pandas基础知识---4

索引：

import numpy as np
import pandas as pd

#选择行与列
df = pd.DataFrame(np.random.rand(12).reshape(3,4)*100,
                  index=['one','two','three'],
                  columns=['a','b','c','d'])
df1 = pd.DataFrame(np.random.rand(12).reshape(3,4)*100,
                  columns=['a','b','c','d'])
print(df)
print("---------------------------")
data1 = df['a']             #选择列，用列来输出
data2 = df[['b','c']]
print(data1)
print(data2)
print("***************************")
#按照列名只选择一列输出Series,选择多列输出DataFrame

data3 = df.loc['one']       #如果要按照行来输出，就要用loc，不能用df['one'],否则报错
data4 = df.loc[['three','two']]
print(data3)
print(data4)
data3 = df[:2]              #切片索引的是行，所以也可以用切片来输出行
print(data3)
print("---------------------------")

data5 = df.loc['one':'three']       #df.loc也可以用来切片行，末端包含
data6 = df1.loc[1:3]
print(data5)
print(data6)
print("***************************")

#df.iloc[] - 按照整数位置，（从轴的0到length-1）选择行
#类似list的索引，其顺序就是DataFrame的整数位置，从0开始计
df = pd.DataFrame(np.random.rand(16).reshape(4,4)*100,
                  index=['one','two','three','four'],
                  columns=['a','b','c','d'])
print(df)
print("------")
print(df.iloc[0])
print(df.iloc[-1])

print(df.iloc[[0,2]])       #多位置索引  顺序可变
print(df.iloc[[3,2,1]])

print(df.iloc[1:3])         #切片索引,末端不包含
print(df.iloc[::2])
print("---------------------------")

多重索引：

import numpy as np
import pandas as pd

#多重索引：比如同时索引行和列
#先选择列再选择行 -- 相当于对于一个数据，先筛选字段，再选择数据量
df = pd.DataFrame(np.random.rand(16).reshape(4,4)*100,
                  index=['one','two','three','four'],
                  columns=['a','b','c','d'])
print(df)
print("---")
print(df['a'].loc[['three','four']])
print("---")
print(df[['b','c','d']].iloc[::2])  #先筛选出bcd，再切片选出步长为2的索引
print("***************************")

del df['a']
print(df)
print(df.drop(['d'],axis=1))    #drop删除列，需要加上axis=1，inplace=False->删除后生成新的数据，不改变原数据

排序：

import numpy as np
import pandas as pd

#排序1 - 按值排序.sort_values
#同样适用于Series
df1 = pd.DataFrame(np.random.rand(16).reshape(4,4)*100,
                  columns=['a','b','c','d'])
print(df1)
print(df1.sort_values(['a'],ascending=True))    #升序
print(df1.sort_values(['a'],ascending=False))   #降序
#ascending参数：设置升序降序，默认升序
#单列排序
print('-'*50)
df2 = pd.DataFrame({'a':[1,1,1,1,2,2,2,2],
                    'b':list(range(8)),
                    'c':list(range(8,0,-1))})
print(df2)
print('-'*50)
print(df2.sort_values(['a','c']))
#多列排序，按列顺序排序
print("******************************************************************")

#排序2 - 索引排序.sort_index
df1 = pd.DataFrame(np.random.rand(16).reshape(4,4)*100,
                   index=[5,4,3,2],
                  columns=['a','b','c','d'])
df2 = pd.DataFrame(np.random.rand(16).reshape(4,4)*100,
                   index=['h','s','x','g'],
                  columns=['a','b','c','d'])
print(df1)
print(df1.sort_index())
print(df2)
print(df2.sort_index())
#按照index排序
#默认ascending=True，inplace=False