fix bugs

config.py

@@ -6,5 +6,10 @@ DATA_START_DATE = '2018-07-05'
 DATA_END_DATE = '2018-08-06'
 
 MODEL_VERSION = ''
+
+
+lr = 0.03
+l2_lambda = 0.002
+
 # processData.py
 # diaryTraining.py

diaryTraining.py

@@ -6,22 +6,21 @@ print("Start training")
 ffm_model = xl.create_ffm()
 ffm_model.setTrain(DIRECTORY_PATH + "train{0}-{1}.csv".format(DATA_START_DATE, VALIDATION_DATE))
 ffm_model.setValidate(DIRECTORY_PATH + "validation{0}.csv".format(VALIDATION_DATE))
-lr =0.03
-l2_lambda = 0.002
-param = {'task': 'binary', 'lr': lr, 'lambda': l2_lambda, 'metric': 'auc'}
 
+param = {'task': 'binary', 'lr': lr, 'lambda': l2_lambda, 'metric': 'auc'}
 
 ffm_model.fit(param, DIRECTORY_PATH + "model_{0}-{1}_lr{2}_lambda{3}.out".format(DATA_START_DATE,
-              DATA_END_DATE,lr,l2_lambda))
+                                                                                 DATA_END_DATE, lr, l2_lambda))
 
 print("predicting")
 ffm_model.setTest(DIRECTORY_PATH + "test{0}.csv".format(TEST_DATE))
 ffm_model.setSigmoid()
 ffm_model.predict(DIRECTORY_PATH + "model_{0}-{1}_lr{2}_lambda{3}.out".format(DATA_START_DATE,
-                  DATA_END_DATE,"0.03","0.002"),
+                                                                              DATA_END_DATE, lr, l2_lambda),
                   DIRECTORY_PATH + "testset{0}_output_model_{1}-{2}_lr{3}_lambda{4}.txt".format(TEST_DATE,
-                                            DATA_START_DATE,DATA_END_DATE,"0.03","0.002"))
-
+                                                                                                DATA_START_DATE,
+                                                                                                DATA_END_DATE, lr,
+                                                                                                l2_lambda))
 
 print('---------------candidates--------------')
 get_eachCityDiaryTop2000()

processData.py

@@ -53,7 +53,7 @@ def feature_en():
     print(data.head(2))
 
     # 持久化候选cid
-    data_set_cid = data[["cid"]].unique()
+    data_set_cid = data["cid"].unique()
     cid_df = pd.DataFrame()
     cid_df['cid'] = data_set_cid
     print("data_set_cid :")

userDiaryPredict.py

@@ -13,6 +13,7 @@ from userProfile import fetch_user_profile
 def device_id_merge(user_profile):
     file_name = DIRECTORY_PATH + "diaryTestSet/{0}DiaryTop2000.csv".format(user_profile['city_id'])
     data = pd.read_csv(file_name)
+
     data["device_id"] = user_profile['device_id']
     now = datetime.datetime.now()
     data["hour"] = now.hour
@@ -22,49 +23,49 @@ def device_id_merge(user_profile):
     data["hour"] = data["hour"].astype("category")
     data["minute"] = data["minute"].astype("category")
     data["y"] = 0
-    data = data.drop("city_id",axis=1)
+    data = data.drop("city_id", axis=1)
     print(data.head(2))
+
     return data
 
 
 # 把ffm.pkl load进来，将上面的表转化为ffm格式
-def transform_ffm_format(ffm_format_pandas, df, device_id):
-    data = ffm_format_pandas.transform(df)
-    now = datetime.datetime.now().strftime("%Y-%m-%d-%H-%M")
+def transform_ffm_format(df, device_id):
+    file_path = DIRECTORY_PATH + "ffm_{0}_{1}.pkl".format(DATA_START_DATE, DATA_END_DATE)
+    with open(file_path, "rb") as f:
+        ffm_format_pandas = pickle.load(f)
+        data = ffm_format_pandas.transform(df)
+        now = datetime.datetime.now().strftime("%Y-%m-%d-%H-%M")
 
-    predict_file_name = DIRECTORY_PATH + "diaryPredictSet/{0}_{1}DiaryTop2000.csv".format(device_id, now)
-    data.to_csv(predict_file_name)
-    user_instance_file_path = ''
-    return user_instance_file_path
+        predict_file_name = DIRECTORY_PATH + "diaryPredictSet/{0}_{1}DiaryTop2000.csv".format(device_id, now)
+        data.to_csv(predict_file_name)
+        user_instance_file_path = ''
+        return user_instance_file_path
 
 
 # 将模型加载，预测，把预测日记的概率值按照降序排序，存到一个表里
 def predict(user_profile):
     ffm_model = xl.create_ffm()
 
-    user_instance_file_path = device_id_merge(device_id)
+    user_instance = device_id_merge(user_profile)
+    user_instance_file_path = transform_ffm_format(user_instance)
 
     ffm_model.setTest(user_instance_file_path)
-    ffm_model.predict(DIRECTORY_PATH + MODEL_VERSION, "./{0}_output.txt".format(device_id))
+    ffm_model.predict(DIRECTORY_PATH + "model_{0}-{1}_lr{2}_lambda{3}.out".format(DATA_START_DATE,
+                                                                                  DATA_END_DATE, lr, l2_lambda),
+                      DIRECTORY_PATH + "/{0}_output.txt".format(user_profile['device_id']))
 
 
 def router(device_id):
     user_profile, is_exist = fetch_user_profile(device_id)
 
-    file_path = DIRECTORY_PATH + "ffm_{0}_{1}.pkl".format(DATA_START_DATE, DATA_END_DATE)
-    with open(file_path, "rb") as f:
-        ffm_format_pandas = pickle.load(f)
-
-
     if is_exist:
-        predict()
+        predict(user_profile)
     else:
-        pass # do something
+        print('Sorry, we don\'t have you')
 
 
 if __name__ == "__main__":
-
     router(device_id='358035085192742')
 
-
 # 预测一些真实的device_id