def test_strava_power_model_auto_compute():
# check that the acceleration and the elevation will be auto-computed
power_auto = strava_power_model(activity, cyclist_weight=70)
activity_ele_acc = activity.copy()
activity_ele_acc = gradient_elevation(activity)
activity_ele_acc = acceleration(activity_ele_acc)
power_ele_acc = strava_power_model(activity_ele_acc, cyclist_weight=70)
assert_series_equal(power_auto, power_ele_acc)
def test_gradient_elevation(activity, append, type_output, shape):
output = gradient_elevation(activity, append=append)
assert isinstance(output, type_output)
assert output.shape == shape
def test_gradient_elevation_error():
activity = pd.DataFrame({'A': np.random.random(1000)})
msg = "elevation and distance data are required"
with pytest.raises(MissingDataError, message=msg):
gradient_elevation(activity)
def test_gradient_elevation(activity, append, type_output, shape):
output = gradient_elevation(activity, append=append)
assert isinstance(output, type_output)
assert output.shape == shape
def test_gradient_elevation_error():
activity = pd.DataFrame({'A': np.random.random(1000)})
msg = "elevation and distance data are required"
with pytest.raises(MissingDataError, message=msg):
gradient_elevation(activity)
if not pd.isnull(activity).any().any():
valid_data.append(activity)
valid_filenames.append(filename)
data = valid_data
###############################################################################
# Data processing
# 1. Compute the acceleration and elevation gradient
# 2. Remove corrupted data (division by zero, etc.)
# 3. Compute the power for each ride using user information
for activity_idx in range(len(data)):
# compute acceleration
data[activity_idx] = acceleration(data[activity_idx])
# compute gradient elevation
data[activity_idx] = gradient_elevation(data[activity_idx])
for activity in data:
activity.replace([np.inf, -np.inf], np.nan, inplace=True)
data_concat = pd.concat(data)
y = data_concat['power']
X = data_concat.drop('power', axis=1)
X.fillna(X.mean(), inplace=True)
groups = []
for group_idx, activity in enumerate(data):
groups += [group_idx] * activity.shape[0]
groups = np.array(groups)
weight_user = {'user_1': 86., 'user_2': 72., 'user_3': 61., 'user_5': 72.}
weight_groups = np.zeros_like(groups)