Commit 1669f4b7 authored by 张彦钊's avatar 张彦钊

change test file

parent 8e11ec4f
...@@ -51,70 +51,69 @@ def feature_engineer(): ...@@ -51,70 +51,69 @@ def feature_engineer():
"where e.stat_date >= '{}'".format(start) "where e.stat_date >= '{}'".format(start)
df = spark.sql(sql) df = spark.sql(sql)
df.write.csv('/recommend/va', mode='overwrite', header=True)
url = "jdbc:mysql://172.16.30.143:3306/zhengxing"
# url = "jdbc:mysql://172.16.30.143:3306/zhengxing" jdbcDF = spark.read.format("jdbc").option("driver", "com.mysql.jdbc.Driver").option("url", url) \
# jdbcDF = spark.read.format("jdbc").option("driver", "com.mysql.jdbc.Driver").option("url", url) \ .option("dbtable", "api_service").option("user", 'work').option("password", 'BJQaT9VzDcuPBqkd').load()
# .option("dbtable", "api_service").option("user", 'work').option("password", 'BJQaT9VzDcuPBqkd').load() jdbcDF.createOrReplaceTempView("api_service")
# jdbcDF.createOrReplaceTempView("api_service") jdbc = spark.read.format("jdbc").option("driver", "com.mysql.jdbc.Driver").option("url", url) \
# jdbc = spark.read.format("jdbc").option("driver", "com.mysql.jdbc.Driver").option("url", url) \ .option("dbtable", "api_doctor").option("user", 'work').option("password", 'BJQaT9VzDcuPBqkd').load()
# .option("dbtable", "api_doctor").option("user", 'work').option("password", 'BJQaT9VzDcuPBqkd').load() jdbc.createOrReplaceTempView("api_doctor")
# jdbc.createOrReplaceTempView("api_doctor")
# sql = "select s.id as diary_service_id,d.hospital_id " \
# sql = "select s.id as diary_service_id,d.hospital_id " \ "from api_service s left join api_doctor d on s.doctor_id = d.id"
# "from api_service s left join api_doctor d on s.doctor_id = d.id" hospital = spark.sql(sql)
# hospital = spark.sql(sql)
# df = df.join(hospital,"diary_service_id","left_outer").fillna("na")
# df = df.join(hospital,"diary_service_id","left_outer").fillna("na") df = df.drop("level2").drop("diary_service_id")
# df = df.drop("level2").drop("diary_service_id") df = df.drop_duplicates(["ucity_id", "level2_ids", "ccity_name", "device_type", "manufacturer",
# df = df.drop_duplicates(["ucity_id", "level2_ids", "ccity_name", "device_type", "manufacturer", "channel", "top", "time", "stat_date", "app_list", "hospital_id", "level3_ids"])
# "channel", "top", "time", "stat_date", "app_list", "hospital_id", "level3_ids"])
# features = ["ucity_id", "ccity_name", "device_type", "manufacturer",
# features = ["ucity_id", "ccity_name", "device_type", "manufacturer", "channel", "top", "time", "stat_date", "hospital_id",
# "channel", "top", "time", "stat_date", "hospital_id", "treatment_method", "price_min", "price_max", "treatment_time", "maintain_time", "recover_time"]
# "treatment_method", "price_min", "price_max", "treatment_time", "maintain_time", "recover_time"]
# df = df.na.fill(dict(zip(features,features)))
# df = df.na.fill(dict(zip(features,features)))
# apps_number, app_list_map = multi_hot(df,"app_list",1)
# apps_number, app_list_map = multi_hot(df,"app_list",1) level2_number,leve2_map = multi_hot(df,"level2_ids",1 + apps_number)
# level2_number,leve2_map = multi_hot(df,"level2_ids",1 + apps_number) level3_number, leve3_map = multi_hot(df, "level3_ids", 1 + apps_number + level2_number)
# level3_number, leve3_map = multi_hot(df, "level3_ids", 1 + apps_number + level2_number)
# unique_values = []
# unique_values = [] for i in features:
# for i in features: unique_values.extend(list(set(df.select(i).rdd.map(lambda x: x[0]).collect())))
# unique_values.extend(list(set(df.select(i).rdd.map(lambda x: x[0]).collect()))) temp = list(range(2 + apps_number + level2_number + level3_number,
# temp = list(range(2 + apps_number + level2_number + level3_number, 2 + apps_number + level2_number + level3_number + len(unique_values)))
# 2 + apps_number + level2_number + level3_number + len(unique_values))) value_map = dict(zip(unique_values, temp))
# value_map = dict(zip(unique_values, temp))
# train = df.select("app_list","level2_ids","level3_ids","stat_date","ucity_id", "ccity_name", "device_type", "manufacturer",
# train = df.select("app_list","level2_ids","level3_ids","stat_date","ucity_id", "ccity_name", "device_type", "manufacturer", "channel", "top", "time", "hospital_id","treatment_method", "price_min",
# "channel", "top", "time", "hospital_id","treatment_method", "price_min", "price_max", "treatment_time","maintain_time", "recover_time","y","z",)\
# "price_max", "treatment_time","maintain_time", "recover_time","y","z",)\ .rdd.filter(lambda x: x[3]!= validate_date).map(lambda x: (app_list_func(x[0], app_list_map), app_list_func(x[1], leve2_map),
# .rdd.filter(lambda x: x[3]!= validate_date).map(lambda x: (app_list_func(x[0], app_list_map), app_list_func(x[1], leve2_map), app_list_func(x[2], leve3_map),value_map[x[3]],value_map[x[4]],
# app_list_func(x[2], leve3_map),value_map[x[3]],value_map[x[4]], value_map[x[5]],value_map[x[6]],value_map[x[7]],value_map[x[8]],
# value_map[x[5]],value_map[x[6]],value_map[x[7]],value_map[x[8]], value_map[x[9]],value_map[x[10]],value_map[x[11]],value_map[x[12]],
# value_map[x[9]],value_map[x[10]],value_map[x[11]],value_map[x[12]], value_map[x[13]],value_map[x[14]],value_map[x[15]],value_map[x[16]],
# value_map[x[13]],value_map[x[14]],value_map[x[15]],value_map[x[16]], value_map[x[17]], x[18],x[19]))
# value_map[x[17]], x[18],x[19])) test = df.select("app_list", "level2_ids", "level3_ids", "stat_date", "ucity_id", "ccity_name", "device_type",
# test = df.select("app_list", "level2_ids", "level3_ids", "stat_date", "ucity_id", "ccity_name", "device_type", "manufacturer","channel", "top", "time", "hospital_id", "treatment_method", "price_min",
# "manufacturer","channel", "top", "time", "hospital_id", "treatment_method", "price_min", "price_max", "treatment_time", "maintain_time", "recover_time", "y", "z", ) \
# "price_max", "treatment_time", "maintain_time", "recover_time", "y", "z", ) \ .rdd.filter(lambda x: x[3] == validate_date)\
# .rdd.filter(lambda x: x[3] == validate_date)\ .map(lambda x: (app_list_func(x[0], app_list_map), app_list_func(x[1], leve2_map),
# .map(lambda x: (app_list_func(x[0], app_list_map), app_list_func(x[1], leve2_map), app_list_func(x[2], leve3_map), value_map[x[3]], value_map[x[4]],
# app_list_func(x[2], leve3_map), value_map[x[3]], value_map[x[4]], value_map[x[5]], value_map[x[6]], value_map[x[7]], value_map[x[8]],
# value_map[x[5]], value_map[x[6]], value_map[x[7]], value_map[x[8]], value_map[x[9]], value_map[x[10]], value_map[x[11]], value_map[x[12]],
# value_map[x[9]], value_map[x[10]], value_map[x[11]], value_map[x[12]], value_map[x[13]], value_map[x[14]], value_map[x[15]], value_map[x[16]],
# value_map[x[13]], value_map[x[14]], value_map[x[15]], value_map[x[16]], value_map[x[17]], x[18], x[19]))
# value_map[x[17]], x[18], x[19]))
print("test.count",test.count())
# print("test.count",test.count()) print("train count",train.count())
# print("train count",train.count())
spark.createDataFrame(test).write.csv('/recommend/va', mode='overwrite', header=True)
# spark.createDataFrame(test).write.csv('/recommend/va', mode='overwrite', header=True) spark.createDataFrame(train).write.csv('/recommend/tr', mode='overwrite', header=True)
# spark.createDataFrame(train).write.csv('/recommend/tr', mode='overwrite', header=True) print("done")
# print("done")
return validate_date,value_map,app_list_map,leve2_map,leve3_map
# return validate_date,value_map,app_list_map,leve2_map,leve3_map
# def get_predict(date,value_map,app_list_map,level2_map,level3_map): # def get_predict(date,value_map,app_list_map,level2_map,level3_map):
......
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