MLLib

Library "MLLib"
Machine Learning Library - Adaptive learning algorithms for parameter optimization

f_kirschenbaum_sgd(feature_z, baseline_ma, baseline_dev, pivot_high, pivot_low, sensitivity_current, learning_rate, sensitivity_min, sensitivity_max, coupling_strength, coupling_gate, pivot_lookback, proximity_pct, survival_prob)
Pivot-based SGD for adaptive sensitivity tuning (Kirschenbaum method)
Parameters:
feature_z (float): Z-score of the predictive feature (e.g., basket vector)
baseline_ma (float): Baseline moving average (center line)
baseline_dev (float): Standard deviation for band calculation
pivot_high (float): Recent pivot high price (na if none)
pivot_low (float): Recent pivot low price (na if none)
sensitivity_current (float): Current sensitivity parameter value
learning_rate (float): Learning rate for SGD updates
sensitivity_min (float): Minimum allowed sensitivity value
sensitivity_max (float): Maximum allowed sensitivity value
coupling_strength (float): Coupling strength for gating updates (0-1)
coupling_gate (float): Minimum coupling threshold for updates
pivot_lookback (int): Lookback period to historical feature/price at pivot
proximity_pct (float): Proximity threshold (0-1) for pivot to be "near band"
survival_prob (float): Survival probability for band calculation (e.g., 0.68 for 1-sigma)
Returns: [new_sensitivity, update_count] Updated sensitivity and number of updates performed

f_sgd_update(param_current, gradient, learning_rate, param_min, param_max, gate_strength, gate_threshold)
Generic SGD parameter update with optional gating
Parameters:
param_current (float): Current parameter value
gradient (float): Gradient (error * feature)
learning_rate (float): Learning rate
param_min (float): Minimum parameter value
param_max (float): Maximum parameter value
gate_strength (float): Gating strength (0-1, optional)
gate_threshold (float): Minimum gate strength to allow full update
Returns: float Updated parameter value

SGDState
SGD learning state for tracking parameter updates
Fields:
param (series float): Current parameter value
updates (series int): Number of updates performed
last_error (series float): Last prediction error

Notes de version

v2

Added:
foutcomelabelstep(bars_elapsed, close_at_signal, atr_at_signal, amp_thresh, k_min, k_max, close_now)
Parameters:
bars_elapsed (int)
close_at_signal (float)
atr_at_signal (float)
amp_thresh (float)
k_min (int)
k_max (int)
close_now (float)

ftrainingbuffernew()

ftrainingbufferpush(tb, v1, v2, v3, v4, v5, v6, v7, pk, amp, hor, bar_i, dir)
Parameters:
tb (TrainingBuffer)
v1 (float)
v2 (float)
v3 (float)
v4 (float)
v5 (float)
v6 (float)
v7 (float)
pk (int)
amp (float)
hor (int)
bar_i (int)
dir (int)

ftrainingbuffercap(tb, max_size)
Parameters:
tb (TrainingBuffer)
max_size (int)

fpendingqueuenew()

fpendingqueuepush(pq, b, c, a, dir, f1, f2, f3, f4, f5, f6, f7, pk)
Parameters:
pq (PendingQueue)
b (int)
c (float)
a (float)
dir (int)
f1 (float)
f2 (float)
f3 (float)
f4 (float)
f5 (float)
f6 (float)
f7 (float)
pk (int)

fpendingqueuepopfront(pq)
Parameters:
pq (PendingQueue)

OutcomeLabel
Fields:
amplitude (series float)
horizon (series int)
ready (series bool)

TrainingBuffer
Fields:
f1 (array<float>)
f2 (array<float>)
f3 (array<float>)
f4 (array<float>)
f5 (array<float>)
f6 (array<float>)
f7 (array<float>)
packed (array<int>)
amplitude (array<float>)
horizon (array<int>)
bar_idx (array<int>)
direction (array<int>)

PendingQueue
Fields:
bar_idx (array<int>)
close_at (array<float>)
atr_at (array<float>)
direction (array<int>)
snap_f1 (array<float>)
snap_f2 (array<float>)
snap_f3 (array<float>)
snap_f4 (array<float>)
snap_f5 (array<float>)
snap_f6 (array<float>)
snap_f7 (array<float>)
snap_packed (array<int>)

Notes de version

v3

Added:
fpendingqueuepushtyped(pq, bar_idx, c0, atr0, dir_, f1, f2, f3, f4, f5, f6, f7, packed, stype)
Parameters:
pq (PendingQueue)
bar_idx (int)
c0 (float)
atr0 (float)
dir_ (int)
f1 (float)
f2 (float)
f3 (float)
f4 (float)
f5 (float)
f6 (float)
f7 (float)
packed (int)
stype (int)

ftrainingbufferpushtyped(tb, f1, f2, f3, f4, f5, f6, f7, packed, amp, hor, bar_idx, dir_, stype)
Parameters:
tb (TrainingBuffer)
f1 (float)
f2 (float)
f3 (float)
f4 (float)
f5 (float)
f6 (float)
f7 (float)
packed (int)
amp (float)
hor (int)
bar_idx (int)
dir_ (int)
stype (int)

Notes de version

v4

Added:
ftrainingbuffernew_atomic()

ftrainingbufferpush_atomic(tb, v1, v2, v3, v4, v5, v6, v7, pk, amp, hor, bar_i, dir, stype, f8)
Parameters:
tb (array<TBSample>)
v1 (float)
v2 (float)
v3 (float)
v4 (float)
v5 (float)
v6 (float)
v7 (float)
pk (int)
amp (float)
hor (int)
bar_i (int)
dir (int)
stype (int)
f8 (float)

ftrainingbuffercap_atomic(tb, max_size)
Parameters:
tb (array<TBSample>)
max_size (int)

fpendingqueuenew_atomic()

fpendingqueuepush_atomic(pq, b, c, a, dir, f1, f2, f3, f4, f5, f6, f7, pk, stype, f8)
Parameters:
pq (array<PQSample>)
b (int)
c (float)
a (float)
dir (int)
f1 (float)
f2 (float)
f3 (float)
f4 (float)
f5 (float)
f6 (float)
f7 (float)
pk (int)
stype (int)
f8 (float)

fpendingqueuepopfront_atomic(pq)
Parameters:
pq (array<PQSample>)

TBSample
Fields:
f1 (series float)
f2 (series float)
f3 (series float)
f4 (series float)
f5 (series float)
f6 (series float)
f7 (series float)
packed (series int)
amplitude (series float)
horizon (series int)
bar_idx (series int)
direction (series int)
sample_type (series int)
f8_val (series float)

PQSample
Fields:
bar_idx (series int)
close_at (series float)
atr_at (series float)
direction (series int)
snap_f1 (series float)
snap_f2 (series float)
snap_f3 (series float)
snap_f4 (series float)
snap_f5 (series float)
snap_f6 (series float)
snap_f7 (series float)
snap_packed (series int)
sample_type (series int)
f8_val (series float)

Notes de version

v6

Updated:
ftrainingbuffercap_atomic(tb)
Parameters:
tb (array<TBSample>)

Bibliothèque Pine

Dans l'esprit TradingView, l'auteur a publié ce code Pine sous forme de bibliothèque open source afin que d'autres programmeurs Pine de notre communauté puissent le réutiliser. Bravo à l'auteur! Vous pouvez utiliser cette bibliothèque à titre privé ou dans d'autres publications open source, mais la réutilisation de ce code dans des publications est régie par nos Règles.

cybermediaboy

Clause de non-responsabilité

Les informations et publications ne sont pas destinées à être, et ne constituent pas, des conseils ou recommandations financiers, d'investissement, de trading ou autres fournis ou approuvés par TradingView. Pour en savoir plus, consultez les Conditions d'utilisation.

Bibliothèque Pine

cybermediaboy