import os
import re
import sys
import time
os.environ["PYARROW_IGNORE_TIMEZONE"] = "1"
sys.path.append(os.path.dirname(sys.path[0])) # 上级目录
from pyspark.storagelevel import StorageLevel
from utils.templates import Templates
# from ..utils.templates import Templates
from pyspark.sql.types import StringType, IntegerType
# 分组排序的udf窗口函数
from pyspark.sql.window import Window
from pyspark.sql import functions as F
class DimAsinTitleInfo(Templates):
def __init__(self, site_name='us', date_type="month", date_info='2022-1'):
super().__init__()
self.site_name = site_name
self.date_type = date_type
self.date_info = date_info
self.db_save_vertical = f'dim_asin_title_info_vertical'
self.db_save_wide = f'dim_asin_title_info_wide'
self.spark = self.create_spark_object(app_name=f"{self.db_save_vertical}: {self.site_name}, {self.date_type}, {self.date_info}")
self.df_theme = self.spark.sql(f"select 1+1;")
self.df_asin_title = self.spark.sql(f"select 1+1;")
self.df_save_vertical = self.spark.sql(f"select 1+1;") # 竖表
self.df_save_wide = self.spark.sql(f"select 1+1;") # 宽表
# 注册自定义函数 (UDF)
self.u_theme_pattern = F.udf(self.udf_theme_pattern, StringType())
# 其他变量
self.pattern = str() # 正则匹配
# 分区参数
self.partitions_by = ['site_name']
self.partitions_num = 100
@staticmethod
def udf_theme_pattern(title, pattern):
results_list = re.findall(pattern, title) # , re.IGNORECASE,
if results_list:
unique_first_values = set() # 集合 -- 自带去重功能
for item in results_list:
theme = item[0].strip() # 去掉匹配的两头空格
unique_first_values.add(theme)
return ','.join(unique_first_values)
else:
return None
def read_data(self):
sql = f"select id, theme_type_en, theme_en, theme_en_lower, theme_ch from ods_theme where site_name='{self.site_name}'"
print("sql:", sql)
self.df_theme = self.spark.sql(sql).cache()
self.df_theme.show(10, truncate=False)
# sql = f"-- select asin, title as asin_volume, date_info from ods_asin_detail where site_name='{self.site_name}' and date_type='week'" # and date_info>='2023-15'
sql = f"select asin, title as asin_title, date_info, site_name from ods_asin_detail where site_name='{self.site_name}' and date_type='week' and date_info>='2023-25'" # and date_info>='2023-15'
print("sql:", sql)
self.df_asin_title = self.spark.sql(sqlQuery=sql).cache()
self.df_asin_title.show(10, truncate=False)
def handle_data(self):
self.handle_filter_dirty_data()
self.handle_theme()
def handle_filter_dirty_data(self):
"""
过滤脏数据+保留最新的title
"""
# 小写
self.df_asin_title = self.df_asin_title.withColumn("asin_title_lower", F.lower(self.df_asin_title["asin_title"]))
# 过滤空值
self.df_asin_title = self.df_asin_title.filter("asin_title_lower is not null")
# 过滤null和none字符串
self.df_asin_title = self.df_asin_title.filter("asin_title_lower not in ('none', 'null', 'nan')")
# 取最新的date_info对应的title
window = Window.partitionBy('asin').orderBy(F.desc('date_info')) # 按照 date_info 列进行分区，并按照 date 列进行排序
self.df_asin_title = self.df_asin_title.withColumn('row_number', F.row_number().over(window)) # 使用窗口函数为每个分区的行编号
self.df_asin_title = self.df_asin_title.filter(self.df_asin_title.row_number == 1).drop('row_number') # 只保留每个分区中 row_number 最大的行，并删除 row_number 列
def handle_theme(self):
pdf_theme = self.df_theme.toPandas()
pattern_list = list(set(pdf_theme.theme_en_lower))
# pattern_list = [f' {pattern} ' for pattern in pattern_list if pattern] # 去掉空字符串 -- 优化匹配
pattern_list = [re.escape(f' {pattern} ') for pattern in pattern_list if pattern] # 去掉空字符串 -- 优化匹配
pattern_list.sort(key=len, reverse=True) # 根据长度进行排序
pattern_str = '|'.join(pattern_list) # | 或匹配
# pattern_str = re.escape(pattern_str)
self.pattern = '(?=(' + pattern_str + '))' # 正则匹配模式
# self.pattern = re.escape(self.pattern)
print("self.pattern:", self.pattern)
df_asin_title = self.df_asin_title.cache() # 后面用作匹配asin_title
self.df_asin_title = self.df_asin_title.withColumn("asin_title_lower", F.concat(F.lit(" "), "asin_title_lower", F.lit(" "))) # 标题两头加空字符串用来匹配整个词
self.df_asin_title = self.df_asin_title.withColumn("theme_en_lower", self.u_theme_pattern('asin_title_lower', F.lit(self.pattern)))
# 将列拆分为数组多列
self.df_asin_title = self.df_asin_title.withColumn("theme_en_lower", F.split(self.df_asin_title["theme_en_lower"], ","))
# 将数组合并到多行
self.df_asin_title = self.df_asin_title.withColumn("theme_en_lower", F.explode(self.df_asin_title["theme_en_lower"]))
# self.df_asin_title.show(100, truncate=False)
# self.df_asin_title.filter("asin='0060574437'").show(100, truncate=False)
# self.df_asin_title.filter('theme_en_lower is null').show(20, truncate=False) # 没有记录
self.df_asin_title = self.df_asin_title.join(
self.df_theme, on=['theme_en_lower'], how='left' # 改成inner, 这样避免正则匹配结果不准
)
self.df_save_vertical = self.df_asin_title
self.df_save_vertical.show(30, truncate=False)
self.df_asin_title = self.df_asin_title.drop_duplicates(['asin', 'theme_type_en', 'theme_ch'])
# self.df_asin_title.filter('theme_en_lower is null').show(20, truncate=False) # 没有记录
# self.df_save.show(30, truncate=False)
self.df_asin_title = self.df_asin_title.withColumn("theme_type_en_counts", F.concat("theme_type_en", F.lit("_counts")))
self.df_asin_title = self.df_asin_title.withColumn("theme_type_en_ids", F.concat("theme_type_en", F.lit("_ids")))
# self.df_asin_title.filter('theme_type_en_counts is null').show(20, truncate=False) # 没有记录
self.df_asin_title = self.df_asin_title.filter('theme_type_en_counts is not null')
pivot_df1 = self.df_asin_title.groupBy("asin").pivot("theme_type_en_counts").agg(F.expr("IFNULL(count(*), 0) AS value"))
pivot_df1 = pivot_df1.na.fill(0)
pivot_df2 = self.df_asin_title.groupBy("asin").pivot("theme_type_en_ids").agg(F.concat_ws(",", F.collect_list("id")))
pivot_df1.show(30, truncate=False)
# pivot_df2.show(30, truncate=False)
self.df_save_wide = df_asin_title.join(
pivot_df1, on='asin', how='left'
).join(
pivot_df2, on='asin', how='left'
)
# self.df_save_wide.show(30, truncate=False)
print(self.df_save_wide.columns)
def save_data(self):
self.reset_partitions(partitions_num=50)
self.save_data_common(
df_save=self.df_save_vertical,
db_save=self.db_save_vertical,
partitions_num=self.partitions_num,
partitions_by=self.partitions_by
)
self.reset_partitions(partitions_num=100)
self.save_data_common(
df_save=self.df_save_wide,
db_save=self.db_save_wide,
partitions_num=self.partitions_num,
partitions_by=self.partitions_by
)
if __name__ == '__main__':
site_name = sys.argv[1] # 参数1：站点
date_type = sys.argv[2] # 参数2：类型：day/week/4_week/month/quarter
date_info = sys.argv[3] # 参数3：年-月-日/年-周/年-月/年-季, 比如: 2022-1
handle_obj = DimAsinTitleInfo(site_name=site_name, date_type=date_type, date_info=date_info)
handle_obj.run()