Pandas如何获取数据的尺寸信息

import pandas as pd

file = pd.read_excel(r"C:\Users\15025\Desktop\uncle\debug.xlsx")
print(file.size)
print(file.shape)
print(len(file))
"""
result:
55
(11, 5)
11
"""

g1.shape
#(171907, 161)
#17W的数据，有161列

for dtype in ['float64','int64','object']:
    selected_dtype = g1.select_dtypes(include = [dtype])
    mean_usage_b = selected_dtype.memory_usage(deep=True).mean()
    mean_usage_mb = mean_usage_b/1024**2
    print('平均内存占用 ',dtype , mean_usage_mb)
'''
deep ： bool，默认为False
如果为True，则通过询问对象 dtype
来深入了解数据 的系统级内存消耗，
并将其包含在返回值中。
'''

#查看每种类型最大 能表示多大的数
int_types = ['uint8','int8','int16','int32','int64']
for it in int_types:
    print(np.iinfo(it))

g1_int = g1.select_dtypes(include = ['int64'])
#生成一个只有int类型的DataFrame
coverted_int = g1_int.apply(pd.to_numeric, downcast='unsigned')
#apply 会将数据一条一条的读取，并传入目标进行执行
#int64 转换为了 unsigned

g1_float = g1.select_dtypes(include = ['float64'])
#生成一个只有int类型的DataFrame
coverted_floar = g1_int.apply(pd.to_numeric, downcast='float')
#apply 会将数据一条一条的读取，并传入目标进行执行
#float64转换为了32

import pandas as pd
g1 = pd.read_csv('game_logs.csv')
g1_obj = g1.select_dtypes(include = ['object'])
g1.shape
#(171907, 78)
g1_obj.describe()
#查看信息生成的介绍
#count 数量
#unique	 不重复的值
#top   
#freq

dow = g1_obj.day_of_week
dow_cat = dow.astype('category')
dow_cat.head()

converted_obj = pd.DataFrame()

for col in g1_obj.columns:
    num_unique_values = len(g1_obj[col].unique())
    num_total_values= len(g1_obj[col])
    if num_unique_values / num_total_values < 0.5:
        converted_obj.loc[:,col] = g1_obj[col].astype('category')
    else:
        converted_obj.loc[:,col] = g1_obj[col]

#时间格式，写成标准格式的是比较占用内存的
#可以转换时间格式
g1['date'] = pd.to_datetime(date,format='%Y%m%d')
#这种比较占用内存

def mem_usage(pandas_obj):
    if isinstance(pandas_obj,pd.DataFrame):
        usage_b = pandas_obj.memory_usage(deep=True).sum()
    else:
        usage_b = pandas_obj.memory_usagee(deep=True)
    
    usage_mb = usage_b/1024**2
    return '{:03.2f} MB'.format(usage_mb)

g1_int = g1.select_dtypes(include = ['int64'])
#生成一个只有int类型的DataFrame
coverted_int = g1_int.apply(pd.to_numeric, downcast='unsigned')
#apply 会将数据一条一条的读取，并传入目标进行执行
#int64 转换为了 unsigned
print(mem_usage(g1_int))
print(mem_usage(coverted_int))