def test_gapfilling_forward_ridge_correct():
arr_with_gaps, real_values = get_array_with_gaps()
# Find all gap indices in the array
id_gaps = np.ravel(np.argwhere(arr_with_gaps == -100.0))
ridge_chain = get_simple_ts_chain(model_root='ridge')
gapfiller = ModelGapFiller(gap_value=-100.0, chain=ridge_chain)
without_gap = gapfiller.forward_filling(arr_with_gaps)
# Get only values in the gaps
predicted_values = without_gap[id_gaps]
true_values = real_values[id_gaps]
rmse_test = mean_squared_error(true_values, predicted_values, squared=False)
assert rmse_test < 1.0
def test_gapfilling_forward_ridge_correct():
arr_with_gaps, real_values = get_array_with_gaps()
# Find all gap indices in the array
id_gaps = np.ravel(np.argwhere(arr_with_gaps == -100.0))
ridge_chain = TsForecastingChain(PrimaryNode('ridge'))
gapfiller = ModelGapFiller(gap_value=-100.0, chain=ridge_chain,
max_window_size=150)
without_gap = gapfiller.forward_filling(arr_with_gaps)
# Get only values in the gaps
predicted_values = without_gap[id_gaps]
true_values = real_values[id_gaps]
rmse_test = mean_squared_error(true_values, predicted_values, squared=False)
# The RMSE must be less than the standard deviation of random noise * 2.0
assert rmse_test < 0.2
def run_gapfilling_example():
"""
This function runs an example of filling in gaps in synthetic data
:return arrays_dict: dictionary with 4 keys ('ridge', 'local_poly',
'batch_poly', 'linear') that can be used to get arrays without gaps
:return gap_data: an array with gaps
:return real_data: an array with actual values in gaps
"""
# Get synthetic time series
gap_data, real_data = get_array_with_gaps()
# Filling in gaps using chain from FEDOT
node_lagged = PrimaryNode('lagged')
node_lagged.custom_params = {'window_size': 100}
node_ridge = SecondaryNode('ridge', nodes_from=[node_lagged])
ridge_chain = Chain(node_ridge)
ridge_gapfiller = ModelGapFiller(gap_value=-100.0, chain=ridge_chain)
without_gap_arr_ridge = \
ridge_gapfiller.forward_inverse_filling(gap_data)
# Filling in gaps using simple methods such as polynomial approximation
simple_gapfill = SimpleGapFiller(gap_value=-100.0)
without_gap_local_poly = \
simple_gapfill.local_poly_approximation(gap_data, 4, 150)
without_gap_batch_poly = \
simple_gapfill.batch_poly_approximation(gap_data, 4, 150)
without_gap_linear = \
simple_gapfill.linear_interpolation(gap_data)
arrays_dict = {
'ridge': without_gap_arr_ridge,
'local_poly': without_gap_local_poly,
'batch_poly': without_gap_batch_poly,
'linear': without_gap_linear
}
return arrays_dict, gap_data, real_data
def run_gapfilling_case(file_path):
"""
The function runs an example of filling in gaps in a time series with
air temperature. Real data case.
:param file_path: path to the file
:return: pandas dataframe with columns 'date','with_gap','ridge',
'composite','temperature'
"""
# Load dataframe
full_path = os.path.join(str(project_root()), file_path)
dataframe = pd.read_csv(full_path)
dataframe['date'] = pd.to_datetime(dataframe['date'])
# Filling in gaps based on inverted ridge regression model
ridge_chain = get_simple_chain()
ridge_gapfiller = ModelGapFiller(gap_value=-100.0, chain=ridge_chain)
with_gap_array = np.array(dataframe['with_gap'])
without_gap_arr_ridge = ridge_gapfiller.forward_inverse_filling(
with_gap_array)
dataframe['ridge'] = without_gap_arr_ridge
# Filling in gaps based on a chain of 5 models
composite_chain = get_composite_chain()
composite_gapfiller = ModelGapFiller(gap_value=-100.0,
chain=composite_chain)
without_gap_composite = composite_gapfiller.forward_filling(with_gap_array)
dataframe['composite'] = without_gap_composite
return dataframe