python pandas处理大数据节省内存的方法
- 数值类型的列进行降级处理
- 字符串类型的列转化为类别类型(category)
- 字符串类型的列的类别数超过总行数的一半时,建议使用object类型
-
''' 减少内存的使用 ''' def reduce_mem_usage(df, verbose=True): numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64', 'object'] start_mem = df.memory_usage().sum() / 1024**2 if verbose:print "Memory usage of the dataframe before converted is :", start_mem, "MB" # print dataset.isnull().any() 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) elif str(col_type)[:5] == 'float': 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) else: num_unique_values = len(df[col].unique()) num_total_values = len(df[col]) rate = num_unique_values/num_total_values #rate = df[col].value_counts(normalize=True, dropna=False).values[0] if rate <0.5: df[col] = df[col].astype('category') end_mem = df.memory_usage().sum() / 1024**2 if verbose:print "Memory usage of the dataframe after converted is :", end_mem, "MB" if verbose: print('Mem. usage decreased to {:5.2f} Mb ({:.1f}% reduction)'.format(end_mem, 100 * (start_mem - end_mem) / start_mem)) return df, ditc(df.types)