Datawhale二手车

baseline
数据简要浏览
Train_data.head()

数据信息查看
Train_data.info()

数据统计信息浏览
Train_data.describe()

构建训练和测试样本

## 选择特征列
feature_cols = [col for col in numerical_cols if col not in ['SaleID','name','regDate','creatDate','price','model','brand','regionCode','seller']]
feature_cols = [col for col in feature_cols if 'Type' not in col]

## 提前特征列，标签列构造训练样本和测试样本
X_data = Train_data[feature_cols]
Y_data = Train_data['price']

X_test  = TestA_data[feature_cols]

print('X train shape:',X_data.shape)
print('X test shape:',X_test.shape)

缺省值用-1填补
X_data = X_data.fillna(-1)
X_test = X_test.fillna(-1)
模型训练与预测

## xgb-Model
xgr = xgb.XGBRegressor(n_estimators=120, learning_rate=0.1, gamma=0, subsample=0.8,\
        colsample_bytree=0.9, max_depth=7) #,objective ='reg:squarederror'

scores_train = []
scores = []

## 5折交叉验证方式
sk=StratifiedKFold(n_splits=5,shuffle=True,random_state=0)
for train_ind,val_ind in sk.split(X_data,Y_data):
    
    train_x=X_data.iloc[train_ind].values
    train_y=Y_data.iloc[train_ind]
    val_x=X_data.iloc[val_ind].values
    val_y=Y_data.iloc[val_ind]
    
    xgr.fit(train_x,train_y)
    pred_train_xgb=xgr.predict(train_x)
    pred_xgb=xgr.predict(val_x)
    
    score_train = mean_absolute_error(train_y,pred_train_xgb)
    scores_train.append(score_train)
    score = mean_absolute_error(val_y,pred_xgb)
    scores.append(score)

print('Train mae:',np.mean(score_train))
print('Val mae',np.mean(scores))

定义xgb和lgb模型函数

def build_model_xgb(x_train,y_train):
    model = xgb.XGBRegressor(n_estimators=150, learning_rate=0.1, gamma=0, subsample=0.8,\
        colsample_bytree=0.9, max_depth=7) #, objective ='reg:squarederror'
    model.fit(x_train, y_train)
    return model

def build_model_lgb(x_train,y_train):
    estimator = lgb.LGBMRegressor(num_leaves=127,n_estimators = 150)
    param_grid = {
        'learning_rate': [0.01, 0.05, 0.1, 0.2],
    }
    gbm = GridSearchCV(estimator, param_grid)
    gbm.fit(x_train, y_train)
    return gbm

切分数据集（Train,Val）进行模型训练，评价和预测

## Split data with val
x_train,x_val,y_train,y_val = train_test_split(X_data,Y_data,test_size=0.3)

print('Train lgb...')
model_lgb = build_model_lgb(x_train,y_train)
val_lgb = model_lgb.predict(x_val)
MAE_lgb = mean_absolute_error(y_val,val_lgb)
print('MAE of val with lgb:',MAE_lgb)

print('Predict lgb...')
model_lgb_pre = build_model_lgb(X_data,Y_data)
subA_lgb = model_lgb_pre.predict(X_test)
print('Sta of Predict lgb:')
Sta_inf(subA_lgb)

print('Train xgb...')
model_xgb = build_model_xgb(x_train,y_train)
val_xgb = model_xgb.predict(x_val)
MAE_xgb = mean_absolute_error(y_val,val_xgb)
print('MAE of val with xgb:',MAE_xgb)

print('Predict xgb...')
model_xgb_pre = build_model_xgb(X_data,Y_data)
subA_xgb = model_xgb_pre.predict(X_test)
print('Sta of Predict xgb:')
Sta_inf(subA_xgb)

进行两模型的结果加权融合

## 这里我们采取了简单的加权融合的方式
val_Weighted = (1-MAE_lgb/(MAE_xgb+MAE_lgb))*val_lgb+(1-MAE_xgb/(MAE_xgb+MAE_lgb))*val_xgb
val_Weighted[val_Weighted<0]=10 # 由于我们发现预测的最小值有负数，而真实情况下，price为负是不存在的，由此我们进行对应的后修正
print('MAE of val with Weighted ensemble:',mean_absolute_error(y_val,val_Weighted))

sub_Weighted = (1-MAE_lgb/(MAE_xgb+MAE_lgb))*subA_lgb+(1-MAE_xgb/(MAE_xgb+MAE_lgb))*subA_xgb

## 查看预测值的统计进行
plt.hist(Y_data)
plt.show()
plt.close()

输出结果

sub = pd.DataFrame()
sub['SaleID'] = TestA_data.SaleID
sub['price'] = sub_Weighted
sub.to_csv('/home/tianchi/myspace/sub_Weighted.csv',index=False)