from skopt import BayesSearchCV
from catboost import CatBoostRegressor
from scipy.stats import norm,uniform
import numpy as np
import pickle
"""
Used to generate trained GB models with different train-test splits.
"""
np.random.seed(100)
df = pickle.load(open('../../data/pairs_pdos.pkl'))
if True:
X,y = train_prep_pdos(df,include_WF=True,dE=0.1)
model_type = 'pdos'
else:
X,y = train_prep(df,include_WF=True)
model_type = 'moments'
if False:
X_train, X_dev, X_test, y_train, y_dev, y_test = split_by_cols(df,X,y,['comp','ads_a','ads_b'])
split_type = 'comp_rxn'
elif True:
X_train, X_dev, X_test, y_train, y_dev, y_test = split_by_cols(df,X,y,['comp'])
split_type = 'comp'
elif False:
X_train, X_dev, X_test, y_train, y_dev, y_test = split_by_cols(df,X,y,['ads_a','ads_b'])
split_type = 'rxn'
else:
print('Model Performance')
print('Average Error: {:0.4f} eV.'.format(mae))
return mae
if __name__ == '__main__':
df = pickle.load(open('data/pairs_pdos.pkl'))
features = 'moments' # #pdos,'moments'
bayes = True
#Feature Selection
if features == 'moments':
X, y = train_prep(df)
elif features == 'pdos':
X, y = train_prep_pdos(df, stack=False, include_WF=False, dE=0.1)
X_train, X_dev, X_test, y_train, y_dev, y_test, groups = split_by_cols(
df, X, y, ['comp', 'ads_a', 'ads_b'], ret_groups=True)
rf = ensemble.RandomForestRegressor(n_estimators=100)
group_kfold = GroupKFold(n_splits=3)
#print(X_train.shape[1]),np.sqrt(X_train.shape[1])
if bayes:
random_grid = { #'n_estimators': (5,100),
'max_features': (int(np.sqrt(X_train.shape[1])), X_train.shape[1]),
'max_depth': (5, 50),
'min_samples_split': (2, 10),
'min_samples_leaf': (2, 5),
key = [
'comp', 'bulk', 'facet', 'coord', 'site_b', 'ads_a', 'ads_b', 'comp_g',
'dE'
]
df = pickle.load(open('data/pairs_pdos.pkl'))
#models = ['rf','lr','krr']#,'NN']
models = ['rf', 'boost']
features = 'pdos' # #pdos,'moments'
split = 'pairs'
#Feature Selection
if features == 'moments':
X, y = train_prep(df)
elif features == 'pdos':
X, y = train_prep_pdos(df, stack=False, include_WF=True)
#X,y = train_prep_pdos(df,include_WF=True,stack=True)
for m in models:
#Train/test split
if split == 'none':
X_train = X
X_test = X
y_train = y
y_test = y
elif split == 'random':
np.random.seed(100)
X_train, X_test, y_train, y_test = train_test_split(
X, y, test_size=0.3) #need to add dev
X_dev, X_test, y_dev, y_test = train_test_split(
X_test, y_test, test_size=0.5) #need to add dev