把top特征和l1、l2特征合并

tensnsorflow/feature_engineering.py

@@ -50,18 +50,19 @@ def get_data():
 
     unique_values = []
     features = ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
-                "channel", "top", "l1", "time", "stat_date"]
+                "channel", "top", "time", "stat_date"]
     for i in features:
         df[i] = df[i].astype("str")
         df[i] = df[i].fillna("lost")
         # 下面这行代码是为了区分不同的列中有相同的值
         df[i] = df[i] + i
         unique_values.extend(list(df[i].unique()))
-    df["l2"] = df["l2"].astype("str")
-    df["l2"] = df["l2"].fillna("lost")
-    # l1和l2中的值允许相同
-    df["l2"] = df["l2"]+"l1"
-    unique_values.extend(list(df["l2"].unique()))
+    for i in ["l1","l2"]:
+        df[i] = df[i].astype("str")
+        df[i] = df[i].fillna("lost")
+        # l1和l2中的值与top类别是一个类别
+        df[i] = df[i]+"top"
+        unique_values.extend(list(df[i].unique()))
 
     print("features:")
     print(len(unique_values))
@@ -78,7 +79,6 @@ def get_data():
         train[i] = train[i].map(value_map)
         test[i] = test[i].map(value_map)
 
-
     print("train shape")
     print(train.shape)
     print("test shape")
@@ -120,14 +120,16 @@ def get_predict(date,value_map):
     print(df.shape)
 
     features = ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
-                "channel", "top", "l1", "time", "stat_date"]
+                "channel", "top", "time", "stat_date"]
     for i in features:
         df[i] = df[i].astype("str")
         df[i] = df[i].fillna("lost")
         df[i] = df[i] + i
-    df["l2"] = df["l2"].astype("str")
-    df["l2"] = df["l2"].fillna("lost")
-    df["l2"] = df["l2"] + "l1"
+    for i in ["l1","l2"]:
+        df[i] = df[i].astype("str")
+        df[i] = df[i].fillna("lost")
+        # l1和l2中的值与top类别是一个类别
+        df[i] = df[i]+"top"
 
     native_pre = df[df["label"] == 0]
     native_pre = native_pre.drop("label", axis=1)
@@ -147,10 +149,12 @@ def get_predict(date,value_map):
 
     print("native")
     print(native_pre.shape)
+    print(native_pre.head())
     write_csv(native_pre, "native",200000)
 
     print("nearby")
     print(nearby_pre.shape)
+    print(nearby_pre.head())
     write_csv(nearby_pre, "nearby", 160000)