python6 pandas模块基础知识以及使用

python笔记

os.listdir()方法
os.listdir()方法返回指定的文件夹中包含的文件或文件夹zhi的列表，这个列表以字母顺序。不包含’.‘和’…’,即使它在文件夹中。
语法
listdir()语法格式如下:
os.listdir(path)
参数:path需要指定的目录路径
返回值:返回指定路径下的文件和文件夹列表
实例

import os
fileList = os.listdir('E:\pycharm\work\cookbook\day6\data')
print(fileList)

输出读取文件
包括(值，类型，数量，维度数，行列)

print(type(detail))
print(detail.values)   # 值
print(detail.columns)
print(detail.dtypes)   # 每一行的类型
print("元素的个数",detail.size)    # 数量
print("5",detail.ndim)   # 维度数
print("6",detail.shape)   # 行列

### 输出
#<class 'pandas.core.frame.DataFrame'>
[[2956 417 610062 ... nan 'caipu/104001.jpg' 1442]
 [2958 417 609957 ... nan 'caipu/202003.jpg' 1442]
 [2961 417 609950 ... nan 'caipu/303001.jpg' 1442]
 ...
 [6756 774 609949 ... nan 'caipu/404005.jpg' 1138]
 [6763 774 610014 ... nan 'caipu/302003.jpg' 1138]
 [6764 774 610017 ... nan 'caipu/302006.jpg' 1138]]
Index(['detail_id', 'order_id', 'dishes_id', 'logicprn_name',
       'parent_class_name', 'dishes_name', 'itemis_add', 'counts', 'amounts',
       'cost', 'place_order_time', 'discount_amt', 'discount_reason',
       'kick_back', 'add_inprice', 'add_info', 'bar_code', 'picture_file',
       'emp_id'],
      dtype='object')
detail_id                     int64
order_id                      int64
dishes_id                     int64
logicprn_name               float64
parent_class_name           float64
dishes_name                  object
itemis_add                    int64
counts                        int64
amounts                       int64
cost                        float64
place_order_time     datetime64[ns]
discount_amt                float64
discount_reason             float64
kick_back                   float64
add_inprice                   int64
add_info                    float64
bar_code                    float64
picture_file                 object
emp_id                        int64
dtype: object
元素的个数 52801
5 2
6 (2779, 19)

使用字典访问单列数据

import pandas as pd
# 使用字典访问单列数据
detail = pd.read_excel("E:\pycharm\work\cookbook\day6\data\meal_order_detail.xlsx")
order_id = detail['order_id']
print(order_id)
print(type(order_id), order_id.shape)

使用访问属性的方式访问单列数据

detail = pd.read_excel("E:\pycharm\work\cookbook\day6\data\meal_order_detail.xlsx")

dishes_name = detail.dishes_name
print(dishes_name)

单列，自主选择行数

detail = pd.read_excel("E:\pycharm\work\cookbook\day6\data\meal_order_detail.xlsx")

dishes_name5 = detail["dishes_name"][1:6]    # [start,end）
print(dishes_name5)

多列多行

detail = pd.read_excel("E:\pycharm\work\cookbook\day6\data\meal_order_detail.xlsx")
orderDish = detail[['order_id','dishes_name']][0:5]
print(orderDish)

所有的列指定行数

detail = pd.read_excel("E:\pycharm\work\cookbook\day6\data\meal_order_detail.xlsx")
order6 = detail[:][1:6]
print(order6)

Dataframe的方法head.tail

detail = pd.read_excel("E:\pycharm\work\cookbook\day6\data\meal_order_detail.xlsx")
print("detail.head()",detail.head())       # head()表示前5行的数据
print("detail.tail()",detail.tail())       # tail()表示后5行的数据

loc函数：通过行索引 “Index” 中的具体值来取行数据（如取"Index"为"A"的行）

iloc函数：通过行号来取行数据（如取第二行的数据）

oc/iloc实现单列切片

detail = pd.read_excel("E:\pycharm\work\cookbook\day6\data\meal_order_detail.xlsx")
dishes_name1 = detail.loc[:,'dishes_name']
print(dishes_name1)

使用loc打印出[‘order_id’,‘dishes_name’]的[1:6)

detail = pd.read_excel("E:\pycharm\work\cookbook\day6\data\meal_order_detail.xlsx")
dishes_name2 = detail.loc[1:6, ['order_id','dishes_name']]
print(dishes_name2)

iloc使用

detail = pd.read_excel("E:\pycharm\work\cookbook\day6\data\meal_order_detail.xlsx")
print(detail.values)
orderDish = detail.iloc[1,[1,5]]
# 第3行第1列的元素，第3行第3列的元素，这里的行列是dataFrame的行列表格，不是excel，
# 因为dataFrame已经重新排序了
print("iloc的orderDish \n",orderDish)

iloc的多行多列

detail = pd.read_excel("E:\pycharm\work\cookbook\day6\data\meal_order_detail.xlsx")
orderDish = detail.iloc[2:7,[1,3]]
print("iloc的orderDish \n",orderDish)

条件切片，指定一个条件
order_id为458的dishes_name

detail = pd.read_excel("E:\pycharm\work\cookbook\day6\data\meal_order_detail.xlsx")
orderDish = detail.loc[detail['order_id']==458, ['order_id','dishes_name']]
print(orderDish)

ix-iloc、loc的比较

#ix-iloc\loc比较
detail = pd.read_excel("E:\pycharm\work\cookbook\day6\data\meal_order_detail.xlsx")

dishes_name_loc = detail.loc[2:6, 'dishes_name']
print(dishes_name_loc)

dishes_name_iloc = detail.iloc[2:6, 5]
print(dishes_name_iloc)

dishes_name_ix = detail.ix[2:6, 5]
print(dishes_name_ix)

更改
将order_id为458的变换为45800

detail = pd.read_excel("E:\pycharm\work\cookbook\day6\data\meal_order_detail.xlsx")
detail.loc[detail['order_id']==458, 'order_id'] = 45800
print(detail.loc[detail['order_id']==458, 'order_id'])
print('/')
print(detail.loc[detail['order_id']==45800, 'order_id'])

增加

detail = pd.read_excel("E:\pycharm\work\cookbook\day6\data\meal_order_detail.xlsx")
detail['payment'] = detail['counts'] * detail['amounts']
print(detail['payment'])
detail['pay_way'] = '现金支付'
print(detail['pay_way'])

删除
删除某列

print(detail.columns)
detail.drop(labels='pay_way', axis=1, inplace=True)
print(detail.columns)

inplace参数的理解：
修改一个对象时：
inplace=True：不创建新的对象，直接对原始对象进行修改；
inplace=False：对数据进行修改，创建并返回新的对象承载其修改结果。

删除某行

detail = pd.read_excel("E:\pycharm\work\cookbook\day6\data\meal_order_detail.xlsx")
print(len(detail))
detail.drop(labels=range(1,11), axis=0, inplace=True)
print(len(detail))

dataframe的统计描述
算个平均值

detail = pd.read_excel("E:\pycharm\work\cookbook\day6\data\meal_order_detail.xlsx")
print("numpy的平均值",np.mean(detail['amounts']))
print('pandas求平均值:',detail['amounts'].mean())
print(detail[['amounts','counts']].describe())

统计一下频数

detail = pd.read_excel("E:\pycharm\work\cookbook\day6\data\meal_order_detail.xlsx")
print(detail['dishes_name'].value_counts())
print(detail['dishes_name'].value_counts()[0:10])