def predict(self, new_df=None, sample_size=1000):
'''
Args:
new_data_frame (pandas dataframe): the dataframe of new locations. Users can also include the truth value of Y.
Note that MSE cannot be computed if truth is not provided.
'''
if new_df:
try:
self.X_test = coordinates_converter(new_df)
self.y_test = new_df[self.response_var]
self.test_loc_cache = new_df[['LATITUDE', 'LONGITUDE']]
except:
raise ValueError(
'The new dataframe should contain LATITUDE, LONGITUDE and the variable column, e.g., PRCP'
)
with self.model:
y_pred = self.gp.conditional("y_pred", self.X_test)
self.simulated_values = pm.sample_ppc(self.trace,
vars=[y_pred],
samples=sample_size)
self.predictions = np.exp(
np.median(self.simulated_values['y_pred'], axis=0))
l1_loss = np.mean(np.abs(self.predictions - self.y_test))
l2_loss = np.mean(np.square(self.predictions - self.y_test))
self.summary = {'l1_loss': l1_loss, 'l2_loss': l2_loss}
output_df = self.test_loc_cache.copy()
output_df['PRED'] = self.predictions
return self.predictions
def predict(self, new_df=None, sample_size=500):
if new_df:
try:
self.X_test = coordinates_converter(new_df)
self.y_test = new_df[self.response_var]
self.test_loc_cache = new_df[['LATITUDE', 'LONGITUDE']]
except:
raise ValueError(
'The new dataframe should contain LATITUDE, LONGITUDE and the variable column, e.g., PRCP'
)
with self.model:
self.X_train.set_value(self.X_test)
self.simulated_values = pm.sample_ppc(self.trace,
samples=sample_size)
self.predictions = np.exp(
np.median(self.simulated_values['y'], axis=0))
l1_loss = np.mean(np.abs(self.predictions - self.y_test))
l2_loss = np.mean(np.square(self.predictions - self.y_test))
self.summary = {'l1_loss': l1_loss, 'l2_loss': l2_loss}
output_df = self.test_loc_cache.copy()
output_df['PRED'] = self.predictions
return self.predictions
def __init__(self, df, response_var='PRCP', split_ratio=0.7):
X = coordinates_converter(df).values
self.response_var = response_var
y = df[self.response_var].values
all_index = list(range(len(df)))
train_size = int(round(len(df) * split_ratio, 0))
train_index = np.random.choice(all_index, train_size)
test_index = [idx for idx in all_index if idx not in train_index]
self.X_train = X[train_index]
self.X_test = X[test_index]
self.y_train = y[train_index]
self.y_test = y[test_index]
self.train_loc_cache = df.loc[train_index, ['LATITUDE', 'LONGITUDE']]
self.test_loc_cache = df.loc[test_index, ['LATITUDE', 'LONGITUDE']]