def CountEn():
'''
英文词频统计
'''
rawpath = os.getcwd()
pathen = rawpath + '/output_encount'
pathencsv = rawpath + '/output_encount_csv'
target_file_name = '/output_en'
lst = lib.name_lst(rawpath + target_file_name)
try:
os.mkdir(pathen)
os.mkdir(pathencsv)
except:
pass
for name in lst:
try:
os.chdir(pathen)
li = lib.count_en(name, target_file_name) # 文件的词，词频总和
lib.to_csv(li, name, pathencsv) # csv函数加在这里（参数使用li）
os.chdir(rawpath)
except:
continue
return ''
def CountZh():
'''
中文词频统计
'''
rawpath = os.getcwd()
pathzh = rawpath + '/output_zhcount'
pathzhcsv = rawpath + '/output_zhcount_csv'
target_file_name = '/output_zh'
lst = lib.name_lst(rawpath + target_file_name)
try:
os.mkdir(pathzh)
os.mkdir(pathzhcsv)
except:
pass
for name in lst:
try:
os.chdir(pathzh)
li = lib.count_zh(name,
target_file_name) # 所有列表的总和，包含所有文件的（词，词频）列表
lib.to_csv(li, name, pathzhcsv)
os.chdir(rawpath)
except:
continue
return ''
from lib import to_csv from validator import SVM, XGB, RFC, VC from preprocess import train_X, train_y, test_X, passenger_id SVM.fit(train_X, train_y) SVM_pred = SVM.predict(test_X) to_csv(SVM_pred, passenger_id, 'SVM') XGB.fit(train_X, train_y) XGB_pred = XGB.predict(test_X) to_csv(XGB_pred, passenger_id, 'XGB') RFC.fit(train_X, train_y) RFC_pred = RFC.predict(test_X) to_csv(RFC_pred, passenger_id, 'RFC') VC.fit(train_X, train_y) VC_pred = VC.predict(test_X) to_csv(VC_pred, passenger_id, 'VC')