python添加行索引_python-熊猫在特定级别向多索引添加行

您可以使用由numpy.repeat和numpy.tile创建的帮助器DataFrame与左联接合并：

#get number of new rows by Counter.most_common(1)

from collections import Counter

no_vals = Counter(df.index.labels[0]).most_common(1)[0][1]

print(no_vals)

3

df1 = pd.DataFrame({'region':np.repeat(df.index.levels[0],no_vals),'id': np.tile(np.arange(no_vals),len(np.unique(df.index.labels[0])))})

print (df1)

region id

0 intro 0

1 intro 1

2 intro 2

3 mid 0

4 mid 1

5 mid 2

6 start 0

7 start 1

8 start 2

9 title 0

10 title 1

11 title 2

#MultiIndex to columns

df = df.reset_index()

#new could with counter of regions

df.insert(1,'id',df.groupby('region').cumcount())

#merge,remove helper id columns and create MultiIndex

df = (df1.merge(df,how='left')

.drop('id',1)

.set_index(['region','position_in_region']))

print (df)

document_0 document_1 document_2

region feat_index position_in_region

intro 9.0 422.0 0.39 0.80 0.81

3.0 5834.0 0.79 0.06 0.15

0.0 8813.0 0.01 0.92 0.19

mid 7.0 3187.0 0.55 0.74 0.17

8.0 9407.0 0.99 0.06 0.11

NaN NaN NaN NaN NaN

start 2.0 997.0 0.67 0.96 0.34

4.0 3154.0 0.61 0.57 0.80

1.0 8416.0 0.84 0.19 0.03

title 6.0 5408.0 0.15 0.29 0.67

5.0 8421.0 0.23 0.24 0.46

NaN NaN NaN NaN NaN

from collections import Counter

no_vals = Counter(df.index.labels[0]).most_common(1)[0][1]

print(no_vals)

3

mux = pd.MultiIndex.from_product([df.index.levels[0],np.arange(no_vals)],names=['region','id'])

print (mux)

MultiIndex(levels=[['intro','mid','start','title'],[0,1,2]],codes=[[0,2,3,3],'id'])

df = df.reset_index(level=[1,2]).set_index(df.groupby(level=0).cumcount(),append=True)

df = (df.reindex(mux).reset_index(level=1,drop=True)

.set_index(['feat_index','position_in_region'],append=True))

print (df)

document_0 document_1 document_2

region feat_index position_in_region

intro 9.0 422.0 0.39 0.80 0.81

3.0 5834.0 0.79 0.06 0.15

0.0 8813.0 0.01 0.92 0.19

mid 7.0 3187.0 0.55 0.74 0.17

8.0 9407.0 0.99 0.06 0.11

NaN NaN NaN NaN NaN

start 2.0 997.0 0.67 0.96 0.34

4.0 3154.0 0.61 0.57 0.80

1.0 8416.0 0.84 0.19 0.03

title 6.0 5408.0 0.15 0.29 0.67

5.0 8421.0 0.23 0.24 0.46

NaN NaN NaN NaN NaN