for index, row in data.iterrows():#iterate over csv file
if index==limit:
break
img=cv2.imread(root_path + '/images/' + str(row['image_id']) + '.jpg')
histogram=np.zeros((3, 256))
for i in range(3):#calc hist for each channel
histogram[i] = cv2.calcHist([img],[i],None,[256],[0,255]).ravel()
X[index]=histogram.ravel()#to 1d array
return X
X = extract_features(train_data, 1500)
y = train_data['image_label'].values[:X.shape[0]].ravel()
grid = {
'knn__n_neighbors': [1, 10, 20, 30, 40, 60, 75, 100, 120, 160, 200],
'knn__metric': ['euclidean', 'manhattan', 'chebyshev'],
'knn__weights': ['uniform', 'distance'],
'preprocess__norm': ['l1', 'l2', 'max']
}
pipeline = Pipeline(steps=[
('preprocess', preprocessing.Normalizer()),
('knn', neighbors.KNeighborsClassifier())
])
model = EvolutionaryAlgorithmSearchCV(pipeline, grid, scoring='roc_auc', verbose=True, n_jobs=4, population_size=10)
model.fit(X, y)
preds = model.predict_proba(extract_features(test_data))[:, 1]
test_data = test_data.drop('image_url', 1)
test_data['image_label'] = preds
test_data.to_csv(root_path + '/res.csv', index=False)
try:
clf = EvolutionaryAlgorithmSearchCV(estimator=clf(),
params=params,
**generic_args).fit(
X_train, y_train)
except:
print 'failed to do: {}'.format(name)
continue
score = clf.score(X_test, y_test)
# Plot the decision boundary. For that, we will assign a color to each
# point in the mesh [x_min, x_max]x[y_min, y_max].
if hasattr(clf, "decision_function"):
Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
else:
Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]
# Put the result into a color plot
Z = Z.reshape(xx.shape)
plot_data[ds_cnt][name] = {
'Z': Z,
'v_score': score,
't_score': clf.best_score_,
'all_logbooks': clf.all_logbooks_[0]
}
ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)
# Plot also the training points
ax.scatter(X_train[:, 0],
X_train[:, 1],
c=y_train,
