for opp in range(len(cobweb_data[0])):
for run in range(len(cobweb_data)):
cobweb_x.append(opp)
cobweb_y.append(cobweb_data[run][opp])
for opp in range(len(naive_data[0])):
for run in range(len(naive_data)):
naive_x.append(opp)
naive_y.append(naive_data[run][opp])
cobweb_x = np.array(cobweb_x)
cobweb_y = np.array(cobweb_y)
naive_x = np.array(naive_x)
naive_y = np.array(naive_y)
cobweb_y_smooth, cobweb_lower_smooth, cobweb_upper_smooth = avg_lines(
cobweb_x, cobweb_y)
naive_y_smooth, naive_lower_smooth, naive_upper_smooth = avg_lines(
naive_x, naive_y)
plt.fill_between(cobweb_x,
cobweb_lower_smooth,
cobweb_upper_smooth,
alpha=0.5,
facecolor="green")
plt.fill_between(naive_x,
naive_lower_smooth,
naive_upper_smooth,
alpha=0.5,
facecolor="red")
plt.plot(cobweb_x, cobweb_y_smooth, label="COBWEB", color="green")
for opp in range(len(trestle_data[0])):
for run in range(len(trestle_data)):
trestle_x.append(opp)
trestle_y.append(trestle_data[run][opp])
for opp in range(len(naive_data[0])):
for run in range(len(naive_data)):
naive_x.append(opp)
naive_y.append(naive_data[run][opp])
trestle_x = np.array(trestle_x)
trestle_y = np.array(trestle_y)
naive_x = np.array(naive_x)
naive_y = np.array(naive_y)
trestle_y_avg, _, _ = avg_lines(trestle_x, trestle_y)
naive_y_avg, _, _ = avg_lines(naive_x, naive_y)
plt.plot(trestle_x, trestle_y_avg, label="TRESTLE", color="green")
plt.plot(naive_x, naive_y_avg, label="Naive Predictor", color="red")
plt.gca().set_ylim([0.00, 1.0])
plt.gca().set_xlim([0, max(naive_x) - 1])
plt.title("Incremental Quadruped Prediction Accuracy")
plt.xlabel("# of Training Examples")
plt.ylabel("Avg. Probability of True Quadruped Type (Accuracy)")
plt.legend(loc=4)
plt.show()
print(recall_data)
precision_x, precision_y = [], []
recall_x, recall_y = [], []
for opp in range(len(precision_data[0])):
for run in range(len(precision_data)):
precision_x.append(opp)
precision_y.append(precision_data[run][opp])
for opp in range(len(recall_data[0])):
for run in range(len(recall_data)):
recall_x.append(opp)
recall_y.append(recall_data[run][opp])
precision_x = np.array(precision_x)
precision_y = np.array(precision_y)
recall_x = np.array(recall_x)
recall_y = np.array(recall_y)
precision_y_smooth, precision_lower_smooth, precision_upper_smooth = avg_lines(
precision_x, precision_y)
recall_y_smooth, recall_lower_smooth, recall_upper_smooth = avg_lines(
recall_x, recall_y)
plt.fill_between(precision_x,
precision_lower_smooth,
precision_upper_smooth,
alpha=0.5,
facecolor="skyblue")
plt.fill_between(recall_x,
recall_lower_smooth,
recall_upper_smooth,
alpha=0.5,
facecolor="salmon")
plt.plot(precision_x,
precision_y_smooth,
label="Precision",
for opp in range(len(cobweb_data[0])):
for run in range(len(cobweb_data)):
cobweb_x.append(opp)
cobweb_y.append(cobweb_data[run][opp])
for opp in range(len(naive_data[0])):
for run in range(len(naive_data)):
naive_x.append(opp)
naive_y.append(naive_data[run][opp])
cobweb_x = np.array(cobweb_x)
cobweb_y = np.array(cobweb_y)
naive_x = np.array(naive_x)
naive_y = np.array(naive_y)
cobweb_y_smooth, cobweb_lower_smooth, cobweb_upper_smooth = avg_lines(
cobweb_x, cobweb_y)
naive_y_smooth, naive_lower_smooth, naive_upper_smooth = avg_lines(
naive_x, naive_y)
plt.fill_between(cobweb_x, cobweb_lower_smooth, cobweb_upper_smooth, alpha=0.5,
facecolor="green")
plt.fill_between(naive_x, naive_lower_smooth, naive_upper_smooth, alpha=0.5,
facecolor="red")
plt.plot(cobweb_x, cobweb_y_smooth, label="COBWEB/3", color="green")
plt.plot(naive_x, naive_y_smooth, label="Naive Predictor", color="red")
plt.gca().set_ylim([0.00, 1.0])
plt.gca().set_xlim([0, max(naive_x)-1])
plt.title("Incremental Iris Classification Prediction Accuracy")
plt.xlabel("# of Training Examples")
for opp in range(len(trestle_data[0])):
for run in range(len(trestle_data)):
trestle_x.append(opp)
trestle_y.append(trestle_data[run][opp])
for opp in range(len(naive_data[0])):
for run in range(len(naive_data)):
naive_x.append(opp)
naive_y.append(naive_data[run][opp])
trestle_x = np.array(trestle_x)
trestle_y = np.array(trestle_y)
naive_x = np.array(naive_x)
naive_y = np.array(naive_y)
trestle_y_avg, _, _ = avg_lines(trestle_x, trestle_y)
naive_y_avg, _, _ = avg_lines(naive_x, naive_y)
plt.plot(trestle_x, trestle_y_avg, label="TRESTLE", color="green")
plt.plot(naive_x, naive_y_avg, label="Naive Predictor", color="red")
plt.gca().set_ylim([0.00, 1.0])
plt.gca().set_xlim([0, max(naive_x)-1])
plt.title("Incremental Quadruped Prediction Accuracy")
plt.xlabel("# of Training Examples")
plt.ylabel("Avg. Probability of True Quadruped Type (Accuracy)")
plt.legend(loc=4)
plt.show()