add exp

tensnsorflow/exp_channel.py

@@ -47,13 +47,25 @@ def clean():
     for i in manufacturer:
        if df.loc[df["manufacturer"]==i].shape[0]/n < 0.0005:
            df.loc[df["manufacturer"] == i,["manufacturer"]] = "other"
-    print(df["manufacturer"].unique())
     channel = df["channel"].unique()
     for i in channel:
         if df.loc[df["channel"] == i].shape[0] / n < 0.0001:
             df.loc[df["channel"] == i, ["channel"]] = "other"
+    from sqlalchemy import create_engine
+    yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@10.66.157.22:4000/jerry_test?charset=utf8')
+    n = 200000
+    for i in range(0,df.shape[0],n):
+        print(i)
+        if i == 0:
+            temp = df.loc[0:n]
+        elif i+n > df.shape[0]:
+            temp = df.loc[i+1:]
+        else:
+            temp = df.loc[i+1:i+n]
+        pd.io.sql.to_sql(temp, "user_feature_clean", yconnect, schema='jerry_test', if_exists='append', index=False)
+        print("insert done")
+
 
-    print(df["channel"].unique())
 
 
 if __name__ == "__main__":