为什么这个双 x 轴重复两次？

Question

我的问题与另一个问题有关How to use factorplot to annotate bars with categorical values or to plot 4 variables?

我设法将条形图绘制在一起并放置了第二个轴。但它仅在 Clf 列中有 2 个值时才有效。对于 4 个值，x 轴重复两次。所以不是有 5 组 4 条，而是 10 组 2 条？请查看图片以了解问题。

我认为问题出在这行代码中：

pos = np.arange(0,l) % (l//2) + (np.arange(0,l)//(l//2)-1)*0.4
ax.bar(pos, df["Max_Acc"], width=0.4, align="edge", ec="k", color=colors)
handles=[plt.Rectangle((0,0),1,1, color=palette[i], ec="k") for i in range(len(uelec))]

但我真的不知道如何解决它。

#CODE FOR THE DATAFRAME
raw_data = {'Max_Acc': [90.71, 87.98, 92.62, 78.93, 73.69,
                       92.62, 94.17, 92.62, 83.81, 79.76,
                       85.36, 89.23, 88.88, 56.23, 89.54,
                       36.25, 14.52, 85.45, 75.45, 45.54],
            'Stage': ['AWA', 'Rem', 'S1', 'S2', 'SWS', 
                      'AWA', 'Rem', 'S1', 'S2', 'SWS',
                      'AWA', 'Rem', 'S1', 'S2', 'SWS', 
                      'AWA', 'Rem', 'S1', 'S2', 'SWS'],
            'Elec': ['Fp1', 'Fp2', 'C4', 'Cz', 'Pz',
                  'C4', 'T3', 'Fp1', 'P4', 'Fp2',
                  'Cz', 'P3', 'P4', 'T4', 'Cp1', 
                  'Cp2', 'T3', 'T4', 'Fp2', 'Fp1'],
            'Clf': ['RF', 'RF', 'RF', 'RF', 'RF',
                    'XG', 'XG', 'XG', 'XG', 'XG', 
                    'SVM','SVM','SVM','SVM','SVM',
                    'KNN','KNN','KNN','KNN','KNN']}

df=pd.DataFrame(raw_data, columns = ['Max_Acc', 'Stage', 'Elec', 'Clf'])
df


#CODE FOR THE PLOT
#To use seaborn palette
palette = sns.color_palette("Set1", 12)
sns.set(style="white")

uelec, uind = np.unique(df["Elec"], return_inverse=1)
cmap = plt.cm.get_cmap("Set1")

colors= [ palette[i] for i in uind]
fig, ax=plt.subplots(figsize=(15, 5)) 
l = len(df)
pos = np.arange(0,l) % (l//2) + (np.arange(0,l)//(l//2)-1)*0.4

ax.bar(pos, df["Max_Acc"], width=0.4, align="edge", ec="k", color=colors)

handles=[plt.Rectangle((0,0),1,1, color=palette[i], ec="k") for i in range(len(uelec))]

legend=ax.legend(bbox_to_anchor=(0., 1.15, 1., .102), handles=handles, labels=list(uelec),
   prop ={'size':10}, loc=9, ncol=8, title=r'Best algorithm using Max_Acc after undersampling' )

legend.get_frame().set_linewidth(0.0) 
plt.setp(legend.get_title(),fontsize='24')

ax.set_xticks(range(l//2))
ax.set_xticklabels(df["Stage"][:l//2])
ax.set_ylim(0, 110)
ax.get_yaxis().set_visible(False)
ax.spines['top'].set_visible(False) 

#Double x-axis
ax.set_xticks(pos+0.2, minor=True)
clf=df['Clf'].tolist()   
ax.set_xticklabels(clf, minor=True)
plt.setp(ax.get_xticklabels(), rotation=0)
ax.tick_params(axis='x', which='major', pad=25, size=0)

ax=ax 
def annotateBars(row, ax=ax): 
    for p in ax.patches:
        ax.annotate("%.2f" % p.get_height(), (p.get_x() + p.get_width() / 2., p.get_height()),
             ha='center', va='center', fontsize=11, color='gray', rotation=90, xytext=(0, 20),
             textcoords='offset points')  

plot = df.apply(annotateBars, ax=ax, axis=1)

我得到的图像

图片应该是：

Answer 1

要绘制具有多个标签的分组条形图，您可以参考this question。为了能够简单地将数据框绘制为分组条形图，您可以旋转您的数据框，一次用于值，一次用于算法。然后，您可以创建算法名称到数字的唯一映射，该映射可由颜色图应用。最好选择超过 11 种不同颜色的颜色图。

import matplotlib.pyplot as plt
import pandas as pd

#CODE FOR THE DATAFRAME
raw_data = {'Max_Acc': [90.71, 87.98, 92.62, 78.93, 73.69,
                       92.62, 94.17, 92.62, 83.81, 79.76,
                       85.36, 89.23, 88.88, 56.23, 89.54,
                       36.25, 14.52, 85.45, 75.45, 45.54],
            'Stage': ['AWA', 'Rem', 'S1', 'S2', 'SWS', 
                      'AWA', 'Rem', 'S1', 'S2', 'SWS',
                      'AWA', 'Rem', 'S1', 'S2', 'SWS', 
                      'AWA', 'Rem', 'S1', 'S2', 'SWS'],
            'Elec': ['Fp1', 'Fp2', 'C4', 'Cz', 'Pz',
                  'C4', 'T3', 'Fp1', 'P4', 'Fp2',
                  'Cz', 'P3', 'P4', 'T4', 'Cp1', 
                  'Cp2', 'T3', 'T4', 'Fp2', 'Fp1'],
            'Clf': ['RF', 'RF', 'RF', 'RF', 'RF',
                    'XG', 'XG', 'XG', 'XG', 'XG', 
                    'SVM','SVM','SVM','SVM','SVM',
                    'KNN','KNN','KNN','KNN','KNN']}

df=pd.DataFrame(raw_data, columns = ['Max_Acc', 'Stage', 'Elec', 'Clf'])

# pivot the dataframe for values and algorithims
df2= pd.pivot(df["Stage"], df['Clf'], df['Max_Acc'])
df3= pd.pivot(df["Stage"], df['Clf'], df['Elec'])

# maping between unique algorithms and some numbers
mapping = dict(zip(df['Elec'].unique(), range(len(df['Elec'].unique()))))
df4 = df3.applymap(lambda x: mapping[x])
palette = plt.cm.tab20


# plot the grouped barplot
ax = df2.plot(kind="bar")

# create positions, colorize bars and annotate bars
pos = []
for (bar, ind) in zip(ax.patches, df4.values.T.flatten()):
    pos.append(bar.get_x()+bar.get_width()/2.)
    bar.set_color(palette(ind))
    ax.annotate("%.2f"%bar.get_height(), (bar.get_x()+bar.get_width()/2., 
                                            bar.get_height()),
             ha='center', va='center', fontsize=10, color='gray', 
             rotation=90, xytext=(0, 20), textcoords='offset points')

# Label minor ticks
ax.set_xticks(pos,minor=True)
lab = []
for i in range(len(pos)):
    l = df2.columns.values[i//len(df2.index.values)]
    lab.append(l)

ax.set_xticklabels(lab,minor=True, rotation=90)
ax.tick_params(axis='x', which='major', pad=30, size=0)
plt.setp(ax.get_xticklabels(), rotation=0)

# legend
handle = lambda ind : plt.Rectangle([0,0],0,0,color=palette(ind))
h, l = zip(*[(handle(ind), la) for (la, ind) in mapping.items() ])

legend=ax.legend(handles=h, labels=l, bbox_to_anchor=(0., 1.15, 1., .102), 
   prop ={'size':10}, loc=9, ncol=6, columnspacing=1,
   title=r'Best algorithm using Max_Acc after undersampling' )

# layout
plt.tight_layout()
plt.subplots_adjust(top=0.8)

ax.set_ylim(0, 120)
ax.get_yaxis().set_visible(False)
ax.spines['top'].set_visible(False) 

plt.show()