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:
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.3)
X_dev, X_test, y_dev, y_test = train_test_split(X_test,y_test,test_size=0.5)
split_type = 'random'
errors = abs(predictions - test_labels)
mae = np.mean(errors)
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),
import pickle
import matplotlib.pyplot as plt
from ML_prep import load_data, split_by_cols, train_prep_pdos, train_prep
import numpy as np
df = pickle.load(open('data/pairs_pdos.pkl'))
X,y = train_prep_pdos(df,include_WF=True,dE=0.1)
X1,y1 = train_prep(df,include_WF=True)
i = 1094
#i = 889
n = 2
figsize = (8,8)
if n == 2:
fig1 = plt.figure(facecolor=(0.75,)*3,figsize=figsize)
fig2 = plt.figure(facecolor=(0.75,)*3,figsize=figsize)
axs = [fig1.add_subplot(111),fig2.add_subplot(111)]
else:
fig = plt.figure(figsize=figsize)
axs = [fig.add_subplot(111)]
while True:
print i
Xi = X[i]
axs[0].fill_between(range(200),[0]*200,Xi[:200],facecolor='deepskyblue',edgecolor='none')
axs[0].fill_between(range(199,352),[0]*(352-199),Xi[199:352],facecolor='deepskyblue',edgecolor='none',alpha=0.3)
if n == 2:
