clf = ensemble.GradientBoostingRegressor(**params)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
# print("MSE: %.4f" % mse)
###############################################################################
# Plot training deviance
# compute test set deviance
test_score = np.zeros((params['n_estimators'],), dtype=np.float64)
for i, y_pred in enumerate(clf.staged_decision_function(X_test)):
test_score[i] = clf.loss_(y_test, y_pred)
plt.figure(figsize=(12, 6))
plt.subplot(1, 2, 1)
plt.title('Deviance')
plt.plot(np.arange(params['n_estimators']) + 1, clf.train_score_, 'b-',
label='Training Set Deviance')
plt.plot(np.arange(params['n_estimators']) + 1, test_score, 'r-',
label='Test Set Deviance')
plt.legend(loc='upper right')
plt.xlabel('Boosting Iterations')
plt.ylabel('Deviance')
###############################################################################
# Plot feature importance
feature_importance = clf.feature_importances_
# make importances relative to max importance
feature_importance = 100.0 * (feature_importance / feature_importance.max())
bottom_h = bottom + height + 0.03
def price_format(x, pos):
# the two args are the value and tick position
return ('$%s,000' % (int(x/1000))) if x else ''
c_dicts = [coord_to_cut, coord_to_color_label, coord_to_clar]
def c_format(c_dict):
def c(x):
try:
return c_dict[x]
except KeyError:
return ''
return c
plt.figure(1, figsize = (4,8))
for i, label in enumerate(['Carat', 'Cut', 'Color', 'Clarity']):
left_start = left + i*(width + 0.03)
rect_main = [left_start, bottom, width, height]
rect_hist = [left_start, bottom_h, width, 0.2]
axScatter = plt.axes(rect_main)
axHist = plt.axes(rect_hist)
axScatter.scatter(data[i], price, s = area, c = color, alpha = 0.3)
axScatter.scatter(data[i], price, s = clar_area, c = color, alpha = 0.5)
axScatter.set_ylim((0, 20000))
axScatter.set_xlabel(label)
axScatter.minorticks_on()
clf = ensemble.GradientBoostingRegressor(**params)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
# print("MSE: %.4f" % mse)
###############################################################################
# Plot training deviance
# compute test set deviance
test_score = np.zeros((params['n_estimators'], ), dtype=np.float64)
for i, y_pred in enumerate(clf.staged_decision_function(X_test)):
test_score[i] = clf.loss_(y_test, y_pred)
plt.figure(figsize=(12, 6))
plt.subplot(1, 2, 1)
plt.title('Deviance')
plt.plot(np.arange(params['n_estimators']) + 1,
clf.train_score_,
'b-',
label='Training Set Deviance')
plt.plot(np.arange(params['n_estimators']) + 1,
test_score,
'r-',
label='Test Set Deviance')
plt.legend(loc='upper right')
plt.xlabel('Boosting Iterations')
plt.ylabel('Deviance')
###############################################################################
c_dicts = [coord_to_cut, coord_to_color_label, coord_to_clar]
def c_format(c_dict):
def c(x):
try:
return c_dict[x]
except KeyError:
return ''
return c
plt.figure(1, figsize=(4, 8))
for i, label in enumerate(['Carat', 'Cut', 'Color', 'Clarity']):
left_start = left + i * (width + 0.03)
rect_main = [left_start, bottom, width, height]
rect_hist = [left_start, bottom_h, width, 0.2]
axScatter = plt.axes(rect_main)
axHist = plt.axes(rect_hist)
axScatter.scatter(data[i], price, s=area, c=color, alpha=0.3)
axScatter.scatter(data[i], price, s=clar_area, c=color, alpha=0.5)
axScatter.set_ylim((0, 20000))
axScatter.set_xlabel(label)
axScatter.minorticks_on()
