reduce_memory.py

import numpy as np
import pandas as pd
from pandas.api.types import is_numeric_dtype
from pandas.core.base import PandasObject

data_int = pd.read_csv('/kaggle/input/icr-integer-data/train_integerized.csv')

def reduce_memory(df, threshold_str = 0.5):
    start_mem = df.memory_usage().sum() / 1024**2
    print(f'Memory usage of dataframe is {start_mem:.2f} MB')

    for col in df.columns:
        col_type = df[col].dtype

        if col_type != 'object' and col_type != 'category':
            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)
                elif 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) 
        elif col_type == 'object':
            num_unique_values = len(df[col].unique())
            num_total_values = len(df[col])
            if num_unique_values / num_total_values < threshold_str:
                df[col] = df[col].astype('category')

    end_mem = df.memory_usage().sum() / 1024**2
    print(f'Memory usage after optimization is: {end_mem:.2f} MB')
    print(f'Decreased by {100 * (start_mem - end_mem) / start_mem:.1f}%')

    return df

PandasObject.reduce_memory = reduce_memory

data_int = data_int.reduce_memory()