2020-11-23

推荐算法1

baseline

节约内存的一个标配函数

def reduce_mem(df):
starttime = time.time()
numerics = [‘int16’, ‘int32’, ‘int64’, ‘float16’, ‘float32’, ‘float64’]
start_mem = df.memory_usage().sum() / 10242
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 pd.isnull(c_min) or pd.isnull(c_max):
continue
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() / 10242
print(’-- Mem. usage decreased to {:5.2f} Mb ({:.1f}% reduction),time spend:{:2.2f} min’.format(end_mem,
100*(start_mem-end_mem)/start_mem,
(time.time()-starttime)/60))
return df