add stat count

word_vector/tests.py

 # from django.test import TestCase
+import os
 
 # create your tests here.
 
-# /opt/spark/bin/spark-submit --master yarn --deploy-mode client --queue root.strategy --driver-memory 16g --executor-memory 1g --executor-cores 1 --num-executors 70 --conf spark.default.parallelism=100 --conf spark.storage.memoryFraction=0.5 --conf spark.shuffle.memoryFraction=0.3 --conf spark.locality.wait=0 --jars /srv/apps/tispark-core-2.1-SNAPSHOT-jar-with-dependencies.jar,/srv/apps/spark-connector_2.11-1.9.0-rc2.jar,/srv/apps/mysql-connector-java-5.1.38.jar /srv/apps/strategy_embedding/word_vector/tests.py
+base_dir = os.getcwd()
+print("base_dir: " + base_dir)
+model_dir = os.path.join(base_dir, "_models")
+data_dir = os.path.join(base_dir, "_data")
+
+if __name__ == "__main__":
+    id1 = ["366825", "203194"]  # 下颚角
+    id2 = ["87874", "84198"]  # 双眼皮
+
+    with open(os.path.join(data_dir, "click_tractate_ids.csv"), "r") as f:
+        data = f.readlines()
+        count = 0
+        id1_count = 0
+        id2_count = 0
+        for i in data:
+            count += 1
+            tmp = i.split("|")
+            device_id = tmp[0]
+            ids = tmp[1].rstrip("\n").split(",")
+            if id1[0] in ids and id1[1] in ids:
+                id1_count += 1
+            if id2[0] in ids and id2[i] in ids:
+                id2_count += 1
+
+    print(count, id1_count, id2_count)