def test_c(flag, sql_flag):
sql_dir = "./data/sql_test.csv"
nor_dir = "./data/normal_test.csv"
allm_dir = "./data/alltest_matrix.csv"
if flag == '1' and sql_flag == '0':
nor_matrix = generate(nor_dir, "./data/nor_matrix.csv", 0)
return nor_matrix
elif flag == '1' and sql_flag == '1':
sql_matrix = generate(sql_dir, "./data/sqltest_matrix.csv", 1)
return sql_matrix
else:
sql_matrix = generate(sql_dir, "./data/sqltest_matrix.csv", 1)
nor_matrix = generate(nor_dir, "./data/nortest_matrix.csv", 0)
df = pd.read_csv(sql_matrix)
df.to_csv(allm_dir, encoding="utf_8_sig", index=False)
df = pd.read_csv(nor_matrix)
df.to_csv(allm_dir,
encoding="utf_8_sig",
index=False,
header=False,
mode='a+')
return allm_dir
# -*- coding: utf-8 -*-
"""
Created on Mon Nov 20 19:06:57 2017
@author: wf
"""
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn import metrics
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from featurepossess import generate
from sklearn.externals import joblib
sql_matrix = generate("./data/sqlnew.csv", "./data/sql_matrix.csv", 1)
nor_matrix = generate("./data/normal_less.csv", "./data/nor_matrix.csv", 0)
df = pd.read_csv(sql_matrix)
df.to_csv("./data/all_matrix.csv", encoding="utf_8_sig", index=False)
df = pd.read_csv(nor_matrix)
df.to_csv("./data/all_matrix.csv",
encoding="utf_8_sig",
index=False,
header=False,
mode='a+')
feature_max = pd.read_csv('./data/all_matrix.csv')
arr = feature_max.values
data = np.delete(arr, -1, axis=1) #删除最后一列
#print(arr)