Commit 41ea4ac6 authored by 张彦钊's avatar 张彦钊

修改测试文件

parent 4d57fbb9
......@@ -34,7 +34,7 @@ def feature_engineer():
validate_date = con_sql(db, sql)[0].values.tolist()[0]
print("validate_date:" + validate_date)
temp = datetime.datetime.strptime(validate_date, "%Y-%m-%d")
start = (temp - datetime.timedelta(days=6)).strftime("%Y-%m-%d")
start = (temp - datetime.timedelta(days=3)).strftime("%Y-%m-%d")
print(start)
sparkConf = SparkConf().set("spark.hive.mapred.supports.subdirectories", "true") \
......@@ -81,7 +81,8 @@ def feature_engineer():
df = df.fillna("na")
app_list_value = [i.split(",") for i in df.select("app_list").collect().unique()]
app_list_value = [i.split(",") for i in set(df.select("app_list").collect())]
app_list_unique = []
for i in app_list_value:
app_list_unique.extend(i)
......
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