verbose=1)
# Train the model on training data
rf.fit(train.drop(["smiles", "logS", "Classification"], axis=1),
train["Classification"])
# Use the forest's predict method on the test data
predictions = rf.predict(
test.drop(["smiles", "logS", "Classification"], axis=1))
predictions_t = rf.predict(
train.drop(["smiles", "logS", "Classification"], axis=1))
#Get r^2
from sklearn.metrics import accuracy_score
print('Train Sklearn accuracy:',
round(accuracy_score(predictions_t, train["Classification"]), 2))
print('Pred Sklearn accuracy:',
round(accuracy_score(predictions, test["Classification"]), 2))
from sklearn.metrics import classification_report
print("Train\n", classification_report(predictions_t, train["Classification"]))
print("Predict\n", classification_report(predictions, test["Classification"]))
try:
from notifyending import notify_ending
notify_ending("Finished fitting random forest")
except:
print("Random forest")
#quit()
import pickle
with open('catboost_backup.pickle', 'wb') as f:
pickle.dump(model, f)
predictrain = model.predict(cattrain)
predictest = model.predict(cattest)
data = {
'Catboost': ['Train', 'Test', 'Validate'],
'Precision': [ptrain, ptest, pvalid]
}
data = pd.DataFrame(data)
data.to_csv("Precision_Catboost.csv")
#LOad model
"""
from_file = CatBoostClassifier()
from_file.load_model("Catboost_Sol")
with open('catboost_backup.pickle', 'rb') as f:
model = pickle.load(f)
"""
try:
from notifyending import notify_ending
notify_ending("Finished fitting random forest with catboost")
except:
print("Random forest")