jeffmylife

.phony: all

all: push

# configuration setup
PROJECT_FILE_NAME=project.yml
CONFIG := python3 -c "import yaml; import json; from pathlib import Path; print(json.dumps(yaml.safe_load(Path(\"$(PROJECT_FILE_NAME)\").read_text())))"
OS := $(shell python3 -c "import platform; print(platform.system())")

# defaults

jeffmylife

import pandas as pd


def sample_dataframe(df, date_column, N):
    """
    Samples a pandas DataFrame to achieve a balanced representation across different date groups.

    This function ensures that smaller date groups (those with counts less than an average size)
    are fully represented in the sample. Larger date groups are sampled uniformly to contribute
    towards a total sample size of N. If the initial sampling process results in a total sample size