print(test_X.shape)
print(test_y.shape)
# Ridge回归
# 一般情况下的Ridge(alpha：正则化强度)
model_ridge = Ridge(alpha=0.5)
model_ridge.fit(train_X, train_y)
print('训练集预测的确定系数R ^ 2: ', model_ridge.score(train_X, train_y))
print('验证集预测的确定系数R ^ 2: ', model_ridge.score(test_X, test_y))
pred_1 = model_ridge.predict(test_X)
print('模型误差: ', mean_squared_error(test_y, pred_1))
# 通过RidgeCV可以设置多个参数值，算法使用交叉验证获取最佳参数
model = RidgeCV(alphas=[0.001, 0.01, 0.1, 1.0])
model.fit(train_X, train_y)
print("模型参数:", model.get_params())
print("模型详情:", model)
print('最佳alpha', model.alpha_) # Ridge()无这个方法，只有RidgeCV算法有
print('训练集预测的确定系数R ^ 2: ', model.score(train_X, train_y))
print('验证集预测的确定系数R ^ 2: ', model.score(test_X, test_y))
pred_2 = model.predict(test_X)
print('Ridge模型误差: ', mean_squared_error(test_y, pred_2))
# Lasso回归
model_lasso = Lasso(alpha=0.01)
model_lasso = LassoCV()
model_lasso = LassoLarsCV()
model_lasso.fit(train_X, train_y)
print("模型参数:", model_lasso.get_params())
print("模型详情:", model_lasso)
y_pred = classifier.predict(X_train)
math.sqrt(mean_squared_error(y_train, y_pred))
####################### END Simple Linear Regression ###############################
####################### Regressao Ridge w/ cross validation ###############################
lambdas = np.logspace(-5, -1, 50)
ridge = RidgeCV(alphas=lambdas, fit_intercept=True, cv=10)
ridge.fit(X_train, y_train)
ridge.alpha_
ridge.cv_values_
ridge.score(X_train, y_train)
ridge.get_params()
ridge.coef_
print('Melhor lamda: %0.5f' % ridge.alpha_)
important_variables = []
club_plus_position = 0
for i in range(len(ridge.coef_)):
if abs(ridge.coef_[i]) >= 0.1:
if (i < len(df.drop(columns=['clube_id', 'posicao_id']).columns)):
important_variables.append(
df.drop(columns=['clube_id', 'posicao_id']).columns[i])
else:
club_plus_position += 1
print('Variáveis mais importantes para o Ridge: ', important_variables)
print(
plt.show()
df2 = df1[df1['charging_efficiency'] <= 20]
len(df2['deviceid'].unique())
# 不同SOC充电效率
df2['charging_efficiency_greater_12.5'] = (df2['charging_efficiency'] >
12.5) * 1
df3 = df2[df2['charging_efficiency'] > 12.5]
from sklearn.linear_model import RidgeCV
x = np.array(df3['start_soc']).reshape(df3['start_soc'].shape[0], 1)
y = np.array(df3['charging_efficiency'])
model = RidgeCV()
model.fit(x, y)
pred = model.predict(np.arange(100).reshape(100, 1))
model.get_params()
model.intercept_
model.coef_[0]
plt.scatter(df2['start_soc'],
df2['charging_efficiency'],
c=df2['charging_efficiency_greater_12.5'])
plt.plot(np.arange(100), pred, color='r')
plt.title('charging efficiency vs soc_range\n(charging efficiency<=20)')
plt.xlabel('start_soc')
plt.ylabel('charging efficiency')
plt.text(
75, 16.5, 'y = {0}x + {1}'.format(round(model.coef_[0], 4),
round(model.intercept_, 4)))
plt.show()
'min_samples_split':(2,3,4),
'min_samples_leaf':(1,2,3)}
rfr = RandomForestRegressor(random_state=seed, warm_start=True)
score = make_scorer(mean_squared_error, greater_is_better=False)
grid_obj = GridSearchCV(rfr, param_grid=parameters, scoring=score, verbose=1, n_jobs=4, cv=5)
grid_obj= grid_obj.fit(X_train, y_train)
rfr = grid_obj.best_estimator_
print rfr.get_params(), '\n'
print "Tuned model has a training RMSE score of {:.4f}.".format(predict_labels(rfr, X_train, y_train))
print "Tuned model has a testing RMSE score of {:.4f}.".format(predict_labels(rfr, X_valid, y_valid))
# RidgeCV
ridge = RidgeCV(alphas=(1e-8, 1e-7, 1e-6, 1e-5, 1e-4, 1e-3, 1e-2, 0.1, 1.0, 10.0), cv=5)
ridge = ridge.fit(X_train, y_train)
print ridge.get_params(), '\n'
print "Tuned model has a training RMSE score of {:.4f}.".format(predict_labels(ridge, X_train, y_train))
print "Tuned model has a testing RMSE score of {:.4f}.".format(predict_labels(ridge, X_valid, y_valid))
# Save regressors
pickle_file = 'regressor.pickle'
try:
f = open(pickle_file, 'wb')
save = {
'random_forest_regressor': rfr,
'ridge': ridge,
}
pickle.dump(save, f, pickle.HIGHEST_PROTOCOL)
f.close()
except Exception as e:
class Model:
params = Params()
testsize = float(params.get_data_params()['testsize'])
random_state = int(params.get_data_params()['randomstate'])
def __init__(self, X, y, **kwargs):
self.X, self.x_val, self.y, self.y_val = train_test_split(
X, y, test_size=self.testsize, random_state=self.random_state)
self.model = None
self.FeatureSelectionType = kwargs['featureselection']
self.features = self.X.columns
self.model_coefficients = None
self.EvalMetrics = kwargs['evalmetric']
self.FeatSelCvFolds = kwargs['featureselectioncvfolds']
self.CvFolds = kwargs['gridsearchcvfolds']
self.gridSearch = kwargs['gridsearchcv']
self.set_model()
self.feature_selection()
self.fit_model()
def __repr__(self):
return "Model(" + str(self.model) + ")"
def set_model(self):
model_name = self.params.get_model()
if model_name == 'lr':
self.model = LinearRegression()
params = self.params.get_linear_reg()
del params['regularization']
self.model = self.model.set_params(**params)
elif model_name == 'svr':
self.model = SVR()
self.model = self.model.set_params(**self.params.get_svr())
else:
pass
def lasso(self):
estimator = LassoCV(cv=5, max_iter=10000)
selector = SelectFromModel(estimator)
selector = selector.fit(self.X, self.y)
bool_mask = selector.get_support()
self.features = list(compress(self.X.columns, bool_mask))
self.X = self.X.loc[:, bool_mask]
self.x_val = self.x_val.loc[:, bool_mask]
def feature_selection(self):
if self.FeatureSelectionType.lower() == "lasso":
self.lasso()
else:
self.features = self.X.columns
def fit_model(self):
print("Fitting model..")
model_type = self.params.get_model()
if self.gridSearch and model_type == 'svr':
params_grid = {'C': [0.001, 0.01, 0.1, 1, 10, 100],
'gamma': [0.0001, 0.001, 0.01, 0.1, 1],
'kernel': ['linear', 'rbf'],
}
reg = GridSearchCV(self.model,
params_grid,
cv=5)
reg.fit(self.X, self.y)
self.model = self.model.set_params(**reg.best_params_)
self.model.fit(self.X, self.y)
elif model_type =='lr':
regularization = self.params.get_linear_reg()['regularization']
if regularization.lower() == 'ridge':
params = self.model.get_params()
del params['copy_X']
del params['n_jobs']
self.model = RidgeCV(cv=5)
self.model = self.model.set_params(**params)
self.model.fit(self.X, self.y)
else:
self.model.fit(self.X, self.y)
else:
self.model.fit(self.X, self.y)
def score_model(self):
cv_fold = int(self.params.get_test_params()['testcvfold'])
train_score_result = []
val_score_result = []
score_result = pd.DataFrame()
y_pred = self.model.predict(self.x_val)
scoring_list = ['r2', 'neg_mean_absolute_error', 'neg_mean_squared_error']
for scoring in scoring_list:
train_score_result.append(
np.abs(np.mean(cross_val_score(self.model,
self.X,
self.y,
scoring=scoring,
cv=cv_fold))))
train_score_result.append(np.sqrt(train_score_result[2]))
val_score_result.append(r2_score(self.y_val, y_pred))
val_score_result.append(mean_absolute_error(self.y_val, y_pred))
val_score_result.append(mean_squared_error(self.y_val, y_pred))
val_score_result.append(np.sqrt(val_score_result[2]))
score_result['mean {}-fold cv'.format(self.FeatSelCvFolds)] = train_score_result
score_result['validation score'] = val_score_result
score_result.index = ['r2', 'MAE', 'MSE', 'RMSE']
print("""
#########################################################
######## Model and final parameters #######
#########################################################\n
{}
""".format(self.model)
)
if self.params.get_model() == 'lr':
coef_feature = pd.DataFrame()
coef_feature['Coefficients'] = self.model.coef_
coef_feature['Feature'] = self.X.columns
else:
print("Predictors used:")
coef_feature = self.X.columns.values
print("{}".format(coef_feature)
)
print("""
#########################################################
######### Score #########
#########################################################\n
{}
""".format(score_result))
