def main():
sf = FS.Select(Sequence=True, Random=True,
Cross=False) #select the way you want to process searching
sf.ImportDF(prepareData(), label='is_trade')
sf.ImportLossFunction(modelscore, direction='descend')
sf.ImportCrossMethod(CrossMethod)
sf.InitialNonTrainableFeatures([
'used', 'instance_id', 'item_property_list', 'context_id',
'context_timestamp', 'predict_category_property', 'is_trade'
])
sf.InitialFeatures([
'item_category_list', 'item_price_level', 'item_sales_level',
'item_collected_level', 'item_pv_level', 'day'
])
sf.GenerateCol(key='mean', selectstep=2)
sf.SetSample(0.1, samplemode=0, samplestate=0)
# sf.SetFeaturesLimit(5)
sf.SetTimeLimit(1)
sf.clf = lgbm.LGBMClassifier(random_state=1,
num_leaves=6,
n_estimators=5000,
max_depth=3,
learning_rate=0.05,
n_jobs=8)
sf.SetLogFile('recordml.log')
sf.run(validation)
def main():
sf = FS.Select(Sequence = True, Random = False, Cross = True)
sf.ImportDF(prepareData(),label = 'Survived')
sf.ImportLossFunction(modelscore,direction = 'ascend')
sf.ImportCrossMethod(CrossMethod)
sf.InitialNonTrainableFeatures(['Survived'])
sf.InitialFeatures([])
sf.AddPotentialFeatures(['Pclass'])
sf.clf = LogisticRegression()
sf.SetLogFile('record.log')
sf.run(validation)
def main():
sf = FS.Select(Sequence = True, Random = True, Cross = True)
sf.ImportDF(prepareData(),label = 'Survived')
sf.ImportLossFunction(modelscore,direction = 'ascend')
sf.ImportCrossMethod(CrossMethod)
sf.NonTrainableFeatures = ['Survived']
sf.InitialFeatures([])
sf.PotentialAdd = ['Pclass']
#sf.clf = lgbm.LGBMClassifier(random_state=1, num_leaves = 6, n_estimators=5000, max_depth=3, learning_rate = 0.05, n_jobs=1)
sf.clf = LogisticRegression()
sf.logfile = 'record.log'
sf.run(validation)
def main():
sf = FS.Select(Sequence = True, Random = False, Cross = True)
sf.ImportDF(prepareData(),label = 'Survived')
sf.ImportLossFunction(modelscore,direction = 'ascend')
sf.ImportCrossMethod(CrossMethod)
sf.InitialNonTrainableFeatures(['Survived'])
sf.InitialFeatures([])
sf.GenerateCol()
sf.SetSample(0.5, samplemode = 0, samplestate = 0)
sf.AddPotentialFeatures(['Pclass'])
sf.clf = LogisticRegression()
sf.SetLogFile('record2.log')
# sf.SetFeaturesLimit(5)
sf.SetTimeLimit(0.2)
sf.run(validation)
def main():
sf = FS.Select(Sequence=True, Random=False, Cross=False)
sf.ImportDF(prepareData(), label='buy')
sf.ImportLossFunction(score1, direction='ascend')
#sf.ImportCrossMethod(CrossMethod)
sf.InitialNonTrainableFeatures(
['buy', 'nextbuy', 'o_date', 'a_date', 'PredictDays', 'user_id'])
sf.InitialFeatures(
['age_x', 'sex_x', 'user_lv_cd_x', 'buycnt', 'daybeforelastbuy_o_ave'])
#sf.PotentialAdd = ['daybeforelastbuy_o_mean']
#sf.clf = lgbm.LGBMClassifier(random_state=1, num_leaves = 6, n_estimators=5000, max_depth=3, learning_rate = 0.05, n_jobs=1)
sf.clf = lgbm.LGBMClassifier(random_state=1,
num_leaves=6,
n_estimators=1000,
max_depth=3,
learning_rate=0.2,
n_jobs=8)
sf.SetLogFile('record.log')
sf.run(validate)
def main():
sf = FS.Select(Sequence=True, Random=False, Cross=False) #初始化选择器，选择你需要的流程
sf.ImportDF(df, label='nextbuy') #导入数据集以及目标标签
sf.ImportLossFunction(score, direction='ascend') #导入评价函数以及优化方向
sf.InitialNonTrainableFeatures(
['buy', 'nextbuy', 'o_date', 'a_date', 'PredictDays',
'user_id']) #初始化不能用的特征
sf.InitialFeatures(
['age_x', 'sex_x', 'user_lv_cd_x', 'buycnt',
'daybeforelastbuy_o_ave']) #初始化其实特征组合
sf.GenerateCol() #生成特征库 （具体该函数变量请参考根目录下的readme）
sf.SetSample(1, samplemode=1) #初始化抽样比例和随机过程
sf.SetTimeLimit(100) #设置算法运行最长时间，以分钟为单位
sf.clf = lgbm.LGBMRegressor(random_state=1,
num_leaves=6,
n_estimators=1000,
max_depth=3,
learning_rate=0.2,
n_jobs=8) #设定回归模型
sf.SetLogFile('record.log') #初始化日志文件
sf.run(validate) #输入检验函数并开始运行
def main():
sf = FS.Select(Sequence = False, Random = True, Cross = False) #select the way you want to process searching
sf.ImportDF(prepareData(),label = 'is_trade')
sf.ImportLossFunction(modelscore,direction = 'descend')
sf.ImportCrossMethod(CrossMethod)
sf.InitialNonTrainableFeatures(['context_timestamp', 'is_trade'])
features_import = loadCSV('model/dif_on_feature_mean_4_25.csv')
initial_features = list(features_import['feature'].values)[::-1][:100]
sf.InitialFeatures(initial_features)
sf.clf = lgbm.LGBMClassifier(max_depth=7,
n_jobs=60,
num_leaves=64,
seed=1080,
learning_rate=0.05,
n_estimators=400,
colsample_bytree = 0.8,
subsample = 0.8)
sf.SetLogFile('./model/record_100_7_50.log')
sf.run(validation)
def main():
sf = FS.Select(Sequence=True, Random=False,
Cross=False) #select the way you want to process searching
sf.ImportDF(prepareData(), label='is_trade')
sf.ImportLossFunction(modelscore, direction='descend')
sf.ImportCrossMethod(CrossMethod)
sf.InitialNonTrainableFeatures(columns_2.drop_columns)
sf.InitialFeatures([])
sf.GenerateCol(key='mean', selectstep=2)
sf.SetSample(0.1, samplemode=0, samplestate=0)
sf.AddPotentialFeatures(columns_2.all_select_columns)
# sf.SetFeaturesLimit(20)
sf.SetTimeLimit(100)
sf.clf = lgbm.LGBMClassifier(random_state=1024,
num_leaves=63,
n_estimators=100,
max_depth=7,
learning_rate=0.1)
sf.SetLogFile(
'/home/share/liangxiao/second_stage/feature_selection/recordml_2.log')
sf.run(validation)
return np.mean(totaltest)
def add(x,y):
return x + y
def substract(x,y):
return x - y
def times(x,y):
return x * y
def divide(x,y):
return (x + 0.001)/(y + 0.001)
CrossMethod = {'+':add,
'-':substract,
'*':times,
'/':divide,}
sf = FS.Select(Sequence = True, Random = False, Cross = False) #初始化选择器，选择你需要的流程
sf.ImportDF(df, label ='label') #导入数据集以及目标标签
#sf.ImportCrossMethod(CrossMethod)
sf.ImportLossFunction(score, direction = 'descend') #导入评价函数以及优化方向
sf.InitialNonTrainableFeatures(['id','date', 'label']) #初始化不能用的特征
sf.InitialFeatures(feature_columns) #初始化其实特征组合
sf.GenerateCol() #生成特征库 （具体该函数变量请参考根目录下的readme）
sf.SetSample(1, samplemode = 1) #初始化抽样比例和随机过程
sf.SetTimeLimit(240) #设置算法运行最长时间，以分钟为单位
sf.clf = lgb.LGBMClassifier(random_state=10, num_leaves =15, n_estimators=200, max_depth=5, learning_rate = 0.1, n_jobs=-1) #设定模型
sf.SetLogFile('record.log') #初始化日志文件
sf.run(validation) #输入检验函数并开始运行