from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import pymysql
import smtplib
from email.mime.text import MIMEText
from email.utils import formataddr
from email.mime.multipart import MIMEMultipart
from email.mime.application import MIMEApplication
import redis
import datetime
from pyspark import SparkConf
import time
from pyspark.sql import SparkSession
import json
import numpy as np
import pandas as pd
from pyspark.sql.functions import lit
from pyspark.sql.functions import concat_ws
def send_email(app,id,e):
# 第三方 SMTP 服务
mail_host = 'smtp.exmail.qq.com' # 设置服务器
mail_user = "zhaowei@igengmei.com" # 用户名
mail_pass = "Gengmei1234" # 口令
sender = 'zhaowei@igengmei.com'
receivers = ['zhaowei@igengmei.com'] # 接收邮件，可设置为你的QQ邮箱或者其他邮箱
e = str(e)
msg = MIMEMultipart()
part = MIMEText('app_id:'+id+':fail', 'plain', 'utf-8')
msg.attach(part)
msg['From'] = formataddr(["gaoyazhe", sender])
# 括号里的对应收件人邮箱昵称、收件人邮箱账号
msg['To'] = ";".join(receivers)
# message['Cc'] = ";".join(cc_reciver)
msg['Subject'] = 'spark streaming:app_name:'+app
try:
with open('error.txt','w') as f:
f.write(e)
f.close()
part = MIMEApplication(open('error.txt', 'r').read())
part.add_header('Content-Disposition', 'attachment', filename="error.txt")
msg.attach(part)
except Exception as e:
print(e)
try:
smtpObj = smtplib.SMTP_SSL(mail_host, 465)
smtpObj.login(mail_user, mail_pass)
smtpObj.sendmail(sender, receivers, msg.as_string())
except smtplib.SMTPException:
print('error')
def get_data_by_mysql(host, port, user, passwd, db, sql):
try:
db = pymysql.connect(host=host, port=port, user=user, passwd=passwd, db=db, cursorclass=pymysql.cursors.DictCursor)
cursor = db.cursor()
cursor.execute(sql)
results = cursor.fetchall()
db.close()
return results
except Exception as e:
print(e)
def get_all_search_word_and_synonym_tags():
"""
:return:dict {"search_word1":[tag_list1],"search_word2":[tag_list2]...}
"""
try:
sql = "select a.keyword , c.id from api_wordrel a " \
"left join api_wordrelsynonym b on a.id = b.wordrel_id " \
"left join api_tag c on b.word=c.name " \
"where a.category in (1,13,10,11,12) and c.tag_type+0<'4'+0 and c.is_online=1"
mysql_results = get_data_by_mysql('172.16.30.141', 3306, 'work', 'BJQaT9VzDcuPBqkd', 'zhengxing', sql)
result_dict = dict()
for data in mysql_results:
if data['keyword'] not in result_dict:
result_dict[data['keyword']] = [data['id']]
else:
result_dict[data['keyword']].append(data['id'])
return result_dict
except Exception as e:
print(e)
def get_all_synonym_tags():
"""
:return:dict {"search_word1":[tag_list1],"search_word2":[tag_list2]...}
"""
try:
sql = "select a.word, b.id from api_wordrelsynonym a left join api_tag b " \
"on a.word=b.name where b.tag_type+0<'4'+0 and b.is_online=1"
mysql_results = get_data_by_mysql('172.16.30.141', 3306, 'work', 'BJQaT9VzDcuPBqkd', 'zhengxing', sql)
result_dict = dict()
for data in mysql_results:
if data['word'] not in result_dict:
result_dict[data['word']] = [data['id']]
else:
result_dict[data['word']].append(data['id'])
return result_dict
except Exception as e:
print(e)
def get_all_word_tags():
try:
search_word_and_synonym_tags = get_all_search_word_and_synonym_tags()
synonym_tags = get_all_synonym_tags()
if search_word_and_synonym_tags and synonym_tags:
return {**synonym_tags, **search_word_and_synonym_tags}
except Exception as e:
print(e)
def compute_henqiang(x):
score = 15-x*((15-0.5)/180)
if score>0.5:
return score
else:
return 0.5
def compute_jiaoqiang(x):
score = 12-x*(12/180)
if score>0.5:
return score
else:
return 0.5
def compute_ruoyixiang(x):
score = 5-x*((5-0.5)/180)
if score>0.5:
return score
else:
return 0.5
def compute_validate(x):
score = 10-x*((10-0.5)/180)
if score>0.5:
return score
else:
return 0.5
def compute_ai_scan(x):
score = 2 - x * ((2 - 0.5) / 180)
if score>0.5:
return score
else:
return 0.5
def get_user_tag_score(cl_id, all_word_tags, size=10):
try:
db_jerry_test = pymysql.connect(host='172.16.40.170', port=4000, user='st_user', passwd='aqpuBLYzEV7tML5RPsN1pntUzFy',
db='jerry_test', charset='utf8')
cur_jerry_test = db_jerry_test.cursor()
# 用户的非搜索行为
user_df_service_sql = "select time,cl_id,score_type,tag_id,tag_referrer,action from user_new_tag_log " \
"where cl_id ='{}' and action != 'do_search' ".format(cl_id)
cur_jerry_test.execute(user_df_service_sql)
data = list(cur_jerry_test.fetchall())
if data:
user_log_df = pd.DataFrame(data)
user_log_df.columns = ["time", "cl_id", "score_type", "tag_id", "tag_referrer", "action"]
else:
user_log_df = pd.DataFrame(columns=["time", "cl_id", "score_type", "tag_id", "tag_referrer", "action"])
# 用户的搜索行为
user_df_search_sql = "select time,cl_id,score_type,tag_id,tag_referrer,action from user_new_tag_log " \
"where cl_id ='{}' and action = 'do_search'".format(cl_id)
cur_jerry_test.execute(user_df_search_sql)
data_search = list(cur_jerry_test.fetchall())
if data_search:
user_df_search = pd.DataFrame(data_search)
user_df_search.columns = ["time", "cl_id", "score_type", "tag_id", "tag_referrer", "action"]
else:
user_df_search = pd.DataFrame(columns=["time", "cl_id", "score_type", "tag_id", "tag_referrer", "action"])
# 搜索词转成tag
for index, row in user_df_search.iterrows():
if row['tag_referrer'] in all_word_tags:
for search_tag in all_word_tags[row['tag_referrer']]:
row['tag_id'] = int(search_tag)
user_log_df = user_log_df.append(row, ignore_index=True)
break
if not user_log_df.empty:
user_log_df["days_diff_now"] = round((int(time.time())-user_log_df["time"]) / (24*60*60))
user_log_df["score"] = user_log_df.apply(
lambda x: compute_henqiang(x.days_diff_now) if x.score_type == "henqiang" else (
compute_jiaoqiang(x.days_diff_now) if x.score_type == "jiaoqiang" else (
compute_ai_scan(x.days_diff_now) if x.score_type == "ai_scan" else (
compute_ruoyixiang(x.days_diff_now) if x.score_type == "ruoyixiang" else compute_validate(x.days_diff_now)))), axis=1)
finally_score = user_log_df.sort_values(by=["score","time"],ascending=False)
finally_score.drop_duplicates(subset="tag_id", inplace=True)
finally_score["weight"] = finally_score['score'] / finally_score['score'].sum()
finally_score["pay_type"] = finally_score.apply(
lambda x: 3 if x.action == "api/order/validate" else (
2 if x.action == "api/settlement/alipay_callback" else 1
), axis=1
)
score_result = finally_score[["tag_id", "cl_id", "score", "weight", "pay_type"]]
score_result.rename(columns={"cl_id": "device_id"}, inplace=True)
# 写tidb
delete_sql = "delete from api_market_personas where device_id='{}'".format(cl_id)
cur_jerry_test.execute(delete_sql)
db_jerry_test.commit()
for index, row in score_result.iterrows():
insert_sql = "insert into api_market_personas values (null, {}, '{}', {}, {}, {})".format(
row['tag_id'], row['device_id'], row['score'], row['weight'], row['pay_type'])
cur_jerry_test.execute(insert_sql)
db_jerry_test.commit()
db_jerry_test.close()
return "sucess"
else:
return "user log is empty"
except Exception as e:
return 'pass'
if __name__ == '__main__':
try:
db_jerry_test = pymysql.connect(host='172.16.40.170', port=4000, user='st_user', passwd='aqpuBLYzEV7tML5RPsN1pntUzFy',
db='jerry_test', charset='utf8')
cur_jerry_test = db_jerry_test.cursor()
# 获取最近30天内的用户设备id
sql_device_ids = "select distinct cl_id from user_new_tag_log " \
"where time > UNIX_TIMESTAMP(DATE_SUB(NOW(), INTERVAL 30 day))"
cur_jerry_test.execute(sql_device_ids)
device_ids_lst = [i[0] for i in cur_jerry_test.fetchall()]
db_jerry_test.close()
#搜索词及其同义词匹配tag
all_word_tags = get_all_word_tags()
# rdd
sparkConf = SparkConf().set("spark.hive.mapred.supports.subdirectories", "true") \
.set("spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive", "true") \
.set("spark.tispark.plan.allow_index_double_read", "false") \
.set("spark.tispark.plan.allow_index_read", "true") \
.set("spark.sql.extensions", "org.apache.spark.sql.TiExtensions") \
.set("spark.tispark.pd.addresses", "172.16.40.170:2379").set("spark.io.compression.codec", "lzf") \
.set("spark.driver.maxResultSize", "8g").set("spark.sql.avro.compression.codec", "snappy")
spark = SparkSession.builder.config(conf=sparkConf).enableHiveSupport().getOrCreate()
spark.sparkContext.setLogLevel("WARN")
device_ids_lst_rdd = spark.sparkContext.parallelize(device_ids_lst)
result = device_ids_lst_rdd.repartition(100).map(lambda x: get_user_tag_score(x, all_word_tags))
result.collect()
except Exception as e:
send_email("dist_update_portrait_market", "dist_update_portrait_market", "dist_update_portrait_market")