pandas读取文件后,可能因为文件存储空间过大,在普通的笔记本电脑上不易操作。在kaggle上学到了一种减少存储空间的方法,现记录如下:
print('Training Set Memory Usage = {:.2f} MB'.format(df_train.memory_usage().sum() / 1024**2))#计算mermory {:.2f}为保存小数点后两位
减小内存的函数如下:
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]):
continue
col_type = df[col].dtype
if col_type != object: #dataframe中的str类型为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")