本文執行個體講述了Python3.5 Pandas子產品缺失值處理和層次索引。分享給大家供大家參考,具體如下:
1、pandas缺失值處理
![](https://img.laitimes.com/img/__Qf2AjLwojIjJCLyojI0JCLicmbw5COiNTZkdjY1MGNmZGO2ATZxQzMjBjNxIzY4ATY5Y2Ym9CX0JXZ252bj91Ztl2Lc52YucWbp5GZzNmLn9Gbi1yZtl2Lc9CX6MHc0RHaiojIsJye.png)
import numpy as np
import pandas as pd
from pandas import Series,DataFrame
df3 = DataFrame([
["Tom",np.nan,456.67,"M"],
["Merry",34,345.56,np.nan],
[np.nan,np.nan,np.nan,np.nan],
["John",23,np.nan,"M"],
["Joe",18,385.12,"F"]
],columns = ["name","age","salary","gender"])
print(df3)
print("=======判斷NaN值=======")
print(df3.isnull())
print("=======判斷非NaN值=======")
print(df3.notnull())
print("=======删除包含NaN值的行=======")
print(df3.dropna())
print("=======删除全部為NaN值的行=======")
print(df3.dropna(how="all"))
df3.ix[2,0] = "Gerry" #修改第2行第0列的值
print(df3)
print("=======删除包含NaN值的列=======")
print(df3.dropna(axis=1))
運作結果:
name age salary gender
0 Tom NaN 456.67 M
1 Merry 34.0 345.56 NaN
2 NaN NaN NaN NaN
3 John 23.0 NaN M
4 Joe 18.0 385.12 F
=判斷NaN值=
name age salary gender
0 False True False False
1 False False False True
2 True True True True
3 False False True False
4 False False False False
=判斷非NaN值=
name age salary gender
0 True False True True
1 True True True False
2 False False False False
3 True True False True
4 True True True True
=删除包含NaN值的行=
name age salary gender
4 Joe 18.0 385.12 F
=删除全部為NaN值的行=
name age salary gender
0 Tom NaN 456.67 M
1 Merry 34.0 345.56 NaN
3 John 23.0 NaN M
4 Joe 18.0 385.12 F
name age salary gender
0 Tom NaN 456.67 M
1 Merry 34.0 345.56 NaN
2 Gerry NaN NaN NaN
3 John 23.0 NaN M
4 Joe 18.0 385.12 F
=删除包含NaN值的列=
name
0 Tom
1 Merry
2 Gerry
3 John
4 Joe
import numpy as np
import pandas as pd
from pandas import Series,DataFrame
df4 = DataFrame(np.random.randn(7,3))
print(df4)
df4.ix[:4,1] = np.nan #第0至3行,第1列的資料
df4.ix[:2,2] = np.nan
print(df4)
print(df4.fillna(0)) #将缺失值用傳入的指定值0替換
print(df4.fillna({1:0.5,2:-1})) #将缺失值按照指定形式填充
運作結果:
0 1 2
0 -0.737618 -0.530302 -2.716457
1 0.810339 0.063028 -0.341343
2 0.070564 0.347308 -0.121137
3 -0.501875 -1.573071 -0.816077
4 -2.159196 -0.659185 -0.885185
5 0.175086 -0.954109 -0.758657
6 0.395744 -0.875943 0.950323
0 1 2
0 -0.737618 NaN NaN
1 0.810339 NaN NaN
2 0.070564 NaN NaN
3 -0.501875 NaN -0.816077
4 -2.159196 NaN -0.885185
5 0.175086 -0.954109 -0.758657
6 0.395744 -0.875943 0.950323
0 1 2
0 -0.737618 0.000000 0.000000
1 0.810339 0.000000 0.000000
2 0.070564 0.000000 0.000000
3 -0.501875 0.000000 -0.816077
4 -2.159196 0.000000 -0.885185
5 0.175086 -0.954109 -0.758657
6 0.395744 -0.875943 0.950323
0 1 2
0 -0.737618 0.500000 -1.000000
1 0.810339 0.500000 -1.000000
2 0.070564 0.500000 -1.000000
3 -0.501875 0.500000 -0.816077
4 -2.159196 0.500000 -0.885185
5 0.175086 -0.954109 -0.758657
6 0.395744 -0.875943 0.950323
2、pandas常用數學統計方法
import numpy as np
import pandas as pd
from pandas import Series,DataFrame
#pandas常用數學統計方法
arr = np.array([
[98.5,89.5,88.5],
[98.5,85.5,88],
[70,85,60],
[80,85,82]
])
df1 = DataFrame(arr,columns=["國文","數學","英語"])
print(df1)
print("=======針對列計算總統計值=======")
print(df1.describe())
print("=======預設計算各列非NaN值個數=======")
print(df1.count())
print("=======計算各行非NaN值個數=======")
print(df1.count(axis=1))
運作結果:
國文 數學 英語
0 98.5 89.5 88.5
1 98.5 85.5 88.0
2 70.0 85.0 60.0
3 80.0 85.0 82.0
=針對列計算總統計值=
國文 數學 英語
count 4.000000 4.000000 4.000000
mean 86.750000 86.250000 79.625000
std 14.168627 2.179449 13.412525
min 70.000000 85.000000 60.000000
25% 77.500000 85.000000 76.500000
50% 89.250000 85.250000 85.000000
75% 98.500000 86.500000 88.125000
max 98.500000 89.500000 88.500000
=預設計算各列非NaN值個數=
國文 4
數學 4
英語 4
dtype: int64
=計算各行非NaN值個數=
0 3
1 3
2 3
3 3
dtype: int64
import numpy as np
import pandas as pd
from pandas import Series,DataFrame、
#2.pandas相關系數與協方差
df2 = DataFrame({
"GDP":[12,23,34,45,56],
"air_temperature":[23,25,26,27,30],
"year":["2001","2002","2003","2004","2005"]
})
print(df2)
print("=========相關系數========")
print(df2.corr())
print("=========協方差========")
print(df2.cov())
print("=========兩個量之間的相關系數========")
print(df2["GDP"].corr(df2["air_temperature"]))
print("=========兩個量之間協方差========")
print(df2["GDP"].cov(df2["air_temperature"]))
運作結果:
GDP air_temperature year
0 12 23 2001
1 23 25 2002
2 34 26 2003
3 45 27 2004
4 56 30 2005
=相關系數
GDP air_temperature
GDP 1.000000 0.977356
air_temperature 0.977356 1.000000
=協方差
GDP air_temperature
GDP 302.5 44.0
air_temperature 44.0 6.7
=兩個量之間的相關系數
0.97735555485
=兩個量之間協方差
44.0
import numpy as np
import pandas as pd
from pandas import Series,DataFrame
#3.pandas唯一值、值計數及成員資格
df3 = DataFrame({
"order_id":["1001","1002","1003","1004","1005"],
"member_id":["m01","m01","m02","m01","m02",],
"order_amt":[345,312.2,123,250.2,235]
})
print(df3)
print("=========去重後的數組=========")
print(df3["member_id"].unique())
print("=========值出現的頻率=========")
print(df3["member_id"].value_counts())
print("=========成員資格=========")
df3 = df3["member_id"]
mask = df3.isin(["m01"])
print(mask)
print(df3[mask])
運作結果:
member_id order_amt order_id
0 m01 345.0 1001
1 m01 312.2 1002
2 m02 123.0 1003
3 m01 250.2 1004
4 m02 235.0 1005
=去重後的數組=
[‘m01’ ‘m02’]
=值出現的頻率=
m01 3
m02 2
Name: member_id, dtype: int64
=成員資格=
0 True
1 True
2 False
3 True
4 False
Name: member_id, dtype: bool
0 m01
1 m01
3 m01
Name: member_id, dtype: object
3、pandas層次索引
import numpy as np
import pandas as pd
from pandas import Series,DataFrame
#3.pandas層次索引
data = Series([998.4,6455,5432,9765,5432],
index=[["2001","2001","2001","2002","2002"],
["蘋果","香蕉","西瓜","蘋果","西瓜"]]
)
print(data)
df4 = DataFrame({
"year":[2001,2001,2002,2002,2003],
"fruit":["apple","banana","apple","banana","apple"],
"production":[2345,5632,3245,6432,4532],
"profits":[245.6,432.7,534.1,354,467.8]
})
print(df4)
print("=======階層化索引=======")
df4 = df4.set_index(["year","fruit"])
print(df4)
print("=======依照索引取值=======")
print(df4.ix[2002,"apple"])
print("=======依照階層化索引統計資料=======")
print(df4.sum(level="year"))
print(df4.mean(level="fruit"))
print(df4.min(level=["year","fruit"]))
運作結果:
2001 蘋果 998.4
香蕉 6455.0
西瓜 5432.0
2002 蘋果 9765.0
西瓜 5432.0
dtype: float64
fruit production profits year
0 apple 2345 245.6 2001
1 banana 5632 432.7 2001
2 apple 3245 534.1 2002
3 banana 6432 354.0 2002
4 apple 4532 467.8 2003
=階層化索引=
production profits
year fruit
2001 apple 2345 245.6
banana 5632 432.7
2002 apple 3245 534.1
banana 6432 354.0
2003 apple 4532 467.8
=依照索引取值=
production 3245.0
profits 534.1
Name: (2002, apple), dtype: float64
=依照階層化索引統計資料=
production profits
year
2001 7977 678.3
2002 9677 888.1
2003 4532 467.8
production profits
fruit
apple 3374 415.833333
banana 6032 393.350000
production profits
year fruit
2001 apple 2345 245.6
banana 5632 432.7
2002 apple 3245 534.1
banana 6432 354.0
2003 apple 4532 467.8
更多關于Python相關内容感興趣的讀者可檢視本站專題:《 Python數學運算技巧總結
》、《 Python資料結構與算法教程
》、《 Python函數使用技巧總結
》、《 Python字元串操作技巧彙總
》、《 Python入門與進階經典教程
》及《 Python檔案與目錄操作技巧彙總
》
希望本文所述對大家Python程式設計有所幫助。