减少pandas数据集所占内存
在kaggle竞赛中,经常会遇到几百甚至上千M的数据,如果用pandas的read_csv直接读取,数据类型一般会被默认为float64或float32,最终导致内存占用太多,计算处理速度变慢或程序被迫停止。
可以使用以下函数对其内存进行缩减,删去不必要的数据。
from pandas.api.types import is_datetime64_any_dtype as is_datetime
from pandas.api.types import is_categorical_dtype
def reduce_mem_usage(df, use_float16=False):
""" iterate through all the columns of a dataframe and modify the data type
to reduce memory usage.
"""
start_mem = df.memory_usage().sum() / 1024**2
print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))
for col in df.columns:
if is_datetime(df[col]) or is_categorical_dtype(df[col]):
# skip datetime type or categorical type
continue
col_type = df[col].dtype
if col_type != object:
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 use_float16 and 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)
else:
df[col] = df[col].astype('category')
end_mem = df.memory_usage().sum() / 1024**2
print('Memory usage after optimization is: {:.2f} MB'.format(end_mem))
print('Decreased by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))