def ExtraTreeGS(X_train, X_test, y_train, y_test):
reg = ExtraTreeRegressor()
grid_values = {
'criterion': ["mse", "mae"],
'max_depth': list(range(20, 25))
}
grid_reg = GridSearchCV(
reg,
param_grid=grid_values,
scoring=['neg_mean_squared_error', 'neg_mean_absolute_error', 'r2'],
refit='r2',
n_jobs=-1,
cv=2,
verbose=100)
grid_reg.fit(X_train, y_train)
reg = grid_reg.best_estimator_
reg.fit(X_train, y_train)
y_pred = reg.predict(X_test)
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred = reg.predict(X=X_train)
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
best_params: dict = grid_reg.best_params_
saveBestParams(nameOfModel="ExtraTreeGS", best_params=best_params)
logSave(nameOfModel="ExtraTreeGS",
reg=reg,
metrics=metrics,
val_metrics=val_metrics)
def ExtraTreeRegressorPrediction(train_X, train_y, test_X, valid_X, valid_y):
etr = ExtraTreeRegressor()
etr.fit(train_X, train_y)
result = etr.predict(test_X)
valid_ypred = etr.predict(valid_X)
valid_mape = mape_loss(valid_y, valid_ypred)
print ' the mape score of ExtraTreeRegressor in valid set is :', valid_mape
return result
def ExtraTree(X_train, X_test, y_train, y_test):
reg = ExtraTreeRegressor()
reg.fit(X_train, y_train)
y_pred = reg.predict(X_test)
printMetrics(y_true=y_test, y_pred=y_pred)
val_metrics = getMetrics(y_true=y_test, y_pred=y_pred)
y_pred = reg.predict(X=X_train)
metrics = getMetrics(y_true=y_train, y_pred=y_pred)
printMetrics(y_true=y_train, y_pred=y_pred)
logSave(nameOfModel="ExtraTree",
reg=reg,
metrics=metrics,
val_metrics=val_metrics)
# In[849]:
ETR
# In[856]:
ETR.fit(x, y)
# In[857]:
ETR_prediction = ETR.predict(x_test)
plt.plot(ETR_prediction[0], label = 'prediction')
plt.plot(y_test.iloc[0], label = 'real')
# In[858]:
print('mean_absolute_error', mean_absolute_error(y_test, ETR_prediction))
print('mean_squared_error', mean_squared_error(y_test, ETR_prediction))
print('Прогноз на завтра:', ETR_prediction[0][-1])
# In[859]:
clf = DecisionTreeRegressor(max_depth= None, min_samples_split = 2, random_state = 0).fit(X,y)
clfE = ExtraTreeRegressor(max_depth=None, min_samples_split=2, random_state=0).fit(X,y)
scores = cross_val_score(clf, X, y, cv = 5)
scoresE = cross_val_score(clfE, X, y, cv = 5)
print('Training Decision',scores.mean())
print('Training Extra', scoresE.mean())
unseen = cross_val_score(clf, testX, testy, cv = 5)
unseenE = cross_val_score(clfE, testX, testy, cv = 5)
print('New Data Decision', unseen.mean())
print('New Data Extra', unseenE.mean())
defaultPrdict = clf.predict(testX)
#defaultPrdictLog = clf.predict_proba(testX)
extraPrdict = clfE.predict(testX)
#extraPrdictLog = clfE.predict_proba(testX)
defaultTrain = clf.predict(X)
extraTrain = clfE.predict(X)
#print(defaultPrdictLog)
print(clfE.n_outputs_)
print(X.shape)
print(extraPrdict)
print(defaultPrdict)
print(testy)
dCompare = [(list(defaultPrdict[i]).index(1), list(testy[i]).index(1)) for i in range(len(testy))]
eCompare = [(list(extraPrdict[i]).index(1) if 1 in list(extraPrdict[i]) else None, list(testy[i]).index(1)) for i in
#svr = SVR()
#svr.fit(X_train,y_train)
#print("Test set score:{:.2f}".format(svr.score(X_test,y_test)))
#print("Best score on train set:{:.2f}".format(svr.best_score_))
#y_pred = svr.predict(X_test)
'''lgb'''
#
gbm = ExtraTreeRegressor()
gbm = GridSearchCV(gbm, param_grid={"min_samples_leaf":[1,4,8,16,32],\
'min_samples_split':[4,10,20,100],\
'max_depth':[2,8,16,32]}, cv=6)
gbm.fit(X_train, y_train)
y_pred = gbm.predict(X_test)
# eval
print("MSE:", metrics.mean_squared_error(y_test, y_pred))
print("Test set score:{:.2f}".format(gbm.score(X_test, y_test)))
#print("AUC Score (Train): %f" % metrics.roc_auc_score(y_test, y_pred))
fig, ax = plt.subplots()
ax.scatter(y_test, y_pred)
ax.plot([y_test.min(), y_test.max()],
[y_pred.min(), y_pred.max()],
'k--',
lw=4)
ax.set_xlabel('Measured')
ax.set_ylabel('Predicted')
plt.show()
from math import *
import pandas as pd
import numpy as np
from sklearn.tree import ExtraTreeRegressor
import matplotlib.pyplot as plt
import re,os
data=pd.read_csv('ice.csv')
x=data[['temp','street']]
y=data['ice']
clf=ExtraTreeRegressor()
clf.fit(x,y)
p=clf.predict(x)
print clf.score(x,y)
t=np.arange(0.0,31.0)
plt.plot(t,data['ice'],'--',t,p,'-')
plt.show()
from sklearn.ensemble import RandomForestRegressor
rf_model=RandomForestRegressor(n_estimators=700,random_state=42)
rf_model.fit(x_train,y_train)
y_predict=rf_model.predict(x_test)
r2_score(y_test,y_predict.ravel())
# ### ExtraTreeRegressor
# In[85]:
from sklearn.tree import ExtraTreeRegressor
extratree_model=ExtraTreeRegressor(random_state=42)
extratree_model.fit(x_train,y_train)
y_predict=extratree_model.predict(x_test)
r2_score(y_test,y_predict.ravel())
# ### Result
#
# So from here we can conclude that out of multiple models RandomForestRegressor model is working well with 90.66% accuracy. which is a very good accuracy.
# In[86]:
# Using pickle we will save our model so that we can use it further
import pickle
pickle.dump(extratree_model,open('model.pkl','wb'))
model=pickle.load(open('model.pkl','rb'))
ri_MakingLT_prepared, ri_MakingLT_labels, test_size=0.20, random_state=42)
# Training Data는 Training Data_really,Training Data_val 분리
ri_MakingLT_prepared_train_re, ri_MakingLT_prepared_train_val, ri_MakingLT_labels_train_re, ri_MakingLT_labels_train_val = train_test_split(
ri_MakingLT_prepared_train,
ri_MakingLT_labels_train,
test_size=0.25,
random_state=42)
###**ExtraTreesRegressor**###
# **ExtraTreesRegressor** 모델 훈련 시킴
from sklearn.tree import ExtraTreeRegressor
Et_tree_reg = ExtraTreeRegressor(max_depth=11, random_state=42)
Et_tree_reg.fit(ri_MakingLT_prepared_train, ri_MakingLT_labels_train)
ri_MakingLT_predicted = Et_tree_reg.predict(ri_MakingLT_prepared_test)
from sklearn.metrics import mean_squared_error
Et_tree_reg_mse = mean_squared_error(ri_MakingLT_labels_test,
ri_MakingLT_predicted)
Et_tree_reg_rmse = np.sqrt(Et_tree_reg_mse)
print(Et_tree_reg_rmse)
from sklearn.metrics import mean_absolute_error
Et_tree_reg_mae = mean_absolute_error(ri_MakingLT_labels_test,
ri_MakingLT_predicted)
print(Et_tree_reg_mae)
Et_tree_reg_mape = (np.abs((ri_MakingLT_predicted - ri_MakingLT_labels_test) /
ri_MakingLT_labels_test).mean(axis=0))
print(Et_tree_reg_mape)
random_state=42)
# Training Data는 Training Data_really,Training Data_val 분리
ri_PaintingLT_prepared_train_re, ri_PaintingLT_prepared_train_val, ri_PaintingLT_labels_train_re, ri_PaintingLT_labels_train_val = train_test_split(
ri_PaintingLT_prepared_train,
ri_PaintingLT_labels_train,
test_size=0.25,
random_state=42)
###**ExtraTreesRegressor**###
# **ExtraTreesRegressor** 모델 훈련 시킴
from sklearn.tree import ExtraTreeRegressor
Et_tree_reg = ExtraTreeRegressor(max_depth=12, random_state=42)
Et_tree_reg.fit(ri_PaintingLT_prepared_train, ri_PaintingLT_labels_train)
ri_PaintingLT_predicted = Et_tree_reg.predict(ri_PaintingLT_prepared_test)
from sklearn.metrics import mean_squared_error
Et_tree_reg_mse = mean_squared_error(ri_PaintingLT_labels_test,
ri_PaintingLT_predicted)
Et_tree_reg_rmse = np.sqrt(Et_tree_reg_mse)
print(Et_tree_reg_rmse)
from sklearn.metrics import mean_absolute_error
Et_tree_reg_mae = mean_absolute_error(ri_PaintingLT_labels_test,
ri_PaintingLT_predicted)
print(Et_tree_reg_mae)
Et_tree_reg_mape = (np.abs(
(ri_PaintingLT_predicted - ri_PaintingLT_labels_test) /
ri_PaintingLT_labels_test).mean(axis=0))
from math import *
import pandas as pd
import numpy as np
from sklearn.tree import ExtraTreeRegressor
import matplotlib.pyplot as plt
import re, os
data = pd.read_csv('ice.csv')
x = data[['temp', 'street']]
y = data['ice']
clf = ExtraTreeRegressor()
clf.fit(x, y)
p = clf.predict(x)
print clf.score(x, y)
t = np.arange(0.0, 31.0)
plt.plot(t, data['ice'], '--', t, p, '-')
plt.show()
name_folder = folder.split("/")[6]
train_data = np.array(pd.read_csv('train_data.csv', sep=';'))
test_data = np.array(pd.read_csv('test_data.csv', sep=';'))
train_labels = np.array(pd.read_csv('train_labels.csv', sep=';'))
test_labels = np.array(pd.read_csv('test_labels.csv', sep=';'))
inicio = time.time()
# importar random forest regressor
from sklearn.tree import ExtraTreeRegressor
# treinar o modelo no conjunto de dados
regression = ExtraTreeRegressor().fit(train_data, train_labels)
# prever
predictions_labels = regression.predict(test_data)
fim = time.time()
df_time = pd.DataFrame({'Execution Time:': [fim - inicio]})
output_path = os.path.join(
'/home/isadorasalles/Documents/Regressao/extra_tree',
'time_' + name_folder)
df_time.to_csv(output_path, sep=';')
from sklearn import metrics
df_metrics = pd.DataFrame({
'Mean Absolute Error':
[metrics.mean_absolute_error(test_labels, predictions_labels)],
'Mean Squared Error':
from sklearn.tree import DecisionTreeRegressor
# Define model. Specify a number for random_state to ensure same results each run
dt = DecisionTreeRegressor(random_state=1)
# Fit model
dt.fit(X_train, y_train)
dt_prediction = dt.predict(X_test)
dt_score = accuracy_score(y_test, dt_prediction)
print(dt_score)
from sklearn.tree import ExtraTreeRegressor
# Define model. Specify a number for random_state to ensure same results each run
etr = ExtraTreeRegressor()
# Fit model
etr.fit(X_train, y_train)
etr_prediction = etr.predict(X_test)
etr_score = accuracy_score(y_test, etr_prediction)
print(etr_score)
X_train = df_train.drop("Survived", axis=1)
y_train = df_train["Survived"]
X_train = X_train.drop("PassengerId", axis=1)
X_test = df_test.drop("PassengerId", axis=1)
xgboost = xgb.XGBClassifier(max_depth=3, n_estimators=300,
learning_rate=0.05).fit(X_train, y_train)
Y_pred = xgboost.predict(X_test)
submission = pd.DataFrame({
"PassengerId": df_test["PassengerId"],
"Survived": Y_pred
})
submission.to_csv('submission.csv', index=False)
def etr(x_train, y_train, x_test):
model = ExtraTreeRegressor()
model.fit(x_train, y_train) # 线性回归建模
predicted = model.predict(x_test)
return (predicted)
evs_t = []
r2_t = []
for tr_i, ts_i in rkf.split(data):
print(i, j, k, c)
train, test = data.iloc[tr_i], data.iloc[ts_i]
train_x = train.drop(columns=['Rainfall'])
train_y = train['Rainfall']
test_x = test.drop(columns=['Rainfall'])
test_y = test['Rainfall']
model = ExtraTreeRegressor(criterion='mse',
splitter='best',
max_depth=i,
min_samples_leaf=j,
min_samples_split=k)
model.fit(train_x, train_y)
ts_p = model.predict(test_x)
mse_t.append(mse(test_y, ts_p))
rmse_t.append(rmse(test_y, ts_p))
mae_t.append(mae(test_y, ts_p))
mdae_t.append(mdae(test_y, ts_p))
evs_t.append(evs(test_y, ts_p))
r2_t.append(r2(test_y, ts_p))
c += 1
dep_f.append(i)
saml_f.append(j)
sams_f.append(k)
mse_f.append(np.mean(mse_t))
rmse_f.append(np.mean(rmse_t))
mae_f.append(np.mean(mae_t))
mdae_f.append(np.mean(mdae_t))
evs_f.append(np.mean(evs_t))
# 학습모델 구축을 위해 data형식을 Vector로 변환
et_X1 = et_m_Inputdata.values
et_Y1 = et_m_Outputdata.values
# Training Data, Test Data 분리
et_X1_train, et_X1_test, et_Y1_train, et_Y1_test = train_test_split(
et_X1, et_Y1, test_size=0.33, random_state=42)
########################################################################################################################
# ExtraTree 모델 구축
making_extratree_model = ExtraTreeRegressor(max_depth=10, random_state=42)
making_extratree_model.fit(et_X1_train, et_Y1_train)
et_m_predicted = making_extratree_model.predict(et_X1_test)
et_m_predicted[et_m_predicted < 0] = 0
# [1,n]에서 [n,1]로 배열을 바꿔주는 과정을 추가
et_length_x1test = len(et_X1_test)
et_m_predicted = et_m_predicted.reshape(et_length_x1test, 1)
# 학습 모델 성능 확인
et_m_mae = abs(et_m_predicted - et_Y1_test).mean(axis=0)
et_m_mape = (np.abs((et_m_predicted - et_Y1_test) / et_Y1_test).mean(axis=0))
et_m_rmse = np.sqrt(((et_m_predicted - et_Y1_test)**2).mean(axis=0))
et_m_rmsle = np.sqrt(
(((np.log(et_m_predicted + 1) - np.log(et_Y1_test + 1))**2).mean(axis=0)))
print(et_m_mae)
print(et_m_mape)
def predict_extra_tree(train_X, train_Y, test, param=30):
clf = ExtraTreeRegressor(min_samples_leaf=param, min_samples_split=1,
criterion='mse')
clf.fit(train_X, train_Y)
preds = clf.predict(test)
return preds
n = X.shape[1]
int_scores = {}
ext_scores = {}
for i in range(1, n + 1):
int_score_tmp1 = inf
ext_score_tmp1 = inf
for features in combinations(range(n), i):
X_cuted = X[:, features]
int_score_tmp2 = inf
ext_score_tmp2 = inf
for train_index, test_index in cv.split(X_cuted):
X_train, X_test = X_cuted[train_index], X_cuted[test_index]
y_train, y_test = y[train_index], y[test_index]
alg.fit(X_train, y_train)
y_pred = alg.predict(X_train)
error = mean_squared_error(y_train, y_pred)
int_score_tmp2 = min(int_score_tmp2, error)
y_pred = alg.predict(X_test)
error = mean_squared_error(y_test, y_pred)
ext_score_tmp2 = min(ext_score_tmp2, error)
int_score_tmp1 = min(int_score_tmp1, int_score_tmp2)
ext_score_tmp1 = min(ext_score_tmp1, ext_score_tmp2)
int_scores[i] = int_score_tmp1
ext_scores[i] = ext_score_tmp1
print(int_scores, ext_scores)
class ExtraTreeClass:
"""
Name : ExtraTreeRegressor
Attribute : None
Method : predict, predict_by_cv, save_model
"""
def __init__(self):
# 알고리즘 이름
self._name = 'extratree'
# 기본 경로
self._f_path = os.path.abspath(
os.path.join(os.path.dirname(os.path.abspath(__file__)),
os.pardir))
# 경고 메시지 삭제
warnings.filterwarnings('ignore')
# 원본 데이터 로드
data = pd.read_csv(self._f_path +
"/regression/resource/regression_sample.csv",
sep=",",
encoding="utf-8")
# 학습 및 테스트 데이터 분리
self._x = (data["year"] <= 2017)
self._y = (data["year"] >= 2018)
# 학습 데이터 분리
self._x_train, self._y_train = self.preprocessing(data[self._x])
# 테스트 데이터 분리
self._x_test, self._y_test = self.preprocessing(data[self._y])
# 모델 선언
self._model = ExtraTreeRegressor()
# 모델 학습
self._model.fit(self._x_train, self._y_train)
# 데이터 전처리
def preprocessing(self, data):
# 학습
x = []
# 레이블
y = []
# 기준점(7일)
base_interval = 7
# 기온
temps = list(data["temperature"])
for i in range(len(temps)):
if i < base_interval:
continue
y.append(temps[i])
xa = []
for p in range(base_interval):
d = i + p - base_interval
xa.append(temps[d])
x.append(xa)
return x, y
# 일반 예측
def predict(self, save_img=False, show_chart=False):
# 예측
y_pred = self._model.predict(self._x_test)
# 스코어 정보
score = r2_score(self._y_test, y_pred)
# 리포트 확인
if hasattr(self._model, 'coef_') and hasattr(self._model,
'intercept_'):
print(f'Coef = {self._model.coef_}')
print(f'intercept = {self._model.intercept_}')
print(f'Score = {score}')
# 이미지 저장 여부
if save_img:
self.save_chart_image(y_pred, show_chart)
# 예측 값 & 스코어
return [list(y_pred), score]
# CV 예측(Cross Validation)
def predict_by_cv(self):
# Regression 알고리즘은 실 프로젝트 상황에 맞게 Cross Validation 구현
return False
# GridSearchCV 예측
def predict_by_gs(self):
pass
# 모델 저장 및 갱신
def save_model(self, renew=False):
# 모델 저장
if not renew:
# 처음 저장
joblib.dump(self._model,
self._f_path + f'/model/{self._name}_rg.pkl')
else:
# 기존 모델 대체
if os.path.isfile(self._f_path + f'/model/{self._name}_rg.pkl'):
os.rename(
self._f_path + f'/model/{self._name}_rg.pkl',
self._f_path +
f'/model/{str(self._name) + str(time.time())}_rg.pkl')
joblib.dump(self._model,
self._f_path + f'/model/{self._name}_rg.pkl')
# 회귀 차트 저장
def save_chart_image(self, data, show_chart):
# 사이즈
plt.figure(figsize=(15, 10), dpi=100)
# 레이블
plt.plot(self._y_test, c='r')
# 예측 값
plt.plot(data, c='b')
# 이미지로 저장
plt.savefig('./chart_images/tenki-kion-lr.png')
# 차트 확인(Optional)
if show_chart:
plt.show()
def __del__(self):
del self._x_train, self._x_test, self._y_train, self._y_test, self._x, self._y, self._model
#X1 = preprocessing.normalize(X1)
X = list(zip(*X1))
Y = cols[11]
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size = 0.2, random_state=rn)
X_train = np.array(X_train)
y_train = np.array(y_train)
X_test = np.array(X_test)
y_test = np.array(y_test)
#print(y_test)
lin_reg_mod = ExtraTreeRegressor()
lin_reg_mod.fit(X_train, y_train)
pred = lin_reg_mod.predict(X_test)
#print(pred)
#print(y_test)
test_set_r2 = r2_score(y_test, pred)
#print(test_set_r2)
tr2+=test_set_r2
#abs_er = mean_absolute_error(y_test, pred)
#tabse+=abs_er
temp = []
for (i,j) in zip(y_test, pred):
t = (abs(i-j))/float(i)
temp.append(t)
#print(temp)
#print(np.meadian(temp))
# from sklearn.model_selection import GridSearchCV
# param_grid = [
# { "max_depth":list(range(1, 100))}
# ]
# grid = GridSearchCV(estimator=ExtraTreeRegressor(random_state=42), param_grid=param_grid, verbose=2, cv=10)
# grid_result = grid.fit(BL_LT_prepared_train,BL_LT_labels_train)
# print('Best Score: ', grid_result.best_score_)
# print('Best Params: ', grid_result.best_params_)
####################################################################################################################
# ExtraTreeRegressor #
####################################################################################################################
Et_tree_reg = ExtraTreeRegressor(max_depth=13, random_state=42)
Et_tree_reg.fit(BL_LT_prepared_train,BL_LT_labels_train)
BL_LT_predicted = Et_tree_reg.predict(BL_LT_prepared_test)
Et_tree_mse = mean_squared_error(BL_LT_labels_test, BL_LT_predicted)
Et_tree_rmse = np.sqrt(Et_tree_mse)
# print(Et_tree_rmse)
Et_tree_mae = mean_absolute_error(BL_LT_labels_test, BL_LT_predicted)
# print(Et_tree_mae)
Et_tree_mape = (np.abs((BL_LT_predicted - BL_LT_labels_test) / BL_LT_labels_test).mean(axis=0))
# print("Et_tree: "+str(Et_tree_mape))
Et_tree_rmsle = np.sqrt(mean_squared_log_error(BL_LT_labels_test, BL_LT_predicted))
# print(Et_tree_rmsle)
