change int to float

tensnsorflow/feature_engineering.py

@@ -63,9 +63,8 @@ def get_data():
     test = df[df["stat_date"] == validate_date+"stat_date"]
     for i in features:
         train[i] = train[i].map(value_map)
-        train[i] = train[i].astype('int64')
         test[i] = test[i].map(value_map)
-        test[i] = test[i].astype('int64')
+
 
     print("train shape")
     print(train.shape)
@@ -123,11 +122,11 @@ def get_predict(date,value_map):
         native_pre[i] = native_pre[i].map(value_map)
         # TODO 没有覆盖到的类别会处理成na，暂时用0填充，后续完善一下
         native_pre[i] = native_pre[i].fillna(0)
-        native_pre[i] = native_pre[i].astype('int64')
+
         nearby_pre[i] = nearby_pre[i].map(value_map)
         # TODO 没有覆盖到的类别会处理成na，暂时用0填充，后续完善一下
         nearby_pre[i] = nearby_pre[i].fillna(0)
-        nearby_pre[i] = nearby_pre[i].astype('int64')
+
 
     print("native")
     print(native_pre.shape)

tensnsorflow/test.py

@@ -29,18 +29,18 @@ def gen_tfrecords(in_file):
 
     for i in range(df.shape[0]):
         features = tf.train.Features(feature={
-            "y": tf.train.Feature(int64_list=tf.train.Int64List(value=[df["y"][i]])),
-            "z": tf.train.Feature(int64_list=tf.train.Int64List(value=[df["z"][i]])),
-            "top": tf.train.Feature(int64_list=tf.train.Int64List(value=[df["top"][i]])),
-            "channel": tf.train.Feature(int64_list=tf.train.Int64List(value=[df["channel"][i]])),
-            "ucity_id": tf.train.Feature(int64_list=tf.train.Int64List(value=[df["ucity_id"][i]])),
-            "clevel1_id": tf.train.Feature(int64_list=tf.train.Int64List(value=[df["clevel1_id"][i]])),
-            "ccity_name": tf.train.Feature(int64_list=tf.train.Int64List(value=[df["ccity_name"][i]])),
-            "device_type": tf.train.Feature(int64_list=tf.train.Int64List(value=[df["device_type"][i]])),
-            "manufacturer": tf.train.Feature(int64_list=tf.train.Int64List(value=[df["manufacturer"][i]])),
-            "level2_ids": tf.train.Feature(int64_list=tf.train.Int64List(value=[df["level2_ids"][i]])),
-            "time": tf.train.Feature(int64_list=tf.train.Int64List(value=[df["time"][i]])),
-            "stat_date": tf.train.Feature(int64_list=tf.train.Int64List(value=[df["stat_date"][i]]))
+            "y": tf.train.Feature(float_list=tf.train.FloatList(value=[df["y"][i]])),
+            "z": tf.train.Feature(float_list=tf.train.FloatList(value=[df["z"][i]])),
+            "top": tf.train.Feature(float_list=tf.train.FloatList(value=[df["top"][i]])),
+            "channel": tf.train.Feature(float_list=tf.train.FloatList(value=[df["channel"][i]])),
+            "ucity_id": tf.train.Feature(float_list=tf.train.FloatList(value=[df["ucity_id"][i]])),
+            "clevel1_id": tf.train.Feature(float_list=tf.train.FloatList(value=[df["clevel1_id"][i]])),
+            "ccity_name": tf.train.Feature(float_list=tf.train.FloatList(value=[df["ccity_name"][i]])),
+            "device_type": tf.train.Feature(float_list=tf.train.FloatList(value=[df["device_type"][i]])),
+            "manufacturer": tf.train.Feature(float_list=tf.train.FloatList(value=[df["manufacturer"][i]])),
+            "level2_ids": tf.train.Feature(float_list=tf.train.FloatList(value=[df["level2_ids"][i]])),
+            "time": tf.train.Feature(float_list=tf.train.FloatList(value=[df["time"][i]])),
+            "stat_date": tf.train.Feature(float_list=tf.train.FloatList(value=[df["stat_date"][i]]))
         })
 
         example = tf.train.Example(features = features)

tensnsorflow/train.py

@@ -53,16 +53,16 @@ def input_fn(filenames, batch_size=32, num_epochs=1, perform_shuffle=False):
         features = {
             "y": tf.FixedLenFeature([], tf.float32),
             "z": tf.FixedLenFeature([], tf.float32),
-            "top": tf.FixedLenFeature([], tf.int64),
-            "channel": tf.FixedLenFeature([], tf.int64),
-            "ucity_id": tf.FixedLenFeature([], tf.int64),
-            "clevel1_id": tf.FixedLenFeature([], tf.int64),
-            "ccity_name": tf.FixedLenFeature([], tf.int64),
-            "device_type": tf.FixedLenFeature([], tf.int64),
-            "manufacturer": tf.FixedLenFeature([], tf.int64),
-            "level2_ids": tf.FixedLenFeature([], tf.int64),
-            "time": tf.FixedLenFeature([], tf.int64),
-            "stat_date": tf.FixedLenFeature([], tf.int64)
+            "top": tf.FixedLenFeature([], tf.float32),
+            "channel": tf.FixedLenFeature([], tf.float32),
+            "ucity_id": tf.FixedLenFeature([], tf.float32),
+            "clevel1_id": tf.FixedLenFeature([], tf.float32),
+            "ccity_name": tf.FixedLenFeature([], tf.float32),
+            "device_type": tf.FixedLenFeature([], tf.float32),
+            "manufacturer": tf.FixedLenFeature([], tf.float32),
+            "level2_ids": tf.FixedLenFeature([], tf.float32),
+            "time": tf.FixedLenFeature([], tf.float32),
+            "stat_date": tf.FixedLenFeature([], tf.float32)
         }
 
         parsed = tf.parse_single_example(record, features)