def RF(self, args): ## Random Forest
logger.info("Running Random Forest... ")
if args.predictor.lower() == 'classifier':
from sklearn.ensemble import RandomForestClassifier as randomforest
rf = randomforest(criterion='entropy',
class_weight='balanced',
random_state=42)
elif args.predictor.lower() == 'regressor':
from sklearn.ensemble import RandomForestRegressor as randomforest
## Initialize RandomForest
rf = randomforest(n_estimators=20000,
max_depth=4,
random_state=42,
max_samples=0.6,
n_jobs=-1)
rf.fit(self.X_train, self.y_train)
# Get the predicted values
self.y_pred = rf.predict(self.X_data)
if args.predictor.lower() == 'regressor':
self.y_pred = logistic.cdf(self.y_pred)
self.data['boosting_score'] = self.y_pred
self.model = rf
return self
def RF(self, args): ## Random Forest
logger.info("Running Random Forest... ")
if args.predictor.lower() == 'classifier':
from sklearn.ensemble import RandomForestClassifier as randomforest
rf = randomforest( #n_estimators = 5000,
criterion='entropy', random_state=42)
elif args.predictor.lower() == 'regressor':
from sklearn.ensemble import RandomForestRegressor as randomforest
## Initialize RandomForest
rf = randomforest(n_estimators=5000,
min_samples_leaf=0.12,
criterion='entropy',
warm_start=True,
max_depth=8)
rf.fit(self.X_train, self.y_train)
# Get the predicted values
self.y_pred = rf.predict(self.X_data)
if args.predictor.lower() == 'regressor':
self.y_pred = logistic.cdf(self.y_pred)
self.data['boosting_score'] = self.y_pred
self.model = rf
return self
def rdf():
x,y,yid = rdfreadvw()
test,testy,testid = rdfreadvw('mytest.vw')
#print len(testy),len(testid)
train = x.toarray()
test = test.toarray()
rf = randomforest()
rf.fit(train,y)
print rf.score(train,y)
pred = rf.predict(test)
# #predprob = rf.predict_proba(test)
with open('rfpred2.txt','w') as f:
for f1,f2 in zip(pred,testid):
print >> f, f1, f2
# submission = pd.DataFrame(
# {'key': test_df.key, 'fare_amount': predicted_values},
# columns = ['key', 'fare_amount'])
# submission.to_csv('submission.csv', index = False)
print(os.listdir('.'))
# In[ ]:
from sklearn.ensemble import RandomForestRegressor as randomforest
# Create the random forest
random_forest = randomforest(n_estimators=20,
max_depth=20,
max_features=None,
oob_score=True,
bootstrap=True,
verbose=1,
n_jobs=-1)
# Train on data
random_forest.fit(
df[[
'trip_distance', 'pickup_longitude', 'pickup_latitude',
'dropoff_longitude', 'dropoff_latitude', 'abs_lat_diff',
'abs_lon_diff', 'passenger_count'
]], df['fare_amount'])
predicted_values = random_forest.predict(test_df[[
'trip_distance', 'pickup_longitude', 'pickup_latitude',
'dropoff_longitude', 'dropoff_latitude', 'abs_lat_diff', 'abs_lon_diff',
'passenger_count'