add print

tensnsorflow/ffm.py

@@ -98,12 +98,7 @@ class multiFFMFormatPandas:
 
         result_map = {}
         for i in data_list:
-            print("before:total")
-            print(len(result_map))
-            print(len(i.get()))
             result_map.update(i.get())
-            print("result_map")
-            print(len(result_map))
 
         pool.close()
         pool.join()
@@ -120,10 +115,10 @@ class multiFFMFormatPandas:
         x = 0
         while True:
             if x + step < data.__len__():
-                data_list.append(data.loc[x:x + step])
-                x = x + step + 1
+                data_list.append(data.iloc[x:x + step])
+                x = x + step
             else:
-                data_list.append(data.loc[x:data.__len__()])
+                data_list.append(data.iloc[x:data.__len__()])
                 break
 
         return data_list
@@ -179,6 +174,8 @@ def get_data():
     ucity_id = list(set(df["ucity_id"].values.tolist()))
     manufacturer = list(set(df["manufacturer"].values.tolist()))
     channel = list(set(df["channel"].values.tolist()))
+    print("before transform")
+    print(df.shape)
 
     return df,validate_date,ucity_id,ccity_name,manufacturer,channel
 
@@ -187,22 +184,24 @@ def transform(a,validate_date):
     model = multiFFMFormatPandas()
     df = model.fit_transform(a, y="y", n=160000, processes=22)
     df = pd.DataFrame(df)
-    df["stat_date"] = df[0].apply(lambda x: x.split(",")[0])
-    df["device_id"] = df[0].apply(lambda x: x.split(",")[1])
-    df["y"] = df[0].apply(lambda x: x.split(",")[2])
-    df["z"] = df[0].apply(lambda x: x.split(",")[3])
-    df["number"] = np.random.randint(1, 2147483647, df.shape[0])
-    df["seq"] = list(range(df.shape[0]))
-    df["seq"] = df["seq"].astype("str")
-    df["data"] = df[0].apply(lambda x: ",".join(x.split(",")[2:]))
-    df["data"] = df["seq"].str.cat(df["data"], sep=",")
-    df = df.drop([0,"seq"], axis=1)
-    print(df.head(2))
-
-    train = df[df["stat_date"] != validate_date]
-    train = train.drop("stat_date",axis=1)
-    test = df[df["stat_date"] == validate_date]
-    test = test.drop("stat_date",axis=1)
+    print("after transform")
+    print(df.shape)
+    # df["stat_date"] = df[0].apply(lambda x: x.split(",")[0])
+    # df["device_id"] = df[0].apply(lambda x: x.split(",")[1])
+    # df["y"] = df[0].apply(lambda x: x.split(",")[2])
+    # df["z"] = df[0].apply(lambda x: x.split(",")[3])
+    # df["number"] = np.random.randint(1, 2147483647, df.shape[0])
+    # df["seq"] = list(range(df.shape[0]))
+    # df["seq"] = df["seq"].astype("str")
+    # df["data"] = df[0].apply(lambda x: ",".join(x.split(",")[2:]))
+    # df["data"] = df["seq"].str.cat(df["data"], sep=",")
+    # df = df.drop([0,"seq"], axis=1)
+    # print(df.head(2))
+
+    # train = df[df["stat_date"] != validate_date]
+    # train = train.drop("stat_date",axis=1)
+    # test = df[df["stat_date"] == validate_date]
+    # test = test.drop("stat_date",axis=1)
     # print("train shape")
     # print(train.shape)
     # train.to_csv(path + "tr.csv", sep="\t", index=False)