os.path.join(main_save_path, "temp")) is False:
os.makedirs(os.path.join(main_save_path, "temp"))
#读取停用词文件
if stopword_filename == "":
stop_words_dic = dict()
else:
stop_words_dic = utils.read_dic(stopword_filename)
print "-----------------现在正在进行特征选择---------------"
dic_path = os.path.join(main_save_path, "model", "dic.key")
feature_select.feature_select(train_docs, global_fun, dic_path, ratio, stop_words_dic)
print "-----------------再根据特征选择后的词典构造新的SVM分类所需的训练样本------------------- "
problem_save_path = os.path.join(main_save_path, "temp", train_name)
label = cons_train_sample_for_cla(train_docs, measure.local_f(local_fun), dic_path, problem_save_path, delete)
print"--------------------选择最优的c,g------------------------------"
if param_select is True:
search_result_save_path = os.path.join(main_save_path, "temp", param_name)
coarse_c_range = (-5, 7, 2)
coarse_g_range = (1, 1, 1)
fine_c_step = 0.5
fine_g_step = 0
c, g = grid_search_param.grid(problem_save_path, search_result_save_path, coarse_c_range,
coarse_g_range, fine_c_step, fine_g_step)
svm_param = " -c " + str(c)
print "-----------------训练模型，并将模型进行保存----------"
model_save_path = os.path.join(main_save_path, "model", model_name)
ctm_train_model(problem_save_path, svm_param, model_save_path)
print "-----------------保存模型配置-----------------"
f_config = file(os.path.join(main_save_path, "model", config_name), 'w')
save_config(f_config, model_name, local_fun, global_fun, svm_param, label)
f_config.close()
print "-----------------训练结束---------------------"
def tms_grid_param(problem_path, result_save_path="../svm.param", svm_type="libsvm", coarse_c_range=(-5,7,2), coarse_g_range=(3,-10,-2), fine_c_step=0.5, fine_g_step=0.5):
'''对SVM的参数进行搜索,如果是libsvm则搜索(c,gamma)，如果是liblinear则搜索(c)。当训练样本的容量大于3000时就会在粗粒度搜索时使用子集，子集的大小为[3000,5000]范围内。
当
必须参数：
problem_path：SVM输入格式文件的路径即名称。
可选参数:
result_save_path:结果文件的保存路径:默认为"../svm.param"
svm_type :选择的SVM的类型，默认为libsvm
coarse_c_range ：粗粒度搜索时c搜索的范围，默认情况下为[-5,7],步长为2
coarse_g_range：粗粒度搜索时g搜索的范围，默认情况下为[3,-10]步长为-2
fine_c_step ：细粒度搜索时c的步长，默认情况下为0.5
fine_c_step ：细粒度搜索时c的步长，默认情况下为0.5
'''
if svm_type=="liblinear":
coarse_g_range=(1,1,1)
fine_g_step=0
c,g = grid_search_param.grid(problem_path, result_save_path, svm_type, coarse_c_range, coarse_g_range, fine_c_step, fine_g_step)
print "best c=%s ,g=%s"%(c,g)
return c,g
def ctm_train(filename, indexes, main_save_path, stopword_filename, svm_param,
config_name, dic_name, model_name, train_name, svm_type,
param_name, ratio, delete, str_splitTag, tc_splitTag, seg,
param_select, global_fun, local_fun, label_file):
'''训练的自动化程序，分词,先进行特征选择，重新定义词典，根据新的词典，自动选择SVM最优的参数。
然后使用最优的参数进行SVM分类，最后生成训练后的模型。
需要保存的文件：（需定义一个主保存路径）
模型文件：词典.key+模型.model
临时文件 ：svm分类数据文件.train
filename 训练文本所在的文件名
indexs需要训练的指标项
main_save_path 模型保存的路径
stopword_filename 停用词的名称以及路径 ;默认不适用停用词
svm_type :svm类型：libsvm 或liblinear
svm_param 用户自己设定的svm的参数,这个要区分libsvm与liblinear参数的限制；例如"-s 0 -t 2 -c 0.2 "
dic_name 用户自定义词典名称;例如“dic.key”
model_name用户自定义模型名称 ;例如"svm.model"
train_name用户自定义训练样本名称 ；例如“svm.train”
param_name用户自定义参数文件名称 ；例如"svm.param"
ratio 特征选择保留词的比例 ；例如 0.4
delete对于所有特征值为0的样本是否删除,True or False
str_splitTag 分词所用的分割符号 例如"^"
tc_splitTag训练样本中各个字段分割所用的符号 ，例如"\t"
seg 分词的选择：0为不进行分词；1为使用mmseg分词；2为使用aliws分词
param_select ;是否进行SVM模型参数的搜索。True即为使用SVM模型grid.搜索，False即为不使用参数搜索。
local_fun：即对特征向量计算特征权重时需要设定的计算方式:x(i,j) = local(i,j)*global(i).可选的有tf,logtf
global_fun :全局权重的计算方式：有"one","idf","rf"
label_file:类标签的解释说明文件。
'''
print "-----------------创建模型文件保存的路径-----------------"
if os.path.exists(main_save_path):
if os.path.exists(os.path.join(main_save_path, "model")) is False:
os.makedirs(os.path.join(main_save_path, "model"))
if os.path.exists(main_save_path):
if os.path.exists(os.path.join(main_save_path, "temp")) is False:
os.makedirs(os.path.join(main_save_path, "temp"))
#设定SVM模型的类型。
tms_svm.set_svm_type(svm_type)
#如果没有给出停用词的文件名，则默认不使用停用词
if stopword_filename == "":
stop_words_dic = dict()
else:
stop_words_dic = fileutil.read_dic(stopword_filename)
#如果需要分词，则对原文件进行分词
if seg != 0:
print "-----------------正在对源文本进行分词-------------------"
segment_file = os.path.dirname(filename) + "/segmented"
segment.file_seg(filename, indexes, segment_file, str_splitTag,
tc_splitTag, seg)
filename = segment_file
#对原训练样本进行词干化处理
print "-----------------正在对源文本进行词干化处理-------------------"
stem.stemFile(filename, str_splitTag, tc_splitTag)
print "-----------------现在正在进行特征选择---------------"
dic_path = os.path.join(main_save_path, "model", dic_name)
feature_select(filename,
indexes,
global_fun,
dic_path,
ratio,
stop_words_dic,
str_splitTag=str_splitTag,
tc_splitTag=tc_splitTag)
print "-----------------再根据特征选择后的词典构造新的SVM分类所需的训练样本------------------- "
problem_save_path = os.path.join(main_save_path, "temp", train_name)
local_fun_str = local_fun
local_fun = measure.local_f(local_fun)
label = cons_train_sample_for_cla(filename, indexes, local_fun, dic_path,
problem_save_path, delete, str_splitTag,
tc_splitTag)
if param_select == True:
print "--------------------选择最优的c,g------------------------------"
search_result_save_path = main_save_path + "temp/" + param_name
if svm_type == "libsvm":
coarse_c_range = (-5, 7, 2)
coarse_g_range = (3, -10, -2)
fine_c_step = 0.5
fine_g_step = 0.5
c, g = grid_search_param.grid(problem_save_path,
search_result_save_path, svm_type,
coarse_c_range, coarse_g_range,
fine_c_step, fine_g_step)
svm_param = svm_param + " -c " + str(c) + " -g " + str(g)
if svm_type == "liblinear" or (svm_type == "libsvm" and
is_linear_kernal(svm_param) is True):
coarse_c_range = (-5, 7, 2)
coarse_g_range = (1, 1, 1)
fine_c_step = 0.5
fine_g_step = 0
c, g = grid_search_param.grid(problem_save_path,
search_result_save_path, svm_type,
coarse_c_range, coarse_g_range,
fine_c_step, fine_g_step)
svm_param = svm_param + " -c " + str(c)
print "-----------------训练模型，并将模型进行保存----------"
model_save_path = main_save_path + "model/" + model_name
ctm_train_model(problem_save_path, svm_type, svm_param, model_save_path)
print "-----------------保存模型配置-----------------"
f_config = file(os.path.join(main_save_path, "model", config_name), 'w')
save_config(f_config, dic_name, model_name, local_fun_str, global_fun, seg,
svm_type, svm_param, label_file, label)
f_config.close()
def ctm_train(filename,indexes,main_save_path,stopword_filename,svm_param,config_name,dic_name,model_name,train_name,svm_type,param_name,ratio,delete,str_splitTag,tc_splitTag,seg,param_select,global_fun,local_fun,label_file):
'''训练的自动化程序，分词,先进行特征选择，重新定义词典，根据新的词典，自动选择SVM最优的参数。
然后使用最优的参数进行SVM分类，最后生成训练后的模型。
需要保存的文件：（需定义一个主保存路径）
模型文件：词典.key+模型.model
临时文件 ：svm分类数据文件.train
filename 训练文本所在的文件名
indexs需要训练的指标项
main_save_path 模型保存的路径
stopword_filename 停用词的名称以及路径 ;默认不适用停用词
svm_type :svm类型：libsvm 或liblinear
svm_param 用户自己设定的svm的参数,这个要区分libsvm与liblinear参数的限制；例如"-s 0 -t 2 -c 0.2 "
dic_name 用户自定义词典名称;例如“dic.key”
model_name用户自定义模型名称 ;例如"svm.model"
train_name用户自定义训练样本名称 ；例如“svm.train”
param_name用户自定义参数文件名称 ；例如"svm.param"
ratio 特征选择保留词的比例 ；例如 0.4
delete对于所有特征值为0的样本是否删除,True or False
str_splitTag 分词所用的分割符号 例如"^"
tc_splitTag训练样本中各个字段分割所用的符号 ，例如"\t"
seg 分词的选择：0为不进行分词；1为使用mmseg分词；2为使用aliws分词
param_select ;是否进行SVM模型参数的搜索。True即为使用SVM模型grid.搜索，False即为不使用参数搜索。
local_fun：即对特征向量计算特征权重时需要设定的计算方式:x(i,j) = local(i,j)*global(i).可选的有tf,logtf
global_fun :全局权重的计算方式：有"one","idf","rf"
label_file:类标签的解释说明文件。
'''
print "-----------------创建模型文件保存的路径-----------------"
if os.path.exists(main_save_path):
if os.path.exists(os.path.join(main_save_path,"model")) is False:
os.makedirs(os.path.join(main_save_path,"model"))
if os.path.exists(main_save_path):
if os.path.exists(os.path.join(main_save_path,"temp")) is False:
os.makedirs(os.path.join(main_save_path,"temp"))
#设定SVM模型的类型。
tms_svm.set_svm_type(svm_type)
#如果没有给出停用词的文件名，则默认不使用停用词
if stopword_filename =="":
stop_words_dic=dict()
else:
stop_words_dic = fileutil.read_dic(stopword_filename)
#如果需要分词，则对原文件进行分词
if seg!=0:
print "-----------------正在对源文本进行分词-------------------"
segment_file = os.path.dirname(filename)+"/segmented"
segment.file_seg(filename,indexes,segment_file,str_splitTag,tc_splitTag,seg)
filename = segment_file
#对原训练样本进行词干化处理
print "-----------------正在对源文本进行词干化处理-------------------"
stem.stemFile(filename,str_splitTag,tc_splitTag)
print "-----------------现在正在进行特征选择---------------"
dic_path= os.path.join(main_save_path,"model",dic_name)
feature_select(filename,indexes,global_fun,dic_path,ratio,stop_words_dic,str_splitTag=str_splitTag,tc_splitTag=tc_splitTag)
print "-----------------再根据特征选择后的词典构造新的SVM分类所需的训练样本------------------- "
problem_save_path = os.path.join(main_save_path,"temp",train_name)
local_fun_str = local_fun
local_fun = measure.local_f(local_fun)
label = cons_train_sample_for_cla(filename,indexes,local_fun,dic_path,problem_save_path,delete,str_splitTag,tc_splitTag)
if param_select ==True:
print"--------------------选择最优的c,g------------------------------"
search_result_save_path = main_save_path +"temp/"+param_name
if svm_type=="libsvm":
coarse_c_range=(-5,7,2)
coarse_g_range=(3,-10,-2)
fine_c_step=0.5
fine_g_step=0.5
c,g=grid_search_param.grid(problem_save_path,search_result_save_path,svm_type,coarse_c_range,coarse_g_range,fine_c_step,fine_g_step)
svm_param = svm_param + " -c "+str(c)+" -g "+str(g)
if svm_type=="liblinear" or (svm_type=="libsvm" and is_linear_kernal(svm_param) is True):
coarse_c_range=(-5,7,2)
coarse_g_range=(1,1,1)
fine_c_step=0.5
fine_g_step=0
c,g=grid_search_param.grid(problem_save_path,search_result_save_path,svm_type,coarse_c_range,coarse_g_range,fine_c_step,fine_g_step)
svm_param = svm_param + " -c "+str(c)
print "-----------------训练模型，并将模型进行保存----------"
model_save_path = main_save_path+"model/"+model_name
ctm_train_model(problem_save_path,svm_type,svm_param,model_save_path)
print "-----------------保存模型配置-----------------"
f_config = file(os.path.join(main_save_path,"model",config_name),'w')
save_config(f_config,dic_name,model_name,local_fun_str,global_fun,seg,svm_type,svm_param,label_file,label)
f_config.close()
def main():
usage = "usage:%prog [options] version=%prog 1.0"
parser = OptionParser(usage=usage)
parser.add_option("-s",
"--step",
type="choice",
choices=["1", "2", "3", "4", "5"],
dest="step",
help="step1 is auto training the svm model")
parser.add_option("-p", "--path", dest="save_main_path")
parser.add_option("-P", "--problem_path", dest="problem_save_path")
parser.add_option("-i",
"--indexes",
dest="indexes",
action="callback",
type="string",
default=[1],
callback=list_callback)
parser.add_option("-w",
"--stopword",
action="store_false",
dest="stopword",
default=True)
parser.add_option("-n",
"--config_name",
dest="config_name",
default="tms.config")
parser.add_option("-d", "--dic_name", dest="dic_name", default="dic.key")
parser.add_option("-D", "--dic_path", dest="dic_path")
parser.add_option("-m",
"--model_name",
dest="model_name",
default="tms.model")
parser.add_option("-t",
"--train_name",
dest="train_name",
default="tms.train")
parser.add_option("-a",
"--param_name",
dest="param_name",
default="tms.param")
parser.add_option("-r", "--ratio", dest="ratio", type="float", default=0.4)
parser.add_option("-A",
"--svm_param",
dest="svm_param",
default="'-s 0 -t 2 -c 1.0 -g 0.25'")
parser.add_option("-T",
"--tc_splitTag",
dest="tc_splitTag",
type="string",
default="\t")
parser.add_option("-S",
"--str_splitTag",
dest="str_splitTag",
type="string",
default="^")
parser.add_option("-v",
"--svm_type",
dest="svm_type",
default="libsvm",
type="choice",
choices=["libsvm", "liblinear"])
parser.add_option("-e",
"--segment",
type="choice",
dest="segment",
default=0,
choices=[0, 1, 2])
parser.add_option("-c",
"--param_select",
action="store_false",
dest="param_select",
default=True)
parser.add_option("-g",
"--global_fun",
dest="global_fun",
default="one",
type="choice",
choices=["one", "idf", "rf"])
parser.add_option("-l",
"--local_fun",
dest="local_fun",
default="tf",
type="choice",
choices=["tf"])
parser.add_option("-b",
"--label_file",
dest="label_file",
type="string",
default="")
options, args = parser.parse_args()
if options.indexes:
indexes = [int(i) for i in options.indexes]
if options.step:
step = int(options.step)
if options.stopword == False:
stopword_filename = ""
else:
stopword_filename = os.path.dirname(args[0]) + "/stopwords.txt"
if options.svm_param:
svm_param = options.svm_param.replace("'", "")
if step == 1:
train_model.ctm_train(args[0],
indexes,
options.save_main_path,
stopword_filename,
config_name=options.config_name,
svm_type=options.svm_type,
segment=options.segment,
param_select=options.param_select,
global_fun=options.global_fun,
local_fun=options.local_fun,
svm_param=svm_param,
dic_name=options.dic_name,
model_name=options.model_name,
train_name=options.train_name,
param_name=options.param_name,
ratio=options.ratio,
delete=True,
str_splitTag=options.str_splitTag,
tc_splitTag=options.tc_splitTag,
label_file=options.label_file)
if step == 2:
train_model.ctm_feature_select(args[0],
indexes,
options.global_fun,
options.save_main_path,
options.dic_name,
options.ratio,
stopword_filename,
str_splitTag=options.str_splitTag,
tc_splitTag=options.tc_splitTag)
if step == 3:
if os.path.exists(options.save_main_path):
if os.path.exists(options.save_main_path + "temp/") is False:
os.makedirs(options.save_main_path + "temp/")
sample_save_path = options.save_main_path + "temp/svm.train"
train_model.cons_train_sample_for_cla(
args[0],
indexes,
options.local_fun,
options.dic_path,
sample_save_path,
delete=True,
str_splitTag=options.str_splitTag,
tc_splitTag=options.tc_splitTag)
if step == 4:
search_result_save_path = options.save_main_path + "temp/" + "svm.param"
tms_svm.set_svm_type(options.svm_type)
if options.svm_type == "libsvm":
coarse_c_range = (-5, 7, 2)
coarse_g_range = (3, -10, -2)
fine_c_step = 0.5
fine_g_step = 0.5
if options.svm_type == "liblinear":
coarse_c_range = (-5, 7, 2)
coarse_g_range = (1, 1, 1)
fine_c_step = 0.5
fine_g_step = 0
c, g = grid_search_param.grid(args[0], search_result_save_path,
options.svm_type, coarse_c_range,
coarse_g_range, fine_c_step, fine_g_step)
print "best c = %s\t g = %s\n" % (c, g)
if step == 5:
model_save_path = options.save_main_path + "model/" + options.model_name
train_model.ctm_train_model(options.problem_save_path, svm_param,
model_save_path)
def main():
usage ="usage:%prog [options] version=%prog 1.0"
parser = OptionParser(usage=usage)
parser.add_option("-s","--step",type="choice",choices=["1","2","3","4","5"],dest="step",help="step1 is auto training the svm model")
parser.add_option("-p","--path",dest="save_main_path")
parser.add_option("-P","--problem_path",dest="problem_save_path")
parser.add_option("-i","--indexes",dest="indexes",action="callback",type="string",default=[1],callback=list_callback)
parser.add_option("-w","--stopword",action="store_false",dest="stopword",default=True)
parser.add_option("-n","--config_name",dest="config_name",default="tms.config")
parser.add_option("-d","--dic_name",dest="dic_name",default="dic.key")
parser.add_option("-D","--dic_path",dest="dic_path")
parser.add_option("-m","--model_name",dest="model_name",default="tms.model")
parser.add_option("-t","--train_name",dest="train_name",default="tms.train")
parser.add_option("-a","--param_name",dest="param_name",default="tms.param")
parser.add_option("-r","--ratio",dest="ratio",type="float",default=0.4)
parser.add_option("-A","--svm_param",dest="svm_param",default="'-s 0 -t 2 -c 1.0 -g 0.25'")
parser.add_option("-T","--tc_splitTag",dest="tc_splitTag",type="string",default="\t")
parser.add_option("-S","--str_splitTag",dest="str_splitTag",type="string",default="^")
parser.add_option("-v","--svm_type",dest="svm_type",default="libsvm",type="choice",choices=["libsvm","liblinear"])
parser.add_option("-e","--segment",type="choice",dest="segment",default=0,choices=[0,1,2])
parser.add_option("-c","--param_select",action="store_false",dest="param_select",default=True)
parser.add_option("-g","--global_fun",dest="global_fun",default="one",type="choice",choices=["one","idf","rf"])
parser.add_option("-l","--local_fun",dest="local_fun",default="tf",type="choice",choices=["tf"])
parser.add_option("-b","--label_file",dest="label_file",type="string",default="")
options, args = parser.parse_args()
if options.indexes:
indexes = [int(i) for i in options.indexes]
if options.step:
step = int(options.step)
if options.stopword ==False:
stopword_filename=""
else:
stopword_filename = os.path.dirname(args[0])+"/stopwords.txt"
if options.svm_param:
svm_param = options.svm_param.replace("'","")
if step==1:
train_model.ctm_train(args[0],indexes,options.save_main_path,stopword_filename,config_name=options.config_name,svm_type =options.svm_type,segment=options.segment,param_select=options.param_select,global_fun=options.global_fun,local_fun=options.local_fun,svm_param=svm_param,dic_name=options.dic_name,model_name=options.model_name,train_name=options.train_name,param_name=options.param_name,ratio=options.ratio,delete=True,str_splitTag=options.str_splitTag,tc_splitTag=options.tc_splitTag,label_file=options.label_file)
if step==2:
train_model.ctm_feature_select(args[0],indexes,options.global_fun,options.save_main_path,options.dic_name,options.ratio,stopword_filename,str_splitTag=options.str_splitTag,tc_splitTag=options.tc_splitTag)
if step==3:
if os.path.exists(options.save_main_path):
if os.path.exists(options.save_main_path+"temp/") is False:
os.makedirs(options.save_main_path+"temp/")
sample_save_path = options.save_main_path +"temp/svm.train"
train_model.cons_train_sample_for_cla(args[0],indexes,options.local_fun,options.dic_path,sample_save_path,delete=True,str_splitTag=options.str_splitTag,tc_splitTag=options.tc_splitTag)
if step==4:
search_result_save_path = options.save_main_path +"temp/"+"svm.param"
tms_svm.set_svm_type(options.svm_type)
if options.svm_type=="libsvm":
coarse_c_range=(-5,7,2)
coarse_g_range=(3,-10,-2)
fine_c_step=0.5
fine_g_step=0.5
if options.svm_type =="liblinear":
coarse_c_range=(-5,7,2)
coarse_g_range=(1,1,1)
fine_c_step=0.5
fine_g_step=0
c,g=grid_search_param.grid(args[0],search_result_save_path,options.svm_type,coarse_c_range,coarse_g_range,fine_c_step,fine_g_step)
print "best c = %s\t g = %s\n"%(c,g)
if step==5:
model_save_path = options.save_main_path+"model/"+options.model_name
train_model.ctm_train_model(options.problem_save_path,svm_param,model_save_path)
