Hamilton with a single value node

my_functions.py

# --- my_functions.py
import pandas as pd


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 single_avg(spend: pd.Series) -> float:
    """Function that returns a single value"""
    return spend.mean()


def spend_per_sigup_time_average(single_avg: float, spend_per_signup: pd.Series) -> pd.Series:
    """Function that uses an intermediary single value as input"""
    return single_avg * spend_per_signup

my_script.py

# --- my_script.py -- Run this
import importlib
import logging
import sys

import pandas as pd
from hamilton import driver

logger = logging.getLogger(__name__)
logging.basicConfig(stream=sys.stdout)
initial_columns = {  # load from actuals or wherever -- this is our initial data we use as input.
    'signups': pd.Series([1, 10, 50, 100, 200, 400]),
    'spend': pd.Series([10, 10, 20, 40, 40, 50]),
}
# we need to tell hamilton where to load function definitions from
module_name = 'my_functions'
module = importlib.import_module(module_name)
dr = driver.Driver(initial_columns, module)  # can pass in multiple modules
# we need to specify what we want in the final dataframe.
output_columns = [
    'spend',
    'signups',
    'avg_3wk_spend',
    'spend_per_signup',
    'spend_per_sigup_time_average' # <--- this is the column we want.
]
# let's create the dataframe!
df = dr.execute(output_columns, display_graph=True)
print(df)