trainFile = TrainFile("../data/train.csv", True) trainFile.Read() testFile = TestFile("../data/test.csv", True) testFile.Read() print "Data loaded..." X = np.array(trainFile.data) Y = np.array(trainFile.labels) # just like the face recognition, we compute the avg digit image avg_digit = compute_avg_digits(X, configs.IMAGE_WIDTH) print "Avg digit computed ..." # Substract each input with the avg X_normalized_avg = normalize_with_avg(X, avg_digit) X_normalized = preprocessing.normalize(X_normalized_avg) print "Normalize X ..." # Eigen Face n_component = 0.07 pca = PCA(n_components=configs.IMAGE_WIDTH * configs.IMAGE_WIDTH * n_component) features = pca.fit_transform(X_normalized) print "Transform done ..." # split into training and testing #cutoff = len(Y) * 0.75 #features_train = np.array(features[:cutoff]) #Y_train = np.array(Y[:cutoff]) #features_test = np.array(features[cutoff:]) #Y_test = np.array(Y[cutoff:])
trainFile = TrainFile("../data/train.csv", True) trainFile.Read() testFile = TestFile("../data/test.csv", True) testFile.Read() print "Data loaded..." X = np.array(trainFile.data) Y = np.array(trainFile.labels) # just like the face recognition, we compute the avg digit image avg_digit = compute_avg_digits(X, configs.IMAGE_WIDTH) print "Avg digit computed ..." # Substract each input with the avg X_normalized_avg = normalize_with_avg(X, avg_digit) X_normalized = preprocessing.normalize(X_normalized_avg) print "Normalize X ..." # Eigen Face n_component = 0.07 pca = PCA(n_components=configs.IMAGE_WIDTH * configs.IMAGE_WIDTH * n_component) features = pca.fit_transform(X_normalized) print "Transform done ..." # split into training and testing # cutoff = len(Y) * 0.75 # features_train = np.array(features[:cutoff]) # Y_train = np.array(Y[:cutoff]) # features_test = np.array(features[cutoff:]) # Y_test = np.array(Y[cutoff:])
trainFile = TrainFile("../data/train.csv", True) trainFile.Read() testFile = TestFile("../data/test.csv", True) testFile.Read() print "Data loaded..." X = np.array(trainFile.data) Y = np.array(trainFile.labels) # just like the face recognition, we compute the avg digit image avg_digit = compute_avg_digits(X, configs.IMAGE_WIDTH) print "Avg digit computed ..." # Substract each input with the avg X_normalized_avg = normalize_with_avg(X, avg_digit) X_normalized = preprocessing.normalize(X_normalized_avg) print "Normalize X ..." # Eigen Face for n_component in [ 0.06, 0.07, 0.08 ]: pca = PCA(n_components=configs.IMAGE_WIDTH * configs.IMAGE_WIDTH * n_component) features = pca.fit_transform(X_normalized) print "Transform done ..." features = np.array(features) Y = np.array(Y) # Using Random forest n_trees = 1000 model = RandomForestClassifier(n_estimators=n_trees)
trainFile = TrainFile("../data/train.csv", True) trainFile.Read() testFile = TestFile("../data/test.csv", True) testFile.Read() print "Data loaded..." X = np.array(trainFile.data) Y = np.array(trainFile.labels) # just like the face recognition, we compute the avg digit image avg_digit = compute_avg_digits(X, configs.IMAGE_WIDTH) print "Avg digit computed ..." # Substract each input with the avg X_normalized_avg = normalize_with_avg(X, avg_digit) X_normalized = preprocessing.normalize(X_normalized_avg) print "Normalize X ..." # ICA Face ica = FastICA() features = ica.fit_transform(X_normalized) print "Transform done ..." # split into training and testing cutoff = len(Y) * 0.75 features_train = np.array(features[:cutoff]) Y_train = np.array(Y[:cutoff]) features_test = np.array(features[cutoff:]) Y_test = np.array(Y[cutoff:])