from question_query import create_questions_df
from answer_query import create_answers_df
from data_cleaning import DataCleaner
from model_tester import FindOptimalModels
if __name__ == '__main__':
numrows = 1e6
print("Connecting and getting ~{}".format(numrows))
a = create_answers_df(numrows)
print("Got rows, cleaning data")
a_train_dc = DataCleaner(a, questions=False, training=True,
simple_regression=True, time_split=False,
normalize=False)
A, b = a_train_dc.get_clean()
default_models = [RandomForestRegressor, GradientBoostingRegressor]
param_dict = {'rf': {'n_estimators': [50, 100, 5000], 'max_depth':
[2, 3, 5]},
'gbr': {'learning_rate': [.001, .01, .1, .2], 'max_depth':
[2, 3, 5], 'n_estimators': [50, 100, 5000]}}
print('Finding optimal models')
finder = FindOptimalModels(A, b, question=False, time_split=False)
finder.baseline_model()
fitted_models = finder.run_default_models(default_models)
print("starting grid search")
opt_params = finder.run_grid_search(fitted_models, param_dict)
opt_results = finder.run_optimized_models()
from answer_query import create_answers_df
from data_cleaning import DataCleaner
from model_tester import FindOptimalModels
if __name__ == '__main__':
numrows = 1e6
print("Connecting and getting ~{}".format(numrows))
q = create_questions_df(numrows)
print("Got rows, cleaning data")
q_train_dc = DataCleaner(q,
questions=True,
training=True,
simple_regression=True,
time_split=False,
normalize=False)
X, y = q_train_dc.get_clean()
default_models = [RandomForestRegressor, GradientBoostingRegressor]
param_dict = {
'rf': {
'n_estimators': [50, 100, 5000],
'max_depth': [2, 3, 5]
},
'gbr': {
'learning_rate': [.001, .01, .1, .2],
'max_depth': [2, 3, 5],
'n_estimators': [50, 100, 5000]
}
}
print('Finding optimal models')