# -*- coding: utf-8 -*-
"""
Created on Mon Nov 28 13:22:08 2016
@author: yy
"""
## part1: 模型訓練
import pandas as pd
import numpy as np
import os
from datetime import datetime
import xgboost as xgb
traindata=pd.read_csv("/home/op1/yy/traindata.csv")
traindata["add_date"]= pd.to_datetime(traindata["orderdate"]) #轉化為日期格式
#時間過濾
traindata_a=traindata[(traindata["add_date"]<'2016-10-31')] #訓練集
testdata_a=traindata[(traindata["add_date"]>='2016-10-31') & (traindata["add_date"]<='2016-11-06') & (traindata["rank1"]<=500)] #預測集
#特徵列表
colnames=[
#'masterhotel'
'order_cii_notcancelcii'
,'city'
,'order_cii_ahead_1day'
,'order_cii_ahead_3days_avg'
,'order_cii_ahead_7days_avg'
,'order_cii_30days_avg'
,'order_cii_ahead_sameoneweek'
,'order_cii_ahead_sametwoweeks_avg'
,'star'
,'goldstar'
,'level'
,'ratingservice'
,'novoters'
,'week_day'
,'working_day'
,'cii_ahead_sameoneweek'
,'cii_ahead_sametwoweeks_avg'
,'cii_ahead_samethreeweeks_avg'
,'cii_ahead_samefourweeks_avg'
,'simple_estimate_constant'
,'cii_ahead_1day_avg'
,'cii_ahead_3days_avg'
,'cii_ahead_7days_avg'
,'order_ahead_lt_1days'
,'order_ahead_lt_2days'
,'order_ahead_lt_3days'
,'order_ahead_lt_7days'
,'order_ahead_lt_14days'
,'order_alldays'
,'click_ahead_1day'
,'click_ahead_2days'
,'click_ahead_3days'
,'click_ahead_7days'
,'click_ahead_14days'
,'browse_0day_uv'
,'browse_1day_uv'
,'browse_2day_uv'
,'browse_3day_uv'
,'browse_4day_uv'
,'browse_5day_uv'
,'browse_6day_uv'
,'browse_7_14day_uv'
,'browse_14daymore_uv'
,'order_cii_14days_avg'
,'order_cii_21days_avg'
,'order_cii_ahead_samethreeweeks_avg'
,'order_cii_ahead_samefourweeks_avg']
#dtrain = xgb.DMatrix( data, label=label)
#dtrain = xgb.DMatrix(data, label=label)
#訓練集構建
label=traindata_a[colnames[0]]
dtrain = xgb.DMatrix(traindata_a[colnames[1:]], label=traindata_a[colnames[0]])
num_round=800
params = {}
params["objective"] = "reg:linear"
params["eta"] = 0.1
params["max_depth"] = 4
params["eval_metric"] = "rmse"
params["silent"] = 0
plst = list(params.items()) #Using 5000 rows for early stopping.
bst = xgb.train( plst, dtrain, num_round)
#預測集構建
dtest=xgb.DMatrix(testdata_a[colnames[1:]])
#結果預測
y_bar=bst.predict(dtest)
#y.shape
## 評價指標
#testdata_a[colnames[0,]]
#testdata_a.columns
actual_values=testdata_a[["masterhotel","add_date","order_cii_notcancelcii","rank1"]]
actual_values["y_bar"]=y_bar
actual_values["mae"]=abs(actual_values["y_bar"]-actual_values["order_cii_notcancelcii"])
top100=actual_values[actual_values["rank1"]<=100]
mae100=top100.groupby("add_date").mean()
mae500=actual_values.groupby("add_date").mean()
## part2: 儲存模型，方便後續直接呼叫
bst.save_model('xgb.model') # 用於儲存訓練出的模型
#模型初始化
bst=xgb.Booster() #注意：名字要保持一致，否則報錯！
bst.load_model('/home/op1/yuanmin/xgb.model')
y_bar=bst.predict(dtest)
## 引數重要性
pd.Series(bst.get_fscore()).sort_values(ascending=False)
pd.Series(bst.get_fscore()).sort_values(ascending=False)/sum(pd.Series(bst.get_fscore()).sort_values(ascending=False)) #重要性歸一化
---------------------
作者：山谷來客
來源：CSDN
原文：blog.csdn.net/u010035907/…
版權宣告：本文為博主原創文章，轉載請附上博文連結！
更多學習資料可關注：gzitcast