Created
February 23, 2020 04:10
-
-
Save Japkeerat/683e7dab1cbf30c44169e769e16f00f8 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
file = 'hotel_bookings.csv' | |
data = pd.read_csv(file) | |
def reduce_mem_usage(df): # Unknown Author | |
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) | |
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) | |
end_mem = df.memory_usage().sum() / 1024**2 | |
print('Mem. usage decreased to {:5.2f} Mb ({:.1f}% reduction)'.format(end_mem, 100 * (start_mem - end_mem) / start_mem)) | |
return df | |
data = reduce_mem_usage(data) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment