sagemaker_datawrangler_apply_flow_to_pandas_dataframe.py

1import pandas as pd
2import sagemaker_datawrangler
3
4# Load your dataset
5df = pd.read_csv("your_dataset.csv")
6
7# Path to your SageMaker Data Wrangler flow file (.flow)
8# This file is exported from the SageMaker Studio Data Wrangler UI
9flow_path = "example.flow"
10
11# Apply the Data Wrangler flow to your local DataFrame
12# The sagemaker-datawrangler library patches pandas to include the 'wrangle' method
13wrangled_df, flow_report = df.wrangle(flow_path=flow_path)
14
15# Display the transformed data
16print(wrangled_df.head())
17
18# Optional: Review the flow report for information about the transformations applied
19print(flow_report)