关于DataFrame数据的查询和编辑

# 选取列
import pandas as pd
import numpy as np
data = {
    'name':[杨大润','李玉芳','马庆显'],
    'age':[21,19,23],
    'address':['兰州','上海','北京']
}
df = pd.DataFrame(data)
print(df)
w1 = df['name']
print("以列名取一列数据:\n", w1)
w2 = df[['name','age']]
print("以列名取两份数据：\n", w2)

# 取行  从0开始的
import pandas as pd
data = {
    'name':['杨大润','李玉芳','马庆显'],
    'age':[21,19,23],
    'address':['贵州','上海','北京']
}
df = pd.DataFrame(data)
print(df)
print('显示前两行：\n', df[:2])
print('显示2行：\n', df[1:2])
# head从第一行取，默认前五行
print(df.head())
print(df.head(1))
# tail默认最后五行   可以带数字取最后的
print(df.tail())
print(df.tail(1))
# sample随机抽取n行显示
print(df.sample(1))

# loc
import pandas as pd
import numpy as np
data = {
   'name':['杨将军（大润）', '李女将（玉芳）', '马（军师）庆显', '韦女将（思妍）', '徐大将（佳宇）'],
   'location':['游走', '下路', '打野', '中单', '上单'],
   'dynasty':['蜀', '蜀', '战国', '汉', '蜀'],
   'year':[1999, 2000, 2020, 2050, 3030]
}
df1 = pd.DataFrame(data, columns=['name','location','dynasty','address','year'],index=['a','b','c','d','e'])
df2 = df1.set_index('dynasty')
print(df2)
print("取name和year两列的数据:\n",df2.loc[:,['name','year']])
print("取汉，战国行中name，year的数据：\n",df2.loc[['汉','战国'],['name','year']])

#插入一行数据append
#加列并赋值
import pandas as pd
import numpy as np
data = {
	'name':['杨将军（大润）', '李女将（玉芳）', '马（军师）庆显', '韦女将（思妍）', '徐大将（佳宇）'],
	'location':['游走', '下路', '打野', '中单', '上单'],
	'dynasty':['蜀', '蜀', '战国', '汉', '蜀'],
	'year':[1999, 2000, 2020, 2050, 3030]
}
df1 = pd.DataFrame(data, columns=['name','location','dynasty','address','year'],index=['0','1','2','3','4'])

df1['C'] = 10
df1['age'] = [24,33,19,40,80]

data1 = {
    'name':'吴医师（宗蔚）',
    'location':'打野',
    'dynasty':'唐',
    'year':1909
}
df1.append(data1,ignore_index=True)

print(df1)
print(df1.append(data1,ignore_index=True))

import numpy as np
import pandas as pd

df = pd.DataFrame(data=[['杨大润', '男', 22], ['李玉芳', '女', 18], ['韦思妍', '女', 18],
                        ['马庆显', '男', 23], ['徐佳宇', '女', 18], ['吴宗蔚', '女', 21]], index=[1, 2, 3, 4, 5, 6],
                  columns=['name', 'sex', 'age'])
# 测试数据。
print(df)

h=df.drop([1,3],axis = 0,inplace = False)         #删除index值为1和3的两行，
print(h)


l=df.drop(['name'],axis = 1,inplace = False)   #删除name列。
print(l)