help='L1 or L2 penalization.')
parser.add_argument('C',
help='Regularization parameter.')
parser.add_argument('fit_intercept',
help='Whether to include a constant bias term in the loss function.')
parser.add_argument('n_components_pca',
help='n_components for PCA.')
parser.add_argument('model_fname',
help='Absolute path to pickle the fitted CvModel.')
args = parser.parse_args()
n_components_pca = None if args.n_components_pca == 'None' else int(args.n_components_pca)
Id, X, y = extract_training_data('/nfs/raid13/babar/dchao/KaggleCS155/data/kaggle_train_tf_idf.csv')
# trans/clf specs
n_folds = 5
scaler = StandardScaler()
pca = PCA(n_components=n_components_pca, whiten=True)
trans = Pipeline([('scale_center', scaler),('pca', pca)]).fit(X)
clf = LogisticRegression(
penalty = args.penalty,
C = float(args.C),
fit_intercept = bool(args.fit_intercept),
class_weight = 'auto'
)
cv_clf = CvModel(n_folds, trans, clf)
cv_clf.fit(X, y)
joblib.dump(cv_clf, args.model_fname)
from sklearn.externals import joblib
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestClassifier
if __name__ == '__main__':
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('n_estimators',
help='n_estimators of RandomForestClassifier.')
parser.add_argument(
'max_features',
help='Number of features to split for RandomForestClassifier.')
parser.add_argument('model_fname',
help='Absolute path to pickle the fitted CvModel.')
args = parser.parse_args()
Id, X, y = extract_training_data(
'/nfs/raid13/babar/dchao/KaggleCS155/data/kaggle_train_tf_idf.csv')
# trans/clf specs
n_folds = 5
scaler = StandardScaler().fit(X)
clf = RandomForestClassifier(n_estimators=int(args.n_estimators),
max_features=int(args.max_features))
cv_clf = CvModel(n_folds, scaler, clf)
cv_clf.fit(X, y, [1. if yi == 0 else 3. for yi in y])
joblib.dump(cv_clf, args.model_fname)
if __name__ == '__main__':
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('n_estimators',
help='n_estimators of AdaBoostClassifier.')
parser.add_argument('max_depth',
help='max_depth of base estimator DecisionTreeClassifier.')
parser.add_argument('learning_rate',
help='learning_rate of each tree.')
parser.add_argument('model_fname',
help='Absolute path to pickle the fitted CvModel.')
args = parser.parse_args()
Id, X, y = extract_training_data('/nfs/raid13/babar/dchao/KaggleCS155/data/kaggle_train_tf_idf.csv')
# trans/clf specs
n_folds = 5
scaler = StandardScaler().fit(X)
dtclf = DecisionTreeClassifier(max_depth=int(args.max_depth))
clf = AdaBoostClassifier(
base_estimator=dtclf,
n_estimators=int(args.n_estimators),
learning_rate=float(args.learning_rate)
)
cv_clf = CvModel(n_folds, scaler, clf)
cv_clf.fit(X, y)
joblib.dump(cv_clf, args.model_fname)
if __name__ == '__main__':
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('n_estimators',
help='n_estimators of RandomForestClassifier.')
parser.add_argument(
'max_features',
help='Number of features to split for RandomForestClassifier.')
parser.add_argument(
'C', help='Regularization parameter for L1 feature selection.')
parser.add_argument('model_fname',
help='Absolute path to pickle the fitted CvModel.')
args = parser.parse_args()
Id, X, y = extract_training_data(
'/nfs/raid13/babar/dchao/KaggleCS155/data/kaggle_train_tf_idf.csv')
# trans/clf specs
n_folds = 5
scaler = StandardScaler()
lasso = LinearSVC(C=float(args.C), penalty='l1', dual=False)
trans = Pipeline([('center_scale', scaler),
('feature_selection', lasso)]).fit_transform(X, y)
clf = RandomForestClassifier(n_estimators=int(args.n_estimators),
max_features=int(args.max_features))
cv_clf = CvModel(n_folds, trans, clf)
cv_clf.fit(X, y, input_trans=False)
joblib.dump(cv_clf, args.model_fname)
