GBDT分类

#now let's get started
n_times = 20
learning_rate=0.1
log_of_odds=np.zeros([n_times+1,n_samples])

residuals = np.zeros([n_times+1,n_samples])
loss = [0] * (n_times+1)
prediction = np.zeros([n_times+1,n_samples])
score = np.zeros([n_times+1])
#calculation
log_of_odds[0] = [log_of_odds0] * n_samples
prediction[0] = [probability0] * n_samples
score[0]=np.sum((prediction[0]>0.5)*1.0==y) / n_samples
residuals[0] = y - prediction[0]
loss[0] = loss0.sum()
trees = []
gamma_value = np.zeros([n_times+1,8])
gamma = np.zeros([n_times+1,n_samples])

for i in range(n_times):
    dt = DecisionTreeRegressor(max_depth=2)
    dt=dt.fit(X, residuals[i])
    tree = dt.tree_
    trees.append(tree)
    leaf_indeces=dt.apply(X)
    unique_leafs=np.unique(leaf_indeces)
    n_leaf=len(unique_leafs)
    #for leaf 1
    for ileaf in range(n_leaf):
        leaf_index=unique_leafs[ileaf]
        n_leaf=len(leaf_indeces[leaf_indeces==leaf_index])
        previous_probability = prediction[i][leaf_indeces==leaf_index]
        denominator = np.sum(previous_probability * (1-previous_probability))
        igamma = tree.value[ileaf+1][0][0] * n_leaf / denominator
        gamma_value[i][ileaf]=igamma

    gamma[i] = [gamma_value[i][np.where(unique_leafs==index)] for index in leaf_indeces]
    # next 
    log_of_odds[i+1] = log_of_odds[i] + learning_rate * gamma[i]

    prediction[i+1] = np.array([np.exp(odds)/(np.exp(odds)+1) for odds in log_of_odds[i+1]])
    score[i+1]=np.sum((prediction[i+1]>0.5)*1.0==y) / n_samples
    residuals[i+1] = y - prediction[i+1]
    loss[i+1]=np.sum(-y * log_of_odds[i+1] + np.log(1+np.exp(log_of_odds[i+1])))