对用户访问session进行分析--模拟生成源数据

package com.chb.shopanalysis;


import java.util.ArrayList;
import java.util.Arrays;
import java.util.Iterator;
import java.util.List;
import java.util.Random;
import java.util.UUID;

import org.apache.spark.SparkConf;
import org.apache.spark.SparkContext;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.sql.DataFrame;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.SQLContext;
import org.apache.spark.sql.hive.HiveContext;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.StructType;
import org.json.JSONObject;

import scala.Tuple2;

import com.chb.shopanalysis.conf.Constants;
import com.chb.shopanalysis.dao.ITaskDAO;
import com.chb.shopanalysis.dao.impl.DAOFactory;
import com.chb.shopanalysis.domain.Task;
import com.chb.shopanalysis.utils.*;


/**
 * 模拟数据程序
 * @author chb
 *
 */
public class MockData {
    public static void main(String[] args) {
        // 构建Spark上下文
        SparkConf conf = new SparkConf()
        .setAppName(Constants.SPARK_APP_NAME_SESSION)
        .setMaster("local");    
        JavaSparkContext sc = new JavaSparkContext(conf);
        SQLContext sqlContext = new HiveContext(sc.sc());

        // 生成模拟测试数据
        mock(sc, sqlContext);


    }


    /**
     * 模拟数据
     * @param sc
     * @param sqlContext
     */
    public static void mock(JavaSparkContext sc, SQLContext sqlContext) {
        List<Row> rows = new ArrayList<Row>();

        String[] searchKeywords = new String[] {"火锅", "蛋糕", "重庆辣子鸡", "重庆小面",
                "呷哺呷哺", "新辣道鱼火锅", "国贸大厦", "太古商场", "日本料理", "温泉"};
        String date = DateUtils.getTodayDate();
        String[] actions = new String[]{"search", "click", "order", "pay"};
        Random random = new Random();

        for(int i = 0; i < 100; i++) {
            long userid = random.nextInt(100);    

            for(int j = 0; j < 10; j++) {
                String sessionid = UUID.randomUUID().toString().replace("-", "");  
                System.out.println(sessionid);
                String baseActionTime = date + " " + random.nextInt(23);

                for(int k = 0; k < random.nextInt(100); k++) {
                    long pageid = random.nextInt(10);    
                    String actionTime = baseActionTime + ":" + StringUtils.fulfuill(String.valueOf(random.nextInt(59))) + ":" + StringUtils.fulfuill(String.valueOf(random.nextInt(59)));
                    String searchKeyword = null;
                    Long clickCategoryId = null;
                    Long clickProductId = null;
                    String orderCategoryIds = null;
                    String orderProductIds = null;
                    String payCategoryIds = null;
                    String payProductIds = null;

                    String action = actions[random.nextInt(4)];
                    if("search".equals(action)) {
                        searchKeyword = searchKeywords[random.nextInt(10)];   
                    } else if("click".equals(action)) {
                        clickCategoryId = Long.valueOf(String.valueOf(random.nextInt(100)));    
                        clickProductId = Long.valueOf(String.valueOf(random.nextInt(100)));  
                    } else if("order".equals(action)) {
                        orderCategoryIds = String.valueOf(random.nextInt(100));  
                        orderProductIds = String.valueOf(random.nextInt(100));
                    } else if("pay".equals(action)) {
                        payCategoryIds = String.valueOf(random.nextInt(100));  
                        payProductIds = String.valueOf(random.nextInt(100));
                    }

                    Row row = RowFactory.create(date, userid, sessionid, 
                            pageid, actionTime, searchKeyword,
                            clickCategoryId, clickProductId,
                            orderCategoryIds, orderProductIds,
                            payCategoryIds, payProductIds);
                    rows.add(row);
                }
            }
        }

        JavaRDD<Row> rowsRDD = sc.parallelize(rows);

        StructType schema = DataTypes.createStructType(Arrays.asList(
                DataTypes.createStructField("start", DataTypes.StringType, true),
                DataTypes.createStructField("user_id", DataTypes.LongType, true),
                DataTypes.createStructField("session_id", DataTypes.StringType, true),
                DataTypes.createStructField("page_id", DataTypes.LongType, true),
                DataTypes.createStructField("action_time", DataTypes.StringType, true),
                DataTypes.createStructField("search_keyword", DataTypes.StringType, true),
                DataTypes.createStructField("click_category_id", DataTypes.LongType, true),
                DataTypes.createStructField("click_product_id", DataTypes.LongType, true),
                DataTypes.createStructField("order_category_ids", DataTypes.StringType, true),
                DataTypes.createStructField("order_product_ids", DataTypes.StringType, true),
                DataTypes.createStructField("pay_category_ids", DataTypes.StringType, true),
                DataTypes.createStructField("pay_product_ids", DataTypes.StringType, true)));

        DataFrame df = sqlContext.createDataFrame(rowsRDD, schema);
        df.show(10);
        df.registerTempTable("user_visit_action_tmp");  
        sqlContext.sql("insert into user_visit_action select * from user_visit_action_tmp");


        /**
         * ==================================================================
         */

        rows.clear();
        String[] sexes = new String[]{"male", "female"};
        for(int i = 0; i < 100; i ++) {
            long userid = i;
            String username = "user" + i;
            String name = "name" + i;
            int age = random.nextInt(60);
            String professional = "professional" + random.nextInt(100);
            String city = "city" + random.nextInt(100);
            String sex = sexes[random.nextInt(2)];

            Row row = RowFactory.create(userid, username, name, age, 
                    professional, city, sex);
            rows.add(row);
        }

        rowsRDD = sc.parallelize(rows);

        StructType schema2 = DataTypes.createStructType(Arrays.asList(
                DataTypes.createStructField("user_id", DataTypes.LongType, true),
                DataTypes.createStructField("username", DataTypes.StringType, true),
                DataTypes.createStructField("nickname", DataTypes.StringType, true),
                DataTypes.createStructField("age", DataTypes.IntegerType, true),
                DataTypes.createStructField("professional", DataTypes.StringType, true),
                DataTypes.createStructField("city", DataTypes.StringType, true),
                DataTypes.createStructField("sex", DataTypes.StringType, true)));

        DataFrame df2 = sqlContext.createDataFrame(rowsRDD, schema2);
        df2.registerTempTable("user_info_tmp");  
        sqlContext.sql("insert into user_info select * from user_info_tmp");

    }
}