pandas中的数值计算及统计基础

  1 import pandas as pd
  2 import numpy as np
  3 
  4 df = pd.DataFrame({
  5     'key1': [4, 5, 3, np.nan, 2],
  6     'key2': [1, 2, np.nan, 4, 5],
  7     'key3': [1, 2, 3, 'j', 'k']
  8 }, index=['a', 'b', 'c', 'd', 'e'])
  9 print(df)
 10 print(df['key1'].dtype,df['key2'].dtype,df['key3'].dtype)
 11 print('-------')
 12 '''
 13    key1  key2 key3
 14 a   4.0   1.0    1
 15 b   5.0   2.0    2
 16 c   3.0   NaN    3
 17 d   NaN   4.0    j
 18 e   2.0   5.0    k
 19 float64 float64 object
 20 -------
 21 '''
 22 # 计算每一列的均值 df.mean()
 23 # 只统计数字列，默认忽略nan。
 24 print(df.mean())
 25 '''
 26 key1    3.5
 27 key2    3.0
 28 dtype: float64
 29 '''
 30 # 不忽略nan值计算均值
 31 # skipna默认为True，如果为False，有NaN的列统计结果仍为NaN
 32 m3 = df.mean(skipna=False)
 33 print(m3)
 34 '''
 35 key1   NaN
 36 key2   NaN
 37 dtype: float64
 38 '''
 39 # 计算单一列的均值
 40 print('计算单一列的均值',df['key2'].mean())
 41 '''
 42 计算单一列的均值 3.0
 43 '''
 44 
 45 df2 = pd.DataFrame({
 46     'key1': [1, 3, 5],
 47     'key2': [2, 4, 6],
 48     'key3': [3, 5, 7]
 49 }, index=['a', 'b', 'c'])
 50 # print(df2)
 51 # print('--------df2')
 52 # 计算df2每一行的均值并将其结果添加到新的列
 53 df2['mean'] = df2.mean(axis=1)
 54 print(df2)
 55 '''
 56    key1  key2  key3  mean
 57 a     1     2     3   2.0
 58 b     3     4     5   4.0
 59 c     5     6     7   6.0
 60 '''
 61 
 62 # 统计非NaN值的数量  count()
 63 print(df)
 64 print('-'*6)
 65 print(df.count())
 66 '''
 67    key1  key2 key3
 68 a   4.0   1.0    1
 69 b   5.0   2.0    2
 70 c   3.0   NaN    3
 71 d   NaN   4.0    j
 72 e   2.0   5.0    k
 73 ------
 74 key1    4
 75 key2    4
 76 key3    5
 77 dtype: int64
 78 '''
 79 
 80 # 统计
 81 print(df)
 82 print('-' * 6)
 83 print('df的最小值',df.min())
 84 print('df的最大值',df.max())
 85 print('df的key2列的最大值',df['key2'].max())
 86 print('统计df的分位数，参数q确定位置',df.quantile(q=0.75))
 87 print('对df求和',df.sum())
 88 print('求df的中位数，median(),50%分位数',df.median())
 89 print('求df的标准差，std()',df.std())
 90 print('求df的方差，var()',df.var())
 91 print('求skew样本的偏度,skew()',df.skew())
 92 print('求kurt样本的峰度，kurt()',df.kurt())
 93 print('df累计求和，cumsum()',df['key2'].cumsum())
 94 print('df累计求积，cumprod()',df['key2'].cumprod())
 95 print('求df的累计最大值，cummax()', df['key2'].cummax())
 96 print('求df的累计最小值，cummin()', df['key2'].cummin())
 97 '''
 98    key1  key2 key3
 99 a   4.0   1.0    1
100 b   5.0   2.0    2
101 c   3.0   NaN    3
102 d   NaN   4.0    j
103 e   2.0   5.0    k
104 ------
105 df的最小值 key1    2.0
106 key2    1.0
107 dtype: float64
108 df的最大值 key1    5.0
109 key2    5.0
110 dtype: float64
111 df的key2列的最大值 5.0
112 统计df的分位数，参数q确定位置 key1    4.25
113 key2    4.25
114 Name: 0.75, dtype: float64
115 对df求和 key1    14.0
116 key2    12.0
117 dtype: float64
118 求df的中位数，median(),50%分位数 key1    3.5
119 key2    3.0
120 dtype: float64
121 求df的标准差，std() key1    1.290994
122 key2    1.825742
123 dtype: float64
124 求df的方差，var() key1    1.666667
125 key2    3.333333
126 dtype: float64
127 求skew样本的偏度,skew() key1    0.0
128 key2    0.0
129 dtype: float64
130 求kurt样本的峰度，kurt() key1   -1.2
131 key2   -3.3
132 dtype: float64
133 df累计求和，cumsum() a     1.0
134 b     3.0
135 c     NaN
136 d     7.0
137 e    12.0
138 Name: key2, dtype: float64
139 df累计求积，cumprod() a     1.0
140 b     2.0
141 c     NaN
142 d     8.0
143 e    40.0
144 Name: key2, dtype: float64
145 求df的累计最大值，cummax() a    1.0
146 b    2.0
147 c    NaN
148 d    4.0
149 e    5.0
150 Name: key2, dtype: float64
151 求df的累计最小值，cummin() a    1.0
152 b    1.0
153 c    NaN
154 d    1.0
155 e    1.0
156 Name: key2, dtype: float64
157 '''
158 
159 # 唯一值 ：unique()
160 s = pd.Series(list('kjdhsakjdhjfh'))
161 sq = s.unique()
162 print(s)
163 print(sq)
164 print('sq的类型：',type(sq))
165 print('对sq进行重新排序：',pd.Series(sq).sort_values())
166 '''
167 0     k
168 1     j
169 2     d
170 3     h
171 4     s
172 5     a
173 6     k
174 7     j
175 8     d
176 9     h
177 10    j
178 11    f
179 12    h
180 dtype: object
181 ['k' 'j' 'd' 'h' 's' 'a' 'f']
182 sq的类型： <class 'numpy.ndarray'>
183 对sq进行重新排序： 5    a
184 2    d
185 6    f
186 3    h
187 1    j
188 0    k
189 4    s
190 dtype: object
191 '''
192 # 对某一列进行值的计数，只能对一列，不能对Dataframe
193 print(df['key2'].value_counts())
194 
195 # 判断Dataframe中的每个元素是否都是在某个列表中
196 print(df)
197 df_isin = df.isin([1,3])
198 print(df_isin)
199 '''
200    key1  key2 key3
201 a   4.0   1.0    1
202 b   5.0   2.0    2
203 c   3.0   NaN    3
204 d   NaN   4.0    j
205 e   2.0   5.0    k
206 
207 
208     key1   key2   key3
209 a  False   True   True
210 b  False  False  False
211 c   True  False   True
212 d  False  False  False
213 e  False  False  False
214 '''