Datawhale AI 夏令营 siRNA药物药效预测 task03

1.lgm优化

1.1 低Remaining范围样本高权重

weight_ls = np.array(feats['mRNA_remaining_pct'].apply(lambda x:2 if ((x<=30)and(x>=0)) else 1))

1.2 使用官方评价指标作为损失函数

# calculate_metrics函数用于计算评估指标
def calculate_metrics(preds, data, threshold=30):
    y_pred = preds
    y_true = data.get_label()
    mae = np.mean(np.abs(y_true - y_pred))
    # if mae < 0: mae = 0
    # elif mae >100: mae = 100

    y_true_binary = ((y_true <= threshold) & (y_true >= 0)).astype(int)
    y_pred_binary = ((y_pred <= threshold) & (y_pred >= 0)).astype(int)

    mask = (y_pred >= 0) & (y_pred <= threshold)
    range_mae = (
        mean_absolute_error(y_true[mask], y_pred[mask]) if np.sum(mask) > 0 else 100
    )
    # if range_mae < 0: range_mae = 0
    # elif range_mae >100: range_mae = 100

    # precision = precision_score(y_true_binary, y_pred_binary, average="binary")
    # recall = recall_score(y_true_binary, y_pred_binary, average="binary")

    if np.sum(y_pred_binary) > 0:
        precision = (np.array(y_pred_binary) & y_true_binary).sum()/np.sum(y_pred_binary)
    else:
        precision = 0
    if np.sum(y_true_binary) > 0:
        recall = (np.array(y_pred_binary) & y_true_binary).sum