def get_sparse_onehot_features():
X, y, X_holdout, ids = prepare_data("./data", drop_categorical=False)
cat_idx = get_cat_columns()
encoder = OneHotEncoder(categorical_features=cat_idx, sparse=True, handle_unknown="ignore")
X[:, cat_idx] = X[:, cat_idx] + 1
X_holdout[:, cat_idx] = X_holdout[:, cat_idx] + 1
X = encoder.fit_transform(X)
X_holdout = encoder.transform(X_holdout)
return X.tocsr(), y, X_holdout.tocsr(), ids
def build_multinomial_nb_features():
X, y, X_holdout, _ = prepare_data("./data", drop_categorical=False)
cat_idx = get_cat_columns()
X, X_holdout = X[:, cat_idx], X_holdout[:, cat_idx]
X = X + 1
X_holdout = X_holdout + 1
print "Getting OOB predictions from mNB"
clf = MultinomialNB(alpha=1)
X_1, X_2 = build_base_features(clf, X, X_holdout, y, 10)
np.vstack((X_1, X_2)).tofile('./features/NB_oob.npy')
grid_cv = GridSearchCV(SVC(probability=True, random_state=SEED),
param_grid=params,
scoring='log_loss',
n_jobs=-1,
cv=5,
verbose=1)
grid_cv.fit(X_train, y_train)
return grid_cv
if __name__ == "__main__":
X, y, X_holdout, ids = prepare_data("./data", drop_categorical=False)
# prepare the categorical columns
cat_idx = get_cat_columns()
encoder = OneHotEncoder(categorical_features=cat_idx, sparse=True, handle_unknown="ignore")
n_rows = X.shape[0]
X[:, cat_idx] = X[:, cat_idx] + 1
X_holdout[:, cat_idx] = X_holdout[:, cat_idx] + 1
X = encoder.fit_transform(X)
X_holdout = encoder.transform(X_holdout)
print "Run SVC with {} data points and {} features.".format(X.shape[0], X.shape[1])
t0 = time()
grid_cv = find_svm_model(X, y)
best_clf = grid_cv.best_estimator_
print "CV log-loss: {}".format(grid_cv.best_score_)
best_clf.fit(X, y)
