Skip to content

S
serviceRec
Commit e41bc4ed authored by 郭羽's avatar 郭羽
Browse files
Options

update feature

parent 50ce4106
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
spark/featureEng.py
View file @ e41bc4ed
...@@ -166,7 +166,7 @@ def addUserFeatures(samples,dataVocab,multiVocab): ...@@ -166,7 +166,7 @@ def addUserFeatures(samples,dataVocab,multiVocab):
.withColumn("userPositiveHistory", arrayReverseUdf(F.col("userPositiveHistory"))) .withColumn("userPositiveHistory", arrayReverseUdf(F.col("userPositiveHistory")))
for i in range(1,11): for i in range(1,11):
samples = samples.withColumn("userRatedHistory"+str(i), F.when(F.col("userPositiveHistory")[i-1].isNotNull(),F.col("userPositiveHistory")[i-1]).otherwise("-1")) samples = samples.withColumn("userRatedHistory"+str(i), F.when(F.col("userPositiveHistory")[i-1].isNotNull(),F.col("userPositiveHistory")[i-1]).otherwise("-1"))
# dataVocab["userRatedHistory"+str(i)] = dataVocab["itemid"] dataVocab["userRatedHistory"+str(i)] = dataVocab["itemid"]
samples = samples.drop("userPositiveHistory") samples = samples.drop("userPositiveHistory")
# user历史点击分值统计 # user历史点击分值统计
...@@ -216,7 +216,7 @@ def addUserFeatures(samples,dataVocab,multiVocab): ...@@ -216,7 +216,7 @@ def addUserFeatures(samples,dataVocab,multiVocab):
def addSampleLabel(ratingSamples): def addSampleLabel(ratingSamples):
ratingSamples = ratingSamples.withColumn('label', when(F.col('rating') >= 8, 1).otherwise(0)) ratingSamples = ratingSamples.withColumn('label', when(F.col('rating') >= 5, 1).otherwise(0))
ratingSamples.show(5, truncate=False) ratingSamples.show(5, truncate=False)
ratingSamples.printSchema() ratingSamples.printSchema()
return ratingSamples return ratingSamples
......
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