from sklearn.pipeline import Pipeline
from sklearn.decomposition import PCA
from sklearn.model_selection import train_test_split
from fastsr.estimators.symbolic_regression import SymbolicRegression
from fastsr.containers.learning_data import LearningData
estimators = [('reduce_dim', PCA()), ('symbolic_regression', SymbolicRegression())]
pipe = Pipeline(estimators)
training_data = LearningData()
training_data.from_file('data/hour_simple_lagged.hdf5')
X_train, X_test, y_train, y_test = train_test_split(training_data.predictors, training_data.response, test_size=0.1,
shuffle=False)
pipe.fit(X_train, y_train)
print(pipe.score(X_train, y_train))
model = SymbolicRegression()
model.fit(X_train, y_train)
print(model.score(X_train, y_train))
required=True)
parser.add_argument('-s', '--seed', help='Random seed.', type=int)
args = parser.parse_args()
if args.experiment == 'TruncationElite':
experiment_class, experiment_name = utils.get_experiment_class_and_name(
TruncationElite)
elif args.experiment == 'TruncationEliteRT':
experiment_class, experiment_name = utils.get_experiment_class_and_name(
TruncationEliteRT)
elif args.experiment == 'TruncationEliteRTNOMUT':
experiment_class, experiment_name = utils.get_experiment_class_and_name(
TruncationEliteRTNOMUT)
training_data = LearningData()
training_data.from_file(args.data)
X_train, X_test, y_train, y_test = train_test_split(training_data.predictors,
training_data.response,
test_size=0.2,
shuffle=False)
print('Training examples: ' + str(X_train.shape[0]))
print('Testing examples: ' + str(X_test.shape[0]))
model = SymbolicRegression(
experiment_class=experiment_class,
variable_type_indices=training_data.variable_type_indices,
variable_names=training_data.variable_names,
variable_dict=training_data.variable_dict,
num_features=training_data.num_variables,
pop_size=100,
ngen=1000,
crossover_probability=.5,
experiment = 'rt'
dataset = 'energy_lagged'
path = '/'.join([dataset, experiment])
models_dir = '/home/cfusting/efsresults/' + path + '/saved_models/'
results_dir = '/home/cfusting/efsscores/' + path
def get_seed(file):
pattern = re.compile('\d+')
match = pattern.search(file)
return match.group(0)
training_data = LearningData()
training_data.from_file(
'/home/cfusting/bunny/range-terminal/data/energy_lagged.hdf5')
X_train, X_test, y_train, y_test = train_test_split(training_data.predictors,
training_data.response,
test_size=0.2,
shuffle=False)
files = [f for f in listdir(models_dir) if isfile(join(models_dir, f))]
scores = {}
all_features = {}
print('Processing seeds for ' + experiment)
for fl in files:
with open(models_dir + '/' + fl, 'rb') as f:
data = pickle.load(f)
seed = get_seed(fl)
print('Processing seed: ' + str(seed))
statistics = data[0]
best_models = data[1]