featuretools实例

### 创建数据框
import pandas as pd

# First dataset contains the basic information for databases.
databases_df = pd.DataFrame({"database_id": [2234, 1765, 8796, 2237, 3398],
"creation_date": ["2018-02-01", "2017-03-02", "2017-05-03", "2013-05-12", "2012-05-09"]})
db_transactions_df = pd.DataFrame({"transaction_id": [26482746, 19384752, 48571125, 78546789, 19998765, 26482646, 12484752, 42471125, 75346789, 16498765, 65487547, 23453847, 56756771, 45645667, 23423498, 12335268, 76435357, 34534711, 45656746, 12312987],
                "database_id": [2234, 1765, 2234, 2237, 1765, 8796, 2237, 8796, 3398, 2237, 3398, 2237, 2234, 8796, 1765, 2234, 2237, 1765, 8796, 2237],
                "transaction_size": [10, 20, 30, 50, 100, 40, 60, 60, 10, 20, 60, 50, 40, 40, 30, 90, 130, 40, 50, 30],
                "transaction_date": ["2018-02-02", "2018-03-02", "2018-03-02", "2018-04-02", "2018-04-02", "2018-05-02", "2018-06-02", "2018-06-02", "2018-07-02", "2018-07-02", "2018-01-03", "2018-02-03", "2018-03-03", "2018-04-03", "2018-04-03", "2018-07-03", "2018-07-03", "2018-07-03", "2018-08-03", "2018-08-03"]})

db_transactions_df.head()

#### 创建实体，并且建立之间的关系
entities = {
"databases" : (databases_df, "database_id"),
"transactions" : (db_transactions_df, "transaction_id")
}
relationships = [("databases", "database_id", "transactions", "database_id")]

#### 自动特征工程
import featuretools as ft

feature_matrix_db_transactions, feature_defs = ft.dfs(entities=entities, relationships=relationships, target_entity="databases")