Skip to content

F
ffm-baseline
Commit 759b7930 authored by 张彦钊's avatar 张彦钊
Browse files
Options

把最近一天的数据集放进训练集

parent a6ae0551
Hide whitespace changes
Inline Side-by-side
Showing with 5 additions and 7 deletions
tensnsorflow/multi.py
View file @ 759b7930
...@@ -85,8 +85,6 @@ def feature_engineer(): ...@@ -85,8 +85,6 @@ def feature_engineer():
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))
print("tets")
print(value_map["top"])
rdd = df.select("app_list","level2_ids","level3_ids","stat_date","ucity_id", "ccity_name", "device_type", "manufacturer", rdd = 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",
...@@ -138,15 +136,15 @@ def get_predict(date,value_map,app_list_map,level2_map,level3_map): ...@@ -138,15 +136,15 @@ def get_predict(date,value_map,app_list_map,level2_map,level3_map):
"channel", "top", "time", "app_list", "hospital_id", "level3_ids"]) "channel", "top", "time", "app_list", "hospital_id", "level3_ids"])
rdd = df.select("app_list", "level2_ids", "level3_ids","ucity_id","device_id","cid_id","label", "y", "z", rdd = df.select("app_list", "level2_ids", "level3_ids","ucity_id","device_id","cid_id","label", "y", "z",
"ccity_name", "device_type","manufacturer", "channel", "top", "time", "hospital_id", "ccity_name", "device_type","manufacturer", "channel", "time", "hospital_id",
"treatment_method", "price_min", "price_max", "treatment_time", "maintain_time", "treatment_method", "price_min", "price_max", "treatment_time", "maintain_time",
"recover_time") \ "recover_time","top") \
.rdd.map(lambda x: (app_list_func(x[0], app_list_map), app_list_func(x[1], level2_map), .rdd.map(lambda x: (app_list_func(x[0], app_list_map), app_list_func(x[1], level2_map),
app_list_func(x[2], level3_map), x[3],x[4],x[5],x[6],x[7],x[8], app_list_func(x[2], level3_map), x[3],x[4],x[5],x[6],x[7],x[8],
value_map[x[3]], value_map[x[9]], value_map[x[3]], value_map[x[9]],
value_map[x[10]], value_map[x[11]], value_map[x[12]], value_map[x[13]], 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[17]], value_map[x[14]], value_map[x[15]], value_map[x[16]], value_map[x[17]],
value_map[x[18]], value_map[x[19]], value_map[x[20]], value_map[x[21]], value_map[x[18]], value_map[x[19]], value_map[x[20]], value_map.get(x[21],30000),
value_map[date])) value_map[date]))
rdd.persist() rdd.persist()
...@@ -161,9 +159,9 @@ def get_predict(date,value_map,app_list_map,level2_map,level3_map): ...@@ -161,9 +159,9 @@ def get_predict(date,value_map,app_list_map,level2_map,level3_map):
.map(lambda x: (x[0], x[1], x[2],x[9],x[10],x[11],x[12],x[13],x[14],x[15], .map(lambda x: (x[0], x[1], x[2],x[9],x[10],x[11],x[12],x[13],x[14],x[15],
x[16,x[17],x[18],x[19],x[20],x[21],x[22],x[23]]))) \ x[16,x[17],x[18],x[19],x[20],x[21],x[22],x[23]]))) \
.toDF("app_list", "level2_ids", "level3_ids","ucity_id", .toDF("app_list", "level2_ids", "level3_ids","ucity_id",
"ccity_name", "device_type","manufacturer", "channel", "top", "time", "hospital_id", "ccity_name", "device_type","manufacturer", "channel", "time", "hospital_id",
"treatment_method", "price_min", "price_max", "treatment_time", "maintain_time", "treatment_method", "price_min", "price_max", "treatment_time", "maintain_time",
"recover_time", "stat_date").write.csv('/recommend/native', mode='overwrite', header=True) "recover_time", "top","stat_date").write.csv('/recommend/native', mode='overwrite', header=True)
nearby_pre = spark.createDataFrame(rdd.filter(lambda x: x[6] == 1).map(lambda x: (x[3], x[4], x[5]))) \ nearby_pre = spark.createDataFrame(rdd.filter(lambda x: x[6] == 1).map(lambda x: (x[3], x[4], x[5]))) \
.toDF("city", "uid", "cid_id") .toDF("city", "uid", "cid_id")
......
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