Jupyter notebook display two pandas tables side by side

Question

I have two pandas dataframes and I would like to display them in Jupyter notebook.

Doing something like:

display(df1)
display(df2)

Answer 1

Combining approaches of gibbone (to set styles and captions) and stevi (adding space) I made my version of function, which outputs pandas dataframes as tables side-by-side:

from IPython.core.display import display, HTML

def display_side_by_side(dfs:list, captions:list):
    """Display tables side by side to save vertical space
    Input:
        dfs: list of pandas.DataFrame
        captions: list of table captions
    """
    output = ""
    combined = dict(zip(captions, dfs))
    for caption, df in combined.items():
        output += df.style.set_table_attributes("style='display:inline'").set_caption(caption)._repr_html_()
        output += "\xa0\xa0\xa0"
    display(HTML(output))

Usage:

display_side_by_side([df1, df2, df3], ['caption1', 'caption2', 'caption3'])

Output:

Answer 2

I ended up using HBOX

import ipywidgets as ipyw

def get_html_table(target_df, title):
    df_style = target_df.style.set_table_attributes("style='border:2px solid;font-size:10px;margin:10px'").set_caption(title)
    return df_style._repr_html_()

df_2_html_table = get_html_table(df_2, 'Data from Google Sheet')
df_4_html_table = get_html_table(df_4, 'Data from Jira')
ipyw.HBox((ipyw.HTML(df_2_html_table),ipyw.HTML(df_4_html_table)))

Answer 3

I decided to add some extra functionality to Yasin's elegant answer, where one can choose both the number of cols and rows; any extra dfs are then added to the bottom. Additionally one can choose in which order to fill the grid (simply change fill keyword to 'cols' or 'rows' as needed)

import pandas as pd
from IPython.display import display,HTML

def grid_df_display(list_dfs, rows = 2, cols=3, fill = 'cols'):
    html_table = "<table style='width:100%; border:0px'>{content}</table>"
    html_row = "<tr style='border:0px'>{content}</tr>"
    html_cell = "<td style='width:{width}%;vertical-align:top;border:0px'>{{content}}</td>"
    html_cell = html_cell.format(width=100/cols)

    cells = [ html_cell.format(content=df.to_html()) for df in list_dfs[:rows*cols] ]
    cells += cols * [html_cell.format(content="")] # pad

    if fill == 'rows': #fill in rows first (first row: 0,1,2,... col-1)
        grid = [ html_row.format(content="".join(cells[i:i+cols])) for i in range(0,rows*cols,cols)]

    if fill == 'cols': #fill columns first (first column: 0,1,2,..., rows-1)
        grid = [ html_row.format(content="".join(cells[i:rows*cols:rows])) for i in range(0,rows)]

    display(HTML(html_table.format(content="".join(grid))))

    #add extra dfs to bottom
    [display(list_dfs[i]) for i in range(rows*cols,len(list_dfs))]

list_dfs = []
list_dfs.extend((pd.DataFrame(2*[{"x":"hello"}]), 
             pd.DataFrame(2*[{"x":"world"}]), 
             pd.DataFrame(2*[{"x":"gdbye"}])))

grid_df_display(3*list_dfs)

test output

Answer 4

Here is Jake Vanderplas' solution I came across just the other day:

import numpy as np
import pandas as pd

class display(object):
    """Display HTML representation of multiple objects"""
    template = """<div style="float: left; padding: 10px;">
    <p style='font-family:"Courier New", Courier, monospace'>{0}</p>{1}
    </div>"""

    def __init__(self, *args):
        self.args = args

    def _repr_html_(self):
        return '\n'.join(self.template.format(a, eval(a)._repr_html_())
                     for a in self.args)

    def __repr__(self):
       return '\n\n'.join(a + '\n' + repr(eval(a))
                       for a in self.args)

Credit: https://github.com/jakevdp/PythonDataScienceHandbook/blob/master/notebooks/03.08-Aggregation-and-Grouping.ipynb

Answer 5

I have ended up writing a function that can do this:

from IPython.display import display_html
def display_side_by_side(*args):
    html_str=''
    for df in args:
        html_str+=df.to_html()
    display_html(html_str.replace('table','table style="display:inline"'),raw=True)

Example usage:

df1 = pd.DataFrame(np.arange(12).reshape((3,4)),columns=['A','B','C','D',])
df2 = pd.DataFrame(np.arange(16).reshape((4,4)),columns=['A','B','C','D',])
display_side_by_side(df1,df2,df1)

Answer 6

Extension of antony's answer If you want to limit de visualization of tables to some numer of blocks by row, use the maxTables variable.

def mydisplay(dfs, names=[]):

    count = 0
    maxTables = 6

    if not names:
        names = [x for x in range(len(dfs))]

    html_str = ''
    html_th = ''
    html_td = ''

    for df, name in zip(dfs, names):
        if count <= (maxTables):
            html_th += (''.join(f'<th style="text-align:center">{name}</th>'))
            html_td += (''.join(f'<td style="vertical-align:top"> {df.to_html(index=False)}</td>'))
            count += 1
        else:
            html_str += f'<tr>{html_th}</tr><tr>{html_td}</tr>'
            html_th = f'<th style="text-align:center">{name}</th>'
            html_td = f'<td style="vertical-align:top"> {df.to_html(index=False)}</td>'
            count = 0


    if count != 0:
        html_str += f'<tr>{html_th}</tr><tr>{html_td}</tr>'


    html_str += f'<table>{html_str}</table>'
    html_str = html_str.replace('table','table style="display:inline"')
    display_html(html_str, raw=True)