def fun_bag_fs(x, *args):
X, y, flag, n_splits, random_seed = args
n_samples, n_var = X.shape
_estimator = [None, None]
base_estimator = _estimator[int(round(x[0]))]
n_estimators = int(round(x[1]))
clf = BaggingRegressor(random_state=random_seed, )
p = {
'base_estimator': base_estimator,
'n_estimators': n_estimators,
}
clf.set_params(**p)
if len(x) <= 2:
ft = np.array([1 for i in range(n_var)])
ft = np.where(ft > 0.5)
else:
ft = np.array([1 if k > 0.5 else 0 for k in x[2::]])
ft = np.where(ft > 0.5)
#x[4::] = [1 if k>0.5 else 0 for k in x[4::]]
#ft = np.array([1 if k>0.5 else 0 for k in x[4::]])
#ft = np.where(ft>0.5)
try:
#cv=KFold(n_splits=n_splits, shuffle=True, random_state=random_seed)
#cv=KFold(n=n_samples, n_folds=5, shuffle=True, random_state=int(random_seed))
cv = KFold(n_splits=n_splits,
shuffle=True,
random_state=int(random_seed))
y_p = cross_val_predict(clf, X[:, ft].squeeze(), y, cv=cv, n_jobs=1)
#r = r2_score(y_p,y)
#r = mean_squared_error(y,y_p)**0.5
#r = -accuracy_score(y,y_p)
#r = -f1_score(y,y_p,average='weighted')
r = RMSE(y_p, y)
except:
y_p = [None]
r = 1e12
#print(r,'\t',p)
if flag == 'eval':
return r
else:
clf.fit(X[:, ft].squeeze(), y)
return {
'Y_TRUE': y,
'Y_PRED': y_p,
'EST_PARAMS': p,
'PARAMS': x,
'EST_NAME': 'BAG',
'ESTIMATOR': clf,
'ACTIVE_VAR': ft,
'DATA': X,
'SEED': random_seed
}
def run():
print "Decision Tree Regression started..."
#Preparing Training data
dir_path = ""
train_file_path = dir_path + "train.csv"
train_file = read_csv(train_file_path,skiprows=1,header=None)
train_file = train_file.drop(train_file.columns[0],axis=1)
train_file = train_file.values
train_X_temp = train_file[5:50000,:-1]
train_Y = train_file[6:50001,-1]
#Combining previous 5 time step data into one row
train_X = np.zeros((train_X_temp.shape[0],8*5))
for i in range(train_X_temp.shape[0]):
for j in range(5):
for k in range(8):
train_X[i][j*8+k] = train_X_temp[i-j][k]
#Preparing testing data
test_file_name = dir_path + "test2.csv"
test_file = read_csv(test_file_name,skiprows=1,header=None)
test_file = test_file.values
test_X = np.array(test_file[:,:-1])
test_y = test_file[:,-1]
#Model training and prediction for different no of trees
estimators = np.arange(10, 100, 10)
print "\nBagged Decision Tree:"
bag_reg = BaggingRegressor(DecisionTreeRegressor(),n_jobs=2,random_state=0).fit(train_X, train_Y)
scores = []
prediction = []
for n in estimators:
bag_reg.set_params(n_estimators=n)
bag_reg.fit(train_X, train_Y)
score = bag_reg.score(test_X, test_y)
print score
scores.append(score)
#prediction.append(bag_reg.predict(test_X))
#plotting the effect of increasing no of trees on accuracy score
plt.title("Effect of n_estimators")
plt.xlabel("n_estimator")
plt.ylabel("score")
plt.plot(estimators, scores)
plt.show()
def test_parallel_regression():
# Check parallel regression.
rng = check_random_state(0)
X_train, X_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=rng)
ensemble = BaggingRegressor(DecisionTreeRegressor(), n_jobs=3, random_state=0).fit(X_train, y_train)
ensemble.set_params(n_jobs=1)
y1 = ensemble.predict(X_test)
ensemble.set_params(n_jobs=2)
y2 = ensemble.predict(X_test)
assert_array_almost_equal(y1, y2)
ensemble = BaggingRegressor(DecisionTreeRegressor(), n_jobs=1, random_state=0).fit(X_train, y_train)
y3 = ensemble.predict(X_test)
assert_array_almost_equal(y1, y3)
def test_parallel_regression():
# Check parallel regression.
rng = check_random_state(0)
X_train, X_test, y_train, y_test = train_test_split(diabetes.data,
diabetes.target,
random_state=rng)
ensemble = BaggingRegressor(DecisionTreeRegressor(),
n_jobs=3,
random_state=0).fit(X_train, y_train)
ensemble.set_params(n_jobs=1)
y1 = ensemble.predict(X_test)
ensemble.set_params(n_jobs=2)
y2 = ensemble.predict(X_test)
assert_array_almost_equal(y1, y2)
ensemble = BaggingRegressor(DecisionTreeRegressor(),
n_jobs=1,
random_state=0).fit(X_train, y_train)
y3 = ensemble.predict(X_test)
assert_array_almost_equal(y1, y3)
