修改ffm多进程方法

utils.py

@@ -89,7 +89,7 @@ class multiFFMFormatPandas:
 
         return self
 
-    def fit_transform(self, df, y=None,n=10000,processes=5):
+    def fit_transform(self, df, y=None,n=1000000,processes=6):
         # n是每个线程运行最大的数据条数,processes是线程数
         self.fit(df, y)
         n = n
@@ -112,7 +112,7 @@ class multiFFMFormatPandas:
                 ffm.append('{}:{}:{}'.format(self.field_index_[col], self.feature_index_[col], val))
         return ' '.join(ffm)
 
-    def transform(self, df,n=10000,processes=1):
+    def transform(self, df,n=10000,processes=2):
         # n是每个线程运行最大的数据条数,processes是线程数
         t = df.dtypes.to_dict()
         data_list = self.data_split_line(df,n)
@@ -120,11 +120,12 @@ class multiFFMFormatPandas:
         # 设置进程的数量
         pool = Pool(processes)
         print("总进度: " + str(len(data_list)))
-        result_map = {}
         for i in range(len(data_list)):
             data_list[i] = pool.apply_async(self.pool_function, (data_list[i], t,))
-            result_map.update(data_list[i].get())
 
+        result_map = {}
+        for i in data_list:
+            result_map.update(i.get())
         pool.close()
         pool.join()