Hier ist ein einfaches Skript, das ich erstellt habe, um zu überprüfen, ob ich die Ergebnisse reproduzieren kann.
Ich brauche reg_y_hat dasselbe sein wie self_y_hat.
Was fehlt mir? Wenn ich weiß, welche Stichproben im Zug auf jedes Blatt fallen, kann ich die Vorhersage selbst aggregieren ...
Code: Select all
import numpy as np
import lightgbm as lgb
from sklearn.model_selection import train_test_split
# Generate some random regression data
np.random.seed(42)
X = np.random.rand(100, 5)
y = 4 * X[:, 0] - 2 * X[:, 1] + np.random.rand(100) * 0.1
# Split the data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Train the LGBMRegressor
model = lgb.LGBMRegressor(objective='regression', n_estimators=10, learning_rate=0.1, random_state=42)
model.fit(X_train, y_train)
# Regular predict:
reg_y_hat = model.predict(X_test)
# Get the train leaf values
train_leaf_indices = model.predict(X_train, pred_leaf=True)
leaf_samples = {(i, leaf_id): [] for i in range(model.n_estimators) for leaf_id in np.unique(train_leaf_indices[:, i])}
# Store corresponding target values for each leaf
for i, row in enumerate(train_leaf_indices):
for j, leaf_id in enumerate(row):
leaf_samples[(j, leaf_id)].append(y_train[i])
# Compute avg for each leaf:
leaf_agg = {}
for key, values in leaf_samples.items():
leaf_agg[key] = np.mean(values)
# Predict by aggregating the mean values:
preds = []
test_leaf_indices = model.predict(X_test, pred_leaf=True)
for row_indices in test_leaf_indices:
row_pred = 0.0
for i, leaf_index in enumerate(row_indices):
row_pred += model.learning_rate * leaf_agg[(i, leaf_index)]
preds.append(row_pred)
self_y_hat = np.array(preds)