quantdata.dysanos.grid.rndysanos.local_tail#
Exact adaptive-neighbour diagnostics for conditional option-return tails.
The estimator uses a uniform k-nearest-neighbour kernel. Its weights are
positive, so estimates of positive and negative return parts remain
nonnegative. Training valuation is leave-one-out; validation queries always
use the training split as their reference sample.
- class quantdata.dysanos.grid.rndysanos.local_tail.LocalTailConfig(*, state_mode, neighbors=1024, instrument_candidate_neighbors=8192, tail_ranks=(1, 2, 10, 20, 50), signal_thresholds=(2.0, 3.0), query_batch_size=3584, instrument_batch_size=20, roundoff_multiplier=32.0, state_scale_floor=1e-06)[source]#
Bases:
objectConfiguration for an exact uniform adaptive-neighbour estimator.
- class quantdata.dysanos.grid.rndysanos.local_tail.LocalTailProgress(*, split, processed_states, total_states, states_with_any_long_candidate, states_with_any_short_candidate, long_only_candidate_states, short_only_candidate_states, both_direction_candidate_states)[source]#
Bases:
objectCumulative one-sided-support counts for a valuation in progress.
- quantdata.dysanos.grid.rndysanos.local_tail.local_neighbor_statistics(neighbor_returns, neighbor_roundoff, *, tail_ranks, neighbor_log_weights=None)[source]#
Return positive/negative parts and signed lower-tail order statistics.
Inputs have shape
(queries, neighbours, instruments). Direction zero is the long return and direction one is the negated return.
- quantdata.dysanos.grid.rndysanos.local_tail.normalize_state(state, *, mean, scale)[source]#
Normalize a state array without changing its shape or float32 dtype.
- quantdata.dysanos.grid.rndysanos.local_tail.prepare_delta_hedged_local_data(universe, *, roundoff_multiplier=32.0)[source]#
Return delta-hedged option returns, roundoff bands, and state fields.
- quantdata.dysanos.grid.rndysanos.local_tail.reduced_option_state(data, *, geometry, mode, instrument=0)[source]#
Return
xstateor one option’s(xstate, log-strike, expiry).
Test whether every option produces the same standardized strike metric.
When log strikes differ only by instrument-specific constants, their standardized values are identical. Expiries are constant and therefore have zero distance. In that case one exact neighbour graph is valid for every separately estimated option.
- quantdata.dysanos.grid.rndysanos.local_tail.state_normalization(training_state, *, scale_floor, path_weights=None)[source]#
Return training-only weighted population location and scale.
- quantdata.dysanos.grid.rndysanos.local_tail.valuate_local_tail(*, reference_state, reference_returns, reference_roundoff, reference_log_weights=None, query_state, query_returns, query_roundoff, query_log_weights=None, reference_instrument_feature=None, query_instrument_feature=None, config, split, leave_one_out, leave_one_out_reference_indices=None, progress=None, progress_interval_seconds=30.0)[source]#
Value all query states with an exact adaptive-neighbour box kernel.