附录3：Pandas实例记录

Pandas广泛用于数据分析，有两种数据结构：Series和DataFrame，Pandas的操作以列为核心，部分原因在于机器学习的特征以列保存

#Pandas实例记录
#基本数据结构：Series和DataFrame
import pandas as pd
from pandas import DataFrame
from pandas import Series

Series部分

#Series部分
# List -> Series
obj = Series([4, 7, -5, 3])
print(obj)
print(obj.values)
print(obj.index)

#手动定义索引
obj2 = Series([4, 7, -5, 3], index=['d', 'b', 'a', 'c'])
print(obj2)
print(obj2['a'])

print(obj2[obj2 > 0])
"""
d    4
b    7
c    3
"""

# 广播计算
print(obj2 * 2)
print(np.exp(obj2))

# Dict -> Series
sdata = {'Ohio': 35000, 'Texas': 71000, 'Oregon': 16000, 'Utah': 5000}
obj3 = Series(sdata)
print(obj3)
"""
Ohio      35000
Oregon    16000
Texas     71000
Utah       5000
"""
print(obj3.index)

states = ['California', 'Ohio', 'Oregon', 'Texas']
obj4 = Series(sdata, index=states) # 自动与dict的key匹配
print(obj4)
"""
California        NaN
Ohio          35000.0
Oregon        16000.0
Texas         71000.0
"""

print(obj3 + obj4) # 数据自动对齐
"""
California         NaN
Ohio           70000.0
Oregon         32000.0
Texas         142000.0
Utah               NaN
"""

obj4.name = '人口'
obj4.index.name = '州'
print(obj4)
"""
州
California        NaN
Ohio          35000.0
Oregon        16000.0
Texas         71000.0
Name: 人口, dtype: float64
"""

obj = Series([4, 7, -5, 3])
obj.index = ['Bob', 'Steve', 'Jeff', 'Ryan'] # 更新索引
obj

DataFrame部分

---

frame的访问是[列][行]，与数组相反

---

#DataFrame部分
data = {'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada'],
        'year': [2000, 2001, 2002, 2001, 2002],
        'pop': [1.5, 1.7, 3.6, 2.4, 2.9]}
frame = DataFrame(data) # key对应frame的列名
print(frame)
"""
   pop   state  year
0  1.5    Ohio  2000
1  1.7    Ohio  2001
2  3.6    Ohio  2002
3  2.4  Nevada  2001
4  2.9  Nevada  2002
"""

print(frame.index)
frame.index = ['X', 'Y', 'Z', 'a', 'b']
print(frame)
#frame的访问是[列][行]，与数组相反
print(frame['state']['Z'])

"""

Index(['X', 'Y', 'Z', 'a', 'b'], dtype='object')
   pop   state  year
X  1.5    Ohio  2000
Y  1.7    Ohio  2001
Z  3.6    Ohio  2002
a  2.4  Nevada  2001
b  2.9  Nevada  2002
Ohio
"""

frame = DataFrame(data, columns=['year', 'state', 'pop']) # 指定列顺序
print(frame)
"""
   year   state  pop
0  2000    Ohio  1.5
1  2001    Ohio  1.7
2  2002    Ohio  3.6
3  2001  Nevada  2.4
4  2002  Nevada  2.9
"""

"""
DF的数据获取
df.iloc[2, 3] #索引从0开始
df.loc[['2018-11-08', '2018-11-06'], ['open', 'close']]
"""