def singleshot():
fn = str(random.randint(1, 25))
filename = 'rt-data-io/' + fn + '.csv'
weightFile = 'Data/weights.h5'
predFile = 'Data/singleCSV/singlePred.h5'
columns = [
'stresses_full_xx', 'stresses_full_yy', 'stresses_full_xy',
'stresses_full_xz', 'stresses_full_yz', 'stresses_full_zz'
]
testFile = 'single.h5'
dictionary = defaultdict(list)
print('working with {},...'.format(filename.split('/')[-1]))
data = helper_functions.csv2dict(filename)
grid_aftershock_count = np.double(data['aftershocksyn'])
temp = grid_aftershock_count.tolist()
dictionary['aftershocksyn'].extend(temp)
for column in columns:
dictionary[column].extend(np.double(data[column]))
columns.append('aftershocksyn')
helper_functions.dict2HDF('single.h5', columns, dictionary)
features_in = [
'stresses_full_xx', 'stresses_full_yy', 'stresses_full_xy',
'stresses_full_xz', 'stresses_full_yz', 'stresses_full_zz'
]
features_out = 'aftershocksyn'
model = helper_functions.createModel()
model.load_weights(weightFile)
X, y = helper_functions.loadDataFromHDF(testFile, features_in,
features_out)
y_pred = model.predict(X)
helper_functions.writeHDF(predFile, X, y)
auc = sklearn.metrics.roc_auc_score(y, y_pred)
return auc
'stresses_full_xy', 'stresses_full_xz',
'stresses_full_yz','stresses_full_zz']
testFile = 'single.h5'
dictionary = defaultdict(list)
print('working with {},...'.format(filename.split('/')[-1]))
data = helper_functions.csv2dict(filename)
grid_aftershock_count = np.double(data['aftershocksyn'])
temp = grid_aftershock_count.tolist()
dictionary['aftershocksyn'].extend(temp)
for column in columns:
dictionary[column].extend(np.double(data[column]))
columns.append('aftershocksyn')
helper_functions.dict2HDF('single.h5', columns, dictionary)
features_in = ['stresses_full_xx',
'stresses_full_yy',
'stresses_full_xy',
'stresses_full_xz',
'stresses_full_yz',
'stresses_full_zz']
features_out = 'aftershocksyn'
model = helper_functions.createModel()
model.load_weights(weightFile)
X, y = helper_functions.loadDataFromHDF(testFile, features_in, features_out)
y_pred = model.predict(X)
helper_functions.writeHDF(predFile, X, y)
auc = sklearn.metrics.roc_auc_score(y, y_pred)
print('{}. working with {}, please wait...'.format(
i, filename.decode('utf-8')))
# calling csv2dict(), to convert the csv file to dictionary
data = helper_functions.csv2dict('Data/csvfiles/' +
str(filename.decode('utf-8')))
# accessing the key aftershocksyn to check for unique values, similar like (set(list[1, 1, 0, 2, 3])) -> outputs [1, 1, 0, 2, 3]
grid_aftershock_count = np.double(data['aftershocksyn'])
# no use of if
#if len(np.unique(grid_aftershock_count)) < 2:
# continue
temp = grid_aftershock_count.tolist()
# adding a (key, value) to the testingSet
dictionary['aftershocksyn'].extend(temp)
# now adding remaining columns
for column in columns:
dictionary[column].extend(np.double(data[column]))
return dictionary
##########################CREATING TESTING DATASET#############################
testingSet = makeDataDict(testingFilenames)
##########################CREATING TRAINING DATASET#############################
trainingSet = makeDataDict(trainingFilenames)
#############################SAVING THE DATASET################################
columns.append('aftershocksyn')
helper_functions.dict2HDF('training_tmp.h5', columns, trainingSet)
helper_functions.dict2HDF('testing_tmp.h5', columns, testingSet)