模型训练xgb

1. model pipeline 拆解

# -*- coding: utf-8 -*-
import pandas as pd
import xgboost as xgb
from sklearn.model_selection import train_test_split
from sklearn import metrics

feature_list = ["chat_7d_cnt", "chat_cnt_self_expression"]
drop_cols = ["uid", "random", "2d_retention"]
LABEL = "is_later_30d_loss"
model_file_path = "model.txt"
data_path = "data.txt"

params = {
    'booster': 'gbtree',
    'objective': 'binary:logistic',
    'eval_metric': 'auc',
    'max_depth': 10,
    'lambda': 10,
    'subsample': 0.85,
    'colsample_bytree': 0.85,
    'min_child_weight': 2,
    'eta': 0.1,
    'seed': 0,
    'nthread': 8,
    'silent': 1
}


if __name__ == "__main__":
    X_train, X_test, y_train, y_test = get_dataset(data_pa