Commit 3c2d3779 authored by 宋柯's avatar 宋柯

模型调试

parent eff7b4c2
......@@ -140,9 +140,9 @@ def getItemStaticFeatures(itemStatisticDays, startDay, endDay):
drop_columns = ['label', 'label_count']
clickStaticFeatures = clickStaticFeatures.drop(*drop_columns)
clickStaticFeatures.show(20, truncate = False)
# clickStaticFeatures.show(20, truncate = False)
expStaticFeatures = expStaticFeatures.drop(*drop_columns)
expStaticFeatures.show(20, truncate = False)
# expStaticFeatures.show(20, truncate = False)
return clickStaticFeatures, expStaticFeatures
......@@ -838,7 +838,7 @@ def get_item_es_feature_df():
_source = res['_source']
data = parseSource(_source)
datas.append(data)
print("card size:",len(datas))
print("card size: ",len(datas))
itemColumns = ['card_id', ITEM_PREFIX + NUMERIC_PREFIX + 'discount',
ITEM_PREFIX + NUMERIC_PREFIX + 'case_count', ITEM_PREFIX + NUMERIC_PREFIX + 'sales_count',
......@@ -855,7 +855,7 @@ def get_item_es_feature_df():
itemEsFeatureDF = spark.createDataFrame(itemEsFeatureDF)
itemEsFeatureDF.printSchema()
itemEsFeatureDF.show(10, truncate=False)
# itemEsFeatureDF.show(10, truncate=False)
return itemEsFeatureDF
......@@ -953,6 +953,7 @@ if __name__ == '__main__':
.join(clickStaticFeatures, on = ["card_id", "partition_date"], how = 'left')\
.join(expStaticFeatures, on = ["card_id", "partition_date"], how = 'left')\
.join(itemEsFeatureDF, on = ["card_id"], how = 'left')
samples = samples.withColumnRenamed("card_id", ITEM_PREFIX + CATEGORY_PREFIX + "card_id")\
.withColumnRenamed("device_id", USER_PREFIX + CATEGORY_PREFIX + "device_id") \
.withColumnRenamed("os", USER_PREFIX + CATEGORY_PREFIX + "os") \
......
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