def model_select(self,
X_train,
X_test,
y_train,
y_test,
feature_method='tf-idf'):
'''
@description: using different embedding feature to train common ML models
@param {type}
X_train, feature of train set
X_test, feature of test set
y_train, label of train set
y_test, label of test set
feature_method, three options , tfidf, word2vec and fasttext
@return: None
'''
# 对比tfidf word2vec fasttext 等词向量以及常见机器学习模型的效果
for model in self.models:
model_name = model.__class__.__name__
print(model_name)
clf = model.fit(X_train, y_train)
Test_predict_label = clf.predict(X_test)
Train_predict_label = clf.predict(X_train)
per, acc, recall, f1 = get_score(y_train, y_test,
Train_predict_label,
Test_predict_label)
# 输出训练集的准确率
logger.info(model_name + '_' + 'Train accuracy %s' % per)
# 输出测试集的准确率
logger.info(model_name + '_' + ' test accuracy %s' % acc)
# 输出recall
logger.info(model_name + '_' + 'test recall %s' % recall)
# 输出F1-score
logger.info(model_name + '_' + 'test F1_score %s' % f1)
def unbalance_helper(self,
imbalance_method='under_sampling',
search_method='grid'):
'''
@description: handle unbalance data, then search best param
@param {type}
imbalance_method, three option, under_sampling for ClusterCentroids, SMOTE for over_sampling, ensemble for BalancedBaggingClassifier
search_method: two options. grid or bayesian optimization
@return: None
'''
logger.info("get all freature")
# 生成所有feature
self.X_train, self.X_test, self.y_train, self.y_test = self.feature_engineer(
)
model_name = None
# 是否使用不平衡数据处理方式，上采样， 下采样， ensemble
###########################################
# TODO: module 4 task 1.1 #
###########################################
if imbalance_method == 'over_sampling':
logger.info("Use SMOTE deal with unbalance data ")
self.X_train, self.y_train = SMOTE().fit_resample(
self.X_train, self.y_train)
self.X_test, self.y_test = SMOTE().fit_resample(
self.X_train, self.y_train)
model_name = 'lgb_over_sampling'
elif imbalance_method == 'under_sampling':
logger.info("Use ClusterCentroids deal with unbalance data ")
self.X_train, self.y_train = ClusterCentroids(
random_state=0).fit_resample(self.X_train, self.y_train)
self.X_test, self.y_test = ClusterCentroids(
random_state=0).fit_resample(self.X_test, self.y_test)
model_name = 'lgb_under_sampling'
elif imbalance_method == 'ensemble':
self.model = BalancedBaggingClassifier(
base_estimator=DecisionTreeClassifier(),
sampling_strategy='auto',
replacement=False,
random_state=0)
model_name = 'ensemble'
logger.info('search best param')
# 使用set_params 将搜索到的最优参数设置为模型的参数
if imbalance_method != 'ensemble':
###########################################
# TODO: module 4 task 1.2 #
###########################################
# param = self.param_search(search_method=search_method)
# param['params']['num_leaves'] = int(param['params']['num_leaves'])
# param['params']['max_depth'] = int(param['params']['max_depth'])
param = {}
param['params'] = {}
param['params']['num_leaves'] = 3
param['params']['max_depth'] = 5
self.model = self.model.set_params(**param['params'])
logger.info('fit model ')
# 训练， 并输出模型的结果
self.model.fit(self.X_train, self.y_train)
###########################################
# TODO: module 4 task 1.3 #
###########################################
Test_predict_label = self.model.predict(self.X_test)
Train_predict_label = self.model.predict(self.X_train)
per, acc, recall, f1 = get_score(self.y_train, self.y_test,
Train_predict_label,
Test_predict_label)
# 输出训练集的精确率
logger.info('Train accuracy %s' % per)
# 输出测试集的准确率
logger.info('test accuracy %s' % acc)
# 输出recall
logger.info('test recall %s' % recall)
# 输出F1-score
logger.info('test F1_score %s' % f1)
self.save(model_name)
def unbalance_helper(self,
imbalance_method='under_sampling',
search_method='grid'):
'''
@description: handle unbalance data, then search best param
@param {type}
imbalance_method, three option, under_sampling for ClusterCentroids, SMOTE for over_sampling, ensemble for BalancedBaggingClassifier
search_method: two options. grid or bayesian optimization
@return: None
'''
logger.info("get all freature")
self.X_train, self.X_test, self.y_train, self.y_test = self.feature_engineer(
)
model_name = None
if imbalance_method == 'over_sampling':
logger.info("Use SMOTE deal with unbalance data ")
# 1. 使用over_sampling 处理样本不平衡问题
print(self.y_train)
self.X_train, self.y_train = SMOTE().fit_resample(
self.X_train, self.y_train)
print(self.y_train)
self.X_test, self.y_test = SMOTE().fit_resample(
self.X_train, self.y_train)
model_name = 'lgb_over_sampling'
elif imbalance_method == 'under_sampling':
logger.info("Use ClusterCentroids deal with unbalance data ")
# 1. 使用 under_sampling 处理样本不平衡问题
print(self.X_train)
#print(self.y_train)
self.X_train, self.y_train = ClusterCentroids(
random_state=0).fit_resample(self.X_train, self.y_train)
print(self.X_train)
#print(self.y_train)
self.X_test, self.y_test = ClusterCentroids(
random_state=0).fit_resample(self.X_test, self.y_test)
model_name = 'lgb_under_sampling'
elif imbalance_method == 'ensemble':
self.model = BalancedBaggingClassifier(
base_estimator=DecisionTreeClassifier(),
sampling_strategy='auto',
replacement=False,
random_state=0)
model_name = 'ensemble'
logger.info('search best param')
if imbalance_method != 'ensemble':
param = self.param_search(search_method=search_method)
param['params']['num_leaves'] = int(param['params']['num_leaves'])
param['params']['max_depth'] = int(param['params']['max_depth'])
self.model = self.model.set_params(**param['params'])
logger.info('fit model ')
self.model.fit(self.X_train, self.y_train)
# 1. 预测测试集的label
# 2. 预测训练机的label
# 3. 计算percision , accuracy, recall, fi_score
Test_predict_label = self.model.predict(self.X_test)
Train_predict_label = self.model.predict(self.X_train)
per, acc, recall, f1 = get_score(self.y_train, self.y_test,
Train_predict_label,
Test_predict_label)
# 输出训练集的准确率
logger.info('Train accuracy %s' % per)
# 输出测试集的准确率
logger.info('test accuracy %s' % acc)
# 输出recall
logger.info('test recall %s' % recall)
# 输出F1-score
logger.info('test F1_score %s' % f1)
self.save(model_name)