print("sklearn implementations")
print(" Decision tree classifier info gain")
evaluate_model(DecisionTreeClassifier(criterion="entropy"))
print(" Random forest info gain")
evaluate_model(RandomForestClassifier(criterion="entropy"))
print(" Random forest info classifier gain, more trees")
evaluate_model(
RandomForestClassifier(criterion="entropy", n_estimators=50))
elif question == '3':
X = load_dataset('clusterData.pkl')['X']
model = Kmeans(k=4)
model.fit(X)
print(model.predict(X))
model.error(X)
#print(X)
plot_2dclustering(X, model.predict(X))
fname = os.path.join("..", "figs", "kmeans_basic.png")
plt.savefig(fname)
print("\nFigure saved as '%s'" % fname)
elif question == '3.1':
X = load_dataset('clusterData.pkl')['X']
N, D = X.shape
print('N =', N)
print('D =', D)
for n in range(50):
model = Kmeans(k=4)
print("sklearn implementations")
print(" Decision tree info gain")
evaluate_model(DecisionTreeClassifier(criterion="entropy"))
print(" Random forest info gain")
evaluate_model(RandomForestClassifier(criterion="entropy"))
print(" Random forest info gain, more trees")
evaluate_model(RandomForestClassifier(criterion="entropy", n_estimators=50))
elif question == '3':
X = load_dataset('clusterData.pkl')['X']
model = Kmeans(k=4)
model.fit(X)
error = model.error(X)
plot_2dclustering(X, model.predict(X))
fname = os.path.join("..", "figs", "kmeans_basic.png")
plt.savefig(fname)
print("\nFigure saved as '%s'" % fname)
elif question == '3.1':
# part 1: implement quantize_image.py
# part 2: make figure
X = load_dataset('clusterData.pkl')['X']
min_model = None
min_error = np.inf
for i in range(50):
model = Kmeans(4)
print("sklearn implementations")
print(" Decision tree info gain")
evaluate_model(DecisionTreeClassifier(criterion="entropy"))
print(" Random forest info gain")
evaluate_model(RandomForestClassifier(criterion="entropy"))
print(" Random forest info gain, more trees")
evaluate_model(
RandomForestClassifier(criterion="entropy", n_estimators=50))
elif question == '3':
X = load_dataset('clusterData.pkl')['X']
model = Kmeans(k=4)
model.fit(X)
print("Error:", model.error(X))
plot_2dclustering(X, model.predict(X))
fname = os.path.join("..", "figs", "kmeans_basic.png")
plt.savefig(fname)
print("\nFigure saved as '%s'" % fname)
elif question == '3.1':
X = load_dataset('clusterData.pkl')['X']
N = 50
lowestError = np.inf
model = Kmeans(k=4)
model.fit(X)
# for n in range(N):
