add test file

tensnsorflow/test.py

 import json
+import numpy as np
 from pyspark import SparkContext
 from pyspark.sql import SQLContext
 import pandas as pd
 from pyspark import  SparkConf
 from multiprocessing import Pool
+import pymysql
 class multiFFMFormatPandas:
     def __init__(self):
         self.field_index_ = None
@@ -24,17 +26,6 @@ class multiFFMFormatPandas:
             self.feature_index_ = dict()
             last_idx = 0
 
-        for col in df.columns:
-            vals = df[col].unique()
-            for val in vals:
-                if pd.isnull(val):
-        if self.feature_index_ is not None:
-            last_idx = max(list(self.feature_index_.values()))
-
-        if self.feature_index_ is None:
-            self.feature_index_ = dict()
-            last_idx = 0
-
         for col in df.columns:
             vals = df[col].unique()
             for val in vals:
@@ -121,6 +112,17 @@ class multiFFMFormatPandas:
                 data_list.append(data.iloc[x:data.__len__()])
                 break
 
+        '''
+        # 返回生成器方法，但是本地测试效率不高
+        x = 0
+        while True:
+            if x + step < data.__len__():
+                yield data.iloc[x:x + step]
+                x = x + step + 1
+            else:
+                yield data.iloc[x:data.__len__()]
+                break
+        '''
 
         return data_list