Question

可以使用python多进程实现smote算法吗

Answer 1

import numpy as np
import csv
#import svm
import pandas as pd
import matplotlib.pyplot as plt
dataset=pd.read_csv(r'xxx.csv')
array=np.array(dataset)
y= np.array(array[:,0], dtype=np.int64)
x = np.array(array[:,1: array.shape[1]], dtype=np.double)
from sklearn.cross_validation import train_test_split
from imblearn.over_sampling import SMOTE
from imblearn.combine import SMOTEENN
def data_prepration(x):
x_features= x.ix[:,x.columns != "y_label_name"]
x_labels=x.ix[:,x.columns=="y_label_name"]
x_features_train,x_features_test,x_labels_train,x_labels_test = train_test_split(x_features,x_labels,test_size=0.3,random_state = 0)
print("length of training data")
print(len(x_features_train))
print("length of test data")
print(len(x_features_test))
return(x_features_train,x_features_test,x_labels_train,x_labels_test)
data_train_x,data_test_x,data_train_y,data_test_y=data_prepration(dataset)
os= SMOTE(random_state=0)
os_data_x,os_data_y=os.fit_sample(data_train_x.values,data_train_y.values.ravel())
columns = data_train_x.columns
os_data_x = pd.DataFrame(data=os_data_x,columns=columns )
print (len(os_data_x))
os_data_y= pd.DataFrame(data=os_data_y,columns=["credit_status"])
# 现在检查下抽样后的数据
print("length of oversampled data is ",len(os_data_x))
print("Number of normal transcation",len(os_data_y[os_data_y["credit_status"]==1]))
print("Number of fraud transcation",len(os_data_y[os_data_y["credit_status"]==0]))
print("Proportion of Normal data in oversampled data is ",len(os_data_y[os_data_y["credit_status"]==0])/len(os_data_x))
print("Proportion of fraud data in oversampled data is ",len(os_data_y[os_data_y["credit_status"]==1])/len(os_data_x))
newtraindata=pd.concat([os_data_x,os_data_y],axis=1)
newtestdata=pd.concat([data_test_x,data_test_y],axis=1)
#train_csv_file= open(r'D:\Data\MijiaOldCustomer\train.csv','wb')
#writer = csv.writer(train_csv_file)
#writer.writerows(newtraindata)
newtraindata.to_csv(r'train.csv',sep=',')
newtestdata.to_csv(r'test.csv
',sep=',')