Pandas用法小结

DataFrame

#.DataFrame()创建一个DF，参数colums为各列属性

import pandas as pd
df=pd.DataFrame(np.random.randn(12).reshape(3,4),columns=['a','b','c','d'])
df

a	b	c	d
0	0.927449	0.461756	0.395449	0.294089
1	-1.296071	-0.780128	0.513385	1.608865
2	-0.071200	-1.105894	-0.568288	-0.216750

#按照字典的形式创建DF

df1=pd.DataFrame({'A':np.arange(4),'B':np.arange(4,8)})
df1
	A	B
0	0	4
1	1	5
2	2	6
3	3	7

#.columns方法显示列属性
#.valus显示值

df1.columns

Index(['A', 'B'], dtype='object')
df.values
array([[-0.6023384 ,  0.67498799, -0.68959674, -0.18298839],
       [ 1.26339357, -1.39439048, -0.67637389,  1.24420078],
       [-2.48233953, -1.42888899, -0.75211092, -0.28422075]])

#.describe()显示DF各种信息，包括中位数，平均值，std等

df.describe()

a	b	c	d
count	3.000000	3.000000	3.000000	3.000000
mean	-0.607095	-0.716097	-0.706027	0.258997
std	1.872871	1.204839	0.040454	0.854711
min	-2.482340	-1.428889	-0.752111	-0.284221
25%	-1.542339	-1.411640	-0.720854	-0.233605
50%	-0.602338	-1.394390	-0.689597	-0.182988
75%	0.330528	-0.359701	-0.682985	0.530606
max	1.263394	0.674988	-0.676374	1.244201

#DF也可转置.T
#参数index（）引入属性

df=pd.DataFrame(np.random.randn(12).reshape(3,4),index=['a','b','c'],columns=['a1','b1','c1','d1'])
df

a1	b1	c1	d1
a	-0.723560	-1.363361	-0.290657	-0.915854
b	1.750881	0.885029	-0.935353	-0.771946
c	-0.074274	0.634728	-0.465676	-1.204649

#用列属性查找一列数据

print(df['a1'])
print(df.a1)
a   -0.723560
b    1.750881
c   -0.074274
Name: a1, dtype: float64

#按行索引选取行数据

print(df[0:2])
          a         b         c         d
0  0.927449  0.461756  0.395449  0.294089
1 -1.296071 -0.780128  0.513385  1.608865

loc()方法

#选择某一行

print(df.loc['a'])
a1    0.157265
b1   -0.091589
c1    0.678737
d1   -0.091182
Name: a, dtype: float64

#选择某一列的第几行元素

# 选中某一列"[]",用行列名称
print(df.loc[:,['a1']])
# 具体某个数
print(df.loc['b','a1'])
         a1
a  0.157265
b  0.827624
c -1.627656
0.8276240510180705

iloc()方法选择数据

#行列索引选择数据

# 某个具体的数，用行列索引
print(df.iloc[0,0])
# 切片
print(df.iloc[0:2,0:2])
-0.7235602120079216
         a1        b1
a -0.723560 -1.363361
b  1.750881  0.885029

#改变选取的值

# 改变位置上的值
df.iloc[0,0]=0
df.loc['b','d1']=0

#按条件赋值

# 按条件赋值
df.a1[df.a1>0]=0
df

a1	b1	c1	d1
a	0.000000	-0.091589	0.678737	-0.091182
b	0.000000	-0.283218	-0.408538	1.446401
c	-1.627656	0.469021	-0.024202	-0.788833

#.fillna()填充缺失数据

df.fillna(value=0)

a1	b1	c1	d1
a	0.000000	-1.363361	-0.290657	-0.915854
b	0.000000	0.885029	-0.935353	0.000000
c	-0.074274	0.634728	-0.465676	-1.204649

plot画图总结

#老规矩引入包
import matplotlib.pyplot as plt
#.plot（），与plt.show()组合使用画图

import matplotlib.pyplot as plt
# plot可视化数据
data=pd.Series(np.random.randn(1000),index=np.arange(1000))
print(data)
data=data.cumsum()
data.plot()
plt.show()

#对于DataFrame添加了index，与columns的数据绘图

散点图

#plot.scatter(x= ,y=’’,color=’’,label=’’,ax=)
ax参数是将两张图合并
#xlim() x轴范围
ylim() y轴范围

# 点图
# 点图
scatter_plot=data.plot.scatter(x='A',y='B',color='Blue',label='Class1')
# # data.plot.scatter(x='A',y='C',s=20,color='Blue',alpha=0.5,label='Class2',ax=scatter_plot)


data.plot(kind="scatter",x="A",y="C",s=50,c='Red',alpha=0.5,label='Class2',ax=scatter_plot,cmap=plt.get_cmap("jet"),colorbar=True)
plt.xlim((-10,10))#x范围
plt.ylim((-10,10))#y范围
plt.show()

数据合并(concat,join)

1.concat
#再次强调axis=对DF纵向操作，axis=1对DF横向操作
#ignore_index=True 使拼接的DF的index(0-----)

df1=pd.DataFrame(np.ones((3,4))*0,columns=['a','b','c','d'])
df2=pd.DataFrame(np.ones((3,4))*1,columns=['a','b','c','d'])
df3=pd.DataFrame(np.ones((3,4))*2,columns=['a','b','c','d'])
res=pd.concat([df1,df2,df3],axis=0,ignore_index=True)#默认axis=0
print(df1)
print(df2)
print(df3)
print(res)
     a    b    c    d
0  0.0  0.0  0.0  0.0
1  0.0  0.0  0.0  0.0
2  0.0  0.0  0.0  0.0
     a    b    c    d
0  1.0  1.0  1.0  1.0
1  1.0  1.0  1.0  1.0
2  1.0  1.0  1.0  1.0
     a    b    c    d
0  2.0  2.0  2.0  2.0
1  2.0  2.0  2.0  2.0
2  2.0  2.0  2.0  2.0
     a    b    c    d
0  0.0  0.0  0.0  0.0
1  0.0  0.0  0.0  0.0
2  0.0  0.0  0.0  0.0
3  1.0  1.0  1.0  1.0
4  1.0  1.0  1.0  1.0
5  1.0  1.0  1.0  1.0
6  2.0  2.0  2.0  2.0
7  2.0  2.0  2.0  2.0
8  2.0  2.0  2.0  2.0

2.join
#inner 保留重复位置
#outer没有数据的填充Null

# join('inner','outer')
df1=pd.DataFrame(np.ones((3,4))*0,columns=['a','b','c','d'],index=[1,2,3])
df2=pd.DataFrame(np.ones((3,4))*1,columns=['b','c','d','e'],index=[2,3,4])
print(df1)
print(df2)
# inner保留重复位置
res1=pd.concat([df1,df2],join='inner',ignore_index=True)
print(res1)
# outer没有的填充Null，默认
res=pd.concat([df1,df2],join='outer',ignore_index=True)
print(res)

     a    b    c    d
1  0.0  0.0  0.0  0.0
2  0.0  0.0  0.0  0.0
3  0.0  0.0  0.0  0.0
     b    c    d    e
2  1.0  1.0  1.0  1.0
3  1.0  1.0  1.0  1.0
4  1.0  1.0  1.0  1.0
     b    c    d
0  0.0  0.0  0.0
1  0.0  0.0  0.0
2  0.0  0.0  0.0
3  1.0  1.0  1.0
4  1.0  1.0  1.0
5  1.0  1.0  1.0
     a    b    c    d    e
0  0.0  0.0  0.0  0.0  NaN
1  0.0  0.0  0.0  0.0  NaN
2  0.0  0.0  0.0  0.0  NaN
3  NaN  1.0  1.0  1.0  1.0
4  NaN  1.0  1.0  1.0  1.0
5  NaN  1.0  1.0  1.0  1.0

join_axes合并

#join_axes[df1.index]:按照df1的index合并DF
#axis=0/1:考虑df1与df2的index,没有数据的填充Null

import numpy as np
import pandas as pd
df1=pd.DataFrame(np.ones((3,4))*0,columns=['a','b','c','d'],index=[1,2,3])
df2=pd.DataFrame(np.ones((3,4))*1,columns=['b','c','d','e'],index=[2,3,4])
res=pd.concat([df2,df1],axis=1,join_axes=[df1.index])
res1=pd.concat([df1,df2],axis=1)
print(res)
print(res1)

     b    c    d    e    a    b    c    d
1  NaN  NaN  NaN  NaN  0.0  0.0  0.0  0.0
2  1.0  1.0  1.0  1.0  0.0  0.0  0.0  0.0
3  1.0  1.0  1.0  1.0  0.0  0.0  0.0  0.0
     a    b    c    d    b    c    d    e
1  0.0  0.0  0.0  0.0  NaN  NaN  NaN  NaN
2  0.0  0.0  0.0  0.0  1.0  1.0  1.0  1.0
3  0.0  0.0  0.0  0.0  1.0  1.0  1.0  1.0
4  NaN  NaN  NaN  NaN  1.0  1.0  1.0  1.0

append添加数据

#向DF横向添加数据
#Series(data,index=),index对应data

# append，在DataFrame横向或纵向添加数据
df1=pd.DataFrame(np.ones((3,4))*0,columns=['a','b','c','d'],index=[1,2,3])
# Series,一行数据
s1=pd.Series([1,2,3,4],index=['a','b','c','d'])
rs=df1.append(s1,ignore_index=True)
print(rs)

     a    b    c    d
0  0.0  0.0  0.0  0.0
1  0.0  0.0  0.0  0.0
2  0.0  0.0  0.0  0.0
3  1.0  2.0  3.0  4.0