examples/model_examples/time-series/utils.py

import logging

import numpy as np
import pandas as pd

logger = logging.getLogger(__name__)


def reduce_mem_usage(df: pd.DataFrame, name: str, verbose=True):
    """Taken from the notebook, this reduces the memory of each column if possible by downcasting the type if it can.

    :param df:
    :param name:
    :param verbose:
    :return:
    """
    numerics = ["int16", "int32", "int64", "float16", "float32", "float64"]
    start_mem = df.memory_usage().sum() / 1024**2
    for col in df.columns:
        col_type = df[col].dtypes
        if col_type in numerics:

            c_min = df[col].min()
            c_max = df[col].max()
            if str(col_type)[:3] == "int":
                if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:
                    df[col] = df[col].astype(np.int8)
                elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:
                    df[col] = df[col].astype(np.int16)
                elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:
                    df[col] = df[col].astype(np.int32)
                elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:
                    df[col] = df[col].astype(np.int64)
            else:
                if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:
                    df[col] = df[col].astype(np.float16)
                if c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:
                    df[col] = df[col].astype(np.float32)
                else:
                    df[col] = df[col].astype(np.float64)
    end_mem = df.memory_usage().sum() / 1024**2
    if verbose:
        logger.info(
            "{}: Mem. usage decreased to {:5.2f} Mb ({:.1f}% reduction)".format(
                name, end_mem, 100 * (start_mem - end_mem) / start_mem
            )
        )
    return df