Python数据分析（3）pandas库的使用：索引，统计函数，排序和NaN数据值处理

#coding=gbk
#pandas 库
#索引对象的其他功能
import numpy as np
import pandas as pd
#1，更换索引 reindex()
frame=pd.Series([1,5,6,3],index=[0,3,5,6])
print(frame)
# 0    1
# 3    5
# 5    6
# 6    3
# dtype: int64
print(frame.reindex(range(6),method='ffill'))   #ffill，填充与前面的值相同
# 0    1
# 1    1
# 2    1
# 3    5
# 4    5
# 5    6
# dtype: int64
print(frame.reindex(range(6),method='bfill'))   #bfill，填充与后面的值相同
# 0    1
# 1    5
# 2    5
# 3    5
# 4    6
# 5    6
# dtype: int64
#2删除列
print(frame.drop(3))#删除索引为3 的行
#还可以删除列，如：print(frame1.drop(['color','object'],axis=1))
frame2=pd.DataFrame(np.arange(16).reshape(4,4),
                    index=['blue','green','black','yellow'],
                    columns=['color','price','object','real'])
print(frame2)
#         color  price  object  real
# blue        0      1       2     3
# green       4      5       6     7
# black       8      9      10    11
# yellow     12     13      14    15

#统计函数
print(frame2.sum()) #求每列的总和
# color     24
# price     28
# object    32
# real      36
print(frame2.mean())    #求平均值
print(frame2.describe())    #计算多个统计量
#            color      price     object       real
# count   4.000000   4.000000   4.000000   4.000000
# mean    6.000000   7.000000   8.000000   9.000000
# std     5.163978   5.163978   5.163978   5.163978    标准方差
# min     0.000000   1.000000   2.000000   3.000000
# 25%     3.000000   4.000000   5.000000   6.000000    四分位图，箱形图
# 50%     6.000000   7.000000   8.000000   9.000000
# 75%     9.000000  10.000000  11.000000  12.000000
# max    12.000000  13.000000  14.000000  15.000000

#排序和排位次
print(frame2.sort_index())  #依据字母的大小正序进行排列
#         color  price  object  real
# black       8      9      10    11
# blue        0      1       2     3
# green       4      5       6     7
# yellow     12     13      14    15
print(frame2.sort_index(ascending=False))   #降序排列
#         color  price  object  real
# yellow     12     13      14    15
# green       4      5       6     7
# blue        0      1       2     3
# black       8      9      10    11
print(frame2.sort_index(axis=1))        #对列进行排序
#         color  object  price  real
# blue        0       2      1     3
# green       4       6      5     7
# black       8      10      9    11
# yellow     12      14     13    15
ser= pd.Series([1,5,2,8,0],index=['blue','green','black','yellow','white'])
print(ser)
# blue      1
# green     5
# black     2
# yellow    8
# white     0
# dtype: int64
#对元素进行排序
# print(ser.order())
# print(frame2.sort_index(by='color'))

#对排位次进行操作    依据元素的大小进行排序
print(ser.rank())
# blue      2.0
# green     4.0
# black     3.0
# yellow    5.0
# white     1.0
# dtype: float64

#相关性和协方差
print(frame2.corr())    #相关性
#         color  price  object  real
# color     1.0    1.0     1.0   1.0
# price     1.0    1.0     1.0   1.0
# object    1.0    1.0     1.0   1.0
# real      1.0    1.0     1.0   1.0
print(frame2.cov()) #协方差
#             color      price     object       real
# color   26.666667  26.666667  26.666667  26.666667
# price   26.666667  26.666667  26.666667  26.666667
# object  26.666667  26.666667  26.666667  26.666667
# real    26.666667  26.666667  26.666667  26.666667

#NaN数据值处理
#1为元素附nan值
ser1= pd.Series([1,5,np.NaN,np.nan,8],index=['blue','green','black','yellow','white'])
print(ser1)
# blue      1.0
# green     5.0
# black     NaN
# yellow    NaN
# white     8.0
# dtype: float64
#2去除nan元素
print(ser1.dropna())
# blue     1.0        吧存在nan元素删掉
# green    5.0
# white    8.0
# dtype: float64
#dataFrame数据结构
frame3=pd.DataFrame([[1,2,np.nan,np.nan],[2,4,6,np.nan],
                    [8,2,np.nan,np.nan],[np.nan,2,10,np.nan]],
                    index=['blue','green','black','yellow'],
                    columns=['color','price','object','real'])
print(frame3)
#         color  price  object  real
# blue      1.0      2     NaN   NaN
# green     2.0      4     6.0   NaN
# black     8.0      2     NaN   NaN
# yellow    NaN      2    10.0   NaN
print(frame3.dropna())      #把行或列出现了nan的都删除了，所以为空了
# Empty DataFrame
# Columns: [color, price, object, real]
# Index: []
print(frame3.dropna(how='all'))#还是为数据 
#3为nan赋值
print(frame3.fillna(0)) #为nan值赋值为0
#         color  price  object  real
# blue      1.0      2     0.0   0.0
# green     2.0      4     6.0   0.0
# black     8.0      2     0.0   0.0
# yellow    0.0      2    10.0   0.0
print(frame3.fillna({'real':3}))#为real这一列赋值3
#         color  price  object  real
# blue      1.0      2     NaN   3.0
# green     2.0      4     6.0   3.0
# black     8.0      2     NaN   3.0
# yellow    NaN      2    10.0   3.0

#pandas 中(loc, iloc, 以及 ix 的区别)

 

#coding=gbk
#pandas 中(loc, iloc, 以及 ix 的区别)
# loc：通过行标签索引数据
# iloc：通过行号索引行数据
# ix：通过行标签或行号索引数据（基于loc和iloc的混合）
import pandas as pd
data = pd.DataFrame([[1,2,3],[4,5,6]],
                    index = ['a','b'],
                    columns=['c','d','e'])
print(data)
#   c  d  e
# a  1  2  3
# b  4  5  6
print(data.loc['a'])    #输入行的标签 
# c    1
# d    2
# e    3
# Name: a, dtype: int64
# print(data.iloc['a'])  输出出错，需要使用行号，是数值型
print(data.iloc[1])
# c    4
# d    5
# e    6
# Name: b, dtype: int64
print(data['c'])        #输出打印出列的数据
# a    1
# b    4
# Name: c, dtype: int64
print('使用ix 方法')
print(data.ix['a'])     #与下方输出的数据一样的
# c    1
# d    2
# e    3
# Name: a, dtype: int64
print(data.ix[0])
# c    1
# d    2
# e    3
# Name: a, dtype: int64

print('-----')

print('-----')
#1.修改列名
data = pd.DataFrame(np.arange(12).reshape(6,2),columns =['a','b'])
print(data)
#     a   b
# 0   0   1
# 1   2   3
# 2   4   5
# 3   6   7
# 4   8   9
# 5  10  11
data.rename(columns ={'a':'key1','b':'key2'},inplace = True)    #inplace 是在原数据上修改
print(data)
#     a   b
# 0   0   1
# 1   2   3
# 2   4   5
# 3   6   7
# 4   8   9
# 5  10  11
d = pd.Series([1,2,3,4,2,4,1])
print(d)
print(d.unique())
print(d.value_counts())
i= d.isin([1,2,5,7])
print(i)    ##计算一个“Series各值是否包含传入的值序列中”的布尔数组
# 0     True
# 1     True
# 2    False
# 3    False
# 4     True
# 5    False
# 6     True
# dtype: bool

#2,值替换 replace（）
data = pd.DataFrame(np.arange(6).reshape(3,2),columns =['a','b'])
print(data)
#    a  b
# 0  0  1
# 1  2  3
# 2  4  5
data['a'] = data['a'].replace({2:100,4:200}) #将2和 4 替换成100 和 200
print(data)
#      a  b
# 0    0  1
# 1  100  3
# 2  200  5
#修改值
cloumns = ['age','name','height','sex']
data = pd.DataFrame([[12,'zhangsan',170,'male'],[18,'lisi',178,'female']],columns=cloumns)
print(data)
#    age      name  height     sex
# 0   12  zhangsan     170    male
# 1   18      lisi     178  female
#修改张三的身高为190
data['height'] = data['height'].replace({170:190})
print(data)
#3数据选取
print(data[data['b']>4])        #选取b行中大于4的数据
#      a  b
# 2  200  5

#创建新的变量test
data = pd.DataFrame(np.arange(12).reshape(3,4),columns = ['a','b','c','d'])
print(data)
#    a  b   c   d
# 0  0  1   2   3
# 1  4  5   6   7
# 2  8  9  10  11
data['test'] = None
s = data['b']> 4
data['test'] = np.where(s,1,0)
print(data)
#    a  b   c   d  test
# 0  0  1   2   3     0
# 1  4  5   6   7     1
# 2  8  9  10  11     1

import pandas as pd
import numpy as np
data = pd.DataFrame(np.arange(12).reshape(3,4),columns = ['a','b','c','d'])
print(data)
#    a  b   c   d
# 0  0  1   2   3
# 1  4  5   6   7
# 2  8  9  10  11
print(data['a'][1]) #返回第 'a'列的第一个元素    4
print(data.ix[0,1]) #返回第一行第二列的元素    1
print(data.iloc[0:2,0:2])       #输出指定的行列数的数据
#    a  b
# 0  0  1
# 1  4  5

 

---