Skip to content

S
serviceRec
Commit b887c0c8 authored by 郭羽's avatar 郭羽
Browse files
Options

service model 优化

parent 4d53aa81
Hide whitespace changes
Inline Side-by-side
Showing with 6 additions and 3 deletions
spark/featureEng2.py
View file @ b887c0c8
...@@ -162,19 +162,22 @@ def addItemFeatures(itemDF,dataVocab,multi_col_vocab): ...@@ -162,19 +162,22 @@ def addItemFeatures(itemDF,dataVocab,multi_col_vocab):
bucket_suffix = "_Bucket" bucket_suffix = "_Bucket"
for col in ['case_count', 'sales_count']: for col in ['case_count', 'sales_count']:
new_col = ITEM_PREFIX + col + bucket_suffix new_col = ITEM_PREFIX + col + bucket_suffix
itemDF = itemDF.withColumn(new_col, numberToBucketUdf(F.col(col))).drop(col) itemDF[new_col] = itemDF[col].map(numberToBucket)
itemDF = itemDF.drop(columns=[col])
dataVocab[new_col] = bucket_vocab dataVocab[new_col] = bucket_vocab
for col in ['sku_price']: for col in ['sku_price']:
new_col = ITEM_PREFIX + col + bucket_suffix new_col = ITEM_PREFIX + col + bucket_suffix
itemDF = itemDF.withColumn(new_col, priceToBucketUdf(F.col(col))).drop(col) itemDF[new_col] = itemDF[col].map(priceToBucket)
itemDF = itemDF.drop(columns=[col])
dataVocab[new_col] = bucket_vocab dataVocab[new_col] = bucket_vocab
# 连续数据处理 # 连续数据处理
number_suffix = "_number" number_suffix = "_number"
for col in ["discount"]: for col in ["discount"]:
new_col = ITEM_PREFIX + col + number_suffix new_col = ITEM_PREFIX + col + number_suffix
itemDF = itemDF.withColumnRenamed(col, new_col) itemDF[new_col] = itemDF[col]
itemDF = itemDF.drop(columns=[col])
return itemDF return itemDF
......
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