test

eda/esmm/Model_pipline/dist_predict.py

@@ -162,14 +162,15 @@ def main(te_file):
 
     preds = Estimator.predict(input_fn=lambda: input_fn(te_file, num_epochs=1, batch_size=10000), predict_keys=["pctcvr","pctr","pcvr"])
 
-    with open("/home/gmuser/esmm/nearby/pred.txt", "w") as fo:
-        for prob in preds:
-            fo.write("%f\t%f\t%f\n" % (prob['pctr'], prob['pcvr'], prob['pctcvr']))
-    #
-    # indices = []
-    # for prob in preds:
-    #     indices.append([prob['pctr'], prob['pcvr'], prob['pctcvr']])
-    # return indices
+    # with open("/home/gmuser/esmm/nearby/pred.txt", "w") as fo:
+    #     for prob in preds:
+    #         fo.write("%f\t%f\t%f\n" % (prob['pctr'], prob['pcvr'], prob['pctcvr']))
+
+    indices = []
+    for prob in preds:
+        indices.append([prob['pctr'], prob['pcvr'], prob['pctcvr']])
+        print(prob['pctcvr'])
+    return indices
 
 def test_map(x):
     return x * x
@@ -205,8 +206,6 @@ if __name__ == "__main__":
     te_files = [[path+"nearby/part-r-00000"],[path+"native/part-r-00000"]]
     rdd_te_files = spark.sparkContext.parallelize(te_files)
     indices = rdd_te_files.repartition(2).map(lambda x: main(x))
-    print(indices.collect())
-
 
     b = time.time()
     print("耗时(分钟)：")