Wydajne typy danych do redukcji pamięci

Dlaczego typy danych wpływają na wydajność

import pandas as pd
import numpy as np

np.random.seed(0)
df = pd.DataFrame({
    'id': np.arange(1000000, dtype='int64'),
    'score': np.random.uniform(0, 100, 1000000).astype('float64'),
    'category': np.random.choice(['A','B','C','D'], 1000000)
})

mem = df.memory_usage(deep=True)
print('Memory per column:')
print(mem)
print(f'Total: {mem.sum() / 1e6:.1f} MB')

Zmniejszanie typu kolumn całkowitoliczbowych

import pandas as pd
import numpy as np

np.random.seed(0)
df = pd.DataFrame({
    'age': np.random.randint(18, 90, 500000).astype('int64'),
    'score': np.random.randint(0, 100, 500000).astype('int64'),
    'large_id': np.random.randint(0, 2**31, 500000).astype('int64')
})

# Downcast integers
for col in df.select_dtypes('int64').columns:
    df[col] = pd.to_numeric(df[col], downcast='integer')

print('Dtypes after downcasting:')
print(df.dtypes)
print(f'\nMemory: {df.memory_usage(deep=True).sum()/1e6:.2f} MB')

Zmniejszanie typu kolumn zmiennoprzecinkowych

import pandas as pd
import numpy as np

np.random.seed(0)
df = pd.DataFrame({'lat': np.random.uniform(-90, 90, 1000000),
                   'lon': np.random.uniform(-180, 180, 1000000),
                   'temp': np.random.uniform(-40, 50, 1000000)})

print('Before:', df.dtypes.unique())
print(f'Memory: {df.memory_usage(deep=True).sum()/1e6:.1f} MB')

for col in df.select_dtypes('float64').columns:
    df[col] = pd.to_numeric(df[col], downcast='float')

print('After:', df.dtypes.unique())
print(f'Memory: {df.memory_usage(deep=True).sum()/1e6:.1f} MB')

Typ danych Categorical

import pandas as pd
import numpy as np

np.random.seed(0)
categories = ['Electronics', 'Clothing', 'Books', 'Food', 'Furniture',
              'Sports', 'Toys', 'Health', 'Garden', 'Automotive']

df = pd.DataFrame({'product_cat': np.random.choice(categories, 1000000)})

mem_before = df.memory_usage(deep=True).sum()
df['product_cat'] = df['product_cat'].astype('category')
mem_after = df.memory_usage(deep=True).sum()

print(f'Object dtype: {mem_before/1e6:.1f} MB')
print(f'Categorical:  {mem_after/1e6:.2f} MB')
print(f'Reduction: {mem_before/mem_after:.0f}x')

Kiedy Categorical oszczędza pamięć

import pandas as pd
import numpy as np

def memory_gain(df, col):
    n = len(df)
    n_unique = df[col].nunique()
    ratio = n_unique / n
    mem_obj = df[col].memory_usage(deep=True)
    df2 = df.copy()
    df2[col] = df2[col].astype('category')
    mem_cat = df2[col].memory_usage(deep=True)
    print(f'{col}: {n_unique} unique / {n} total (ratio={ratio:.3f})')
    print(f'  Object: {mem_obj/1e6:.2f} MB → Categorical: {mem_cat/1e6:.2f} MB')
    print(f'  {"Saves" if mem_cat < mem_obj else "Wastes"} {abs(mem_obj-mem_cat)/1e6:.2f} MB')

np.random.seed(0)
df = pd.DataFrame({
    'low_card': np.random.choice(['A','B','C'], 500000),   # low cardinality
    'high_card': [f'id_{i}' for i in range(500000)]         # high cardinality
})
memory_gain(df, 'low_card')
memory_gain(df, 'high_card')

Categorical zwiększa wydajność GroupBy

import pandas as pd
import numpy as np
import timeit

np.random.seed(0)
df = pd.DataFrame({
    'region': np.random.choice(['North','South','East','West'], 1000000),
    'sales': np.random.randn(1000000)
})

# Object dtype groupby
t1 = timeit.timeit(lambda: df.groupby('region')['sales'].mean(), number=50)

# Categorical dtype groupby
df2 = df.copy()
df2['region'] = df2['region'].astype('category')
t2 = timeit.timeit(lambda: df2.groupby('region')['sales'].mean(), number=50)

print(f'Object dtype groupby: {t1/50*1000:.2f} ms')
print(f'Categorical groupby:  {t2/50*1000:.2f} ms')
print(f'Speedup: {t1/t2:.1f}x')

Używanie typu boolean dla kolumn flag

import pandas as pd
import numpy as np

np.random.seed(0)
df = pd.DataFrame({
    'is_premium': np.random.choice([0, 1], 1000000).astype('int64'),
    'has_discount': np.random.choice(['yes', 'no'], 1000000)
})

print('Before:')
print(df.dtypes)
print(f'Memory: {df.memory_usage(deep=True).sum()/1e6:.1f} MB')

df['is_premium'] = df['is_premium'].astype(bool)
df['has_discount'] = df['has_discount'].map({'yes': True, 'no': False}).astype(bool)

print('\nAfter:')
print(df.dtypes)
print(f'Memory: {df.memory_usage(deep=True).sum()/1e6:.2f} MB')

Automatyzacja optymalizacji typów

import pandas as pd
import numpy as np

def optimise_dtypes(df, cat_threshold=0.5):
    '''Reduce DataFrame memory by choosing smaller dtypes.'''
    for col in df.columns:
        col_type = df[col].dtype
        if col_type == 'int64':
            df[col] = pd.to_numeric(df[col], downcast='integer')
        elif col_type == 'float64':
            df[col] = pd.to_numeric(df[col], downcast='float')
        elif col_type == 'object':
            cardinality = df[col].nunique() / len(df)
            if cardinality < cat_threshold:
                df[col] = df[col].astype('category')
    return df

# Test
np.random.seed(0)
df = pd.DataFrame({'a': np.random.randint(0,100,500000),
                   'b': np.random.randn(500000),
                   'c': np.random.choice(['X','Y','Z'],500000)})

before = df.memory_usage(deep=True).sum()
df = optimise_dtypes(df)
after = df.memory_usage(deep=True).sum()
print(f'Before: {before/1e6:.2f} MB → After: {after/1e6:.2f} MB ({before/after:.1f}x reduction)')

Typy liczb całkowity bez znaku dla danych nieujemnych

import pandas as pd
import numpy as np

np.random.seed(0)
df = pd.DataFrame({
    'product_id': np.random.randint(0, 50000, 1000000).astype('int64'),
    'quantity': np.random.randint(0, 255, 1000000).astype('int64')
})

print('Before (int64):', df.memory_usage(deep=True).sum() / 1e6, 'MB')

# product_id fits in uint16 (0-65535)
df['product_id'] = df['product_id'].astype('uint16')
# quantity fits in uint8 (0-255)
df['quantity'] = df['quantity'].astype('uint8')

print('After (uint16+uint8):', df.memory_usage(deep=True).sum() / 1e6, 'MB')
print('\nDtypes:', df.dtypes.to_dict())

Sprawdzanie pamięci po każdym kroku optymalizacji

import pandas as pd
import numpy as np

np.random.seed(0)
df = pd.DataFrame({
    'user_id': np.random.randint(0, 99999, 1000000).astype('int64'),
    'age': np.random.randint(18, 80, 1000000).astype('int64'),
    'revenue': np.random.uniform(0, 5000, 1000000).astype('float64'),
    'country': np.random.choice(['US','UK','DE','FR','JP'], 1000000),
    'tier': np.random.choice(['free','basic','pro','enterprise'], 1000000)
})

def mem_mb(df):
    return df.memory_usage(deep=True).sum() / 1e6

print(f'Start: {mem_mb(df):.1f} MB')

for c in ['user_id','age']:
    df[c] = pd.to_numeric(df[c], downcast='integer')
print(f'After int downcast: {mem_mb(df):.1f} MB')

df['revenue'] = pd.to_numeric(df['revenue'], downcast='float')
print(f'After float downcast: {mem_mb(df):.1f} MB')

for c in ['country','tier']:
    df[c] = df[c].astype('category')
print(f'After Categorical: {mem_mb(df):.1f} MB')

Zapisywanie i ponowne wczytywanie zoptymalizowanych typów

import pandas as pd
import numpy as np

np.random.seed(0)
df = pd.DataFrame({
    'age': np.random.randint(18, 80, 100000).astype('int8'),   # already optimised
    'score': np.random.randn(100000).astype('float32'),
    'tier': pd.Categorical(np.random.choice(['free','pro'], 100000))
})
print('Dtypes:', df.dtypes.to_dict())

# Save to Parquet (preserves dtypes)
df.to_parquet('/tmp/optimised.parquet', index=False)

# Reload — dtypes preserved!
df_loaded = pd.read_parquet('/tmp/optimised.parquet')
print('\nLoaded dtypes:', df_loaded.dtypes.to_dict())
print(f'Memory: {df_loaded.memory_usage(deep=True).sum()/1e6:.2f} MB')

Szybki sprawdzian

Podsumowanie lekcji