machine learning in python：根据关键字合并多个表（构建组合feature）

三张表；train_set.csv；test_set.csv；feature.csv。三张表通过object_id关联。

<pre name="code" class="python"><strong><span style="font-size:18px;">import pandas as pd
import numpy as np

# load training and test datasets
train = pd.read_csv('../input/train_set.csv')
test = pd.read_csv('../input/test_set.csv')
features = pd.read_csv('../input/feature.csv')
train = pd.merge(train,features,on='object_id',how='inner')
test = pd.merge(test,features,on='object_id',how='inner')

# drop useless columns and create labels
test = test.drop(['id', 'object_id'], axis = 1)
labels = train.cost.values
train = train.drop(['object_id', 'cost'], axis = 1)</span></strong>

版权声明：本文为博主原创文章，未经博主允许不得转载。