accuracies.std()
# Applying Grid Search to find the best model and the best parameters
from sklearn.cross_validation import GridSearchCV
#from sklearn.cross_validation import train_test_split
parameters = [{
'C': [1, 10, 100, 1000],
'kernel': ['linear']
}, {
'C': [1, 10, 100, 1000],
'kernel': ['rbf'],
'gamma': [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]
}]
grid_search = GridSearchCV(estimator=classifier,
param_grid=parameters,
scoring='accuracy',
cv=10,
n_jobs=-1)
grid_search = grid_search.fit(X_train, y_train)
best_accuracy = grid_search.best_score_
best_parameters = grid_search.best_params_
# Visualising the Training set results
from matplotlib.colors import ListedColormap
X_set, y_set = X_train, y_train
X1, X2 = np.meshgrid(
np.arange(start=X_set[:, 0].min() - 1,
stop=X_set[:, 0].max() + 1,
step=0.01),
np.arange(start=X_set[:, 1].min() - 1,
stop=X_set[:, 1].max() + 1,
'clf__C': [1.0, 10.0, 100.0]},
{'vect__ngram_range': [(1, 1)],
'vect__stop_words': [stop, None],
'vect__tokenizer': [tokenizer, tokenizer_porter],
'vect__use_idf':[False],
'vect__norm':[None],
'clf__penalty': ['l1', 'l2'],
'clf__C': [1.0, 10.0, 100.0]},
]
lr_tfidf = Pipeline([('vect', tfidf),
('clf', LogisticRegression(random_state=0))])
gs_lr_tfidf = GridSearchCV(lr_tfidf, param_grid,
scoring='accuracy',
cv=5,
verbose=1,
n_jobs=-1)
gs_lr_tfidf.fit(X_train, y_train)
print('Best parameter set: %s ' % gs_lr_tfidf.best_params_)
print('CV Accuracy: %.3f' % gs_lr_tfidf.best_score_)
clf = gs_lr_tfidf.best_estimator_
print('Test Accuracy: %.3f' % clf.score(X_test, y_test))
#############################################################################
print(50 * '=')
s="Sepal width [standardized]",
ha="center", va="center", fontsize=12)
plt.text(-10.5, 4.5,
s="Petal length [standardized]",
ha="center", va="center",
fontsize=12, rotation=90)
plt.show()
print(mv_clf.get_params())
params = {'decisiontreeclassifier__max_depth': [1, 2],
'pipeline-1__clf__C': [0.001, 0.1, 100.0]}
grid = GridSearchCV(estimator=mv_clf,
param_grid=params,
cv=10,
scoring="roc_auc")
grid.fit(X_train, y_train)
if Version(sklearn_version) < "0.18":
for params, mean_score, scores in grid.grid_scores_:
print("%0.3f +/- %0.2f %r"
% (mean_score, scores.std() / 2.0, params))
else:
cv_keys = ("mean_test_score", "std_test_score", "params")
for r, _ in enumerate(grid.cv_results_["mean_test_score"]):
print("%0.3f +/- %0.2f %r"
% (grid.cv_results_[cv_keys[0]][r],
grid.cv_results_[cv_keys[1]][r] / 2.0,
'vect__ngram_range': [(1, 1)],
'vect__stop_words': [stop, None],
'vect__tokenizer': [tokenizer, tokenizer_porter],
'vect__use_idf': [False],
'vect__norm': [None],
'clf__penalty': ['l1', 'l2'],
'clf__C': [1.0, 10.0, 100.0]
},
]
lr_tfidf = Pipeline([('vect', tfidf),
('clf', LogisticRegression(random_state=0))])
gs_lr_tfidf = GridSearchCV(lr_tfidf,
param_grid,
scoring='accuracy',
cv=5,
verbose=1,
n_jobs=-1)
gs_lr_tfidf.fit(X_train, y_train)
print('Best parameter set: %s ' % gs_lr_tfidf.best_params_)
print('CV Accuracy: %.3f' % gs_lr_tfidf.best_score_)
clf = gs_lr_tfidf.best_estimator_
print('Test Accuracy: %.3f' % clf.score(X_test, y_test))
#############################################################################
print(50 * '=')
print('Section: Working with bigger data - online'
' algorithms and out-of-core learning')
for i, axi in enumerate(ax.flat):
axi.imshow(faces.images[i], cmap='bone')
axi.set(xticks=[], yticks=[], xlabel=faces.target_names[faces.target[i]])
from sklearn.svm import SVC
from sklearn.decomposition import RandomizedPCA
from sklearn.pipeline import make_pipeline
pca = RandomizedPCA(n_components=150, whiten=True, random_state=42)
svc = SVC(kernel='rbf', class_weight='balanced')
model = make_pipeline(pca, svc)
from sklearn.cross_validation import GridSearchCV
param_grid = {'svc__C': [1, 5, 10, 50],
'svc__gamma': [0.0001, 0.0005, 0.001, 0.005]}
grid = GridSearchCV(model, param_grid)
%time grid.fit(Xtrain, ytrain)
print(grid.best_params_)
model = grid.best_estimator_
yfit = model.predict(Xtest)
from sklearn.metrics import classification_report
print(classification_report(ytest, yfit, target_names=faces.target_names))
from sklearn.metrics import confusion_matrix
mat = confusion_matrix(ytest, yfit)
sns.heatmap(mat.T, squart=True, annot=True, fmt='d', cbar=False,
xticklabels=faces.target_names,
yticklabels=faces.target_names)
plt.text(-10.5, 4.5,
s='Petal length [standardized]',
ha='center', va='center',
fontsize=12, rotation=90)
# plt.tight_layout()
# plt.savefig('./figures/voting_panel', bbox_inches='tight', dpi=300)
plt.show()
print(mv_clf.get_params())
params = {'decisiontreeclassifier__max_depth': [1, 2],
'pipeline-1__clf__C': [0.001, 0.1, 100.0]}
grid = GridSearchCV(estimator=mv_clf,
param_grid=params,
cv=10,
scoring='roc_auc')
grid.fit(X_train, y_train)
if Version(sklearn_version) < '0.18':
for params, mean_score, scores in grid.grid_scores_:
print("%0.3f +/- %0.2f %r"
% (mean_score, scores.std() / 2.0, params))
else:
cv_keys = ('mean_test_score', 'std_test_score', 'params')
for r, _ in enumerate(grid.cv_results_['mean_test_score']):
print("%0.3f +/- %0.2f %r"
% (grid.cv_results_[cv_keys[0]][r],
grid.cv_results_[cv_keys[1]][r] / 2.0,
