def test_remove_invalid_record(self): """ DELETE feiras/id must not remove invalid record """ #populate database with valid data load.loadData(os.path.abspath(self.test_data_path)) qtd_stored_before = len(Feira.objects.all()) self.assertIs(qtd_stored_before > 1, True) #get specific record registro_to_remove = 200 #request delete data response = self.client.delete('/feira/%s/' % registro_to_remove, format='json') #validate status code self.assertEqual(response.status_code, requests.codes.not_found) qtd_stored_after = len(Feira.objects.all()) #validate database status self.assertEqual(qtd_stored_before, qtd_stored_after)
def test_query_by_distrito(self): """ GET feiras/distrito/ retrieve records by 'distrito' field """ #populate database with valid data load.loadData(os.path.abspath(self.test_data_path)) #get specific record fdistrito = Feira.objects.all()[0].distrito lstored = [ f.toJson() for f in Feira.objects.filter(distrito=fdistrito) ] #request remote data by distrito response = self.client.get('/feira/distrito/%s/' % fdistrito, format='json') #validate status code self.assertEqual(response.status_code, requests.codes.ok) lremote = response.json() #validate remote data retrieved self.assertListEqual(lstored, lremote)
def test_update_invalid_record(self): """ PUT feiras/{invalid data} must not update a record """ #populate database with valid data load.loadData(os.path.abspath(self.test_data_path)) #get specific record f_object = Feira.objects.all()[0] #change some data f_object.regiao5 = 'nova regiao' f_object.log = 'invalid value' #request update data response = self.client.put('/feira/%s/' % f_object.registro, data=f_object.toJson(), format='json') #validate status code self.assertEqual(response.status_code, requests.codes.bad_request) #validate database status self.assertNotEqual( Feira.objects.get(registro=f_object.registro).toJson(), f_object.toJson())
def test_retrieve_specific_data(self): """ GET feiras/id/ retrieve specific record by id field """ #populate database with valid data load.loadData(os.path.abspath(self.test_data_path)) #get specific record fstored = Feira.objects.all()[0] #get feira records in json format stored = fstored.toJson() #request remote data by id response = self.client.get('/feira/%s/' % fstored.registro, format='json') #validate status code self.assertEqual(response.status_code, requests.codes.ok) remote_data = response.json() #validate remote data retrieved self.assertDictEqual(stored, remote_data)
def update(): """ Метод API позволяющий обновить БД не по таймеру, а принудительно :return: """ try: loadData() return jsonify({"Status": "updated"}) except Exception as e: return jsonify({"Error of update": str(e)})
def main(): print("Loading universe...") universe = loadData() groupMerge(universe, matchTypeAndHasFields("client",["name"]), lambda v: [v["name"]], description="Merged clients based on exact name match") groupMerge(universe, matchTypeAndHasFields("client",["name"]), lambda v: extractNames(v["name"]), description="Merged clients based on extracted and cleaned name match") p = matchTypeAndHasFields("client",["address","city","country","state","zip"]) groupMerge(universe, lambda v: p(v) and v["state"] not in ["DC","VA","MD"] and v["city"] != "DC", lambda v: [(v["address"],v["city"],v["country"],v["state"],v["zip"])], description="Merging clients based on exact matching of address fields (sans DC area)") # groupMerge(universe, # matchTypeAndHasFields("firm",["orgname"]), # mnf("orgname"), # description="Merging firms based on *corrected* orgname") # groupMerge(universe, # matchTypeAndHasFields("firm",["printedname"]), # mnf("printedname"), # description="Merging firms based on *corrected* printedname") project(universe,"clientnames.txt", lambda v: v["type"] == "client", lambda v: ", ".join([v["name"],v["address"],v["city"],v["country"],v["state"],v["zip"]]).lower())
def get_list(filename, question_number): C = load.loadData(filename) m_eff_time = [] m_err_time = [] if question_number == 1: for t in range(0, 31): to_be_cut = C[:, t:t + 2] m_eff, m_err = JackKnife(to_be_cut, question_number) m_eff_time.append(m_eff) m_err_time.append(m_err) elif question_number == 2: for t in range(0, 30): to_be_cut = C[:, t:t + 3] m_eff, m_err = JackKnife(to_be_cut, question_number) m_eff_time.append(m_eff) m_err_time.append(m_err) else: print("error in question_number") exit(1) return np.array(m_eff_time), np.array(m_err_time)
def test_retrieve_all_records_over_existent_data(self): """ GET feiras/ retrieve all records present on database """ #populate database with valid data load.loadData(os.path.abspath(self.test_data_path)) #get feira records in json format lstored = [f.toJson() for f in Feira.objects.all()] #request remote data response = self.client.get('/feira/', format='json') self.assertEqual(response.status_code, requests.codes.ok) lresponse = response.json() self.assertListEqual(lstored, lresponse)
def test_update_registro(self): """ PUT feiras/{registro changed} must not update a record """ #populate database with valid data load.loadData(os.path.abspath(self.test_data_path)) #get specific record f_object = Feira.objects.all()[0] #change some data f_object.registro = 'novo registro' #request update data response = self.client.put('/feira/%s/' % f_object.registro, data=f_object.toJson(), format='json') #validate status code self.assertEqual(response.status_code, requests.codes.not_found)
def test_remove_valid_record(self): """ DELETE feiras/registro remove a valid record """ #populate database with valid data load.loadData(os.path.abspath(self.test_data_path)) #get specific record registro_to_remove = Feira.objects.all()[0].registro #request delete data response = self.client.delete('/feira/%s/' % registro_to_remove, format='json') #validate status code self.assertEqual(response.status_code, requests.codes.no_content) #validate database status self.assertEqual( len(Feira.objects.filter(registro=registro_to_remove)), 0)
def omitOutliers(): dataSet = loadData() dataUse = dataSet.loc[:, 'mcg':'nuc'] result_1 = svm.OneClassSVM(gamma='auto', nu=0.1).fit(dataUse).predict(dataUse) result_2 = IsolationForest().fit(dataUse).predict(dataUse) result_3 = LocalOutlierFactor().fit_predict(dataUse) result_2 = pd.DataFrame( result_2, columns=['Outliers']) #use IsolationForest to drop our outliers dataSet = dataSet.join(result_2) dataSet = dataSet[dataSet['Outliers'] != -1] return (dataSet)
def setData(): data = loadData() dataSet = splitData(data) trainSet = dataSet['trainSet'] testSet = dataSet['testSet'] xtrain = np.array(trainSet.loc[:,'mcg':'nuc']) ytrain = np.array(trainSet['Class']) ytrain = np.array(pd.get_dummies(ytrain)) #print(ytrain) #print(len(ytrain[0])) xtest = np.array(testSet.loc[:,'mcg':'nuc']) ytest = np.array(testSet['Class']) ytest = np.array(pd.get_dummies(ytest)) activation_1 = layers.Dense(units=3, activation='sigmoid') #First layer activation_2 = layers.Dense(units=3, activation='sigmoid') #Second layer output_layer = layers.Dense(units=10,activation='softmax') #Output layer #To build up the model model = Sequential([activation_1,activation_2,output_layer]) #initialized the model sgd = optimizers.SGD(lr=0.1) model.compile(loss='categorical_crossentropy',optimizer=sgd,metrics=['accuracy']) weight_receive= [] print_weights = LambdaCallback(on_epoch_end=lambda batch, logs: ([weight_receive.append(output_layer.get_weights())]).append(activation_2.get_weights())) history = model.fit(xtrain, ytrain, epochs=50,batch_size=1,verbose=0,callbacks = [print_weights]) error = [] for i in range(len(history.history['acc'])): error.append(1-(history.history['acc'][i])) output_weight = output_layer.get_weights() layer2 = activation_2.get_weights() print('Training error:',error[len(error)-1]) print('Outputlayer all weights:','\n',output_weight[0]) print('Outputlayer bias:','\n',output_weight[1]) print('Second Hidden layer all weights:','\n',layer2[0]) print('Second Hidden layer bias:','\n',layer2[1])
import sys import cPickle as pickle import numpy as np import load if __name__ == "__main__": data = load.loadData("/home/liuy/obj/gist.ans.py.data.10000") print "loadData" X = np.matrix(data) X = X.T print X.shape mean = X.mean(1) X -= mean X2 = X * X.T Ml = load.loadData("/tmp/cifar.Ml") X2 += Ml print "adjust" print "dump var" print X2.shape load.save(X2, "/tmp/cifar.var") print "dump mean" print mean.shape load.save(mean, "/tmp/cifar.mean")
def buildNonorW(): L = load.loadData("/tmp/cifar.nonor.L") U = load.loadData("/tmp/cifar.nonor.U") Uk = U[:, 0:conf.K] W = L * Uk return W.T def buildOrthW(): W = load.loadData("/tmp/cifar.north.w") return W[0:conf.K, :] def buildSeqLHW(): W = load.loadData("/tmp/cifar.splh.w") W = np.matrix(W) return W[0:conf.K, :] if __name__ == "__main__": K = conf.K W = buildSeqLHW() data = load.loadData("/home/liuy/obj/gist.ans.py.data.10000") X = np.matrix(data) X = X.T X -= X.mean(1) _, col = X.shape hashingArray = [hashingK(W, X[:, i]) for i in xrange(col)] load.save(hashingArray, "/tmp/cifar.hashingArray")
def train_val(args): torch.set_default_tensor_type('torch.DoubleTensor') if not os.path.exists(args.savedir): os.mkdir(args.savedir) if args.visualizeNet == True: x = Variable(torch.randn(1, 51, 61, 23)) if args.onGPU == True: x = x.cuda() model = net.ResNetC1() total_paramters = 0 for parameter in model.parameters(): i = len(parameter.size()) p = 1 for j in range(i): p *= parameter.size(j) total_paramters += p print('Parameters: ' + str(total_paramters)) logFileLoc = args.savedir + os.sep + args.trainValFile if os.path.isfile(logFileLoc): logger = open(logFileLoc, 'a') logger.write("%s\t%s\t\t\t\t\t%s\t\t\t%s\t\t\t%s\n" % ('Epoch', 'tr_loss', 'val_loss', 'tr_acc', 'val_acc')) logger.flush() else: logger = open(logFileLoc, 'w') logger.write("%s\t%s\t\t\t\t\t%s\t\t\t%s\t\t\t%s\n" % ('Epoch', 'tr_loss', 'val_loss', 'tr_acc', 'val_acc')) logger.flush() image, label = loadData() train_image, test_image, train_label, test_label = train_test_split( image, label, test_size=0.1, random_state=42, shuffle=True) train_image, val_image, train_label, val_label = train_test_split( train_image, train_label, test_size=0.1, random_state=42, shuffle=True) train_data_load = torch.utils.data.DataLoader(myDataLoader.MyDataset( train_image, train_label), batch_size=args.batch_size, shuffle=True, num_workers=args.num_workers, pin_memory=True) val_data_load = torch.utils.data.DataLoader(myDataLoader.MyDataset( val_image, val_label), batch_size=args.batch_size, shuffle=True, num_workers=args.num_workers, pin_memory=True) test_data_load = torch.utils.data.DataLoader(myDataLoader.MyDataset( test_image, test_label), batch_size=args.batch_size, shuffle=True, num_workers=args.num_workers, pin_memory=True) model = net.ResNetC1() if args.onGPU == True: model = model.cuda() criteria = torch.nn.CrossEntropyLoss() if args.onGPU == True: criteria = criteria.cuda() # optimizer = torch.optim.SGD(model.parameters(), lr=args.lr, momentum=0.9, weight_decay=5e-4 # optimizer = torch.optim.Adam(model.parameters(), args.lr, (0.9, 0.999), eps=1e-08, weight_decay=2e-4) optimizer = torch.optim.Adam(model.parameters(), lr=args.lr, weight_decay=5e-4) if args.onGPU == True: cudnn.benchmark = True scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=args.step_loss, gamma=0.1) start_epoch = 0 min_val_loss = 100 for epoch in range(start_epoch, args.max_epochs): loss_train, accuracy_train, report_train = train( args, train_data_load, model, criteria, optimizer) loss_val, accuracy_val, report_val = val(args, val_data_load, model, criteria) logger.write( "%s\t%s\t\t\t\t\t%s\t\t\t%s\t\t\t%s\n" % (epoch, loss_train, loss_val, accuracy_train, accuracy_val)) alleleLoc = args.savedir + os.sep + 'acc_' + str(epoch) + '.txt' log = open(alleleLoc, 'a') log.write("train classification report") log.write("\n") log.write(report_train) log.write("\n") log.write("validation classification report") log.write("\n") log.write(report_val) log.flush() log.close() if loss_val < min_val_loss: if args.save_model == True: model_file_name = args.savedir + os.sep + 'best_model' + '.pth' print('==> Saving the best model') torch.save(model.state_dict(), model_file_name) min_val_loss = loss_val logger.close()
con.row_factory = dictFactory cur = con.cursor() return jsonify( cur.execute(req.format(order, order_p, limit, offset)).fetchall()) except Exception as e: return jsonify({"error": str(e)}) @app.route("/update", methods=["POST"]) def update(): """ Метод API позволяющий обновить БД не по таймеру, а принудительно :return: """ try: loadData() return jsonify({"Status": "updated"}) except Exception as e: return jsonify({"Error of update": str(e)}) if __name__ == "__main__": # Создание процесса фонового обновления БД scheduler = BackgroundScheduler() scheduler.add_job(func=loadData, trigger="interval", seconds=MINUTES * 60) scheduler.start() # Инициализация и запуск generateDB() loadData() app.run(host="0.0.0.0", port=8000)
import load import numpy as np import sys if __name__ == "__main__": M = load.loadData("/tmp/cifar.adjustVar") print M.shape eigVal, _ = np.linalg.eig(M) print min(eigVal) rho = max(0, -min(eigVal)) print rho rho *= 1.2 if rho == 0: print "rho setting 0.1" rho = 0.1 Q = np.eye(M.shape[0]) + 1 / rho * M L = np.linalg.cholesky(Q) U = L.T load.save(L, "/tmp/cifar.nonor.L") load.save(L, "/tmp/cifar.nonor.U")
from sklearn.linear_model import LogisticRegression from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier from sklearn import svm from load import loadData from clean import LabelInfo import numpy as np images, labels = loadData() # If sum across one dimension #for i in range(len(images)): # images[i] = np.sum(images[i], axis=2) for i in range(len(images)): images[i] = images[i].flatten() X_train = images[:len(images) // 10 * 9] X_valid = images[len(images) // 10 * 9:] y_train = labels[:len(images) // 10 * 9] y_valid = labels[len(images) // 10 * 9:] # clf1 = LogisticRegression(random_state=0, solver='lbfgs', multi_class='multinomial').fit(X_train, y_train) # # print('logistic regression score is ', clf1.score(X_valid, y_valid)) # # clf2 = svm.SVC(kernel='linear').fit(X_train, y_train) # # print('SVM score is ', clf2.score(X_valid, y_valid)) clf3 = RandomForestClassifier().fit(X_train, y_train)
import load import numpy as np import sys if __name__ == "__main__": M = load.loadData("/tmp/cifar.adjustVar") print M.shape eigVal, _ = np.linalg.eig(M) print min(eigVal) rho = max(0, - min(eigVal)) print rho rho *= 1.2 if rho == 0: print "rho setting 0.1" rho = 0.1 Q = np.eye(M.shape[0]) + 1/rho *M L = np.linalg.cholesky(Q) U = L.T load.save(L, "/tmp/cifar.nonor.L") load.save(L, "/tmp/cifar.nonor.U")
def buildNonorW(): L = load.loadData("/tmp/cifar.nonor.L") U = load.loadData("/tmp/cifar.nonor.U") Uk = U[:, 0:conf.K] W = L * Uk return W.T
def buildOrthW(): W = load.loadData("/tmp/cifar.north.w") return W[0:conf.K, :]
def buildSeqLHW(): W = load.loadData("/tmp/cifar.splh.w") W = np.matrix(W) return W[0:conf.K, :]
analyze.report(data) elif userResp == '2': read_file.seek(0) data = csv.reader(read_file, None) next(data) analyze.ratingBetweenWdnWk(data) elif userResp == '3': read_file.seek(0) data = csv.reader(read_file, None) next(data) analyze.ratingByTmRange(data) elif userResp == '4': stopProg = True else: print("In-correct Input!") else: print("In-correct file number!") except KeyError: print("") print("No Class Data Found!") print( "Please generate a class report first by using the search for all classes feature!" ) print("---------------------Welcome to CunyFaster---------------------") classData = loadData() #initialize data mainMenu() print("-----------------Thank You For Using CunyFaster----------------")
import scipy.spatial import hashing def query(q, hashingArray): rank = [scipy.spatial.distance.hamming(q, h) for h in hashingArray] K = len(q) r = 2.0 / len(q) return [idx for idx, val in enumerate(rank) if val <= r] if __name__ == "__main__": K = conf.K W = hashing.buildSeqLHW() hashingArray = load.loadData("/tmp/cifar.hashingArray") data = load.loadData("/home/liuy/obj/gist.ans.py.data.10000") X = np.matrix(data) X = X.T X -= X.mean(1) train = load.loadData("/home/liuy/obj/cifar-10-batches-py/data_batch_1") label = train["labels"] precisionLst, recallLst = [], [] idxLst = range(0, len(data)) random.shuffle(idxLst) idxLst = idxLst[0:200] for idx in idxLst: x = X[:, idx]
def evaluate_lenet5(learning_rate=0.1, n_epochs=1000, path='/Users/Davis/Desktop/dataset', nkerns=[20, 30, 40], batch_size=10): """ Demonstrates lenet on MNIST dataset :type learning_rate: float :param learning_rate: learning rate used (factor for the stochastic gradient) :type n_epochs: int :param n_epochs: maximal number of epochs to run the optimizer :type dataset: string :param dataset: path to the dataset used for training /testing (MNIST here) :type nkerns: list of ints :param nkerns: number of kernels on each layer """ trainPath = path + '/train/*jpg' #built path to all 3 folders for all images included. testPath = path + '/test/*jpg' #these are correctly written validPath = path + '/valid/*jpg' # validPath = '/Users/Davis/Desktop/dataset/valid/*jpg' rng = numpy.random.RandomState(23455) #seed your random number generator train_set_x, train_set_y = loadData(trainPath) valid_set_x, valid_set_y = loadData(validPath) test_set_x, test_set_y = loadData(testPath) # compute number of minibatches for training, validation and testing n_train_batches = train_set_x.get_value(borrow=True).shape[0] n_valid_batches = valid_set_x.get_value(borrow=True).shape[0] n_test_batches = test_set_x.get_value(borrow=True).shape[0] n_train_batches /= batch_size n_valid_batches /= batch_size n_test_batches /= batch_size # allocate symbolic variables for the data index = T.lscalar() # index to a [mini]batch # start-snippet-1 x = T.matrix('x') # the data is presented as rasterized images y = T.ivector('y') # the labels are presented as 1D vector of # [int] labels ###################### # BUILD ACTUAL MODEL # ###################### print '... building the model with ' + os.path.split(path)[1] # Reshape matrix of rasterized images of shape (batch_size, 200 * 200) # to a 4D tensor, compatible with our LeNetConvPoolLayer # (200, 200) is the size of MNIST images. layer0_input = x.reshape((batch_size, 1, 100, 100)) # Construct the first convolutional pooling layer: # filtering reduces the image size to (100-5+1 , 100-5+1) = (96, 96) # maxpooling reduces this further to (96/2, 96/2) = (48, 48) # 4D output tensor is thus of shape (batch_size, nkerns[0], 48, 48) layer0 = LeNetConvPoolLayer( rng, input=layer0_input, image_shape=(batch_size, 1, 100, 100), filter_shape=(nkerns[0], 1, 5, 5), poolsize=(2, 2) ) # Construct the second convolutional pooling layer # filtering reduces the image size to (48-5+1, 48-5+1) = (44, 44) # maxpooling reduces this further to (44/2, 44/2) = (22, 22) # 4D output tensor is thus of shape (batch_size, nkerns[1], 22, 22) layer1 = LeNetConvPoolLayer( rng, input=layer0.output, image_shape=(batch_size, nkerns[0], 48, 48), filter_shape=(nkerns[1], nkerns[0], 5, 5), poolsize=(2, 2) ) # Construct the third convolutional pooling layer # filtering reduces the image size to (22-5+1, 22-5+1) = (18, 18) # maxpooling reduces this further to (18/2, 18/2) = (9, 9) # 4D output tensor is thus of shape (batch_size, nkerns[1], 9, 9) layer2 = LeNetConvPoolLayer( rng, input=layer1.output, image_shape=(batch_size, nkerns[1], 22, 22), filter_shape=(nkerns[2], nkerns[1], 5, 5), poolsize=(2, 2) ) # the HiddenLayer being fully-connected, it operates on 2D matrices of # shape (batch_size, num_pixels) (i.e matrix of rasterized images). # This will generate a matrix of shape (batch_size, nkerns[1] * 9 * 9), # or (500, 30 * 9 * 9) = (500, 2430) with the default values. layer3_input = layer2.output.flatten(2) # construct a fully-connected sigmoidal layer layer3 = HiddenLayer( rng, input=layer3_input, n_in=nkerns[2] * 9 * 9, n_out=500, activation=T.tanh ) # classify the values of the fully-connected sigmoidal layer layer4 = LogisticRegression( input=layer3.output, n_in=500, n_out=2 ) # the cost we minimize during training is the NLL of the model cost = layer4.negative_log_likelihood(y) # the data above will do all the work required. However, here is what the following block of code means # we are defining a function. Given some lists of indexes, the ERRORS will be calculated. How the errors # are calculated are described in the code above OUTSIDE of the function definition. This is useful # such that we can separate batch splitting and inputs from the rest of the code... We can also define multiple # functions over the entire feed forward network and just pull variables from within it as it runs! cool! # this is all made possible by the theano.function(). # # create a function to compute the mistakes that are made by the model test_model = theano.function( [index], layer4.errors(y), givens={ x: test_set_x[index * batch_size: (index + 1) * batch_size], y: test_set_y[index * batch_size: (index + 1) * batch_size] } ) validate_model = theano.function( [index], layer4.errors(y), givens={ x: valid_set_x[index * batch_size: (index + 1) * batch_size], y: valid_set_y[index * batch_size: (index + 1) * batch_size] } ) # create a list of all model parameters to be fit by gradient descent params = layer4.params + layer3.params + layer2.params + layer1.params + layer0.params # create a list of gradients for all model parameters grads = T.grad(cost, params) # train_model is a function that updates the model parameters by # SGD Since this model has many parameters, it would be tedious to # manually create an update rule for each model parameter. We thus # create the updates list by automatically looping over all # (params[i], grads[i]) pairs. updates = [ (param_i, param_i - learning_rate * grad_i) for param_i, grad_i in zip(params, grads) ] train_model = theano.function( [index], cost, updates=updates, givens={ x: train_set_x[index * batch_size: (index + 1) * batch_size], y: train_set_y[index * batch_size: (index + 1) * batch_size] } ) # end-snippet-1 ############### # TRAIN MODEL # ############### print '... training' # early-stopping parameters patience = 10000 # look as this many examples regardless patience_increase = 2 # wait this much longer when a new best is # found improvement_threshold = 0.995 # a relative improvement of this much is # considered significant validation_frequency = min(n_train_batches, patience / 2) # go through this many # minibatche before checking the network # on the validation set; in this case we # check every epoch best_validation_loss = numpy.inf #nothing will be > inf, so the worst case is having infinite loss (infinite error) best_iter = 0 #the best iteration will update test_score = 0. #so will the best test score (higher is better) start_time = time.clock() #the starting time is set here, later endtime-starttime = elapsed_time epoch = 0 #we start at zero epochs. Remember that each epoch equals 1 iteration through the ENTIRE training set. done_looping = False #we are NOT done looping! while (epoch < n_epochs) and (not done_looping): #if n_epochs has been reached we stop; if done_looping is triggered we stop. epoch = epoch + 1 #everytime we reach this line, ONE epoch has been completed #note that ITERATIONS mean each MINI-BATCH. For example, for 120 images, #there are 12 iterations and 1 epoch per run through. for minibatch_index in xrange(n_train_batches): #iterates through INDEXES for MINI-BATCHES iter = (epoch - 1) * n_train_batches + minibatch_index #current iteration count. We verified this before. if iter % 100 == 0: #every 100 mini-batches trained, we print how many mini-batches have been trained! print 'training @ iter = ', iter cost_ij = train_model(minibatch_index) #the theano function outputs the cost from the last layer (logistic regression X-Ent Cost) #note that all updates are calculated above along with backprop errors. if (iter + 1) % validation_frequency == 0: #the rest of the code is for early stopping. # compute zero-one loss on validation set validation_losses = [validate_model(i) for i in xrange(n_valid_batches)] this_validation_loss = numpy.mean(validation_losses) print('epoch %i, minibatch %i/%i, validation error %f %%' % (epoch, minibatch_index + 1, n_train_batches, this_validation_loss * 100.)) # if we got the best validation score until now if this_validation_loss < best_validation_loss: #improve patience if loss improvement is good enough if this_validation_loss < best_validation_loss * \ improvement_threshold: patience = max(patience, iter * patience_increase) # save best validation score and iteration number best_validation_loss = this_validation_loss best_iter = iter # test it on the test set test_losses = [ test_model(i) for i in xrange(n_test_batches) ] test_score = numpy.mean(test_losses) print((' epoch %i, minibatch %i/%i, test error of ' 'best model %f %%') % (epoch, minibatch_index + 1, n_train_batches, test_score * 100.)) if patience <= iter: done_looping = True break end_time = time.clock() print('Optimization complete.') print('Best validation score of %f %% obtained at iteration %i, ' 'with test performance %f %%' % (best_validation_loss * 100., best_iter + 1, test_score * 100.)) print >> sys.stderr, ('The code for file ' + os.path.split(__file__)[1] + ' ran for %.2fm' % ((end_time - start_time) / 60.))
# python 3 import numpy as np import matplotlib.pyplot as plt import load import jackknife as jackk import bootstrap as boots import chi_2 as chi if __name__ == "__main__": ''' solution for (3a) ''' C = load.loadData('data2.dat') mean = C.mean(axis=0).reshape(1,32) sum = np.zeros((1,32)) for line in C: sum = sum + (line - mean)**2 deviation = np.sqrt(sum / (200*199)) rel_dev = deviation / mean * 100 # output = open('3a.txt','w') # # form format ouput # for i in range(32): # line = "|{}".format(i+1) +"|{:.3e}|".format(mean[0][i]) + "{:.2f}|".format(deviation[0][i]) + "{:.2f}%| \n".format(rel_dev[0][i]) # output.write(line) # output.close()
import sys import subprocess import load meta, test, train = load.loadData() traindata = train["data"] filenames = train["filenames"] assert len(traindata) == len(filenames) path = "/tmp/cifar/" load.checkDir(path) convert_flag = False if sys.argv[1] == "png": convert_flag = True print "PNG format" else: print "PPM format" for i in xrange(len(traindata)): data = traindata[i] name = path + filenames[i] name += ".ppm" load.writePPM(32, 32, data, name) if convert_flag: objname = name[:-4] cmd = ['convert', name, objname] print cmd
import sys import numpy as np import cPickle as pickle import scipy.spatial import Ml import load train = load.loadData("/home/liuy/obj/cifar-10-batches-py/data_batch_1") labels = train["labels"] data = load.loadData("/home/liuy/obj/gist.ans.py.data.10000") X = np.matrix(data) X = X.T X -= X.mean(1) X0 = X eta = 0.6 # TODO: def T_func(Sk_tidle, Sk): m, n = Sk.shape for i in xrange(m): for j in xrange(n): if Sk_tidle[i, j] * Sk[i, j] >= 0: Sk_tidle[i, j] = 0 return Sk_tidle S = Ml.buildLabelMatrix(labels) Xlf, Slf = Ml.filterMatrix(X0, S)
from sklearn.feature_extraction import DictVectorizer from pyfm import pylibfm import pandas as pd import math import time import load import runFM import calcMRR ## # import group ## # The users in the test set have been grouped according to user_id so that MRR of every group of users can be calculated. ## # This module has been provided for reference. ## # The test set provided has already been grouped by user_id so it is not necessary to perform this step. ## group.arrange("test_100_10K.txt"); # Loading the training and test datasets print('Loading data...') (train_data, y_train, train_users, train_items) = load.loadData("train_final_POP_RND.txt") (test_data, y_test, test_uers, test_items) = load.loadData("test_final_POP_RND.txt") # Running Factorization Machine print('Running FM...') preds = runFM.FM(train_data, test_data, y_train) # Evaluation: Calculating the Mean Reciprocal Rank(MRR) print('Calculating MRR...') calcMRR.MRR(preds)
import ast import json import os from load import loadData N=int(raw_input("Enter the order: ")) #N stands for n-th order markov chain f_dictionary={} #this dictionary contains the original contents in json file and also the ones after changing the data ccording to user input word_count=0 #counts the number of words words=[] #list of all words currentWord='' #the current word prediction='' #the value which we predicted loadData(N) #calls the loadData from load.py which creates the json dictionary with open('dictionary.json') as data_file: #loads data from the json to loaded_dictionary loaded_dictionary=json.load(data_file) for key in loaded_dictionary: #json cant store dictionaries with tuple as keys so it is stored as string to evaluate it back to tuple f_dictionary[ast.literal_eval(key)]=loaded_dictionary[key] while word_count<N: #do no prediction for the starting N words currentWord=raw_input() words.append(currentWord) word_count+=1 previousKey=() #previousKey stores the previous values of key while True: key_find=tuple(words[word_count-N:]) #the current value of key if f_dictionary.has_key(key_find): if f_dictionary.get(key_find)!={}: prediction=max(f_dictionary.get(key_find).iterkeys(), key=(lambda key: f_dictionary.get(key_find)[key])) if prediction !='*****':
from openpyxl import load_workbook from load import loadData doc = load_workbook(filename='CPH_KEA sep2019-1.xlsx') # extracting the active sheet from the document ws = doc.active # loadData() returns a array of all the flighnumbers result = loadData() columns = 0 # loop through collumn 7 in ac for col in ws.iter_rows(min_col=7, max_col=7, min_row=2): for cell in col: cell.value = result[columns] columns = columns + 1 doc.save('CPH_flykoder_opdateret.xlsx')
import load import numpy as np from sklearn import naive_bayes from sklearn.metrics import f1_score, accuracy_score trX, teX, trY, teY = load.loadData(onehot = False, poly = 3, prep = 'std') gnb = naive_bayes.GaussianNB() gnb.fit(trX, trY) print "Training F1: ", f1_score(trY, gnb.predict(trX)) print 'Test F1:', f1_score(teY, gnb.predict(teX))
L = load.loadData("/tmp/cifar.nonor.L") U = load.loadData("/tmp/cifar.nonor.U") Uk = U[:, 0:conf.K] W = L * Uk return W.T def buildOrthW(): W = load.loadData("/tmp/cifar.north.w") return W[0:conf.K, :] def buildSeqLHW(): W = load.loadData("/tmp/cifar.splh.w") W = np.matrix(W) return W[0:conf.K, :] if __name__ == "__main__": K = conf.K W = buildSeqLHW() data = load.loadData("/home/liuy/obj/gist.ans.py.data.10000") X = np.matrix(data) X = X.T X -= X.mean(1) _, col = X.shape hashingArray = [hashingK(W, X[:, i]) for i in xrange(col)] load.save(hashingArray, "/tmp/cifar.hashingArray")