python学习-pandas

1、Series

obj = pd.Series([4, 7, -5, 3]) #创建series
obj.values #获取值
obj.index #获取索引
obj2 = pd.Series([4, 7, -5, 3], index=[‘d‘, ‘b‘, ‘a‘, ‘c‘]) #指定索引创建Series
obj2[‘a‘] #获取值
obj2[[‘c‘, ‘a‘, ‘d‘]] 
obj2[obj2 > 0] #使用boolean数组过滤
np.exp(obj2) #表达式
#可以作为固定长度 有序的字典使用
‘b‘ in obj2 
#通过字典创建Series
sdata = {‘Ohio‘: 35000, ‘Texas‘: 71000, ‘Oregon‘: 16000, ‘Utah‘: 5000}
obj3 = pd.Series(sdata)
#更改索引
 states = [‘California‘, ‘Ohio‘, ‘Oregon‘, ‘Texas‘]
obj4= pd.Series(sdata, index=states)
#判断是否为空
pd.isnull(obj4)
pd.notnull(obj4)
obj4.isnull()

#设置name
obj4.name = ‘population‘
obj4.index.name = ‘state‘
#更改索引
obj.index = [‘Bob‘, ‘Steve‘, ‘Jeff‘, ‘Ryan‘]

2、DataFrame

data = {‘state‘: [‘Ohio‘, ‘Ohio‘, ‘Ohio‘, ‘Nevada‘, ‘Nevada‘, ‘Nevada‘], ‘year‘: [2000, 2001, 2002, 2001, 2002, 2003],
‘pop‘: [1.5, 1.7, 3.6, 2.4, 2.9, 3.2]}
frame = pd.DataFrame(data)
#指定有序列
pd.DataFrame(data, columns=[‘year‘, ‘state‘, ‘pop‘])
#指定列和索引，没有则显示空
frame2 = pd.DataFrame(data, columns=[‘year‘, ‘state‘, ‘pop‘, ‘debt‘], index=[‘one‘, ‘two‘, ‘three‘, ‘four‘,
‘five‘, ‘six‘])

frame2.columns
frame2[‘state‘]
frame2.loc[‘three‘] #获取某行值
#frame 列赋值
frame2[‘debt‘] = np.arange(6.)
val = pd.Series([-1.2, -1.5, -1.7], index=[‘two‘, ‘four‘, ‘five‘])
frame2[‘debt‘] = val
frame2[‘eastern‘] = frame2.state == ‘Ohio‘
 del frame2[‘eastern‘] #删除列

#嵌套字典组成frame
pop = {‘Nevada‘: {2001: 2.4, 2002: 2.9},‘Ohio‘: {2000: 1.5, 2001: 1.7, 2002: 3.6}}
frame3 = pd.DataFrame(pop)

frame3.index.name = ‘year‘; 
frame3.columns.name = ‘state‘
frame2.values

#索引
obj = pd.Series(range(3), index=[‘a‘, ‘b‘, ‘c‘])
index = obj.index
labels = pd.Index(np.arange(3))
obj2 = pd.Series([1.5, -2.5, 0], index=labels)
obj2.index is labels

‘Ohio‘ in frame3.columns
2003 in frame3.index

pd.Index([‘foo‘, ‘foo‘, ‘bar‘, ‘bar‘])#pandas index可以重复

3、重要函数

#reindex
obj = pd.Series([4.5, 7.2, -5.3, 3.6], index=[‘d‘, ‘b‘, ‘a‘, ‘c‘])
obj2 = obj.reindex([‘a‘, ‘b‘, ‘c‘, ‘d‘, ‘e‘])

#reindex 可以改变index column
frame = pd.DataFrame(np.arange(9).reshape((3, 3)), index=[‘a‘, ‘c‘, ‘d‘],
                     columns=[‘Ohio‘, ‘Texas‘, ‘California‘])
frame2 = frame.reindex([‘a‘, ‘b‘, ‘c‘, ‘d‘])
states = [‘Texas‘, ‘Utah‘, ‘California‘]
frame.reindex(columns=states)
frame.loc[[‘a‘, ‘b‘, ‘c‘, ‘d‘], states]

#drop
 obj = pd.Series(np.arange(5.), index=[‘a‘, ‘b‘, ‘c‘, ‘d‘, ‘e‘])
 obj.drop([‘d‘, ‘c‘])

data = pd.DataFrame(np.arange(16).reshape((4, 4)),index=[‘Ohio‘, ‘Colorado‘, ‘Utah‘, ‘New York‘],
columns=[‘one‘, ‘two‘, ‘three‘, ‘four‘])

data.drop([‘Colorado‘, ‘Ohio‘])#drop row
data.drop(‘two‘, axis=1) #通过axis drop列
data.drop([‘two‘, ‘four‘], axis=‘columns‘)#通过columns drop列

obj.drop(‘c‘, inplace=True) #inplace 不创建新对象

4、选择索引

obj = pd.Series(np.arange(4.), index=[‘a‘, ‘b‘, ‘c‘, ‘d‘])
obj[‘b‘]
obj[1]
obj[2:4]
obj[[‘b‘, ‘a‘, ‘d‘]]
obj[[1, 3]]
obj[obj < 2]
obj[‘b‘:‘c‘]
obj[‘b‘:‘c‘] = 5

data = pd.DataFrame(np.arange(16).reshape((4, 4)),
index=[‘Ohio‘, ‘Colorado‘, ‘Utah‘, ‘New York‘],
                    columns=[‘one‘, ‘two‘, ‘three‘, ‘four‘])
data[‘two‘]
data[[‘three‘, ‘one‘]]
data[:2] #选择行
data[data[‘three‘] > 5]

#Selection with loc and iloc
data.loc[‘Colorado‘, [‘two‘, ‘three‘]]
data.iloc[2, [3, 0, 1]] 
data.iloc[[1, 2], [3, 0, 1]]
data.loc[:‘Utah‘, ‘two‘]
data.iloc[:, :3][data.three > 5]

5、运算和排列

df1 = pd.DataFrame(np.arange(12.).reshape((3, 4)), columns=list(‘abcd‘))
df2 = pd.DataFrame(np.arange(20.).reshape((4, 5)), columns=list(‘abcde‘))
df2.loc[1, ‘b‘] = np.nan
df1.add(df2, fill_value=0)
 1 / df1
df1.reindex(columns=df2.columns, fill_value=0)

frame = pd.DataFrame(np.arange(12.).reshape((4, 3)), columns=list(‘bde‘),
index=[‘Utah‘, ‘Ohio‘, ‘Texas‘, ‘Oregon‘])
series = frame.iloc[0]
frame - series
series3 = frame[‘d‘]
frame.sub(series3, axis=‘index‘)

6、功能应用和映射

frame = pd.DataFrame(np.random.randn(4, 3), columns=list(‘bde‘), index=[‘Utah‘, ‘Ohio‘, ‘Texas‘, ‘Oregon‘])
np.abs(frame)

f = lambda x: x.max() - x.min()

frame.apply(f)
frame.apply(f,axis=‘columns‘)

def f(x):
    return pd.Series([x.min(), x.max()], index=[‘min‘, ‘max‘])

format = lambda x: ‘%.2f‘ % x
frame.applymap(format)

frame[‘e‘].map(format)

7、排序和rank

frame = pd.DataFrame(np.arange(8).reshape((2, 4)),index=[‘three‘, ‘one‘],columns=[‘d‘, ‘a‘, ‘b‘, ‘c‘])
frame.sort_index()
frame.sort_index(axis=1, ascending=False)

obj = pd.Series([4, 7, -3, 2]) 
obj.sort_values()

frame = pd.DataFrame({‘b‘: [4, 7, -3, 2], ‘a‘: [0, 1, 0, 1]})
frame.sort_values(by=‘b‘)
frame.sort_values(by=[‘a‘, ‘b‘])

8、统计计算

df= pd.DataFrame([[1.4, np.nan], [7.1, -4.5],[np.nan, np.nan], [0.75, -1.3]],
                 index=[‘a‘, ‘b‘, ‘c‘, ‘d‘], columns=[‘one‘, ‘two‘])
df
 df.sum()
df.sum(axis=‘columns‘)
df.mean(axis=‘columns‘, skipna=False)
df.idxmax()
df.idxmin()
df.cumsum()
df.describe()

obj = pd.Series([‘a‘, ‘a‘, ‘b‘, ‘c‘] * 4)
obj.describe()


import pandas_datareader.data as web

9、Unique Values, Value Counts, and Membership

obj = pd.Series([‘c‘, ‘a‘, ‘d‘, ‘a‘, ‘a‘, ‘b‘, ‘b‘, ‘c‘, ‘c‘])
uniques = obj.unique()
obj.value_counts()
pd.value_counts(obj.values, sort=False)
mask = obj.isin([‘b‘, ‘c‘])
obj[mask]
to_match = pd.Series([‘c‘, ‘a‘, ‘b‘, ‘b‘, ‘c‘, ‘a‘])
unique_vals = pd.Series([‘c‘, ‘b‘, ‘a‘])
pd.Index(unique_vals).get_indexer(to_match)