Commit a0d42a6e authored by 高雅喆's avatar 高雅喆

esmm train data first level1_id

parent 99e8c1dd
......@@ -20,9 +20,9 @@ echo "data2ffm"
${PYTHON_PATH} ${MODEL_PATH}/Feature_pipline/data2ffm.py > ${DATA_PATH}/infer.log
all_sample=$((`cat ${DATA_PATH}/tr.csv | awk -F '\t' '{print$5}' | awk -F ',' '{print$2$3$4}' | sort | uniq | wc -l`))
uniq_feat=$((`cat ${DATA_PATH}/tr.csv | awk -F '\t' '{print$5}' | awk -F ',' '{print$4}' | sort | uniq -u | wc -l`))
repe_feat=$((all_sample-uniq_feat))
echo "Bayes Error Rate" : $((repe_feat*100/all_sample))%
uniq_feat=$((`cat ${DATA_PATH}/tr.csv | awk -F '\t' '{print$5}' | awk -F ',' '{print$4}' | sort | uniq -u | wc -l`))
repe_feat=$((all_sample-uniq_feat))
echo "Bayes Error Rate": $((repe_feat*100/all_sample))%
echo "split data"
split -l $((`wc -l < ${DATA_PATH}/tr.csv`/15)) ${DATA_PATH}/tr.csv -d -a 4 ${DATA_PATH}/tr/tr_ --additional-suffix=.csv
......
......@@ -211,7 +211,18 @@ object EsmmData {
)
// union_data_scity_id.createOrReplaceTempView("union_data_scity_id")
union_data_scity_id.show()
GmeiConfig.writeToJDBCTable("jdbc:mysql://10.66.157.22:4000/jerry_test?user=root&password=3SYz54LS9#^9sBvC&rewriteBatchedStatements=true",union_data_scity_id, table="esmm_train_data",SaveMode.Append)
val union_data_scity_id2 = sc.sql(
s"""
|select device_id,cid_id,first(stat_date) stat_date,first(ucity_id) ucity_id,first(diary_service_id) diary_service_id,first(y) y,
|first(z) z,first(clevel1_id) clevel1_id,first(slevel1_id) slevel1_id,first(ccity_name) ccity_name,first(scity_id) scity_id
|from union_data_scity_id
|group by device_id,cid_id
""".stripMargin
)
GmeiConfig.writeToJDBCTable("jdbc:mysql://10.66.157.22:4000/jerry_test?user=root&password=3SYz54LS9#^9sBvC&rewriteBatchedStatements=true",union_data_scity_id2, table="esmm_train_data",SaveMode.Append)
} else {
println("esmm_train_data already have param.date data")
......
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