网易云课堂:
https://study.163.com/course/courseMain.htm?courseId=1003240004
莫烦主页:
https://morvanzhou.github.io/tutorials/data-manipulation/np-pd/
import pandas as pd
import numpy as np
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.arange(24).reshape((6,4)),index=dates, columns=['A','B','C','D'])
# print(df)
'''
A B C D
2013-01-01 0 1 2 3
2013-01-02 4 5 6 7
2013-01-03 8 9 10 11
2013-01-04 12 13 14 15
2013-01-05 16 17 18 19
2013-01-06 20 21 22 23
'''
# df.iloc[2,2] = 1111
# df.loc['20130101','B'] = 2222
# print(df)
'''
A B C D
2013-01-01 0 2222 2 3
2013-01-02 4 5 6 7
2013-01-03 8 9 1111 11
2013-01-04 12 13 14 15
2013-01-05 16 17 18 19
2013-01-06 20 21 22 23
'''
# df.B[df.A>4] = 0
'''
A B C D
2013-01-01 0 1 2 3
2013-01-02 4 5 6 7
2013-01-03 8 0 10 11
2013-01-04 12 0 14 15
2013-01-05 16 0 18 19
2013-01-06 20 0 22 23
'''
# df.A[df.A>4] = 0
'''
A B C D
2013-01-01 0 1 2 3
2013-01-02 4 5 6 7
2013-01-03 0 9 10 11
2013-01-04 0 13 14 15
2013-01-05 0 17 18 19
2013-01-06 0 21 22 23
'''
# df[df.A>4] = 0
'''
A B C D
2013-01-01 0 1 2 3
2013-01-02 4 5 6 7
2013-01-03 0 0 0 0
2013-01-04 0 0 0 0
2013-01-05 0 0 0 0
2013-01-06 0 0 0 0
'''
# df['F'] = np.nan
'''
A B C D F
2013-01-01 0 1 2 3 NaN
2013-01-02 4 5 6 7 NaN
2013-01-03 8 9 10 11 NaN
2013-01-04 12 13 14 15 NaN
2013-01-05 16 17 18 19 NaN
2013-01-06 20 21 22 23 NaN
'''
# df['E'] = pd.Series([1,2,3,4,5,6], index=pd.date_range('20130101',periods=6))
#用上面的方法也可以加上 Series 序列(但是长度必须对齐)
'''
A B C D E
2013-01-01 0 1 2 3 1
2013-01-02 4 5 6 7 2
2013-01-03 8 9 10 11 3
2013-01-04 12 13 14 15 4
2013-01-05 16 17 18 19 5
2013-01-06 20 21 22 23 6
'''
print(df)
import pandas as pd
import numpy as np
dates = pd.date_range('20130101', periods=6)
df = pd.DataFrame(np.arange(24).reshape((6,4)),index=dates, columns=['A','B','C','D'])
df.iloc[0,1] = np.nan
df.iloc[1,2] = np.nan
# print(df)
'''
A B C D
2013-01-01 0 NaN 2.0 3
2013-01-02 4 5.0 NaN 7
2013-01-03 8 9.0 10.0 11
2013-01-04 12 13.0 14.0 15
2013-01-05 16 17.0 18.0 19
2013-01-06 20 21.0 22.0 23
'''
#如果想直接去掉有 NaN 的行或列, 可以使用 dropna
# df.dropna(axis=0,how='any')
# 0: 对行进行操作; 1: 对列进行操作
# 'any': 只要存在 NaN 就 drop 掉; 'all': 必须全部是 NaN 才 drop
'''
A B C D
2013-01-03 8 9.0 10.0 11
2013-01-04 12 13.0 14.0 15
2013-01-05 16 17.0 18.0 19
2013-01-06 20 21.0 22.0 23
'''
# df.fillna(value=0) #将 NaN 的值用其他值代替, 比如代替成 0:
# print(df.isnull()) #判断是否有缺失数据 NaN, 为 True 表示缺失数据
'''
A B C D
2013-01-01 False True False False
2013-01-02 False False True False
2013-01-03 False False False False
2013-01-04 False False False False
2013-01-05 False False False False
2013-01-06 False False False False
'''
# 如果这个表很大,看不过来,可以用下面这句:
# print(np.any(df.isnull()) == True ) #True
print(df)
#pandas可以读取与存取的资料格式有很多种,像csv、excel、json、html与pickle等…, 详细请看官方说明文件
#范例下载:https://github.com/MorvanZhou/tutorials/blob/master/numpy%26pandas/15_read_to/student.csv
import pandas as pd #加载模块
#读取csv
data = pd.read_csv('student.csv')
#打印出data
print(data)
data.to_pickle('student.pickle')
import pandas as pd
import numpy as np
#定义资料集
df1 = pd.DataFrame(np.ones((3,4))*0, columns=['a','b','c','d'])
'''
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
'''
df2 = pd.DataFrame(np.ones((3,4))*1, columns=['a','b','c','d'])
'''
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
'''
df3 = pd.DataFrame(np.ones((3,4))*2, columns=['a','b','c','d'])
'''
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
'''
#concat纵向合并,就是上下合并
res = pd.concat([df1, df2, df3], axis=0) #axis=1 是横向合并
#axis=0是预设值,因此未设定任何参数时,函数默认axis=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
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
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
'''
#仔细观察会发现结果的index是0, 1, 2, 0, 1, 2, 0, 1, 2,若要将index重置,请看例子二。
#承上一个例子,并将index_ignore设定为True
res = pd.concat([df1, df2, df3], axis=0, ignore_index=True)
'''
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
'''
#join (合并方式)
#函数默认join='outer'。此方式是依照column来做纵向合并,有相同的column上下合并在一起,其他独自的column个自成列,原本没有值的位置皆以NaN填充。
#定义资料集
df1 = pd.DataFrame(np.ones((3,4))*0, columns=['a','b','c','d'], index=[1,2,3])
'''
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
'''
df2 = pd.DataFrame(np.ones((3,4))*1, columns=['b','c','d','e'], index=[2,3,4])
'''
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
'''
#纵向"外"合并df1与df2
# res = pd.concat([df1, df2])
res = pd.concat([df1, df2], axis=0, join='outer')
'''
a b c d e
1 0.0 0.0 0.0 0.0 NaN
2 0.0 0.0 0.0 0.0 NaN
3 0.0 0.0 0.0 0.0 NaN
2 NaN 1.0 1.0 1.0 1.0
3 NaN 1.0 1.0 1.0 1.0
4 NaN 1.0 1.0 1.0 1.0
'''
#承上一个例子,join='inner',只有相同的column合并在一起,其他的会被抛弃
#纵向"内"合并df1与df2
res = pd.concat([df1, df2], axis=0, join='inner')
'''
b c d
1 0.0 0.0 0.0
2 0.0 0.0 0.0
3 0.0 0.0 0.0
2 1.0 1.0 1.0
3 1.0 1.0 1.0
4 1.0 1.0 1.0
'''
#重置index并打印结果
res = pd.concat([df1, df2], axis=0, join='inner', ignore_index=True)
'''
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
'''
#join_axes (依照 axes 合并)
#依照`df1.index`进行横向合并
res = pd.concat([df1, df2], axis=1, join_axes=[df1.index]) # 只照顾df1的index
'''
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
'''
#移除join_axes,并打印结果
res = pd.concat([df1, df2], axis=1) #这样的话df1,df2的index都被照顾到了
'''
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)
# append只有纵向合并,没有横向合并。
#定义资料集
df1 = pd.DataFrame(np.ones((3,4))*0, columns=['a','b','c','d'])
'''
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
'''
df2 = pd.DataFrame(np.ones((3,4))*1, columns=['a','b','c','d'])
'''
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
'''
df3 = pd.DataFrame(np.ones((3,4))*1, columns=['a','b','c','d'])
'''
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
'''
#将df2合并到df1的下面,以及重置index,并打印出结果
res = df1.append(df2, ignore_index=True) #append一个
'''
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
'''
#合并多个df,将df2与df3合并至df1的下面,以及重置index,并打印出结果
# res = df1.append([df2, df3], ignore_index=True) #append两个
'''
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 1.0 1.0 1.0 1.0
7 1.0 1.0 1.0 1.0
8 1.0 1.0 1.0 1.0
'''
#定义新数据集
df1 = pd.DataFrame(np.ones((3,4))*0, columns=['a','b','c','d'])
'''
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
'''
s1 = pd.Series([1,2,3,4], index=['a','b','c','d'])
'''
a 1
b 2
c 3
d 4
dtype: int64
'''
#合并series,将s1合并至df1,以及重置index,并打印出结果
# res = df1.append(s1, ignore_index=True) #只添加一行数据
'''
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
'''
# print(res)
#pandas中的merge和concat类似,但主要是用于两组有key column的数据,统一索引的数据. 通常也被用在Database的处理当中.
#依据一组key合并
import pandas as pd
#定义资料集并打印出
left = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'],
'A': ['A0', 'A1', 'A2', 'A3'],
'B': ['B0', 'B1', 'B2', 'B3']})
right = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3'],
'C': ['C0', 'C1', 'C2', 'C3'],
'D': ['D0', 'D1', 'D2', 'D3']})
# print(left)
'''
key A B
0 K0 A0 B0
1 K1 A1 B1
2 K2 A2 B2
3 K3 A3 B3
'''
# print(right)
'''
key C D
0 K0 C0 D0
1 K1 C1 D1
2 K2 C2 D2
3 K3 C3 D3
'''
#依据key column合并,并打印出
# res = pd.merge(left, right, on='key')
# print(res)
'''
key A B C D
0 K0 A0 B0 C0 D0
1 K1 A1 B1 C1 D1
2 K2 A2 B2 C2 D2
3 K3 A3 B3 C3 D3
'''
#依据两组key合并
#合并时有4种方法how = ['left', 'right', 'outer', 'inner'],预设值how='inner'
#定义资料集并打印出
left = pd.DataFrame({'key1': ['K0', 'K0', 'K1', 'K2'],
'key2': ['K0', 'K1', 'K0', 'K1'],
'A': ['A0', 'A1', 'A2', 'A3'],
'B': ['B0', 'B1', 'B2', 'B3']})
right = pd.DataFrame({'key1': ['K0', 'K1', 'K1', 'K2'],
'key2': ['K0', 'K0', 'K0', 'K0'],
'C': ['C0', 'C1', 'C2', 'C3'],
'D': ['D0', 'D1', 'D2', 'D3']})
# print(left)
# A B key1 key2
# 0 A0 B0 K0 K0
# 1 A1 B1 K0 K1
# 2 A2 B2 K1 K0
# 3 A3 B3 K2 K1
# print(right)
# C D key1 key2
# 0 C0 D0 K0 K0
# 1 C1 D1 K1 K0
# 2 C2 D2 K1 K0
# 3 C3 D3 K2 K0
#依据key1与key2 columns进行合并,并打印出四种结果['left', 'right', 'outer', 'inner']
# res = pd.merge(left, right, on=['key1', 'key2']) #默认的是 inner
# res = pd.merge(left, right, on=['key1', 'key2'], how='inner') #只考虑相同的部分,不同的丢弃
# print(res)
# A B key1 key2 C D
# 0 A0 B0 K0 K0 C0 D0
# 1 A2 B2 K1 K0 C1 D1
# 2 A2 B2 K1 K0 C2 D2
# res = pd.merge(left, right, on=['key1', 'key2'], how='outer')
# print(res)
# A B key1 key2 C D
# 0 A0 B0 K0 K0 C0 D0
# 1 A1 B1 K0 K1 NaN NaN
# 2 A2 B2 K1 K0 C1 D1
# 3 A2 B2 K1 K0 C2 D2
# 4 A3 B3 K2 K1 NaN NaN
# 5 NaN NaN K2 K0 C3 D3
# res = pd.merge(left, right, on=['key1', 'key2'], how='left') #以left的key1,key2为主
# print(res)
# A B key1 key2 C D
# 0 A0 B0 K0 K0 C0 D0
# 1 A1 B1 K0 K1 NaN NaN
# 2 A2 B2 K1 K0 C1 D1
# 3 A2 B2 K1 K0 C2 D2
# 4 A3 B3 K2 K1 NaN NaN
# res = pd.merge(left, right, on=['key1', 'key2'], how='right') #以right的key1,key2为主
# print(res)
# A B key1 key2 C D
# 0 A0 B0 K0 K0 C0 D0
# 1 A2 B2 K1 K0 C1 D1
# 2 A2 B2 K1 K0 C2 D2
# 3 NaN NaN K2 K0 C3 D3
#定义资料集并打印出
df1 = pd.DataFrame({'col1':[0,1], 'col_left':['a','b']})
df2 = pd.DataFrame({'col1':[1,2,2],'col_right':[2,2,2]})
# print(df1)
# col1 col_left
# 0 0 a
# 1 1 b
# print(df2)
# col1 col_right
# 0 1 2
# 1 2 2
# 2 2 2
# 依据col1进行合并,并启用indicator=True,最后打印出
#indicator默认的参数是false
# res = pd.merge(df1, df2, on='col1', how='outer', indicator=True)
# print(res)
# col1 col_left col_right _merge
# 0 0.0 a NaN left_only
# 1 1.0 b 2.0 both
# 2 2.0 NaN 2.0 right_only
# 3 2.0 NaN 2.0 right_only
# 自定indicator column的名称,并打印出
# res = pd.merge(df1, df2, on='col1', how='outer', indicator='indicator_column')
# print(res)
# col1 col_left col_right indicator_column
# 0 0.0 a NaN left_only
# 1 1.0 b 2.0 both
# 2 2.0 NaN 2.0 right_only
# 3 2.0 NaN 2.0 right_only
#定义资料集并打印出
left = pd.DataFrame({'A': ['A0', 'A1', 'A2'],
'B': ['B0', 'B1', 'B2']},
index=['K0', 'K1', 'K2'])
right = pd.DataFrame({'C': ['C0', 'C2', 'C3'],
'D': ['D0', 'D2', 'D3']},
index=['K0', 'K2', 'K3'])
# print(left)
# A B
# K0 A0 B0
# K1 A1 B1
# K2 A2 B2
# print(right)
# C D
# K0 C0 D0
# K2 C2 D2
# K3 C3 D3
#依据左右资料集的index进行合并,how='outer',并打印出
# res = pd.merge(left, right, left_index=True, right_index=True, how='outer')
# print(res)
# A B C D
# K0 A0 B0 C0 D0
# K1 A1 B1 NaN NaN
# K2 A2 B2 C2 D2
# K3 NaN NaN C3 D3
#依据左右资料集的index进行合并,how='inner',并打印出
# res = pd.merge(left, right, left_index=True, right_index=True, how='inner')
# print(res)
# A B C D
# K0 A0 B0 C0 D0
# K2 A2 B2 C2 D2
#定义资料集
boys = pd.DataFrame({'k': ['K0', 'K1', 'K2'], 'age': [1, 2, 3]})
# print(boys)
'''
k age
0 K0 1
1 K1 2
2 K2 3
'''
girls = pd.DataFrame({'k': ['K0', 'K0', 'K3'], 'age': [4, 5, 6]})
# print(girls)
'''
k age
0 K0 4
1 K0 5
2 K3 6
'''
#使用suffixes解决overlapping的问题
# res = pd.merge(boys, girls, on='k', suffixes=['_boy', '_girl'], how='inner')
# print(res)
# age_boy k age_girl
# 0 1 K0 4
# 1 1 K0 5
res = pd.merge(boys, girls, on='k', suffixes=['_boy', '_girl'], how='outer')
print(res)
'''
k age_boy age_girl
0 K0 1.0 4.0
1 K0 1.0 5.0
2 K1 2.0 NaN
3 K2 3.0 NaN
4 K3 NaN 6.0
'''
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
# # 随机生成1000个数据
# data = pd.Series(np.random.randn(1000),index=np.arange(1000))
# #这是一个线性的数据,我们随机生成1000个数据,Series 默认的 index 就是从0开始的整数,但是这里我显式赋值以便让大家看的更清楚
# # print(data)
# # 为了方便观看效果, 我们累加这个数据
# data1 = data.cumsum()
# # print(data1)
# # pandas 数据可以直接观看其可视化形式
# data1.plot() #因为是随机数字,故每次刷新后图形可能不一样
# #就这么简单,熟悉 matplotlib 的朋友知道如果需要plot一个数据,我们可以使用 plt.plot(x=, y=),把x,y的数据作为参数存进去,但是data本来就是一个数据,所以我们可以直接plot。
# plt.show()
data = pd.DataFrame(
np.random.randn(1000,4), #生成一个1000*4的dataframe
index=np.arange(1000),
columns=list("ABCD")
)
# data.cumsum()
# data.plot()
# plt.show()
'''
这个就是我们刚刚生成的4个column的数据,因为有4组数据,所以4组数据会分别plot出来。
plot 可以指定很多参数,具体的用法大家可以自己查一下这里
'''
'''
除了plot,我经常会用到还有scatter,这个会显示散点图,首先给大家说一下在 pandas 中有多少种方法
bar
hist
box
kde
area
scatter
hexbin
但是我们今天不会一一介绍,主要说一下 plot 和 scatter. 因为scatter只有x,y两个属性,我们我们就可以分别给x, y指定数据
'''
ax = data.plot.scatter(x='A',y='B',color='Blue',label='Class1')
data.plot.scatter(x='A',y='C',color='LightGreen',label='Class2',ax=ax)
plt.show()