1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58

# Automated feature engineering example
import featuretools as ft
import pandas as pd

# Create sample transaction data
customers = pd.DataFrame({
    'customer_id': [1, 2, 3],
    'join_date': pd.to_datetime(['2020-01-01', '2020-02-01', '2020-03-01']),
    'age': [25, 35, 45]
})

transactions = pd.DataFrame({
    'transaction_id': range(1, 11),
    'customer_id': [1, 1, 2, 2, 2, 3, 3, 3, 3, 3],
    'amount': [10, 25, 15, 30, 20, 50, 35, 40, 25, 60],
    'timestamp': pd.date_range('2020-01-15', periods=10, freq='7D')
})

# Create entity set
es = ft.EntitySet(id='customer_data')

# Add entities
es = es.add_dataframe(
    dataframe_name='customers',
    dataframe=customers,
    index='customer_id',
    time_index='join_date'
)

es = es.add_dataframe(
    dataframe_name='transactions',
    dataframe=transactions,
    index='transaction_id',
    time_index='timestamp'
)

# Add relationship
relationship = ft.Relationship(
    parent_dataframe_name='customers',
    parent_column_name='customer_id',
    child_dataframe_name='transactions',
    child_column_name='customer_id'
)
es = es.add_relationship(relationship)

# Automatically generate features
feature_matrix, feature_defs = ft.dfs(
    entityset=es,
    target_dataframe_name='customers',
    max_depth=2
)

print("Generated features:")
for feature in feature_defs:
    print(f"- {feature}")

print("\nFeature matrix:")
print(feature_matrix)