RovOpt/rov_train_new.py

import warnings

warnings.filterwarnings("ignore")
import os
import pandas as pd
import gc
import math
import numpy as np
import time
import lightgbm as lgb
from sklearn.model_selection import train_test_split
from sklearn.model_selection import StratifiedKFold
from sklearn.metrics import mean_absolute_percentage_error, r2_score
from sklearn import metrics
import pickle
from sklearn.metrics import mean_squared_error
import seaborn as sns
import matplotlib.pylab as plt
from odps import ODPS
from odps.df import DataFrame as odpsdf
from datetime import datetime as dt
import datetime
import process_feature
import _pickle as cPickle

def getRovfeaturetable(dt, table):
    odps = ODPS('LTAI4FtW5ZzxMvdw35aNkmcp', '0VKnydcaHK3ITjylbgUsLubX6rwiwc', 'usercdm',
                endpoint='http://service.cn.maxcompute.aliyun.com/api', connect_timeout=3000, \
                read_timeout=500000, pool_maxsize=1000, pool_connections=1000)

    featureArray = []
    for record in odps.read_table(table, partition='dt=%s' % dt):
        valueFeature = {}
        for i in process_feature.featurename:
            if i == 'dt':
                valueFeature[i] = dt
            else:
                valueFeature[i] = record[i]
        featureArray.append(valueFeature)
    featureArray = pd.DataFrame(featureArray)
    print(dt, table, 'feature table finish')
    return featureArray

def getdatasample(date, max_range, table):
    new_date = dt.strptime(date, '%Y%m%d')
    datelist = []
    testlist = []
    for i in range(0, max_range):
        delta = datetime.timedelta(days=i)
        tar_dt = new_date - delta
        datelist.append(tar_dt.strftime("%Y%m%d"))
    for tm in datelist:
        testlist.append(getRovfeaturetable(tm, table))
    data = pd.concat(testlist)
    data.reset_index(inplace=True)
    data = data.drop(axis=1, columns='index')
    return data

def clean_data(df):
    y = df['futre7dayreturn']
    df_vids = df['videoid']
    #drop string
    x = df.drop(['videoid', 'videotags', 'videotitle', 'videodescr', 'videodistribute_title', 'videoallwords', 'words_without_tags'])
    #drop future
    x = df.drop(['futr5viewcount', 'futr5returncount', 'futre7dayreturn'])
    return x, y , df_vids

def train(x,y):
    X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.33, random_state=42)
    params = {
        "objective": "regression",
        "metric": "rmse",
        "num_leaves": 30,
        "learning_rate": 0.1,
        "bagging_fraction": 0.7,
        "feature_fraction": 0.7,
        "bagging_frequency": 5,
        "bagging_seed": 2018,
        "verbosity": -1
    }
    lgtrain = lgb.Dataset(X_train, label=y_train)
    lgval = lgb.Dataset(X_test, label=y_test)
    evals_result = {}
    model = lgb.train(params, lgtrain, 10000, valid_sets=[lgval], early_stopping_rounds=100, verbose_eval=20,
                      evals_result=evals_result)

    pred_test_y = model.predict(X_test, num_iteration=model.best_iteration)
    err_mape = mean_absolute_percentage_error(y_test, pred_test_y)
    r2 = r2_score(y_test, pred_test_y)
    print('err_mape', err_mape)
    print('r2', r2)

    return pred_test_y, model, evals_result
    
if __name__ == '__main__':
    with open(r"train_data.pickle", "rb") as input_file:
        train_data = cPickle.load(input_file)    
    with open(r"predict_data.pickle", "rb") as input_file:
        predict_data = cPickle.load(input_file)   

    #train
    x,y,_ = clean_data(train_data)
    train(x, y)