update

output/output_article_distribution_0917.py

+# -*- coding:UTF-8 -*-
+# @Time  : 2020/9/17 16:26
+# @File  : output_article_distribution_0917.py
+# @email : litao@igengmei.com
+# @author : litao
+
+
+# -*- coding:UTF-8 -*-
+# @Time  : 2020/9/11 10:59
+# @File  : portary_article_distribution.py
+# @email : litao@igengmei.com
+# @author : litao
+
+
+import hashlib
+import json
+
+import pymysql
+import xlwt, datetime
+import redis
+from meta_base_code.utils.func_from_redis_get_portrait import user_portrait_scan_info,get_user_portrait_tag3_from_redis
+from meta_base_code.utils.func_from_es_get_article import get_es_article_num,get_user_post_from_mysql
+# from pyhive import hive
+from maintenance.func_send_email_with_file import send_file_email
+from typing import Dict, List
+from elasticsearch_7 import Elasticsearch
+from elasticsearch_7.helpers import scan
+import sys
+import time
+from pyspark import SparkConf
+from pyspark.sql import SparkSession, DataFrame
+
+
+# from pyspark.sql.functions import lit
+# import pytispark.pytispark as pti
+startTime = time.time()
+sparkConf = SparkConf()
+sparkConf.set("spark.sql.crossJoin.enabled", True)
+sparkConf.set("spark.debug.maxToStringFields", "100")
+sparkConf.set("spark.tispark.plan.allow_index_double_read", False)
+sparkConf.set("spark.tispark.plan.allow_index_read", True)
+sparkConf.set("spark.hive.mapred.supports.subdirectories", True)
+sparkConf.set("spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive", True)
+sparkConf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
+sparkConf.set("mapreduce.output.fileoutputformat.compress", False)
+sparkConf.set("mapreduce.map.output.compress", False)
+sparkConf.set("prod.gold.jdbcuri",
+              "jdbc:mysql://172.16.30.136/doris_prod?user=doris&password=o5gbA27hXHHm&rewriteBatchedStatements=true")
+sparkConf.set("prod.mimas.jdbcuri",
+              "jdbc:mysql://172.16.30.138/mimas_prod?user=mimas&password=GJL3UJe1Ck9ggL6aKnZCq4cRvM&rewriteBatchedStatements=true")
+sparkConf.set("prod.gaia.jdbcuri",
+              "jdbc:mysql://172.16.30.143/zhengxing?user=work&password=BJQaT9VzDcuPBqkd&rewriteBatchedStatements=true")
+sparkConf.set("prod.tidb.jdbcuri",
+              "jdbc:mysql://172.16.40.158:4000/eagle?user=st_user&password=aqpuBLYzEV7tML5RPsN1pntUzFy&rewriteBatchedStatements=true")
+sparkConf.set("prod.jerry.jdbcuri",
+              "jdbc:mysql://172.16.40.158:4000/jerry_prod?user=st_user&password=aqpuBLYzEV7tML5RPsN1pntUzFy&rewriteBatchedStatements=true")
+sparkConf.set("prod.tispark.pd.addresses", "172.16.40.158:2379")
+sparkConf.set("prod.tispark.pd.addresses", "172.16.40.170:4000")
+sparkConf.set("prod.tidb.database", "jerry_prod")
+sparkConf.setAppName("test")
+
+spark = (SparkSession.builder.config(conf=sparkConf).config("spark.sql.extensions", "org.apache.spark.sql.TiExtensions")
+         .config("spark.tispark.pd.addresses", "172.16.40.170:2379").enableHiveSupport().getOrCreate())
+
+spark.sql("ADD JAR hdfs:///user/hive/share/lib/udf/brickhouse-0.7.1-SNAPSHOT.jar")
+spark.sql("ADD JAR hdfs:///user/hive/share/lib/udf/hive-udf-1.0-SNAPSHOT.jar")
+spark.sql("CREATE TEMPORARY FUNCTION json_map AS 'brickhouse.udf.json.JsonMapUDF'")
+spark.sql("CREATE TEMPORARY FUNCTION is_json AS 'com.gmei.hive.common.udf.UDFJsonFormatCheck'")
+spark.sql("CREATE TEMPORARY FUNCTION arrayMerge AS 'com.gmei.hive.common.udf.UDFArryMerge'")
+
+task_list = []
+task_days = 2
+
+
+def con_sql(sql):
+    # 从数据库的表里获取数据
+
+    db = pymysql.connect(host='172.16.40.158', port=4000, user='st_user', passwd='aqpuBLYzEV7tML5RPsN1pntUzFy',
+                         db='jerry_prod')
+    cursor = db.cursor()
+    cursor.execute(sql)
+    result = cursor.fetchall()
+    db.close()
+    return result
+
+
+second_demands_zero_dict = {
+    # "answer":{},
+    "tractate":{},
+    # "diary":{},
+}
+project_zero_dict = {
+    # "answer":{},
+    "tractate":{},
+    # "diary":{},
+}
+t = 1
+day_num = 0 - t
+now = (datetime.datetime.now() + datetime.timedelta(days=day_num))
+last_30_day_str = (now + datetime.timedelta(days=-31)).strftime("%Y%m%d")
+today_str = now.strftime("%Y%m%d")
+today_str_format = now.strftime("%Y-%m-%d")
+yesterday_str = (now + datetime.timedelta(days=-1)).strftime("%Y%m%d")
+yesterday_str_format = (now + datetime.timedelta(days=-1)).strftime("%Y-%m-%d")
+one_week_age_str = (now + datetime.timedelta(days=-7)).strftime("%Y%m%d")
+sql = """select first_device from online.ml_user_history_detail where partition_date = {today_str} and last_active_date >= {last_30_day_str}
+""".format(today_str=today_str,last_30_day_str=last_30_day_str)
+print(sql)
+new_urser_device_id_df = spark.sql(sql)
+new_urser_device_id_df.createOrReplaceTempView("device_id_view")
+new_urser_device_id_df.show(1)
+sql_res = new_urser_device_id_df.collect()
+
+bulk_dict = {
+    0: [0, 0, 0],
+    10: [0, 0, 0],
+    50: [0, 0, 0],
+    100: [0, 0, 0],
+    200: [0, 0, 0],
+    500: [0, 0, 0],
+    1000: [0, 0, 0],
+}
+
+
+task_list = []
+second_demands_count_dict,tags_v3_count_dict=get_user_post_from_mysql()
+print(second_demands_count_dict,tags_v3_count_dict)
+time.sleep(10)
+
+user_portrait_scan = user_portrait_scan_info()
+for redis_count,spark_res in enumerate(sql_res):
+    # if redis_count >= 50:break
+    second_demands = []
+    projects = []
+    total_answer_content_num = 0
+    total_tractate_content_num = 0
+    total_diary_content_num = 0
+    res = get_user_portrait_tag3_from_redis(spark_res.device_id)
+    if res.get("second_demands"):
+        second_demands = res.get("second_demands")
+        # print(count_res)
+        for tag in second_demands:
+            if tag in tags_v3_count_dict:
+                total_tractate_content_num += second_demands_count_dict[tag]
+    if res.get("projects"):
+        projects = res.get("projects")
+        # print(count_res)
+        for tag in projects:
+            if tag in tags_v3_count_dict:
+                total_tractate_content_num += tags_v3_count_dict[tag]
+    # print(total_answer_content_num, total_tractate_content_num, total_diary_content_num)
+    tmp_count_num = 0
+
+
+    if 0 <= total_tractate_content_num < 10:
+        bulk_dict[0][1] += 1
+    elif 10 <= total_tractate_content_num < 50:
+        bulk_dict[10][1] += 1
+    elif 50 <= total_tractate_content_num < 100:
+        bulk_dict[50][1] += 1
+    elif 100 <= total_tractate_content_num < 200:
+        bulk_dict[100][1] += 1
+    elif 200 <= total_tractate_content_num < 500:
+        bulk_dict[200][1] += 1
+    elif 500 <= total_tractate_content_num < 1000:
+        bulk_dict[500][1] += 1
+    else:
+        bulk_dict[1000][1] += 1
+
+    if redis_count % 5000 == 0:
+        print(bulk_dict)
+
+
+print(bulk_dict)
+
+
+