def make_predictions(body, overwrite=False):
"""
Function for making predictions over a time range and locations by a given model
:param body:
:param overwrite:
:return: bool, list - boolean whether it is successful and list with predictions and uncertanties
"""
dataset = DatasetsApi.get_dataset(body, use_dataframe=True)
if dataset is None:
return False, []
# get dataset with empty pollutant values
incomplete_dataset = dataset if overwrite else dataset[
dataset['Pollutant'].isnull()]
# split the dataset, do not normalize until means and stds are taken from the model
X_predict, y_predict, _, _, stats = MainTransformer.get_training_and_test_set(
incomplete_dataset,
'Pollutant',
'Uncertainty',
size=1,
normalize=False)
model, model_record, err = ModelApi.get_model_by_name(body['name'])
predictions = []
print(err)
if err is None:
training_dataset_stats = {}
print('Verifying features...')
if X_predict is None or X_predict.shape[1] != model.n_features:
print('Wrong number of features')
print(X_predict.shape[1] - 1)
print(model.n_features)
return False, []
print('Checking model stats...')
if 'dataset_stats' in model.stats:
training_dataset_stats = model.stats['dataset_stats']
feature_names = set(training_dataset_stats.keys())
dataset_features = set(X_predict)
dataset_features.discard('DateTime')
print('Checking feature names...')
if feature_names != dataset_features:
return False, []
print('Normalizing...')
MainTransformer.normalize(X_predict,
stats=training_dataset_stats,
inplace=True)
else:
return False, []
print('Preidicting...')
predictions = model.predict(X_predict, uncertainty=True)
MainTransformer.unnormalize(X_predict,
training_dataset_stats,
inplace=True)
MainTransformer.remove_periodic_f(X_predict)
X_predict.loc[:, 'Pollutant'] = Series([x[0] for x in predictions],
index=X_predict.index)
X_predict.loc[:,
'Uncertainty'] = Series([x[1] for x in predictions],
index=X_predict.index)
# add predictions to the DB
print('Done. Adding to database...')
optional_data_keyset = set(body['data'].keys())
dataframe_optional_data = set(X_predict.keys()).difference(
ModelApi.REQUIRED_FIELDS)
keys_with_data_to_be_added = optional_data_keyset.intersection(
dataframe_optional_data)
results = []
for index, row in X_predict.iterrows():
if row['Pollutant'] is not None and math.isnan(
row['Pollutant']):
continue
input_instance = {
'date_time': index,
'longitude': row['Longitude'],
'latitude': row['Latitude'],
'pollutant': body['pollutant'],
'pollution_value': row['Pollutant'],
'uncertainty': row['Uncertainty'],
'data': {}
}
print(body['pollutant'])
print(row['Pollutant'])
for key in keys_with_data_to_be_added:
input_instance['data'][key] = row[key]
result = DatasetsApi.insert_single_prediction(input_instance)
results.append(result)
predictions = ModelApi.__predictions_to_primitive_float(
predictions)
print('failed following: ')
print(list(filter(lambda x: not x[0], results)))
return True, predictions
return False, predictions # in case that model does not exist
def make_single_prediction(body):
"""
Function for making predictions over a time range and locations by a given model
:param body:
:return: bool, list - boolean whether it is successful and list with predictions and uncertanties
"""
if not isinstance(body, dict):
return False, []
if 'name' not in body:
return False, []
if 'pollutant' not in body:
return False, []
model, model_record, err = ModelApi.get_model_by_name(body['name'])
predictions = []
if err is None:
prev = None
if isinstance(model, ConvolutionalNeuralNetwork):
prev = model.seq_length
training_dataset_stats = {}
if 'dataset_stats' in model.stats:
training_dataset_stats = model.stats['dataset_stats']
X_predict = DatasetsApi.get_single_instance_dataset(
body, stats=training_dataset_stats, prev=prev)
if X_predict is None:
return False, []
feature_names = set(training_dataset_stats.keys())
dataset_features = set(X_predict)
dataset_features.discard('DateTime')
if feature_names != dataset_features:
print(feature_names)
print(dataset_features)
return False, []
else:
return False, []
predictions = model.predict(X_predict, uncertainty=True)
MainTransformer.unnormalize(X_predict,
training_dataset_stats,
inplace=True)
MainTransformer.remove_periodic_f(X_predict)
X_predict.loc[:, 'Pollutant'] = Series([x[0] for x in predictions],
index=X_predict.index)
X_predict.loc[:,
'Uncertainty'] = Series([x[1] for x in predictions],
index=X_predict.index)
# add predictions to the DB
keys_with_data_to_be_added = {}
if 'data' in body:
optional_data_keyset = set(body['data'].keys())
dataframe_optional_data = set(X_predict.keys()).difference(
ModelApi.REQUIRED_FIELDS)
keys_with_data_to_be_added = optional_data_keyset.intersection(
dataframe_optional_data)
results = []
for index, row in X_predict.iterrows():
if row['Pollutant'] is not None and math.isnan(
row['Pollutant']):
continue
input_instance = {
'date_time': index,
'longitude': row['Longitude'],
'latitude': row['Latitude'],
'pollutant': body['pollutant'],
'pollution_value': row['Pollutant'],
'uncertainty': row['Uncertainty'],
'data': {}
}
if 'data' in body:
for key in keys_with_data_to_be_added:
input_instance['data'][key] = row[key]
result = DatasetsApi.insert_single_instance(input_instance,
predicted=True)
result = DatasetsApi.insert_single_prediction(input_instance)
results.append(result)
predictions = ModelApi.__predictions_to_primitive_float(
predictions)
print('failed following: ')
print(list(filter(lambda x: not x[0], results)))
return True, predictions
return False, predictions # in case that model does not exist