def main():
l, h, e, trainSetFile, testSetFile = getArgs()
trainDataSet = arff.load(open(trainSetFile, 'r'))
testDataSet = arff.load(open(testSetFile, 'r'))
labels = trainDataSet['attributes'][-1][1]
fullTrain, fullTest = dataprocess.process(trainDataSet, testDataSet,
labels)
ann = NeuralNet(h, 1, fullTrain)
trainInfo = ann.train(fullTrain, e, l)
for item in trainInfo:
print('Epoch: {0}\tCross-entropy error: {1}\tCorrectly classified instances: {2}\tMisclassified instances: {3}'.format\
(item[0], item[1], item[2], item[3]))
testInfo, correct, wrong = ann.test(fullTest, labels)
for item in testInfo:
print('Activation of output unit: {0}\tPredicted class: {1}\tCorrect class: {2}'.format\
(item[0], item[1], item[2]))
print('Correctly classified instances: {0}\tMisclassified instances: {1}'.
format(correct, wrong))
def get(self):
args = parser.parse_args(strict=True)
ageMin = 0
if (args['ageMin'] is not None):
ageMin = args['ageMin']
ageMax = 100
if (args['ageMax'] is not None):
ageMin = args['ageMax']
gap = 0
if (args['gap'] is not None):
gap = args['gap']
overlap = 0
if (args['overlap'] is not None):
overlap = args['overlap']
fileName = 'data/Ace_Beta_Diur_1SamplingRate.txt'
if (args['fileName'] is not None):
fileName = args['fileName']
drugList = ['1', '3', '5']
if (args['drugList'] is not None):
drugList = args['drugList']
drugList = "".join(drugList)
patients, drugStats = dataprocess.process(fileName = fileName, drugList = drugList, overlap = overlap, gap = gap, ageMin = ageMin, ageMax = ageMax)
patientsObj = dataprocess.patientsJSON(patients)
drugsObj = dataprocess.drugsJSON(drugStats, drugList)
return { "patients": patientsObj,
"drugs" : drugsObj }
import numpy as np
import cv2 as cv
from collections import deque
import baselinemodel as bm
import dataprocess as dp
from keras.datasets import mnist
(X_train, y_train), (X_test, y_test) = mnist.load_data()
x, y, input, output = dp.process(X_train, y_train)
model = bm.baseline_model(input, output)
model.fit(x, y)
def predict(k):
l = np.zeros((1, 28, 28), dtype=np.uint8)
l[0] = k
v = dp.inputProcess(l)
i = model.predict_class(v)
print(i)
def image_resize(image, width=None, height=None, inter=cv.INTER_AREA):
# initialize the dimensions of the image to be resized and
# grab the image size
dim = None
(h, w) = image.shape[:2]
total = 0
resultnum = 0
#print(clname[0][-1])
for j in range(len(clname)):
a = np.array(data)[:, j]
a = a.reshape(1, -1)
# print("a.shape before")
# print(a.shape)
a = dp.PCA.transform(a)
# print("a.shape after")
# print(a.shape)
#print(a)
for i in range(len(list_)):
if (i != int(clname[j][11])):
name = list_[i]
line, number = dp.process(name)
if (len(clname[j]) > 13):
#print(clname[j])
#print(idf.Archimedes(a,line,number,int(0)))
if (idf.Archimedes(a, line, number, int(clname[j][13:]))):
resultnum += 1
else:
#print(0)
#print(clname[j])
# print(idf.Archimedes(a,line,number,int(0)))
if (idf.Archimedes(a, line, number, int(0))):
resultnum += 1
total += 1
print(total)
print("identificationattack结果是：")
print(resultnum / total)
import os
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.multiclass import OneVsRestClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
import json
# Load Data
train_set = pd.read_csv('data/hackathon_loreal_train_set.csv')
test_set = pd.read_csv('data/hackathon_loreal_test_set.csv')
if os.path.isfile('data/data_process.csv'):
train_set = pd.read_csv('data/data_process.csv', sep=";")
else:
process(train_set, "train_process")
X_train = train_set.text
y_train = train_set[['skincare', 'hair', 'make-up', 'other']]
categories = ['skincare', 'hair', 'make-up', 'other']
#X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30, random_state=42)
# Define a pipeline combining a text feature extractor with multi lable classifier
LogReg_pipeline = Pipeline([
('tfidf', TfidfVectorizer()),
('clf', OneVsRestClassifier(LogisticRegression(solver='sag'), n_jobs=1)),
])
if os.path.isfile('data/data_process.csv'):
test_set = pd.read_csv('data/test_process.csv', sep=";")
else: