如何从 ipywidgets 输出返回 pandas 数据帧

Question

我正在 jupyter 笔记本中处理一个数据集，我希望能够以 ipywidgets 输出中返回的数据帧的形式访问该数据。

我尝试过多种选择，但我一生都无法弄清楚如何访问过滤后的结果。

这是设置过滤器和列表框的代码。包含所有代码的完整笔记本在 这里

import pandas as pd
import numpy as np
import ipywidgets as widgets
from ipywidgets import Layout, AppLayout
from IPython.display import display
import functools
 
data = {'year': ['2000', '2000','2000','2000','2001','2001','2001','2001', '2002',  '2002', '2002', '2002',
                 '2003','2003','2003','2003','2004', '2004','2004','2004', '2005', '2005', '2005', '2005', 
                 '2006', '2006', '2006', '2006', '2006', '2007', '2007', '2007', '2007', '2008', '2008', '2008', '2008',
                 '2009', '2009', '2009', '2009'],
        
        'purpose':['Holiday', 'Business', 'VFR', 'Study', 'Holiday', 'Business', 'VFR', 'Study', 'Holiday', 'Business',
                   'VFR', 'Study', 'Holiday', 'Business', 'VFR', 'Study', 'Holiday', 'Business', 'VFR', 'Study', 'Holiday',
                   'Business', 'VFR', 'Study', 'Holiday', 'Business', 'VFR', 'Study', 'Holiday', 'Business', 'VFR', 'Study',
                   'Holiday', 'Business', 'VFR', 'Study', 'Holiday', 'Business', 'VFR', 'Study', 'Holiday'
                  ], 
        
        'market':['Belgium', 'Luxembourg', 'France', 'Spain', 'Norway', 'Sweden', 'Germany', 'Austria', 'Denmark',
                  'Portugal', 'Greece', 'Croatia', 'Belgium', 'Luxembourg', 'France', 'Spain', 'Norway', 'Sweden',
                  'Germany', 'Austria', 'Denmark', 'Portugal', 'Greece', 'Croatia', 'Belgium', 'Luxembourg', 'France',
                  'Spain', 'Norway', 'Sweden', 'Germany', 'Austria', 'Denmark', 'Portugal', 'Greece', 'Croatia', 'Belgium',
                  'Luxembourg', 'France', 'Spain', 'Norway'
                 ]} 
 
df_london = pd.DataFrame (data, columns = ['year','purpose', 'market'])
 
# Get our unique values
ALL = 'ALL'
def unique_sorted_values_plus_ALL(array):
    unique = array.unique().tolist()
    unique.sort()
    unique.insert(0, ALL)
    return unique

output = widgets.Output()

# Dropdown listbox
dropdown_year = widgets.Dropdown(description='Year',
                                  options = unique_sorted_values_plus_ALL(df_london.year))

# Function to filter our dropdown listboxe
def common_filtering(year):
    df = df_london.copy()
        
    filters = []
    
    # Evaluate our dropdown listbox and return booleans for our selections
    if year is not ALL:
        filters.append(df['year'] == year)
    
    output.clear_output()
    
    with output:
        if filters:
            df_filter = functools.reduce(lambda x,y: x&y, filters)
            display(df.loc[df_filter])
        else:
            display(df)

def dropdown_year_eventhandler(change):
    common_filtering(change.new)

dropdown_year.observe(dropdown_year_eventhandler, names='value')

ui = widgets.HBox([dropdown_year])

display(ui, output)

我确信这是一个简单的问题，但我自己无法解决。

问候

汤姆

Answer 1

函数中的代码observe无法以您可以使用的方式真正返回值。或者，您可以设置一个global变量，并将过滤后的数据框分配给该全局变量。我output_dataframe在下面的例子中使用了。

import pandas as pd
import numpy as np
import ipywidgets as widgets
from ipywidgets import Layout, AppLayout
from IPython.display import display
import functools
 
data = {'year': ['2000', '2000','2000','2000','2001','2001','2001','2001', '2002',  '2002', '2002', '2002',
                 '2003','2003','2003','2003','2004', '2004','2004','2004', '2005', '2005', '2005', '2005', 
                 '2006', '2006', '2006', '2006', '2006', '2007', '2007', '2007', '2007', '2008', '2008', '2008', '2008',
                 '2009', '2009', '2009', '2009'],
        
        'purpose':['Holiday', 'Business', 'VFR', 'Study', 'Holiday', 'Business', 'VFR', 'Study', 'Holiday', 'Business',
                   'VFR', 'Study', 'Holiday', 'Business', 'VFR', 'Study', 'Holiday', 'Business', 'VFR', 'Study', 'Holiday',
                   'Business', 'VFR', 'Study', 'Holiday', 'Business', 'VFR', 'Study', 'Holiday', 'Business', 'VFR', 'Study',
                   'Holiday', 'Business', 'VFR', 'Study', 'Holiday', 'Business', 'VFR', 'Study', 'Holiday'
                  ], 
                'market':['Belgium', 'Luxembourg', 'France', 'Spain', 'Norway', 'Sweden', 'Germany', 'Austria', 'Denmark',
                  'Portugal', 'Greece', 'Croatia', 'Belgium', 'Luxembourg', 'France', 'Spain', 'Norway', 'Sweden',
                  'Germany', 'Austria', 'Denmark', 'Portugal', 'Greece', 'Croatia', 'Belgium', 'Luxembourg', 'France',
                  'Spain', 'Norway', 'Sweden', 'Germany', 'Austria', 'Denmark', 'Portugal', 'Greece', 'Croatia', 'Belgium',
                  'Luxembourg', 'France', 'Spain', 'Norway'
                 ]} 
 
df_london = pd.DataFrame (data, columns = ['year','purpose', 'market'])
 
output_dataframe = None

# Get our unique values
ALL = 'ALL'
def unique_sorted_values_plus_ALL(array):
    unique = array.unique().tolist()
    unique.sort()
    unique.insert(0, ALL)
    return unique

output = widgets.Output()

# Dropdown listbox
dropdown_year = widgets.Dropdown(description='Year',
                                  options = unique_sorted_values_plus_ALL(df_london.year))

        
        
# Function to filter our dropdown listboxe
def common_filtering(year):
    global output_dataframe
    df = df_london.copy()
        
    filters = []
    
    # Evaluate our dropdown listbox and return booleans for our selections
    if year is not ALL:
        filters.append(df['year'] == year)
    
    output.clear_output()
    
    with output:
        if filters:
            df_filter = functools.reduce(lambda x,y: x&y, filters)
            output_dataframe = df.loc[df_filter]
        else:
            output_dataframe = df
        display(output_dataframe)

def dropdown_year_eventhandler(change):
    common_filtering(change.new)

dropdown_year.observe(dropdown_year_eventhandler, names='value')

ui = widgets.HBox([dropdown_year])

display(ui, output)