如何在Python中做華夫餅圖？ （方餅圖）

Question

事情是這樣的：

有一個很好的封裝to do it in R。在Python，最好，我可以弄清楚是這樣的，使用squarify封裝（由a post on how to do treemaps啓發）：

import numpy as np 
import pandas as pd 
import matplotlib as mpl 
import matplotlib.pyplot as plt 
import seaborn as sns # just to have better line color and width 
import squarify 
# for those using jupyter notebooks 
%matplotlib inline 


df = pd.DataFrame({ 
        'v1': np.ones(100), 
        'v2': np.random.randint(1, 4, 100)}) 
df.sort_values(by='v2', inplace=True) 

# color scale 
cmap = mpl.cm.Accent 
mini, maxi = df['v2'].min(), df['v2'].max() 
norm = mpl.colors.Normalize(vmin=mini, vmax=maxi) 
colors = [cmap(norm(value)) for value in df['v2']] 

# figure 
fig = plt.figure() 
ax = fig.add_subplot(111, aspect="equal") 
ax = squarify.plot(df['v1'], color=colors, ax=ax) 
ax.set_xticks([]) 
ax.set_yticks([]); 

但是，當我創建不是100個，但200個元素（或其他非正方形數字），正方形變得不對齊。

另一個問題是，如果我改變v2的一些分類變量（例如，百作爲，BS，CS和DS），我得到這個錯誤：

could not convert string to float: 'a'

所以，能任何人都可以幫助我解決這兩個問題：

• 我該如何解決非平方觀測值的對準問題？
• 如何在v2中使用分類變量？

除此之外，如果有其他可以更有效地創建華夫餅圖的python包，我真的很開放。

Answer 1

我花了幾天來構建更加通用的解決方案，PyWaffle。

您可以通過

pip install pywaffle 

的源代碼安裝：https://github.com/ligyxy/PyWaffle

PyWaffle不使用matshow（）方法，但建立這些廣場一個接一個。這使得定製更容易。此外，它提供的是一個自定義的圖類，它返回一個圖形對象。通過更新圖形的屬性，基本上可以控制圖表中的所有內容。

一些例子：

有色的或透明的背景：

import matplotlib.pyplot as plt 
from pywaffle import Waffle 

data = {'Democratic': 48, 'Republican': 46, 'Libertarian': 3} 
fig = plt.figure(
    FigureClass=Waffle, 
    rows=5, 
    values=data, 
    colors=("#983D3D", "#232066", "#DCB732"), 
    title={'label': 'Vote Percentage in 2016 US Presidential Election', 'loc': 'left'}, 
    labels=["{0} ({1}%)".format(k, v) for k, v in data.items()], 
    legend={'loc': 'lower left', 'bbox_to_anchor': (0, -0.4), 'ncol': len(data), 'framealpha': 0} 
) 
fig.gca().set_facecolor('#EEEEEE') 
fig.set_facecolor('#EEEEEE') 
plt.show() 

使用圖標替換正方形：

data = {'Democratic': 48, 'Republican': 46, 'Libertarian': 3} 
fig = plt.figure(
    FigureClass=Waffle, 
    rows=5, 
    values=data, 
    colors=("#232066", "#983D3D", "#DCB732"), 
    legend={'loc': 'upper left', 'bbox_to_anchor': (1, 1)}, 
    icons='child', icon_size=18, 
    icon_legend=True 
) 

多個副區在一個圖表：

import pandas as pd 
data = pd.DataFrame(
    { 
     'labels': ['Hillary Clinton', 'Donald Trump', 'Others'], 
     'Virginia': [1981473, 1769443, 233715], 
     'Maryland': [1677928, 943169, 160349], 
     'West Virginia': [188794, 489371, 36258], 
    }, 
).set_index('labels') 

fig = plt.figure(
    FigureClass=Waffle, 
    plots={ 
     '311': { 
      'values': data['Virginia']/30000, 
      'labels': ["{0} ({1})".format(n, v) for n, v in data['Virginia'].items()], 
      'legend': {'loc': 'upper left', 'bbox_to_anchor': (1.05, 1), 'fontsize': 8}, 
      'title': {'label': '2016 Virginia Presidential Election Results', 'loc': 'left'} 
     }, 
     '312': { 
      'values': data['Maryland']/30000, 
      'labels': ["{0} ({1})".format(n, v) for n, v in data['Maryland'].items()], 
      'legend': {'loc': 'upper left', 'bbox_to_anchor': (1.2, 1), 'fontsize': 8}, 
      'title': {'label': '2016 Maryland Presidential Election Results', 'loc': 'left'} 
     }, 
     '313': { 
      'values': data['West Virginia']/30000, 
      'labels': ["{0} ({1})".format(n, v) for n, v in data['West Virginia'].items()], 
      'legend': {'loc': 'upper left', 'bbox_to_anchor': (1.3, 1), 'fontsize': 8}, 
      'title': {'label': '2016 West Virginia Presidential Election Results', 'loc': 'left'} 
     }, 
    }, 
    rows=5, 
    colors=("#2196f3", "#ff5252", "#999999"), # Default argument values for subplots 
    figsize=(9, 5) # figsize is a parameter of plt.figure 
) 

Answer 2

我已經放在一起了一個工作示例，下面，我認爲滿足您的需求。需要做一些工作來全面概括這種方法，但我認爲你會發現這是一個好的開始。訣竅是使用matshow()解決您的非方形問題，並構建自定義圖例以輕鬆解釋分類值。

import numpy as np 
import pandas as pd 
import matplotlib as mpl 
import matplotlib.pyplot as plt 
import matplotlib.patches as mpatches 

# Let's make a default data frame with catagories and values. 
df = pd.DataFrame({ 'catagories': ['cat1', 'cat2', 'cat3', 'cat4'], 
        'values': [84911, 14414, 10062, 8565] }) 
# Now, we define a desired height and width. 
waffle_plot_width = 20 
waffle_plot_height = 7 

classes = df['catagories'] 
values = df['values'] 

def waffle_plot(classes, values, height, width, colormap): 

    # Compute the portion of the total assigned to each class. 
    class_portion = [float(v)/sum(values) for v in values] 

    # Compute the number of tiles for each catagories. 
    total_tiles = width * height 
    tiles_per_class = [round(p*total_tiles) for p in class_portion] 

    # Make a dummy matrix for use in plotting. 
    plot_matrix = np.zeros((height, width)) 

    # Popoulate the dummy matrix with integer values. 
    class_index = 0 
    tile_index = 0 

    # Iterate over each tile. 
    for col in range(waffle_plot_width): 
     for row in range(height): 
      tile_index += 1 

      # If the number of tiles populated is sufficient for this class... 
      if tile_index > sum(tiles_per_class[0:class_index]): 

       # ...increment to the next class. 
       class_index += 1  

      # Set the class value to an integer, which increases with class. 
      plot_matrix[row, col] = class_index 

    # Create a new figure. 
    fig = plt.figure() 

    # Using matshow solves your "non-square" problem. 
    plt.matshow(plot_matrix, cmap=colormap) 
    plt.colorbar() 

    # Get the axis. 
    ax = plt.gca() 

    # Minor ticks 
    ax.set_xticks(np.arange(-.5, (width), 1), minor=True); 
    ax.set_yticks(np.arange(-.5, (height), 1), minor=True); 

    # Gridlines based on minor ticks 
    ax.grid(which='minor', color='w', linestyle='-', linewidth=2) 

    # Manually constructing a legend solves your "catagorical" problem. 
    legend_handles = [] 
    for i, c in enumerate(classes): 
     lable_str = c + " (" + str(values[i]) + ")" 
     color_val = colormap(float(i+1)/len(classes)) 
     legend_handles.append(mpatches.Patch(color=color_val, label=lable_str)) 

    # Add the legend. Still a bit of work to do here, to perfect centering. 
    plt.legend(handles=legend_handles, loc=1, ncol=len(classes), 
       bbox_to_anchor=(0., -0.1, 0.95, .10)) 

    plt.xticks([]) 
    plt.yticks([]) 

# Call the plotting function. 
waffle_plot(classes, values, waffle_plot_height, waffle_plot_width, 
      plt.cm.coolwarm) 

下面是這個腳本產生的輸出示例。正如你所看到的，它對我來說效果相當好，並滿足你所有的需求。只要讓我知道它是否會給你帶來麻煩。請享用！