如何绘制scikit学习分类报告？

是否可以使用matplotlib scikit-learn分类报告进行绘图？我们假设我打印分类报告如下:

print '\n*Classification Report:\n', classification_report(y_test, predictions)
    confusion_matrix_graph = confusion_matrix(y_test, predictions)

我得到:

Clasification Report:
             precision    recall  f1-score   support

          1       0.62      1.00      0.76        66
          2       0.93      0.93      0.93        40
          3       0.59      0.97      0.73        67
          4       0.47      0.92      0.62       272
          5       1.00      0.16      0.28       413

avg / total       0.77      0.57      0.49       858

我如何"绘制"avobe图表？

1> Franck Derno..：

---

扩展Bin的答案:

import matplotlib.pyplot as plt
import numpy as np

def show_values(pc, fmt="%.2f", **kw):
    '''
    Heatmap with text in each cell with matplotlib's pyplot
    Source: /sf/ask/17360801/ 
    By HYRY
    '''
    from itertools import izip
    pc.update_scalarmappable()
    ax = pc.get_axes()
    #ax = pc.axes# FOR LATEST MATPLOTLIB
    #Use zip BELOW IN PYTHON 3
    for p, color, value in izip(pc.get_paths(), pc.get_facecolors(), pc.get_array()):
        x, y = p.vertices[:-2, :].mean(0)
        if np.all(color[:3] > 0.5):
            color = (0.0, 0.0, 0.0)
        else:
            color = (1.0, 1.0, 1.0)
        ax.text(x, y, fmt % value, ha="center", va="center", color=color, **kw)


def cm2inch(*tupl):
    '''
    Specify figure size in centimeter in matplotlib
    Source: /sf/ask/17360801/
    By gns-ank
    '''
    inch = 2.54
    if type(tupl[0]) == tuple:
        return tuple(i/inch for i in tupl[0])
    else:
        return tuple(i/inch for i in tupl)


def heatmap(AUC, title, xlabel, ylabel, xticklabels, yticklabels, figure_RdBu'):
    '''
    Inspired by:
    - /sf/ask/17360801/ 
    - /sf/ask/17360801/
    '''

    # Plot it out
    fig, ax = plt.subplots()    
    #c = ax.pcolor(AUC, edgecolors='k', linedashed', linewidths=0.2, cmap='RdBu', vmin=0.0, vmax=1.0)
    c = ax.pcolor(AUC, edgecolors='k', linedashed', linewidths=0.2, cmap=cmap)

    # put the major ticks at the middle of each cell
    ax.set_yticks(np.arange(AUC.shape[0]) + 0.5, minor=False)
    ax.set_xticks(np.arange(AUC.shape[1]) + 0.5, minor=False)

    # set tick labels
    #ax.set_xticklabels(np.arange(1,AUC.shape[1]+1), minor=False)
    ax.set_xticklabels(xticklabels, minor=False)
    ax.set_yticklabels(yticklabels, minor=False)

    # set title and x/y labels
    plt.title(title)
    plt.xlabel(xlabel)
    plt.ylabel(ylabel)      

    # Remove last blank column
    plt.xlim( (0, AUC.shape[1]) )

    # Turn off all the ticks
    ax = plt.gca()    
    for t in ax.xaxis.get_major_ticks():
        t.tick1On = False
        t.tick2On = False
    for t in ax.yaxis.get_major_ticks():
        t.tick1On = False
        t.tick2On = False

    # Add color bar
    plt.colorbar(c)

    # Add text in each cell 
    show_values(c)

    # Proper orientation (origin at the top left instead of bottom left)
    if correct_orientation:
        ax.invert_yaxis()
        ax.xaxis.tick_top()       

    # resize 
    fig = plt.gcf()
    #fig.set_size_inches(cm2inch(40, 20))
    #fig.set_size_inches(cm2inch(40*4, 20*4))
    fig.set_size_inches(cm2inch(figure_width, figure_height))



def plot_classification_report(classification_report, title='Classification report ', cmap='RdBu'):
    '''
    Plot scikit-learn classification report.
    Extension based on /sf/ask/17360801/ 
    '''
    lines = classification_report.split('\n')

    classes = []
    plotMat = []
    support = []
    class_names = []
    for line in lines[2 : (len(lines) - 2)]:
        t = line.strip().split()
        if len(t) <2: continue
        classes.append(t[0])
        v = [float(x) for x in t[1: len(t) - 1]]
        support.append(int(t[-1]))
        class_names.append(t[0])
        print(v)
        plotMat.append(v)

    print('plotMat: {0}'.format(plotMat))
    print('support: {0}'.format(support))

    xlabel = 'Metrics'
    ylabel = 'Classes'
    xticklabels = ['Precision', 'Recall', 'F1-score']
    yticklabels = ['{0} ({1})'.format(class_names[idx], sup) for idx, sup  in enumerate(support)]
    figure_width = 25
    figure_height = len(class_names) + 7
    correct_orientation = False
    heatmap(np.array(plotMat), title, xlabel, ylabel, xticklabels, yticklabels, figure_width, figure_height, correct_orientation, cmap=cmap)


def main():
    sampleClassificatiOnReport= """             precision    recall  f1-score   support

          Acacia       0.62      1.00      0.76        66
          Blossom       0.93      0.93      0.93        40
          Camellia       0.59      0.97      0.73        67
          Daisy       0.47      0.92      0.62       272
          Echium       1.00      0.16      0.28       413

        avg / total       0.77      0.57      0.49       858"""


    plot_classification_report(sampleClassificationReport)
    plt.savefig('test_plot_classif_report.png', dpi=200, format='png', bbox_inches='tight')
    plt.close()

if __name__ == "__main__":
    main()
    #cProfile.run('main()') # if you want to do some profiling

输出:

更多类(~40)的示例:

---

当前版本的`matplotlib`似乎无法使用所述解决方案.行`ax = pc.get_axes()`必须改为`ax = pc.axes`.

---

如果没有itertools，请删除“从itertools导入izip”，然后用zip替换izip。

---

但是为什么要使用izip？它比zip慢并且与Python3不兼容：https：//stackoverflow.com/questions/32659552/izip-not-working-in-python-3-x

2> Bin..：

---

我刚刚为此编写了一个函数plot_classification_report().希望能帮助到你.该函数取出了classification_report函数的put作为参数并绘制得分.这是功能.

def plot_classification_report(cr, title='Classification report ', with_avg_total=False, cmap=plt.cm.Blues):

    lines = cr.split('\n')

    classes = []
    plotMat = []
    for line in lines[2 : (len(lines) - 3)]:
        #print(line)
        t = line.split()
        # print(t)
        classes.append(t[0])
        v = [float(x) for x in t[1: len(t) - 1]]
        print(v)
        plotMat.append(v)

    if with_avg_total:
        aveTotal = lines[len(lines) - 1].split()
        classes.append('avg/total')
        vAveTotal = [float(x) for x in t[1:len(aveTotal) - 1]]
        plotMat.append(vAveTotal)


    plt.imshow(plotMat, interpolation='nearest', cmap=cmap)
    plt.title(title)
    plt.colorbar()
    x_tick_marks = np.arange(3)
    y_tick_marks = np.arange(len(classes))
    plt.xticks(x_tick_marks, ['precision', 'recall', 'f1-score'], rotation=45)
    plt.yticks(y_tick_marks, classes)
    plt.tight_layout()
    plt.ylabel('Classes')
    plt.xlabel('Measures')

对于您提供的示例classification_report.这是代码和输出.

sampleClassificatiOnReport= """             precision    recall  f1-score   support

          1       0.62      1.00      0.76        66
          2       0.93      0.93      0.93        40
          3       0.59      0.97      0.73        67
          4       0.47      0.92      0.62       272
          5       1.00      0.16      0.28       413

avg / total       0.77      0.57      0.49       858"""


plot_classification_report(sampleClassificationReport)

以下是如何将其与sklearn classification_report输出一起使用:

from sklearn.metrics import classification_report
classificatiOnReport= classification_report(y_true, y_pred, target_names=target_names)

plot_classification_report(classificationReport)

使用此功能,您还可以将"平均/总计"结果添加到绘图中.要使用它,只需添加如下参数with_avg_total:

plot_classification_report(classificationReport, with_avg_total=True)

3> larrywgray..：

---

我的解决方案是使用python包,Yellowbrick.简而言之,Yellowbrick将scikit-learn与matplotlib相结合,为您的模型生成可视化效果.在几行中,您可以执行上面建议的操作. http://www.scikit-yb.org/en/latest/api/classifier/classification_report.html

from sklearn.naive_bayes import GaussianNB
from yellowbrick.classifier import ClassificationReport

# Instantiate the classification model and visualizer
bayes = GaussianNB()
visualizer = ClassificationReport(bayes, classes=classes, support=True)

visualizer.fit(X_train, y_train)  # Fit the visualizer and the model
visualizer.score(X_test, y_test)  # Evaluate the model on the test data
visualizer.poof()             # Draw/show/poof the data