def plot_classification_report(classification_report, title, cmap='RdBu'):
'''
Plot scikit-learn classification report.
Extension based on https://stackoverflow.com/a/31689645/395857
'''
lines = classification_report.split('\n')
classes = []
plotMat = []
support = []
class_names = []
for line in lines[2 : (len(lines) - 4)]:
t = line.strip().split()
if len(t) < 2: continue
classes.append(t[0])
v = []
for x in t[1: len(t) - 2]:
if t[1] != 'avg':
v.append(float(x))
support.append(int(t[-1]))
class_names.append(t[0])
plotMat.append(v)
xlabel = 'Métricas'
ylabel = 'Zonas'
xticklabels = ['Precisión', 'Exhaustividad']
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(numpy.array(plotMat), title, xlabel, ylabel, xticklabels, yticklabels, figure_width, figure_height, correct_orientation, cmap=cmap)
def plot_classification_report(classification_report, title='Classification Report ', cmap='RdBu'):
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 plot_classification_report(classification_report,
title='Classification report ',
cmap='RdBu',
figsize=(12, 9),
ax=None):
'''
Plot scikit-learn classification report.
Extension based on http://stackoverflow.com/a/31689645/395857
'''
from matplotlib.cbook import MatplotlibDeprecationWarning
import warnings
warnings.simplefilter('ignore', MatplotlibDeprecationWarning)
classes = []
plotMat = []
support = []
class_names = []
lines = classification_report.split('\n')
for line in lines[2:(len(lines) - 1)]:
t = line.strip().replace('avg / total', 'micro-avg').split()
if len(t) < 2: continue
classes.append(t[0])
v = [float(x) * 100 for x in t[1:len(t) - 1]]
support.append(int(t[-1]))
class_names.append(t[0])
plotMat.append(v)
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 = 16
# figure_height = len(class_names) + 8
correct_orientation = True
# Plot it out
if ax is None:
fig, ax = plt.subplots(figsize=figsize)
else:
fig = plt.gcf()
fig.sca(ax)
heatmap(np.array(plotMat),
title,
xlabel,
ylabel,
xticklabels,
yticklabels,
ax,
correct_orientation,
cmap=cmap)
def plot_classification_report(self,
classification_report,
title='Classification report ',
cmap='RdYlGn'):
'''
Plot scikit-learn classification report.
Extension based on https://stackoverflow.com/a/31689645/395857
'''
func_name = self.plot_classification_report.__name__
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)
self.verbose('plotMat: {0}'.format(plotMat), func_name)
self.verbose('support: {0}'.format(support), func_name)
xlabel, ylabel = 'Metrics', '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
ax = DataPlots.heatmap(np.array(plotMat),
title,
xlabel,
ylabel,
xticklabels,
yticklabels,
figure_width,
figure_height,
correct_orientation,
cmap=cmap)
return ax
def plot_classification_report(classification_report, model, accuracy):
"""
Tämä funktio tulostaa luokitteluraportin taulukkoon
"""
lines = classification_report.split('\n')
plotMat = []
class_names = []
for line in lines[2:(len(lines) - 5)]:
t = line.strip().split()
if len(t) < 2: continue
v = ['{0:.2f}'.format(float(x)) for x in t[1:len(t) - 1]]
class_names.append(t[0])
plotMat.append(v)
lastline = lines[len(lines) - 2]
t = lastline.strip().split()
lastline_class_name = ['_'.join(t[0:2])]
lastline_values = [['{0:.2f}'.format(float(x)) for x in t[2:len(t) - 1]]]
fig, (ax1, ax2) = plt.subplots(2, sharey=True)
xlabel = 'Metrics'
ylabel = 'Classes'
xticklabels = ['Precision', 'Recall', 'F1-score']
yticklabels = [
' {} '.format(class_names[i])
for i in range(len(class_names))
]
the_table = ax1.table(cellText=plotMat,
cellLoc='center',
rowLabels=yticklabels,
colLabels=xticklabels,
colWidths=[0.3 for x in range(len(xticklabels))],
loc=1)
the_table1 = ax2.table(cellText=lastline_values,
cellLoc='center',
rowLabels=lastline_class_name,
colWidths=[0.3 for x in range(len(xticklabels))],
loc=1)
ax1.axis('tight')
ax1.axis('off')
ax2.axis('tight')
ax2.axis('off')
accuracytext = 'Accuracy for classifier {}: {}'.format(model, accuracy)
plt.text(-0.062, 0.00, accuracytext)
ax1.set(title='Classification report for {}'.format(model))
from sklearn import metrics
from sklearn.metrics import accuracy_score,confusion_matrix,classification_report
from sklearn.cross_validation import cross_val_score
from sklearn.metrics import precision_score
Y_pred=best_estimator.predict(X_test)
#评价模型
accuracy_score = accuracy_score(Y_test,Y_pred)
confusion_matrix = confusion_matrix(Y_test,Y_pred,labels=[0,1,2])
# precision = metrics.precision_score(Y_test,Y_pred)#二分类
# recall = metrics.recall_score(Y_test,Y_pred)#二分类
# f1_score = metrics.f1_score(Y_test,Y_pred)#二分类
precision = metrics.precision_score(Y_test,Y_pred,average="macro")#多分类
recall = metrics.recall_score(Y_test,Y_pred,average="macro")#多分类
f1_score = metrics.f1_score(Y_test,Y_pred,average="macro")#多分类
classification_report = classification_report(Y_test,Y_pred)
classification_report_split=classification_report.split() #提取矩阵中的值
endtime = time.time()
'''
输出文件
'''
out="\n 最优分类器:"+str(best_estimator)+\
"\n The confusion matrix is:\n"+str(confusion_matrix)
f=open('canshu.txt','a')
print(out+'\n\n',file=f)
f.close()
#储存数据
pred_result[str(name)]=np.transpose(Y_pred)
evaluate_result.loc[str(name)]=[accuracy_score
,precision
