pandas 基础
serise
import pandas as pd
from pandas import Series, DataFrame
obj = Series([4, -7, 5, 3])
obj
0 4
1 -7
2 5
3 3
dtype: int64
obj.values
array([ 4, -7, 5, 3], dtype=int64)
obj.index
RangeIndex(start=0, stop=4, step=1)
obj[[1,3]]
# 跳着选取数据
1 -7
3 3
dtype: int64
obj[1:3]
1 -7
2 5
dtype: int64
pd.isnull(obj)
0 False
1 False
2 False
3 False
dtype: bool
- reindex可以用来插值
obj.reindex(range(5), method = 'ffill')
0 4
1 -7
2 5
3 3
4 3
dtype: int64
- 标签切片是闭区间的
dataframe
data = {'state': ['asd','qwe','sdf','ert'],
'year': [2000, 2001, 2002, 2003],
'pop': [1.5,1.7,3.6,2.4]}
data = DataFrame(data)
data
.dataframe thead tr:only-child th {
text-align: right;
}
.dataframe thead th {
text-align: left;
}
.dataframe tbody tr th {
vertical-align: top;
}
| pop | state | year | |
|---|---|---|---|
| 0 | 1.5 | asd | 2000 |
| 1 | 1.7 | qwe | 2001 |
| 2 | 3.6 | sdf | 2002 |
| 3 | 2.4 | ert | 2003 |
data.year
# 比r里提取列要方便点
0 2000
1 2001
2 2002
3 2003
Name: year, dtype: int64
data['debt'] = range(4)
data
.dataframe thead tr:only-child th {
text-align: right;
}
.dataframe thead th {
text-align: left;
}
.dataframe tbody tr th {
vertical-align: top;
}
| pop | state | year | debt | |
|---|---|---|---|---|
| 0 | 1.5 | asd | 2000 | 0 |
| 1 | 1.7 | qwe | 2001 | 1 |
| 2 | 3.6 | sdf | 2002 | 2 |
| 3 | 2.4 | ert | 2003 | 3 |
- index是不能修改的
a = data.index
a[1] = 6
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-9-57677294f950> in <module>()
1 a = data.index
----> 2 a[1] = 6
F:\Anaconda\lib\site-packages\pandas\core\indexes\base.py in __setitem__(self, key, value)
1668
1669 def __setitem__(self, key, value):
-> 1670 raise TypeError("Index does not support mutable operations")
1671
1672 def __getitem__(self, key):
TypeError: Index does not support mutable operations
data.columns
Index(['pop', 'state', 'year', 'debt'], dtype='object')
- .ix标签索引功能，输入行和列
- 不加.ix只能选取其中的某列或某行，不能列与行同时选取
data[:3]
.dataframe thead tr:only-child th {
text-align: right;
}
.dataframe thead th {
text-align: left;
}
.dataframe tbody tr th {
vertical-align: top;
}
| pop | state | year | debt | |
|---|---|---|---|---|
| 0 | 1.5 | asd | 2000 | 0 |
| 1 | 1.7 | qwe | 2001 | 1 |
| 2 | 3.6 | sdf | 2002 | 2 |
data.ix[:,:3]
.dataframe thead tr:only-child th {
text-align: right;
}
.dataframe thead th {
text-align: left;
}
.dataframe tbody tr th {
vertical-align: top;
}
| pop | state | year | |
|---|---|---|---|
| 0 | 1.5 | asd | 2000 |
| 1 | 1.7 | qwe | 2001 |
| 2 | 3.6 | sdf | 2002 |
| 3 | 2.4 | ert | 2003 |
- 删除某列用drop，axis = 0表示行，1表示列
- 删除后原数据不变
data.drop(0,axis=0)
.dataframe thead tr:only-child th {
text-align: right;
}
.dataframe thead th {
text-align: left;
}
.dataframe tbody tr th {
vertical-align: top;
}
| pop | state | year | debt | |
|---|---|---|---|---|
| 1 | 1.7 | qwe | 2001 | 1 |
| 2 | 3.6 | sdf | 2002 | 2 |
| 3 | 2.4 | ert | 2003 | 3 |
data.drop('year', axis=1)
.dataframe thead tr:only-child th {
text-align: right;
}
.dataframe thead th {
text-align: left;
}
.dataframe tbody tr th {
vertical-align: top;
}
| pop | state | debt | |
|---|---|---|---|
| 0 | 1.5 | asd | 0 |
| 1 | 1.7 | qwe | 1 |
| 2 | 3.6 | sdf | 2 |
| 3 | 2.4 | ert | 3 |
data
.dataframe thead tr:only-child th {
text-align: right;
}
.dataframe thead th {
text-align: left;
}
.dataframe tbody tr th {
vertical-align: top;
}
| pop | state | year | debt | |
|---|---|---|---|---|
| 0 | 1.5 | asd | 2000 | 0 |
| 1 | 1.7 | qwe | 2001 | 1 |
| 2 | 3.6 | sdf | 2002 | 2 |
| 3 | 2.4 | ert | 2003 | 3 |
import numpy as np
df = DataFrame(np.arange(9).reshape(3, 3))
df
.dataframe thead tr:only-child th {
text-align: right;
}
.dataframe thead th {
text-align: left;
}
.dataframe tbody tr th {
vertical-align: top;
}
| 0 | 1 | 2 | |
|---|---|---|---|
| 0 | 0 | 1 | 2 |
| 1 | 3 | 4 | 5 |
| 2 | 6 | 7 | 8 |
- applymap()可以对dataframe每一个元素运用函数
- apply()可以对每一维数组运用函数
df.applymap(lambda x: '%.2f' % x)
.dataframe thead tr:only-child th {
text-align: right;
}
.dataframe thead th {
text-align: left;
}
.dataframe tbody tr th {
vertical-align: top;
}
| 0 | 1 | 2 | |
|---|---|---|---|
| 0 | 0.00 | 1.00 | 2.00 |
| 1 | 3.00 | 4.00 | 5.00 |
| 2 | 6.00 | 7.00 | 8.00 |
data.sort_values(by='pop')
# 对某一列排序
.dataframe thead tr:only-child th {
text-align: right;
}
.dataframe thead th {
text-align: left;
}
.dataframe tbody tr th {
vertical-align: top;
}
| pop | state | year | debt | |
|---|---|---|---|---|
| 0 | 1.5 | asd | 2000 | 0 |
| 1 | 1.7 | qwe | 2001 | 1 |
| 3 | 2.4 | ert | 2003 | 3 |
| 2 | 3.6 | sdf | 2002 | 2 |
data.describe()
.dataframe thead tr:only-child th {
text-align: right;
}
.dataframe thead th {
text-align: left;
}
.dataframe tbody tr th {
vertical-align: top;
}
| pop | year | debt | |
|---|---|---|---|
| count | 4.000000 | 4.000000 | 4.000000 |
| mean | 2.300000 | 2001.500000 | 1.500000 |
| std | 0.948683 | 1.290994 | 1.290994 |
| min | 1.500000 | 2000.000000 | 0.000000 |
| 25% | 1.650000 | 2000.750000 | 0.750000 |
| 50% | 2.050000 | 2001.500000 | 1.500000 |
| 75% | 2.700000 | 2002.250000 | 2.250000 |
| max | 3.600000 | 2003.000000 | 3.000000 |
df.isin([1])
.dataframe thead tr:only-child th {
text-align: right;
}
.dataframe thead th {
text-align: left;
}
.dataframe tbody tr th {
vertical-align: top;
}
| 0 | 1 | 2 | |
|---|---|---|---|
| 0 | False | True | False |
| 1 | False | False | False |
| 2 | False | False | False |
- None、NaN会被当作NA处理
- df.shape不加括号相当于dim()
df.shape
(3, 3)
- dropna删除缺失值
df.ix[:1, :1] = None
df
.dataframe thead tr:only-child th {
text-align: right;
}
.dataframe thead th {
text-align: left;
}
.dataframe tbody tr th {
vertical-align: top;
}
| 0 | 1 | 2 | |
|---|---|---|---|
| 0 | NaN | NaN | 2 |
| 1 | NaN | NaN | 5 |
| 2 | 6.0 | 7.0 | 8 |
- 填充缺失值可以调用字典，不同行添加不同值
df.fillna({0:11, 1:22})
.dataframe thead tr:only-child th {
text-align: right;
}
.dataframe thead th {
text-align: left;
}
.dataframe tbody tr th {
vertical-align: top;
}
| 0 | 1 | 2 | |
|---|---|---|---|
| 0 | 11.0 | 22.0 | 2 |
| 1 | 11.0 | 22.0 | 5 |
| 2 | 6.0 | 7.0 | 8 |
df
.dataframe thead tr:only-child th {
text-align: right;
}
.dataframe thead th {
text-align: left;
}
.dataframe tbody tr th {
vertical-align: top;
}
| 0 | 1 | 2 | |
|---|---|---|---|
| 0 | NaN | NaN | 2 |
| 1 | NaN | NaN | 5 |
| 2 | 6.0 | 7.0 | 8 |
df.fillna({0:11, 1:22}, inplace=True)
.dataframe thead tr:only-child th {
text-align: right;
}
.dataframe thead th {
text-align: left;
}
.dataframe tbody tr th {
vertical-align: top;
}
| 0 | 1 | 2 | |
|---|---|---|---|
| 0 | 11.0 | 22.0 | 2 |
| 1 | 11.0 | 22.0 | 5 |
| 2 | 6.0 | 7.0 | 8 |
df
.dataframe thead tr:only-child th {
text-align: right;
}
.dataframe thead th {
text-align: left;
}
.dataframe tbody tr th {
vertical-align: top;
}
| 0 | 1 | 2 | |
|---|---|---|---|
| 0 | 11.0 | 22.0 | 2 |
| 1 | 11.0 | 22.0 | 5 |
| 2 | 6.0 | 7.0 | 8 |
- inplace修改对象不产生副本