def mergeNGAdata(
nametrain='/Users/aklimasewski/Documents/data/cybertrainyeti10_residfeb.csv',
nametest='/Users/aklimasewski/Documents/data/cybertestyeti10_residfeb.csv',
filenamenga='/Users/aklimasewski/Documents/data/NGA_mag2_9.csv',
n=13):
from sklearn.model_selection import train_test_split
train_data1, test_data1, train_targets1, test_targets1, feature_names = readindata(
nametrain=
'/Users/aklimasewski/Documents/data/cybertrainyeti10_residfeb.csv',
nametest=
'/Users/aklimasewski/Documents/data/cybertestyeti10_residfeb.csv',
n=n)
train_data1, test_data1, feature_names = add_az(train_data1, test_data1,
feature_names)
# filenamenga = '/Users/aklimasewski/Documents/data/NGA_mag2_9.csv'
nga_data1, nga_targets1, feature_names = readindataNGA(filenamenga, n)
nga_data1, feature_names = add_azNGA(filenamenga, nga_data1, feature_names)
# ngatrain, ngatest, ngatrain_targets, ngatest_targets = train_test_split(nga_data1,nga_targets1, test_size=0.2, random_state=1)
ngatrain, ngatest, ngatrain_targets, ngatest_targets, ngacells_train, ngacells_test = train_test_split(
nga_data1, nga_targets1, cells_nga, test_size=0.2, random_state=1)
train_data1 = np.concatenate([train_data1, ngatrain], axis=0)
test_data1 = np.concatenate([test_data1, ngatest], axis=0)
train_data1 = np.concatenate([train_data1, ngatrain], axis=0)
test_data1 = np.concatenate([test_data1, ngatest], axis=0)
train_targets1 = np.concatenate([train_targets1, ngatrain_targets], axis=0)
test_targets1 = np.concatenate([test_targets1, ngatest_targets], axis=0)
return train_data1, test_data1, train_targets1, test_targets1, feature_names
def mergeNGAdata(
nametrain='/Users/aklimasewski/Documents/data/cybertrainyeti10_residfeb.csv',
nametest='/Users/aklimasewski/Documents/data/cybertestyeti10_residfeb.csv',
filenamenga='/Users/aklimasewski/Documents/data/NGA_mag2_9.csv',
n=13):
'''
Read in NGA data file, train test split and merge with cybershake data
Parameters
----------
nametrain: path for cybershake training data csv
nametest: path for cybershake testing data csv
filenamenga: integer number of hidden layers
n: number of model input features
Returns
-------
train_data1: numpy array of training features
test_data1: numpy array of testing features
train_targets1: numpy array of training features
test_targets1: numpy array of testing features
feature_names: numpy array feature names
'''
from sklearn.model_selection import train_test_split
train_data1, test_data1, train_targets1, test_targets1, feature_names = readindata(
nametrain=
'/Users/aklimasewski/Documents/data/cybertrainyeti10_residfeb.csv',
nametest=
'/Users/aklimasewski/Documents/data/cybertestyeti10_residfeb.csv',
n=n)
train_data1, test_data1, feature_names = add_az(train_data1, test_data1,
feature_names)
# filenamenga = '/Users/aklimasewski/Documents/data/NGA_mag2_9.csv'
nga_data1, nga_targets1, feature_names = readindataNGA(filenamenga, n)
nga_data1, feature_names = add_azNGA(filenamenga, nga_data1, feature_names)
# ngatrain, ngatest, ngatrain_targets, ngatest_targets = train_test_split(nga_data1,nga_targets1, test_size=0.2, random_state=1)
ngatrain, ngatest, ngatrain_targets, ngatest_targets = train_test_split(
nga_data1, nga_targets1, test_size=0.2, random_state=1)
train_data1 = np.concatenate([train_data1, ngatrain], axis=0)
test_data1 = np.concatenate([test_data1, ngatest], axis=0)
train_data1 = np.concatenate([train_data1, ngatrain], axis=0)
test_data1 = np.concatenate([test_data1, ngatest], axis=0)
train_targets1 = np.concatenate([train_targets1, ngatrain_targets], axis=0)
test_targets1 = np.concatenate([test_targets1, ngatest_targets], axis=0)
return train_data1, test_data1, train_targets1, test_targets1, feature_names
filenamenga = '/Users/aklimasewski/Documents/data/NGA_mag2_9.csv'
nga_data1, nga_targets1, feature_names = readindataNGA(filenamenga, n)
nga_data1, feature_names = add_azNGA(filenamenga, nga_data1, feature_names)
# nga_data1,feature_names = add_locfeatNGA(filenamenga,nga_data1,feature_names)
if az == True:
nga_data1, feature_names = add_azNGA(nga_data1, feature_names)
# read in cyber shake trainineg and testing data
train_data1, test_data1, train_targets1, test_targets1, feature_names = readindata(
nametrain=
'/Users/aklimasewski/Documents/data/cybertrainyeti10_residfeb.csv',
nametest='/Users/aklimasewski/Documents/data/cybertestyeti10_residfeb.csv',
n=n)
train_data1, test_data1, feature_names = add_az(train_data1, test_data1,
feature_names)
x_train, y_train, x_nga, y_nga, x_range, x_train_raw, x_nga_raw = transform_data(
transform_method, train_data1, nga_data1, train_targets1, nga_targets1,
feature_names, folder_pathNGA)
# load model and fit
loadedmodel = keras.models.load_model(folder_path + 'model/')
pre_nga = loadedmodel.predict(x_nga)
resid_nga = np.asarray(nga_targets1) - pre_nga
pre_train = loadedmodel.predict(x_train)
resid_train = np.asarray(train_targets1) - pre_train
period = [10, 7.5, 5, 4, 3, 2, 1, 0.5, 0.2, 0.1]
def ANN_2step(folder_pathmod1,
folder_pathmod2,
epochs1=50,
epochs2=50,
numlayers1=1,
numlayers2=1,
units1=[20],
units2=[20]):
'''
2 ANNs: 1st is the base ANN, 2nd ANN uses 1st model residuals as targets and cell location features
Parameters
----------
folder_pathmod1: path for saving png files for the first ANN
folder_pathmod2: path for saving png files for the second ANN
epochs1: number of training epochs for the first ANN
epochs2: number of training epochs for the second ANN
numlayers1: integer number of hidden layers for the first ANN
numlayers2: integer number of hidden layers for the second ANN
units1: array of number of units for hidden layers for first ANN
units2: array of number of units for hidden layers for second ANN
Returns
-------
None.
creates two ANNS and saves model files and figures
'''
from sklearn.preprocessing import PowerTransformer
if not os.path.exists(folder_pathmod1):
os.makedirs(folder_pathmod1)
# read in training, testing, and cell data
train_data1, test_data1, train_targets1, test_targets1, feature_names = readindata(
nametrain=
'/Users/aklimasewski/Documents/data/cybertrainyeti10_residfeb.csv',
nametest=
'/Users/aklimasewski/Documents/data/cybertestyeti10_residfeb.csv',
n=n)
train_data1, test_data1, feature_names = add_az(train_data1, test_data1,
feature_names)
cells = pd.read_csv(folder_path + 'gridpointslatlon_train.csv',
header=0,
index_col=0)
cells_test = pd.read_csv(folder_path + 'gridpointslatlon_test.csv',
header=0,
index_col=0)
x_train, y_train, x_test, y_test, x_range, x_train_raw, x_test_raw = transform_data(
transform_method, train_data1, test_data1, train_targets1,
test_targets1, feature_names, folder_pathmod1)
resid, resid_test, pre_train, pre_test = create_ANN(
x_train, y_train, x_test, y_test, feature_names, numlayers1, units1,
epochs1, transform_method, folder_pathmod1)
period = [10, 7.5, 5, 4, 3, 2, 1, 0.5, 0.2, 0.1]
plot_resid(resid, resid_test, folder_pathmod1)
# second ANN
if not os.path.exists(folder_pathmod2):
os.makedirs(folder_pathmod2)
train_targets1 = resid
test_targets1 = resid_test
train_data1 = np.asarray(cells)
test_data1 = np.asarray(cells_test)
transform_method = PowerTransformer()
feature_names = np.asarray([
'eventlat',
'eventlon',
'midlat',
'midlon',
'sitelat',
'sitelon',
])
x_train, y_train, x_test, y_test, x_range, x_train_raw, x_test_raw = transform_data(
transform_method, train_data1, test_data1, train_targets1,
test_targets1, feature_names, folder_pathmod2)
resid, resid_test, pre_train, pre_test = create_ANN(
x_train, y_train, x_test, y_test, feature_names, numlayers2, units2,
epochs2, transform_method, folder_pathmod2)
period = [10, 7.5, 5, 4, 3, 2, 1, 0.5, 0.2, 0.1]
plot_resid(resid, resid_test, folder_pathmod2)
def ANN_gridpoints(folder_pathmod, epochs=50, numlayers=1, units=[20]):
'''
ANN with cell locations as additional features
Parameters
----------
folder_pathmod: path for saving png files
epochs: number of training epochs
numlayers: integer number of hidden layers
units: array of number of units for hidden layers
Returns
-------
None.
creates ANNS and saves model files and figures
'''
cells = pd.read_csv(folder_path + 'gridpointslatlon_train.csv',
header=0,
index_col=0)
cells_test = pd.read_csv(folder_path + 'gridpointslatlon_test.csv',
header=0,
index_col=0)
if not os.path.exists(folder_pathmod):
os.makedirs(folder_pathmod1)
transform_method = 'Norm' #function or text
n = 13
train_data1, test_data1, train_targets1, test_targets1, feature_names = readindata(
nametrain=
'/Users/aklimasewski/Documents/data/cybertrainyeti10_residfeb.csv',
nametest=
'/Users/aklimasewski/Documents/data/cybertestyeti10_residfeb.csv',
n=n)
train_data1, test_data1, feature_names = add_az(train_data1, test_data1,
feature_names)
# add the cell features
train_data1 = np.concatenate([train_data1, cells], axis=1)
test_data1 = np.concatenate([test_data1, cells_test], axis=1)
feature_names = np.concatenate([
feature_names,
[
'eventlat',
'eventlon',
'midlat',
'midlon',
'sitelat',
'sitelon',
]
],
axis=0)
x_train, y_train, x_test, y_test, x_range, x_train_raw, x_test_raw = transform_data(
transform_method, train_data1, test_data1, train_targets1,
test_targets1, feature_names, folder_pathmod)
resid, resid_test, pre_train, pre_test = create_ANN(
x_train, y_train, x_test, y_test, feature_names, numlayers, units,
epochs, transform_method, folder_pathmod)
plot_resid(resid, resid_test, folder_pathmod1)
def mergeNGAdata_cells(
nametrain='/Users/aklimasewski/Documents/data/cybertrainyeti10_residfeb.csv',
nametest='/Users/aklimasewski/Documents/data/cybertestyeti10_residfeb.csv',
filenamenga='/Users/aklimasewski/Documents/data/NGA_mag2_9.csv',
n=13):
'''
Read in NGA data file, train test split and merge with cybershake data
Parameters
----------
nametrain: path for cybershake training data csv
nametest: path for cybershake testing data csv
filenamenga: integer number of hidden layers
n: number of model input features
Returns
-------
train_data1: numpy array of training features
test_data1: numpy array of testing features
train_targets1: numpy array of training features
test_targets1: numpy array of testing features
feature_names: numpy array feature names
'''
from sklearn.model_selection import train_test_split
cells = pd.read_csv(folder_path + 'gridpointslatlon_train.csv',
header=0,
index_col=0)
cells_test = pd.read_csv(folder_path + 'gridpointslatlon_test.csv',
header=0,
index_col=0)
cells_nga = pd.read_csv(folder_path + 'gridpointslatlon_nga.csv',
header=0,
index_col=0)
train_data1, test_data1, train_targets1, test_targets1, feature_names = readindata(
nametrain=
'/Users/aklimasewski/Documents/data/cybertrainyeti10_residfeb.csv',
nametest=
'/Users/aklimasewski/Documents/data/cybertestyeti10_residfeb.csv',
n=n)
train_data1, test_data1, feature_names = add_az(train_data1, test_data1,
feature_names)
nga_data1, nga_targets1, feature_names = readindataNGA(filenamenga, n)
nga_data1, feature_names = add_azNGA(filenamenga, nga_data1, feature_names)
nga_data1 = np.concatenate([nga_data1, cells_nga], axis=0)
ngatrain, ngatest, ngatrain_targets, ngatest_targets = train_test_split(
nga_data1, nga_targets1, test_size=0.2, random_state=1)
feature_names = np.concatenate([
feature_names,
[
'eventlat',
'eventlon',
'midlat',
'midlon',
'sitelat',
'sitelon',
]
],
axis=0)
train_data1 = np.concatenate([train_data1, cells], axis=1)
test_data1 = np.concatenate([test_data1, cells_test], axis=1)
train_data1 = np.concatenate([train_data1, ngatrain], axis=0)
test_data1 = np.concatenate([test_data1, ngatest], axis=0)
train_targets1 = np.concatenate([train_targets1, ngatrain_targets], axis=0)
test_targets1 = np.concatenate([test_targets1, ngatest_targets], axis=0)
return train_data1, test_data1, train_targets1, test_targets1, feature_names