update

doc/src/week48/week48.do.txt

@@ -686,7 +686,6 @@ plt.plot(polydegree, error, label='Error')
 plt.plot(polydegree, bias, label='bias')
 plt.plot(polydegree, variance, label='Variance')
 plt.legend()
-save_fig("gdregression")
 plt.show()
 !ec
 
@@ -725,14 +724,11 @@ print("Test set accuracy with Gradient boosting and scaled data: {:.2f}".format(
 import scikitplot as skplt
 y_pred = gd_clf.predict(X_test_scaled)
 skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)
-save_fig("gdclassiffierconfusion")
 plt.show()
 y_probas = gd_clf.predict_proba(X_test_scaled)
 skplt.metrics.plot_roc(y_test, y_probas)
-save_fig("gdclassiffierroc")
 plt.show()
 skplt.metrics.plot_cumulative_gain(y_test, y_probas)
-save_fig("gdclassiffiercgain")
 plt.show()
 !ec
 
@@ -754,53 +750,6 @@ sketch for efficient proposal calculation. It introduces a novel sparsity-aware
 
 It is now the algorithm which wins essentially all ML competitions!!!
 
-!split
-===== Regression Case =====
-
-!bc pycod
-import matplotlib.pyplot as plt
-import numpy as np
-from sklearn.model_selection import train_test_split
-import xgboost as xgb
-import scikitplot as skplt
-from sklearn.metrics import mean_squared_error
-
-n = 100
-maxdegree = 6
-
-# Make data set.
-x = np.linspace(-3, 3, n).reshape(-1, 1)
-y = np.exp(-x**2) + 1.5 * np.exp(-(x-2)**2)+ np.random.normal(0, 0.1, x.shape)
-
-error = np.zeros(maxdegree)
-bias = np.zeros(maxdegree)
-variance = np.zeros(maxdegree)
-polydegree = np.zeros(maxdegree)
-X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2)
-
-for degree in range(maxdegree):
-    model =  xgb.XGBRegressor(objective ='reg:squarederror', colsaobjective ='reg:squarederror', colsample_bytree = 0.3, learning_rate = 0.1,max_depth = degree, alpha = 10, n_estimators = 200)
-
-    model.fit(X_train,y_train)
-    y_pred = model.predict(X_test)
-    polydegree[degree] = degree
-    error[degree] = np.mean( np.mean((y_test - y_pred)**2) )
-    bias[degree] = np.mean( (y_test - np.mean(y_pred))**2 )
-    variance[degree] = np.mean( np.var(y_pred) )
-    print('Max depth:', degree)
-    print('Error:', error[degree])
-    print('Bias^2:', bias[degree])
-    print('Var:', variance[degree])
-    print('{} >= {} + {} = {}'.format(error[degree], bias[degree], variance[degree], bias[degree]+variance[degree]))
-
-plt.xlim(1,maxdegree-1)
-plt.plot(polydegree, error, label='Error')
-plt.plot(polydegree, bias, label='bias')
-plt.plot(polydegree, variance, label='Variance')
-plt.legend()
-plt.show()
-
-!ec
 
 !split
 ===== Xgboost on the Cancer Data =====
@@ -839,25 +788,20 @@ print("Test set accuracy with Gradient Boosting and scaled data: {:.2f}".format(
 import scikitplot as skplt
 y_pred = xg_clf.predict(X_test_scaled)
 skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)
-save_fig("xdclassiffierconfusion")
 plt.show()
 y_probas = xg_clf.predict_proba(X_test_scaled)
 skplt.metrics.plot_roc(y_test, y_probas)
-save_fig("xdclassiffierroc")
 plt.show()
 skplt.metrics.plot_cumulative_gain(y_test, y_probas)
-save_fig("gdclassiffiercgain")
 plt.show()
 
 
 xgb.plot_tree(xg_clf,num_trees=0)
 plt.rcParams['figure.figsize'] = [50, 10]
-save_fig("xgtree")
 plt.show()
 
 xgb.plot_importance(xg_clf)
 plt.rcParams['figure.figsize'] = [5, 5]
-save_fig("xgparams")
 plt.show()
 
 !ec