SHOW:
|
|
- or go back to the newest paste.
| 1 | pca = ('reduce_dim', PCA(n_components = N_features / 2))
| |
| 2 | svc = ('svc', SVC(kernel = 'poly', C = 10, degree = 4, max_iter = 10000000))
| |
| 3 | kmeans = ('kmeans', KMeans(n_clusters = 5))
| |
| 4 | tree = ('tree', DecisionTreeClassifier())
| |
| 5 | transform = ('anova', feature_selection.SelectPercentile(feature_selection.f_classif, percentile = 50))
| |
| 6 | ||
| 7 | parameters = {
| |
| 8 | "reduce_dim__n_components": [N_features / 2, N_features / 3, N_features / 4], | |
| 9 | "kmeans__n_clusters": [3, 6, 8, 10] | |
| 10 | } | |
| 11 | ||
| 12 | estimators = [ | |
| 13 | pca, | |
| 14 | kmeans, | |
| 15 | tree | |
| 16 | ] | |
| 17 | pipe = Pipeline(estimators) | |
| 18 | grid = GridSearchCV(pipe, param_grid = parameters, n_jobs=-1, cv = KFold(n_splits=3, random_state = 42)) | |
| 19 | clf = grid | |
| 20 | ||
| 21 | ||
| 22 | # Example starting point. Try investigating other evaluation techniques! | |
| 23 | from sklearn.model_selection import train_test_split | |
| 24 | features_train, features_test, labels_train, labels_test = \ | |
| 25 | train_test_split(features, labels, test_size=0.3, random_state=42, shuffle = False) | |
| 26 | ||
| 27 | clf.fit(features, labels) | |
| 28 | print clf.best_score_ |
