def test_dataframe_input(self, cat):
"""
Any dataframe should be valid input provided it has the required columns.
"""
data = [[10.1, 10.1, 0, "some_id"]]
cols = ["latitude", "longitude", "elevation", "id"]
df = pd.DataFrame(data, columns=cols)
dist_df = get_distance_df(df, cat)
# make sure output has expected shape and ids
assert len(dist_df) == len(cat) * len(df)
id1 = dist_df.index.get_level_values("id1")
assert "some_id" in set(id1)
def __init__(
self,
catalog: Catalog,
inventory: Inventory,
st_dict: Dict[str, Stream],
motion_type: Union[str, Dict[str, str]] = 'velocity',
phases: Optional[Collection[str]] = None,
):
# check inputs
st_dict, catalog = self._validate_inputs(catalog, inventory, st_dict)
# get a df of all input data, perform sanity checks
self.distance = get_distance_df(catalog, inventory)
df = self._get_meta_df(catalog, inventory, st_dict, phases=phases)
self.data = df
# add sampling rate to stats
sampling_rate = self.data['sampling_rate'].unique()[0]
self._stats = AttribDict(motion_type=motion_type,
sampling_rate=sampling_rate)
def test_cat_cat(self, cat):
""" ensure it works with two catalogs """
df = get_distance_df(cat, cat)
event_ids = {str(x.resource_id) for x in cat}
combinations = set(itertools.permutations(event_ids, 2))
assert combinations == set(df.index)
def distance_df(self, cat, inv):
""" Return a dataframe from all the crandall events and stations. """
return get_distance_df(entity_1=cat, entity_2=inv)