examples/aws/sagemaker/app/functions.py

# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements.  See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership.  The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License.  You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied.  See the License for the
# specific language governing permissions and limitations
# under the License.

import pandas as pd

from hamilton.function_modifiers import extract_columns


@extract_columns("spend", "signups")
def raw_table(input_table: pd.DataFrame) -> pd.DataFrame:
    return input_table


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