Skip to content

A
Amazon-Selection-Data
Commit 14af7a9b by wangjing
Options

no message

parent ba46b2f2
Showing with 16 additions and 16 deletions
Pyspark_job/dim/dim_st_detail_week.py
......@@ -105,7 +105,7 @@ class DwtStDetailWeek(object):
)
self.df_st_detail_last_week.cache()
print("1周前数据如下：")
self.df_st_detail_last_week.show(10, True)
# self.df_st_detail_last_week.show(10, True)
self.df_st_detail_last_4_week = self.df_st_detail.filter(f"date_info > '{self.date_info_4_week_ago}'")
for col in self.cols:
......@@ -114,7 +114,7 @@ class DwtStDetailWeek(object):
)
self.df_st_detail_last_4_week.cache()
print("近4周数据如下：")
self.df_st_detail_last_4_week.show(10, True)
# self.df_st_detail_last_4_week.show(10, True)
self.df_st_detail_4_week_ago = self.df_st_detail.filter(f"date_info = '{self.date_info_4_week_ago}'")
for col in self.cols:
......@@ -123,7 +123,7 @@ class DwtStDetailWeek(object):
)
self.df_st_detail_4_week_ago.cache()
print("4周前数据如下：")
self.df_st_detail_4_week_ago.show(10, True)
# self.df_st_detail_4_week_ago.show(10, True)
self.df_st_detail_12_week_ago = self.df_st_detail.filter(f"date_info = '{self.date_info_12_week_ago}'")
for col in self.cols:
......@@ -132,11 +132,11 @@ class DwtStDetailWeek(object):
)
self.df_st_detail_12_week_ago.cache()
print("12周前数据如下：")
self.df_st_detail_12_week_ago.show(10, True)
# self.df_st_detail_12_week_ago.show(10, True)
self.df_st_detail = self.df_st_detail.filter(f"date_info = '{self.date_info}'").cache()
print("本周数据如下：")
self.df_st_detail.show(10, True)
# self.df_st_detail.show(10, True)
sql = f"""
select rank, search_num as search_volume, rate as st_search_rate, date_info from ods_rank_search_rate_repeat where site_name = '{self.site_name}';
......@@ -147,14 +147,14 @@ class DwtStDetailWeek(object):
'date_info_rank', F.row_number().over(window=window)
).filter('date_info_rank=1').drop('date_info_rank', 'date_info').cache()
print("搜索词排名+搜索量+转化率如下：")
self.df_st_rank.show(10, True)
# self.df_st_rank.show(10, True)
sql = f"""
select st_key, search_term from ods_st_key where site_name = '{self.site_name}';
"""
self.df_st_key = self.spark.sql(sql).cache()
print("搜索词key如下：")
self.df_st_key.show(10, True)
# self.df_st_key.show(10, True)
sql = f"""
select search_term, st_bsr_cate_1_id_new as category_id, st_bsr_cate_current_id_new as category_current_id, market_cycle_type, date_info from dwt_aba_st_analytics where site_name = '{self.site_name}' and date_type = 'month' and date_info <= '{self.year_month}';
......@@ -165,7 +165,7 @@ class DwtStDetailWeek(object):
'date_info_rank', F.row_number().over(window=window)
).filter('date_info_rank=1').drop('date_info_rank', 'date_info').cache()
print("分类、市场周期月数据如下：")
self.df_st_month.show(10, True)
# self.df_st_month.show(10, True)
# 从pgsql获取特殊字符匹配字典表：match_character_dict
pg_sql = f"""
......@@ -196,7 +196,7 @@ class DwtStDetailWeek(object):
'search_term', 'rank_change_1_week_ago', 'rank_rate_1_week_ago'
).cache()
print("1周前排名变化数据如下：")
self.df_st_detail_1_week_ago.show(10, True)
# self.df_st_detail_1_week_ago.show(10, True)
self.df_st_detail_2_week_ago = self.df_st_detail_week.filter(F.col('date_info') == self.date_info_2_week_ago).withColumnRenamed(
'rank_change_last_1_week', 'rank_change_2_week_ago'
......@@ -206,7 +206,7 @@ class DwtStDetailWeek(object):
'search_term', 'rank_change_2_week_ago', 'rank_rate_2_week_ago'
).cache()
print("2周前排名变化数据如下：")
self.df_st_detail_2_week_ago.show(10, True)
# self.df_st_detail_2_week_ago.show(10, True)
self.df_st_detail_3_week_ago = self.df_st_detail_week.filter(F.col('date_info') == self.date_info_3_week_ago).withColumnRenamed(
'rank_change_last_1_week', 'rank_change_3_week_ago'
......@@ -216,7 +216,7 @@ class DwtStDetailWeek(object):
'search_term', 'rank_change_3_week_ago', 'rank_rate_3_week_ago'
).cache()
print("3周前排名变化数据如下：")
self.df_st_detail_3_week_ago.show(10, True)
# self.df_st_detail_3_week_ago.show(10, True)
self.df_st_detail_week.unpersist()
def handle_st_flag(self):
......@@ -229,7 +229,7 @@ class DwtStDetailWeek(object):
'is_search_text', F.lit(1)
).select('search_term', 'is_search_text').cache()
print("热搜词如下：")
df_hot_search_term.show(10, True)
# df_hot_search_term.show(10, True)
# 上升词：本周环比上周排名增长50%的搜索词
df_rising_search_term = self.df_st_detail.join(
......@@ -238,7 +238,7 @@ class DwtStDetailWeek(object):
"is_ascending_text", (((F.col('rank_last_week') - F.col('rank')) / F.col('rank_last_week')) >= 0.5).cast('int')
).select('search_term', 'is_ascending_text').cache()
print("上升词如下：")
df_rising_search_term.show(10, True)
# df_rising_search_term.show(10, True)
# 新增词：本周环比上周新出现的搜索词
df_first_search_term = self.df_st_detail.join(
......@@ -247,7 +247,7 @@ class DwtStDetailWeek(object):
'is_first_text', F.lit(1)
).select('search_term', 'is_first_text').cache()
print("新增词如下：")
df_first_search_term.show(10, True)
# df_first_search_term.show(10, True)
# 高回报词：最近4周都出现且点击占比（总）>转化占比（总）
df_high_return_search_term = self.df_st_detail_last_4_week.groupBy(['search_term', 'date_info']).agg(
......@@ -263,7 +263,7 @@ class DwtStDetailWeek(object):
'is_high_return_text', F.lit(1)
).select('search_term', 'is_high_return_text').cache()
print("高回报词如下：")
df_high_return_search_term.show(10, True)
# df_high_return_search_term.show(10, True)
self.df_st_detail = self.df_st_detail.join(
df_hot_search_term, 'search_term', 'left'
......
Pyspark_job/sqoop_export/dim_st_detail_week.py
......@@ -14,7 +14,7 @@ if __name__ == '__main__':
CommonUtil.judge_is_work_hours(
site_name=site_name, date_type=date_type, date_info=date_info,
principal='chenyuanjie', priority=1, export_tools_type=1, belonging_to_process='ABA周增长'
principal='hejiangming', priority=1, export_tools_type=1, belonging_to_process='ABA周增长'
)
db_type = DbTypes.postgresql_cluster.name
......
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