python数据分析之DataFrame内存优化

#方法1 就是使用查看dataframe信息的命令
user_log.info()
#方法2 使用memory_usage()或者getsizeof(user_log)
import time
import sys
print('all_data占据内存约: {:.2f} GB'.format(user_log.memory_usage().sum()/ (1024**3)))
print('all_data占据内存约: {:.2f} GB'.format(sys.getsizeof(user_log)/(1024**3)))

def reduce_mem_usage(df):
    starttime = time.time()
    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 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() / 1024**2
    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

#首先读取到csv中如何传入函数生称新的csv
user_log2=reduce_mem_usage(pd.read_csv(r'/Users/liucong/MainFiles/ML/tianchi/tianmiao/user_log_format1.csv'))