Synthetic Dataset Overview

In [1]:

    

from sklearn import cross_validation as cv
from sklearn import svm

plt.style.use('ggplot')

from kcat.datasets import Synthetic


    

In [2]:

    

# Define parameters
sizes = (50, 100, 200, 400)
ps = np.linspace(0, 1, num=11)
repeat = 150
# Try all possible combinations
results = np.zeros((len(sizes), len(ps), repeat))
for i, m in enumerate(sizes):
    for j, p in enumerate(ps):
        print("{} {}".format(m, p), end=', ')
        for k in range(repeat):
            # Generate a new dataset
            Xq, Xc, y = Synthetic(m, n=25, c=2, p=p).data_arrays
            clf = svm.SVC(kernel='rbf')
            results[i][j][k] = cv.cross_val_score(clf, Xc, y, cv=5).mean()
# Invert results to show error rate instead of success rate
results = 1.0 - results


    

    




50 0.0, 50 0.1, 50 0.2, 50 0.30000000000000004, 50 0.4, 50 0.5, 50 0.6000000000000001, 50 0.7000000000000001, 50 0.8, 50 0.9, 50 1.0, 100 0.0, 100 0.1, 100 0.2, 100 0.30000000000000004, 100 0.4, 100 0.5, 100 0.6000000000000001, 100 0.7000000000000001, 100 0.8, 100 0.9, 100 1.0, 200 0.0, 200 0.1, 200 0.2, 200 0.30000000000000004, 200 0.4, 200 0.5, 200 0.6000000000000001, 200 0.7000000000000001, 200 0.8, 200 0.9, 200 1.0, 400 0.0, 400 0.1, 400 0.2, 400 0.30000000000000004, 400 0.4, 400 0.5, 400 0.6000000000000001, 400 0.7000000000000001, 400 0.8, 400 0.9, 400 1.0, 

In [3]:

    

# Plot error
figure(figsize=(10, 5))
styles = (':', '-.', '--', '-')
for i, m in enumerate(sizes):
    plot(ps, results[i].mean(axis=1), styles[i], linewidth=1.5, color=(0.7, 0.4, 0))
xlabel("P")
ylabel("Error")
ylim(0, 0.5)
legend(["Size {}".format(m) for m in sizes])
# title("Classification Error using RBF Kernel".format(m))


    

    
Out[3]:





<matplotlib.legend.Legend at 0x7f4ede379dd8>