ffm转化累计相加

eda/esmm/Feature_pipline/data2ffm.py

@@ -38,6 +38,10 @@ class multiFFMFormatPandas:
         self.y = None
 
     def fit(self, df, y=None):
+        b = df.dtypes
+        c = list(b.values)
+        d =tuple(df.dtypes.to_dict())
+        f = dict(zip(d,c))
         self.y = y
         df_ffm = df[df.columns.difference([self.y])]
         if self.field_index_ is None:
@@ -49,19 +53,24 @@ class multiFFMFormatPandas:
         if self.feature_index_ is None:
             self.feature_index_ = dict()
 
-        for col in df.columns:
-            self.feature_index_[col] = 1
-            last_idx = 1
-            vals = list(df[col].unique())
-            vals.append("na")
-            vals = set(vals)
-            for val in vals:
-                if pd.isnull(val):
-                    continue
-                name = '{}_{}'.format(col, val)
-                if name not in self.feature_index_:
-                    self.feature_index_[name] = last_idx
-                    last_idx += 1
+        last_idx = 1
+        l = list(df.columns)
+        l.remove(y)
+        for col in l:
+            if f[col]=="O":
+                vals = list(df[col].unique())
+                vals.append("na")
+                vals = set(vals)
+                for val in vals:
+                    if pd.isnull(val):
+                        continue
+                    name = '{}_{}'.format(col, val)
+                    if name not in self.feature_index_:
+                        self.feature_index_[name] = last_idx
+                        last_idx += 1
+            else:
+                self.feature_index_[col] = last_idx
+                last_idx += 1
         return self
 
     def fit_transform(self, df, y=None,n=50000,processes=4):
@@ -131,14 +140,6 @@ class multiFFMFormatPandas:
             return pd.Series({idx: self.transform_row_(row, t) for idx, row in df.iterrows()})
 
 
-    # 下面这个方法不是这个类原有的方法，是新增的。目的是用来判断这个用户是不是在训练数据集中存在
-    def is_feature_index_exist(self, name):
-        if name in self.feature_index_:
-            return True
-        else:
-            return False
-
-
 def get_data():
     db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
     sql = "select max(stat_date) from esmm_train_data"