Transform

transform.py

"""Provides optional transform functions for different data sources."""

import pandas as pd


def nyt_cases_counties(df):
    """Transforms NYT county-level COVID data"""
    # Cast date as datetime
    df['date'] = pd.to_datetime(df['date'])
    # Store FIPS codes as standard 5 digit strings
    df['fips'] = df['fips'].astype(str).str.extract('(.*)\.', expand=False).str.zfill(5)
    # Drop Puerto Rico due to missing deaths data, cast deaths to int
    df = df.loc[df['state'] != 'Puerto Rico'].copy()
    df['deaths'] = df['deaths'].astype(int)
    return df

# Script truncated for Medium