数据竞赛房租预测——特征工程+模型选择

最新推荐文章于 2022-11-24 21:48:45 发布

humashanshao

最新推荐文章于 2022-11-24 21:48:45 发布

阅读量466

点赞数

分类专栏：数据挖掘

本文链接：https://blog.csdn.net/sinat_38075329/article/details/103951034

版权

该博客主要探讨了数据竞赛中房租预测问题的解决流程，包括数据处理阶段的异常值处理和特征合并，接着通过计算统计特征和使用groupby及聚类方法进一步增强特征。最后，作者讨论了模型选择的重要性和策略。

摘要由CSDN通过智能技术生成

数据处理

def preprocessingData(data):
    # 填充缺失值
    data['rentType'][data['rentType'] == '--'] = '未知方式'
    
    # 转换object类型数据
    columns = ['rentType','communityName','houseType', 'houseFloor', 'houseToward', 'houseDecoration',  'region', 'plate']
    
    for feature in columns:
        data[feature] = LabelEncoder().fit_transform(data[feature])

    # 将buildYear列转换为整型数据
    buildYearmean = pd.DataFrame(data[data['buildYear'] != '暂无信息']['buildYear'].mode())
    data.loc[data[data['buildYear'] == '暂无信息'].index, 'buildYear'] = buildYearmean.iloc[0, 0]
    data['buildYear'] = data['buildYear'].astype('int')

    # 处理pv和uv的空值
    data['pv'].fillna(data['pv'].mean(), inplace=True)
    data['uv'].fillna(data['uv'].mean(), inplace=True)
    data['pv'] = data['pv'].astype('int')
    data['uv'] = data['uv'].astype('int')

    # 分割交易时间
    def month(x):
        month = int(x.split('/')[1])
        return month
    def day(x):
        day = int(x.split('/')[2])
        return day
    data['month'] = data['tradeTime'].apply(lambda x: month(x))
    data['day'] = data['tradeTime'].apply(lambda x: day(x))
    
    # 去掉部分特征
    data.drop('city', axis=1, inplace=True)
    data.drop('tradeTime', axis=1, inplace=True)
    data.drop('ID', axis=1, inplace=True)
    return data

data_train = preprocessingData(data_train)
data_test=preprocessingData(data_test)
print(data_train.head(2))
print(data_test.head(2))

异常值处理

# 异常值处理
def IF_drop(train):
    IForest = IsolationForest(contamination=0.01)
    IForest.fit(train["tradeMoney"].values.reshape(-1,1))
    y_pred = IForest.predict(train["tradeMoney"].values.reshape(-1,1))
    drop_index = train.loc[y_pred==-1].index
    print(drop_index)
    train.drop(drop_index,inplace=True)
    return train

data_train=IF_drop(data_train)

# 丢弃部分异常值
data_train = data_train[data_train.area <= 200]
data_train = data_train[(data_train.tradeMoney <=16000) & (data_train.tradeMoney >=700)]
data_train.drop(data_train[(data_train['totalFloor'] == 0)].index, inplace=True)

# 针对每一个region的数据，对area和tradeMoney两个维度进行深度清洗。 采用主观+数据可视化的方式。
def cleanData(data):
    data.drop(data[(data['region']=='RG00001') & (data['tradeMoney']<1000)&(data['area']>50)].index,inplace=True)
    data.drop(data[(data['region']=='RG00001') & (data['tradeMoney']>25000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00001') & (data['area']>250)&(data['tradeMoney']<20000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00001') & (data['area']>400)&(data['tradeMoney']>50000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00001') & (data['area']>100)&(data['tradeMoney']<2000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00002') & (data['area']<100)&(data['tradeMoney']>60000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00003') & (data['area']<300)&(data['tradeMoney']>30000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00003') & (data['tradeMoney']<500)&(data['area']<50)].index,inplace=True)
    data.drop(data[(data['region']=='RG00003') & (data['tradeMoney']<1500)&(data['area']>100)].index,inplace=True)
    data.drop(data[(data['region']=='RG00003') & (data['tradeMoney']<2000)&(data['area']>300)].index,inplace=True)
    data.drop(data[(data['region']=='RG00003') & (data['tradeMoney']>5000)&(data['area']<20)].index,inplace=True)
    data.drop(data[(data['region']=='RG00003') & (data['area']>600)&(data['tradeMoney']>40000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00004') & (data['tradeMoney']<1000)&(data['area']>80)].index,inplace=True)
    data.drop(data[(data['region']=='RG00006') & (data['tradeMoney']<200)].index,inplace=True)
    data.drop(data[(data['region']=='RG00005') & (data['tradeMoney']<2000)&(data['area']>180)].index,inplace=True)
    data.drop(data[(data['region']=='RG00005') & (data['tradeMoney']>50000)&(data['area']<200)].index,inplace=True)
    data.drop(data[(data['region']=='RG00006') & (data['area']>200)&(data['tradeMoney']<2000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00007') & (data['area']>100)&(data['tradeMoney']<2500)].index,inplace=True)
    data.drop(data[(data['region']=='RG00010') & (data['area']>200)&(data['tradeMoney']>25000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00010') & (data['area']>400)&(data['tradeMoney']<15000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00010') & (data['tradeMoney']<3000)&(data['area']>200)].index,inplace=True)
    data.drop(data[(data['region']=='RG00010') & (data['tradeMoney']>7000)&(data['area']<75)].index,inplace=True)
    data.drop(data[(data['region']=='RG00010') & (data['tradeMoney']>12500)&(data['area']<100)].index,inplace=True)
    data.drop(data[(data['region']=='RG00004') & (data['area']>400)&(data[&#