import os.path from sklearn.neighbors import KNeighborsClassifier sys.path.insert(0, '.') from optimize_model import optimize_model submission_file = 'submission_knn_f3.csv' features_files = [['data/Dog_1/features_02.txt']] """ features_files = [['data/Dog_1/features_02.txt', 'data/Dog_2/features_01.txt', 'data/Dog_3/features_01.txt', 'data/Dog_4/features_01.txt', 'data/Dog_5/features_01.txt', 'data/Patient_1/features_01.txt', 'data/Patient_2/features_01.txt']] """ for f in features_files: if type(f) == str: sys.exit('Each element of features_files must be a list of files.') print f optimize_model(f, submission_file, min_features=1, max_features=2, classifier=KNeighborsClassifier, parameters={'n_neighbors': [5, 10, 15], 'weights': ['uniform', 'distance']}, outlier_sigma=2, normalize_probs=None, n_cv=100) raw_input('Press Enter to end.')
#!/usr/bin/env python import sys import os.path sys.path.insert(0, '.') from optimize_model import optimize_model submission_file = 'submission_log_reg_f1to4_reopt_rocslope10.csv' features_files = [['data/Dog_1/features_02.txt'], ['data/Dog_2/features_01.txt'], ['data/Dog_3/features_01.txt'], ['data/Dog_4/features_01.txt'], ['data/Dog_5/features_01.txt'], ['data/Patient_1/features_01.txt'], ['data/Patient_2/features_01.txt']] for f in features_files: if type(f) == str: sys.exit('Each element of features_files must be a list of files.') print f optimize_model(f, submission_file, max_features=4, outlier_sigma=2, normalize_probs='ROCSlope', n_cv=100) raw_input('Press Enter to end.')
import os.path from sklearn.svm import SVC sys.path.insert(0, '.') from optimize_model import optimize_model submission_file = 'submission_svm_f1to2.csv' features_files = [['data/Dog_1/features_02.txt'], ['data/Dog_2/features_01.txt'], ['data/Dog_3/features_01.txt'], ['data/Dog_4/features_01.txt'], ['data/Dog_5/features_01.txt'], ['data/Patient_1/features_01.txt'], ['data/Patient_2/features_01.txt']] for f in features_files: if type(f) == str: sys.exit('Each element of features_files must be a list of files.') print f optimize_model(f, submission_file, min_features=1, max_features=2, feature_columns=range(2, 27), classifier=SVC, parameters={'C': [0.1, 1, 10], 'gamma': [0.25, 0.5, 1], 'kernel': ['rbf'], 'probability': [True], 'class_weight': ['auto']}, outlier_sigma=2, normalize_probs='IsoReg', n_cv=20) raw_input('Press Enter to end.')
import sys import os.path from sklearn.ensemble import RandomForestClassifier sys.path.insert(0, '.') from optimize_model import optimize_model submission_file = 'submission_rf_f4to7imp_all.csv' features_files = [['data/Dog_1/features_02.txt', 'data/Dog_2/features_01.txt', 'data/Dog_3/features_01.txt', 'data/Dog_4/features_01.txt', 'data/Dog_5/features_01.txt', 'data/Patient_1/features_01.txt', 'data/Patient_2/features_01.txt']] for f in features_files: if type(f) == str: sys.exit('Each element of features_files must be a list of files.') print f optimize_model(f, submission_file, min_features=4, max_features=7, feature_columns=[11, 5, 4, 10, 2, 9, 6], classifier=RandomForestClassifier, parameters={'n_estimators': [10, 50], 'criterion': ['entropy'], 'min_samples_leaf': [3, 6, 10]}, outlier_sigma=2, normalize_probs=None, n_cv=100) raw_input('Press Enter to end.')