import pandas as pd
import numpy as np
digits_train = pd.read_csv('../Datasets/Breast-Cancer/optdigits.tra', header=None)
digits_test = pd.read_csv('../Datasets/Breast-Cancer/optdigits.tes', header=None)
x_digits = digits_train[np.arange(64)]
y_digits = digits_train[64]
X_train = x_digits.dropna(how='any')
y_train = y_digits.dropna(how='any')
x_digits_test = digits_test[np.arange(64)]
y_digits_test = digits_test[64]
X_test = x_digits_test.dropna(how='any')
y_test = y_digits_test.dropna(how='any')
print(X_train)
print(y_train)
from sklearn.svm import LinearSVC
svc = LinearSVC()
svc.fit(X_train,y_train)
y_predict = svc.predict(X_test)
from sklearn.decomposition import PCA
estimator = PCA(n_components=20)
pca_X_train = estimator.fit_transform(X_train)
pca_X_test = estimator.transform(X_test)
pca_svc = LinearSVC()
pca_svc.fit(pca_X_train,y_train)
pca_y_predict = pca_svc.predict(pca_X_test)
target_namearray = []
from sklearn.metrics import classification_report
print('The accuracy of linesvm is',svc.score(X_test,y_test))
print(classification_report(y_test,y_predict,target_names = np.arange(10).astype(str)))
from matplotlib import pyplot as plt
def show_values(pc, fmt="%.2f", **kw):
'''
Heatmap with text in each cell with matplotlib's pyplot
Source: https://stackoverflow.com/a/25074150/395857
By HYRY
'''
global zip
import itertools
zip = getattr(itertools, 'izip', zip)
pc.update_scalarmappable()
ax = pc.axes
for p, color, value in zip(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: https://stackoverflow.com/a/22787457/395857
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_width=40, figure_height=20, correct_orientation=False, cmap='RdBu'):
'''
Inspired by:
- https://stackoverflow.com/a/16124677/395857
- https://stackoverflow.com/a/25074150/395857
'''
# Plot it out
fig, ax = plt.subplots()
#c = ax.pcolor(AUC, edgecolors='k', linestyle= 'dashed', linewidths=0.2, cmap='RdBu', vmin=0.0, vmax=1.0)
c = ax.pcolor(AUC, edgecolors='k', linestyle= 'dashed', 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 https://stackoverflow.com/a/31689645/395857
'''
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)
#傳入相應的report結果
def main():
sampleClassificationReport =classification_report(y_test,y_predict,target_names = np.arange(10).astype(str))
plot_classification_report(sampleClassificationReport)
plt.savefig('test_plot_classif_report.png', dpi=200, format='png', bbox_inches='tight')
plt.close()
sampleClassificationReport1 =classification_report(y_test,pca_y_predict,target_names = np.arange(10).astype(str))
plot_classification_report(sampleClassificationReport1)
plt.savefig('test_plot_classif_report1.png', dpi=200, format='png', bbox_inches='tight')
plt.close()
if __name__ == "__main__":
main()
#cProfile.run('main()') # if you want to do some profiling
print('The accuracy of svm linesvm is',pca_svc.score(pca_X_test,y_test))
print(classification_report(y_test,pca_y_predict,target_names = np.arange(10).astype(str)))壓縮後性能略微有下降，但使用pca後降低了68.75%的維度
The accuracy of linesvm is 0.9259877573734001
precision recall f1-score support
0 0.99 0.98 0.99 178
1 0.86 0.90 0.88 182
2 0.96 0.98 0.97 177
3 0.99 0.90 0.94 183
4 0.94 0.97 0.95 181
5 0.91 0.96 0.94 182
6 0.99 0.98 0.98 181
7 0.98 0.92 0.95 179
8 0.75 0.90 0.82 174
9 0.93 0.77 0.84 180
avg / total 0.93 0.93 0.93 1797The accuracy of svm linesvm is 0.9304396215915415
precision recall f1-score support
0 0.96 0.98 0.97 178
1 0.90 0.88 0.89 182
2 0.98 0.98 0.98 177
3 0.96 0.90 0.93 183
4 0.95 0.97 0.96 181
5 0.88 0.97 0.92 182
6 0.97 0.98 0.98 181
7 0.98 0.87 0.92 179
8 0.89 0.90 0.90 174
9 0.84 0.86 0.85 180
avg / total 0.93 0.93 0.93 1797
