How to render two pd.DataFrames in jupyter noteboo

问题:

Is there an easy way to quickly see contents of two pd.DataFrames side-by-side in Jupyter notebooks?

df1 = pd.DataFrame([(1,2),(3,4)], columns=['a', 'b'])
df2 = pd.DataFrame([(1.1,2.1),(3.1,4.1)], columns=['a', 'b'])
df1, df2

回答1:

The closest to what you want could be:

> df1.merge(df2, right_index=1, left_index=1, suffixes=("_1", "_2"))
   a_1  b_1  a_2  b_2
0    1    2  1.1  2.1
1    3    4  3.1  4.1

It's not specific of the notebook, but it will work, and it's not that complicated. Another solution would be to convert your dataframe to an image and put them side by side in subplots. But it's a bit far-fetched and complicated.

回答2:

You should try this function from @Wes_McKinney

def side_by_side(*objs, **kwds):
    ''' Une fonction print objects side by side '''
    from pandas.io.formats.printing import adjoin
    space = kwds.get('space', 4)
    reprs = [repr(obj).split('\n') for obj in objs]
    print(adjoin(space, *reprs))


# building a test case of two DataFrame
import pandas as pd
import numpy as np


n, p = (10, 3)  # dfs' shape

# dfs indexes and columns labels
index_rowA = [t[0]+str(t[1]) for t in zip(['rA']*n, range(n))]
index_colA = [t[0]+str(t[1]) for t in zip(['cA']*p, range(p))]

index_rowB = [t[0]+str(t[1]) for t in zip(['rB']*n, range(n))]
index_colB = [t[0]+str(t[1]) for t in zip(['cB']*p, range(p))]

# buliding the df A and B
dfA = pd.DataFrame(np.random.rand(n,p), index=index_rowA, columns=index_colA)
dfB = pd.DataFrame(np.random.rand(n,p), index=index_rowB, columns=index_colB)

side_by_side(dfA,dfB) Outputs

          cA0       cA1       cA2              cB0       cB1       cB2
rA0  0.708763  0.665374  0.718613    rB0  0.320085  0.677422  0.722697
rA1  0.120551  0.277301  0.646337    rB1  0.682488  0.273689  0.871989
rA2  0.372386  0.953481  0.934957    rB2  0.015203  0.525465  0.223897
rA3  0.456871  0.170596  0.501412    rB3  0.941295  0.901428  0.329489
rA4  0.049491  0.486030  0.365886    rB4  0.597779  0.201423  0.010794
rA5  0.277720  0.436428  0.533683    rB5  0.701220  0.261684  0.502301
rA6  0.391705  0.982510  0.561823    rB6  0.182609  0.140215  0.389426
rA7  0.827597  0.105354  0.180547    rB7  0.041009  0.936011  0.613592
rA8  0.224394  0.975854  0.089130    rB8  0.697824  0.887613  0.972838
rA9  0.433850  0.489714  0.339129    rB9  0.263112  0.355122  0.447154

回答3:

I ended up using a helper function to quickly compare two data frames:

def cmp(df1, df2, topn=10):
    n = topn
    a = df1.reset_index().head(n=n)
    b = df2.reset_index().head(n=n)

    span = pd.DataFrame(data=[('-',) for _ in range(n)], columns=['sep'])

    a = a.merge(span, right_index=1, left_index=1)
    return a.merge(b, right_index=1, left_index=1, suffixes=['_L', '_R'])