fix sql bug

diaryTraining.py

 import xlearn as xl
 from config import *
-from diaryCandidateSet import get_eachCityDiaryTop2000
 
-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))
 
-param = {'task': 'binary', 'lr': lr, 'lambda': l2_lambda, 'metric': 'auc'}
+def train():
+    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))
 
-ffm_model.fit(param, DIRECTORY_PATH + "model_{0}-{1}_lr{2}_lambda{3}.out".format(DATA_START_DATE,
-                                                                                 DATA_END_DATE, lr, l2_lambda))
+    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))
+
+    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, 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, 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, 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, lr,
-                                                                                                l2_lambda))
 
-print('---------------candidates--------------')
-get_eachCityDiaryTop2000()

readme.txt

+(1) 在服务器上创建nvwa隔离环境：
+ssh -A gaoyazhe@bastion.prod.gengmei
+rank-compute01
+virtualenv -p /usr/bin/python3 nvwa
+source nvwa/bin/activate
+(2) 在nvwa中安装xlearn：
+#参考链接：http://xlearn-doc.readthedocs.io/en/latest/install.html
+cd nvwa
+git clone https://github.com/aksnzhy/xlearn.git
+cd xlearn
+./build.sh
+(3) 在nvwa中安装相关工具包：
+pip install pymysql
+pip install numpy
+sudo apt-get install python3-dev
+pip install pandas
+问题：
+#安装pandas出错：Python.h: No such file or directory
+#解决方案：sudo apt-get install python3-dev
+pip install scipy
+pip install scikit-learn
+pip uninstall numpy
+pip install numpy==1.14.5
+问题：
+#import sklearn出错：RuntimeWarning: numpy.dtype size changed, may indicate binary incompatibility
+#解决方案：pip uninstall numpy；pip install numpy==1.14.5
+(4) requirements:
+pymysql=='0.9.2'
+numpy=='1.14.5'
+pandas=='0.22.0'
+scipy=='1.1.0'
+sklearn=='0.19.2'
\ No newline at end of file

train.py

+from processData import *
+from diaryTraining import *
+from diaryCandidateSet import get_eachCityDiaryTop2000
+
+
+# 把数据获取、特征转换、模型训练的模型串联在一起
+if __name__ == "__main__":
+    data_fe = feature_en()
+    ffm_transform(data_fe)
+    train()
+    print('---------------prepare candidates--------------')
+    get_eachCityDiaryTop2000()
+

userProfile.py

@@ -3,6 +3,7 @@ from utils import con_sql
 
 def fetch_user_profile(device_id):
     # TODO sql语句中的device_id可能对应多个city_id
-    sql = "select device_id,city_id from data_feed_click limit 1"
+    sql = "select device_id,city_id from " \
+          "data_feed_click where device_id = '{0}' limit 1".format(device_id)
     user_profile = con_sql(sql)
     return user_profile, user_profile.empty