缺失值處理

'''
【課程2.1】  缺失值處理

數據缺失主要包括記錄缺失和字段信息缺失等狀況,其對數據分析會有較大影響,致使結果不肯定性更加顯著

缺失值的處理:刪除記錄 / 數據插補 / 不處理

'''
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from scipy import stats
% matplotlib inline
# 判斷是否有缺失值數據 - isnull,notnull
# isnull:缺失值爲True,非缺失值爲False
# notnull:缺失值爲False,非缺失值爲True

s = pd.Series([12,33,45,23,np.nan,np.nan,66,54,np.nan,99])
df = pd.DataFrame({'value1':[12,33,45,23,np.nan,np.nan,66,54,np.nan,99,190],
                  'value2':['a','b','c','d','e',np.nan,np.nan,'f','g',np.nan,'g']})
# 建立數據

print(s.isnull())  # Series直接判斷是不是缺失值,返回一個Series
print(df.notnull())  # Dataframe直接判斷是不是缺失值,返回一個Series
print(df['value1'].notnull())  # 經過索引判斷
print('------')

s2 = s[s.isnull() == False]  
df2 = df[df['value2'].notnull()]    # 注意和 df2 = df[df['value2'].notnull()] ['value1'] 的區別
print(s2)
print(df2)
# 篩選非缺失值

  輸出:app

0    False
1    False
2    False
3    False
4     True
5     True
6    False
7    False
8     True
9    False
dtype: bool
   value1 value2
0    True   True
1    True   True
2    True   True
3    True   True
4   False   True
5   False  False
6    True  False
7    True   True
8   False   True
9    True  False
10   True   True
0      True
1      True
2      True
3      True
4     False
5     False
6      True
7      True
8     False
9      True
10     True
Name: value1, dtype: bool
------
0    12.0
1    33.0
2    45.0
3    23.0
6    66.0
7    54.0
9    99.0
dtype: float64
0      12.0
1      33.0
2      45.0
3      23.0
4       NaN
7      54.0
8       NaN
10    190.0
Name: value1, dtype: float64

  

# 刪除缺失值 - dropna

s = pd.Series([12,33,45,23,np.nan,np.nan,66,54,np.nan,99])
df = pd.DataFrame({'value1':[12,33,45,23,np.nan,np.nan,66,54,np.nan,99,190],
                  'value2':['a','b','c','d','e',np.nan,np.nan,'f','g',np.nan,'g']})
# 建立數據

s.dropna(inplace = True)
df2 = df['value1'].dropna()
print(s)
print(df2)
# drop方法:可直接用於Series,Dataframe
# 注意inplace參數,默認False → 生成新的值

  輸出:dom

0    12.0
1    33.0
2    45.0
3    23.0
6    66.0
7    54.0
9    99.0
dtype: float64
0      12.0
1      33.0
2      45.0
3      23.0
6      66.0
7      54.0
9      99.0
10    190.0
Name: value1, dtype: float64

 

# 填充/替換缺失數據 - fillna、replace

s = pd.Series([12,33,45,23,np.nan,np.nan,66,54,np.nan,99])
df = pd.DataFrame({'value1':[12,33,45,23,np.nan,np.nan,66,54,np.nan,99,190],
                  'value2':['a','b','c','d','e',np.nan,np.nan,'f','g',np.nan,'g']})
# 建立數據

s.fillna(0,inplace = True)
print(s)
print('------')
# s.fillna(value=None, method=None, axis=None, inplace=False, limit=None, downcast=None, **kwargs)
# value:填充值
# 注意inplace參數

df['value1'].fillna(method = 'pad',inplace = True)
print(df)
print('------')
# method參數:
# pad / ffill → 用以前的數據填充 
# backfill / bfill → 用以後的數據填充 

s = pd.Series([1,1,1,1,2,2,2,3,4,5,np.nan,np.nan,66,54,np.nan,99])
s.replace(np.nan,'缺失數據',inplace = True)
print(s)
print('------')
# df.replace(to_replace=None, value=None, inplace=False, limit=None, regex=False, method='pad', axis=None)
# to_replace → 被替換的值
# value → 替換值

s.replace([1,2,3],np.nan,inplace = True)
print(s)
# 多值用np.nan代替

  輸出:函數

0    12.0
1    33.0
2    45.0
3    23.0
4     0.0
5     0.0
6    66.0
7    54.0
8     0.0
9    99.0
dtype: float64
------
    value1 value2
0     12.0      a
1     33.0      b
2     45.0      c
3     23.0      d
4     23.0      e
5     23.0    NaN
6     66.0    NaN
7     54.0      f
8     54.0      g
9     99.0    NaN
10   190.0      g
------
0        1
1        1
2        1
3        1
4        2
5        2
6        2
7        3
8        4
9        5
10    缺失數據
11    缺失數據
12      66
13      54
14    缺失數據
15      99
dtype: object
------
0      NaN
1      NaN
2      NaN
3      NaN
4      NaN
5      NaN
6      NaN
7      NaN
8        4
9        5
10    缺失數據
11    缺失數據
12      66
13      54
14    缺失數據
15      99
dtype: object

 

# 缺失值插補
# 幾種思路:均值/中位數/衆數插補、臨近值插補、插值法
# (1)均值/中位數/衆數插補

s = pd.Series([1,2,3,np.nan,3,4,5,5,5,5,np.nan,np.nan,6,6,7,12,2,np.nan,3,4])
#print(s)
print('------')
# 建立數據

u = s.mean()     # 均值
me = s.median()  # 中位數
mod = s.mode()   # 衆數
print('均值爲:%.2f, 中位數爲:%.2f' % (u,me))
print('衆數爲:', mod.tolist())
print('------')
# 分別求出均值/中位數/衆數

s.fillna(u,inplace = True)
print(s)
# 用均值填補

  輸出:spa

------
均值爲:4.56, 中位數爲:4.50
衆數爲: [5.0]
------
0      1.0000
1      2.0000
2      3.0000
3      4.5625
4      3.0000
5      4.0000
6      5.0000
7      5.0000
8      5.0000
9      5.0000
10     4.5625
11     4.5625
12     6.0000
13     6.0000
14     7.0000
15    12.0000
16     2.0000
17     4.5625
18     3.0000
19     4.0000
dtype: float64

 

# 缺失值插補
# 幾種思路:均值/中位數/衆數插補、臨近值插補、插值法
# (2)臨近值插補

s = pd.Series([1,2,3,np.nan,3,4,5,5,5,5,np.nan,np.nan,6,6,7,12,2,np.nan,3,4])
#print(s)
print('------')
# 建立數據

s.fillna(method = 'ffill',inplace = True)
print(s)
# 用前值插補

  輸出:3d

------
0      1.0
1      2.0
2      3.0
3      3.0
4      3.0
5      4.0
6      5.0
7      5.0
8      5.0
9      5.0
10     5.0
11     5.0
12     6.0
13     6.0
14     7.0
15    12.0
16     2.0
17     2.0
18     3.0
19     4.0
dtype: float64

 

# 缺失值插補
# 幾種思路:均值/中位數/衆數插補、臨近值插補、插值法
# (3)插值法 —— 拉格朗日插值法

from scipy.interpolate import lagrange
x = [3, 6, 9]
y = [10, 8, 4]
print(lagrange(x,y))
print(type(lagrange(x,y)))
# 的輸出值爲的是多項式的n個係數
# 這裏輸出3個值,分別爲a0,a1,a2
# y = a0 * x**2 + a1 * x + a2 → y = -0.11111111 * x**2 + 0.33333333 * x + 10

print('插值10爲:%.2f' % lagrange(x,y)(10))
print('------')
# -0.11111111*100 + 0.33333333*10 + 10 = -11.11111111 + 3.33333333 +10 = 2.22222222

  輸出:code

        2
-0.1111 x + 0.3333 x + 10
<class 'numpy.lib.polynomial.poly1d'>
插值10爲:2.22
------

 

# 缺失值插補
# 幾種思路:均值/中位數/衆數插補、臨近值插補、插值法
# (3)插值法 —— 拉格朗日插值法,實際運用

data = pd.Series(np.random.rand(100)*100)
data[3,6,33,56,45,66,67,80,90] = np.nan
print(data.head())
print('總數據量:%i' % len(data))
print('------')
# 建立數據

data_na = data[data.isnull()]
print('缺失值數據量:%i' % len(data_na))
print('缺失數據佔比:%.2f%%' % (len(data_na) / len(data) * 100))
# 缺失值的數量

data_c = data.fillna(data.median())  #  中位數填充缺失值
fig,axes = plt.subplots(1,4,figsize = (20,5))
data.plot.box(ax = axes[0],grid = True,title = '數據分佈')
data.plot(kind = 'kde',style = '--r',ax = axes[1],grid = True,title = '刪除缺失值',xlim = [-50,150])
data_c.plot(kind = 'kde',style = '--b',ax = axes[2],grid = True,title = '缺失值填充中位數',xlim = [-50,150])
# 密度圖查看缺失值狀況

def na_c(s,n,k=5):
    y = s[list(range(n-k,n+1+k))] # 取數
    y = y[y.notnull()]  # 剔除空值
    return(lagrange(y.index,list(y))(n))
# 建立函數,作插值,因爲數據量緣由,以空值先後5個數據(共10個數據)爲例作插值

na_re = []
for i in range(len(data)):
    if data.isnull()[i]:
        data[i] = na_c(data,i)
        print(na_c(data,i))
        na_re.append(data[i])
data.dropna(inplace=True)  # 清除插值後仍存在的缺失值
data.plot(kind = 'kde',style = '--k',ax = axes[3],grid = True,title = '拉格朗日插值後',xlim = [-50,150])
print('finished!')
# 缺失值插值

  輸出:blog

0    17.824704
1    17.585902
2    31.765869
3          NaN
4    51.779036
dtype: float64
總數據量:100
------
缺失值數據量:9
缺失數據佔比:9.00%
55.4089720353
71.8125483135
64.3771972656
114.778320313
96.9274902344
-0.108276367188
-79.5625
836.0
1208.0
finished!

相關文章
相關標籤/搜索