функция предиката принимает массив формы (n_samples, n_features). Я предполагаю n_features=3
в вашем случае, поэтому:
print('Your prediction for [12,44,0] is', gb_clf.predict([[12,44,0]])
Пример:
from sklearn.datasets import make_hastie_10_2
from sklearn.ensemble import GradientBoostingClassifier
X, y = make_hastie_10_2(random_state=0) # has 10 features
X_train, X_test = X[:2000], X[2000:]
y_train, y_test = y[:2000], y[2000:]
clf = GradientBoostingClassifier(n_estimators=100, learning_rate=1.0, max_depth=1, random_state=0).fit(X_train, y_train)
sample = [list(range(10))] # we provide 10 features for prediction
print('Prediction:', clf.predict(sample))
You can search forward as well. From the bash info manual, "8.2.5 Searching for Commands in the History":
To search backward in the history for a particular string, type
C-r
. TypingC-s
searches forward through the history.
The problem with Ctrl-S however is that sometimes collides with XON/XOFF flow control (in Konsole for instance). The searching is a readline feature however, and you should be able to bind it to some other key. Update: Simpler and better is just to disable XON/XOFF by running
stty -ixon