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
# path of trained model files
folder_path = '/Users/aklimasewski/Documents/model_results/base/ANNbase_nga_20ep_50hidden/'
folder_pathNGA = folder_path + 'NGAtest/'
if not os.path.exists(folder_pathNGA):
os.makedirs(folder_pathNGA)
n = 13
az = True
transform_method = 'Norm'
# compare to NGA data
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(
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