hello_world

To get started:

Dynamically pull and run

from hamilton import dataflows, driver
# downloads into ~/.hamilton/dataflows and loads the module -- WARNING: ensure you know what code you're importing!
hello_world = dataflows.import_module("hello_world", "skrawcz")
dr = (
    driver.Builder()
    .with_config({})  # replace with configuration as appropriate
    .with_modules(hello_world)
    .build()
)
# If you have sf-hamilton[visualization] installed, you can see the dataflow graph
# In a notebook this will show an image, else pass in arguments to save to a file
# dr.display_all_functions()
# Execute the dataflow, specifying what you want back. Will return a dictionary.
result = dr.execute(
    [hello_world.CHANGE_ME, ...],  # this specifies what you want back
    inputs={...}  # pass in inputs as appropriate
)

Use published library version

pip install sf-hamilton-contrib --upgrade  # make sure you have the latest

from hamilton import dataflows, driver
# Make sure you've done - `pip install sf-hamilton-contrib --upgrade`
from hamilton.contrib.user.skrawcz import hello_world
dr = (
    driver.Builder()
    .with_config({})  # replace with configuration as appropriate
    .with_modules(hello_world)
    .build()
)
# If you have sf-hamilton[visualization] installed, you can see the dataflow graph
# In a notebook this will show an image, else pass in arguments to save to a file
# dr.display_all_functions()
# Execute the dataflow, specifying what you want back. Will return a dictionary.
result = dr.execute(
    [hello_world.CHANGE_ME, ...],  # this specifies what you want back
    inputs={...}  # pass in inputs as appropriate
)

Modify for your needs

Now if you want to modify the dataflow, you can copy it to a new folder (renaming is possible), and modify it there.

dataflows.copy(hello_world, "path/to/save/to")

---

Purpose of this module

This module implements a hello world dataflow to show transforming columns from a dataframe.

You can pass in your own values for spend & signups, or use the default.

Configuration Options

This module can be configured with the following options:

• {"default": "True"} to run it without any inputs.
• {} to have to pass in spend and signups.

Limitations

None to really note.

Source code

__init__.py

import logging

logger = logging.getLogger(__name__)

from hamilton import contrib

with contrib.catch_import_errors(__name__, __file__, logger):
    import pandas as pd

from hamilton.function_modifiers import config, extract_columns


@extract_columns("spend", "signups")
@config.when(default="True")
def default_data() -> pd.DataFrame:
    return pd.DataFrame(
        {
            "signups": pd.Series([1, 10, 50, 100, 200, 400]),
            "spend": pd.Series([10, 10, 20, 40, 40, 50]),
        }
    )


def avg_3wk_spend(spend: pd.Series) -> pd.Series:
    """Rolling 3 week average spend."""
    return spend.rolling(3).mean()


def spend_per_signup(spend: pd.Series, signups: pd.Series) -> pd.Series:
    """The cost per signup in relation to spend."""
    return spend / signups


def spend_mean(spend: pd.Series) -> float:
    """Shows function creating a scalar. In this case it computes the mean of the entire column."""
    return spend.mean()


def spend_zero_mean(spend: pd.Series, spend_mean: float) -> pd.Series:
    """Shows function that takes a scalar. In this case to zero mean spend."""
    return spend - spend_mean


def spend_std_dev(spend: pd.Series) -> float:
    """Function that computes the standard deviation of the spend column."""
    return spend.std()


def spend_zero_mean_unit_variance(spend_zero_mean: pd.Series, spend_std_dev: float) -> pd.Series:
    """Function showing one way to make spend have zero mean and unit variance."""
    return spend_zero_mean / spend_std_dev


if __name__ == "__main__":
    # run as a script to test Hamilton's execution
    import __init__ as hello_world

    from hamilton import base, driver

    dr = driver.Driver(
        {"default": "True"},
        hello_world,
        adapter=base.DefaultAdapter(),
    )
    # create the DAG image
    dr.display_all_functions("dag", {"format": "png", "view": False})

Requirements

pandas