Commit 39694915 authored by 高雅喆's avatar 高雅喆

update

parent 33fcbb2c
......@@ -16,6 +16,7 @@ import json
import numpy as np
import pandas as pd
from pyspark.sql.functions import lit
from pyspark.sql.functions import *
def compute_henqiang(x):
......@@ -144,12 +145,12 @@ if __name__ == '__main__':
result_rename = result.selectExpr("_1 as cl_id", "_2 as tag_list")
stat_date = datetime.datetime.today().strftime('%Y-%m-%d')
result_last = result_rename.withColumn("stat_date", lit(stat_date))
df = result_last.toPandas()
df = result_last.select("stat_date", "cl_id", concat_ws(',', 'tag_list').alias("tag_list"))
df.show()
# result_last.write.jdbc(
# mode="overwrite",
# url="jdbc:mysql://172.16.40.158:4000/jerry_test?user=root&password=3SYz54LS9#^9sBvC&useSSL=true",
# table="user_portrait_tags",
# properties={"driver": 'com.mysql.jdbc.Driver'})
df.write.jdbc(
mode="overwrite",
url="jdbc:mysql://172.16.40.158:4000/jerry_test?user=root&password=3SYz54LS9#^9sBvC&useSSL=true",
table="user_portrait_tags",
properties={"driver": 'com.mysql.jdbc.Driver'})
except Exception as e:
print(e)
\ No newline at end of file
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment