rov-offline/ad_xgboost_predict.py

import os
import pandas as pd
import xgboost as xgb
from xgboost.sklearn import XGBClassifier


# 1. 模型加载
model = XGBClassifier()
booster = xgb.Booster()
booster.load_model('./data/ad_xgb.model')
model._Booster = booster
# 2. 预测：ad_status = 0, 不出广告
df_0 = pd.read_csv('./data/predict_data/predict_data_0.csv')
columns_0 = df_0.columns.values.tolist()
y_pred_proba_0 = model.predict_proba(df_0[columns_0[2:]])
df_0['y_0'] = y_pred_proba_0

# 3. 预测：ad_status = 1, 不出广告
df_1 = pd.read_csv('./data/predict_data/predict_data_1.csv')
columns_1 = df_1.columns.values.tolist()
y_pred_proba_1 = model.predict_proba(df_1[columns_1[2:]])
df_0['y_1'] = y_pred_proba_1

# 4. merge 结果
res_df = pd.merge(df_0, df_1, how='left', on=['apptype', 'mid', 'videoid'])
print(res_df.head())
res_df['res_predict'] = res_df['y_0'] - res_df['y_1']