def weight_graph(regularization='l1'):
weights, params = [], []
for c in np.arange(-4, 6):
lr = LogisticRegression(penalty=regularization,
C=10**c,
random_state=0)
lr.fit(X_train_std, y_train)
weights.append(lr.coef_[1])
params.append(10**c)
weights = np.array(weights)
for column, color in zip(range(weights.shape[1]), colors):
plt.plot(params,
weights[:, column],
label=columnsXY[column + 1],
color=color)
plt.axhline(0, color='black', linestyle='--', linewidth=3)
plt.xlim([10**(-5), 10**5])
plt.ylabel('weight coefficient')
plt.xlabel('C')
plt.xscale('log')
title = 'regularization {}'.format(regularization)
plt.title(title)
plt.legend(loc='upper left')
ax.legend(loc='upper center',
bbox_to_anchor=(1.38, 1.03),
ncol=1,
fancybox=True)
ocr_utils.show_figures(plt, title + ' path')
def weight_graph(regularization = 'l1'):
weights, params = [], []
for c in np.arange(0, 6):
lr = LogisticRegression(penalty=regularization, C=10**c, random_state=0)
lr.fit(X_train_std, y_train)
weights.append(lr.coef_[1])
params.append(10**c)
weights = np.array(weights)
for column, color in zip(range(weights.shape[1]), colors):
plt.plot(params, weights[:, column],
label=columnsXY[column+1],
color=color)
plt.axhline(0, color='black', linestyle='--', linewidth=3)
plt.xlim([10**(-5), 10**5])
plt.ylabel('weight coefficient')
plt.xlabel('C')
plt.xscale('log')
title = 'regularization {}'.format(regularization)
plt.title(title)
plt.legend(loc='upper left')
ax.legend(loc='upper center',
bbox_to_anchor=(1.38, 1.03),
ncol=1, fancybox=True)
ocr_utils.show_figures(plt,title + ' path')
roc_auc = auc(x=fpr, y=tpr)
plt.plot(fpr,
tpr,
color=clr,
linestyle=ls,
label='%s (auc = %0.2f)' % (label, roc_auc))
plt.legend(loc='lower right')
plt.plot([0, 1], [0, 1], linestyle='--', color='gray', linewidth=2)
plt.xlim([-0.1, 1.1])
plt.ylim([-0.1, 1.1])
plt.grid()
title = 'Majority Vote Receiver Operation Curve'
plt.title(title)
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
ocr_utils.show_figures(plt, title)
sc = StandardScaler()
X_train_std = sc.fit_transform(X_train)
X_train_std = sc.fit_transform(X_train)
from itertools import product
all_clf = [pipe1, clf2, pipe3, mv_clf]
x_min = X_train_std[:, 0].min() - 1
x_max = X_train_std[:, 0].max() + 1
y_min = X_train_std[:, 1].min() - 1
y_max = X_train_std[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.1),
tot = sum(eigen_vals)
var_exp = [(i / tot) for i in sorted(eigen_vals, reverse=True)]
cum_var_exp = np.cumsum(var_exp)
var_exp = var_exp[:20]
cum_var_exp = cum_var_exp[:2*n_components]
title='explained variance'
plt.bar(range(1, len(var_exp)+1), var_exp, alpha=0.5, align='center', label='individual explained variance')
plt.step(range(1, len(cum_var_exp)+1), cum_var_exp, where='mid',
label='cumulative explained variance')
plt.ylabel('Explained variance ratio')
plt.xlabel('Principal components')
plt.legend(loc='best')
plt.tight_layout()
plt.title(title)
ocr_utils.show_figures(plt,title)
# Make a list of (eigenvalue, eigenvector) tuples
eigen_pairs = [(np.abs(eigen_vals[i]), eigen_vecs[:,i]) for i in range(len(eigen_vals))]
# Sort the (eigenvalue, eigenvector) tuples from high to low
eigen_pairs.sort(reverse=True)
# The eigenpairs with the highest explained variance
w = np.hstack((eigen_pairs[0][1][:, np.newaxis],
eigen_pairs[1][1][:, np.newaxis]))
print('Matrix W:\n', w[:2*n_components,:])
X_train_pca = X_train_image.dot(w)
print ('projection of first dataset sample on first 2 eignvectors {}'.format(X_train_image[0].dot(w)))
return np.where(self.activation(X) >= 0.0, 1, -1)
title = 'Gradient Descent Learning rate 0.01'
fig, ax = plt.subplots(nrows=1, ncols=2, figsize=(8, 4))
ada1 = AdalineGD(n_iter=10, eta=0.01).fit(X, y)
ax[0].plot(range(1, len(ada1.cost_) + 1), np.log10(ada1.cost_), marker='o')
ax[0].set_xlabel('Epochs')
ax[0].set_ylabel('log(Sum-squared-error)')
ax[0].set_title('Adaline - Learning rate 0.01')
ada2 = AdalineGD(n_iter=10, eta=0.0001).fit(X, y)
ax[1].plot(range(1, len(ada2.cost_) + 1), ada2.cost_, marker='o')
ax[1].set_xlabel('Epochs')
ax[1].set_ylabel('Sum-squared-error')
ax[1].set_title('Adaline - Learning rate 0.0001')
ocr_utils.show_figures(plt, title)
#
# plt.plot(range(1,len(ada1.cost_)+1), np.log10(ada1.cost_), marker='o',label = title)
# plt.title(title)
# ocr_utils.show_figures(plt, title)
#
# ada2 = AdalineGD(n_iter=15, eta=0.0001).fit(X, y)
# title = 'Gradient Descent Learning rate 0.0001'
# plt.plot(range(1,len(ada2.cost_)+1), np.log10(ada2.cost_) ,marker='x',label = title)
# plt.title(title)
# ocr_utils.show_figures(plt, title)
# standardize features
X_std = np.copy(X)
title = 'Gradient Descent Learning rate 0.01'
fig, ax = plt.subplots(nrows=1, ncols=2, figsize=(8, 4))
ada1 = AdalineGD(n_iter=10, eta=0.01).fit(X, y)
ax[0].plot(range(1, len(ada1.cost_) + 1), np.log10(ada1.cost_), marker='o')
ax[0].set_xlabel('Epochs')
ax[0].set_ylabel('log(Sum-squared-error)')
ax[0].set_title('Adaline - Learning rate 0.01')
ada2 = AdalineGD(n_iter=10, eta=0.0001).fit(X, y)
ax[1].plot(range(1, len(ada2.cost_) + 1), ada2.cost_, marker='o')
ax[1].set_xlabel('Epochs')
ax[1].set_ylabel('Sum-squared-error')
ax[1].set_title('Adaline - Learning rate 0.0001')
ocr_utils.show_figures(plt, title)
#
# plt.plot(range(1,len(ada1.cost_)+1), np.log10(ada1.cost_), marker='o',label = title)
# plt.title(title)
# ocr_utils.show_figures(plt, title)
#
# ada2 = AdalineGD(n_iter=15, eta=0.0001).fit(X, y)
# title = 'Gradient Descent Learning rate 0.0001'
# plt.plot(range(1,len(ada2.cost_)+1), np.log10(ada2.cost_) ,marker='x',label = title)
# plt.title(title)
# ocr_utils.show_figures(plt, title)
# standardize features
X_std = np.copy(X)
X_std[:, 0] = (X[:, 0] - X[:, 0].mean()) / X[:, 0].std()
X_std[:, 1] = (X[:, 1] - X[:, 1].mean()) / X[:, 1].std()