import sys,random,os,pickle
from multiprocessing import Pool
from sklearn.svm import SVC
from sklearn import metrics
from sklearn import cross_validation
from sklearn.cross_validation import train_test_split
from sklearn.externals import joblib
import pandas as pd
train = pd.read_csv("E:/training38085.csv")
test = pd.read_csv("E:/test38085.csv")
test_x = test.drop("bad_good",axis=1)
#生成validation set
val = pd.read_csv('E:/validation20000_950.csv')
train_y = train.bad_good
train_x = train.drop(['bad_good'],axis=1)
val_y = val.bad_good
val_x = val.drop(['bad_good'],axis=1)
print(test_x.shape)
print(train_x.shape)
print(val_x.shape)
def pipeline(iteration,C,gamma,random_seed):
x_train, _x , y_train, _y = train_test_split(train_x,train_y,test_size=0.4,random_state=random_seed)
print(x_train.shape)
clf = SVC(C=C,kernel='rbf',gamma=gamma,probability=True,cache_size=7000,class_weight='balanced',verbose=True,random_state=random_seed)
clf.fit(x_train,y_train)
#predict test set
pred = clf.predict_proba(test_x)
Traceback (most recent call last):
File "", line 1, in
报错： “pred = clf.predict_proba(test_x)
NameError: name 'clf' is not defined”
上面def pipline 有clf ,为啥还会报错呢。前面的代码没有报错
