数据竞赛模拟_房租预测（2数据清洗）

最新推荐文章于 2021-10-22 13:10:49 发布

一-叶知秋

最新推荐文章于 2021-10-22 13:10:49 发布

阅读量207

点赞数

分类专栏：编程

本文链接：https://blog.csdn.net/weixin_44370010/article/details/103909546

版权

编程专栏收录该内容

23 篇文章 0 订阅

订阅专栏

任务2 数据清洗

1 缺失值处理

导入包

#coding:utf-8
#导入warnings包，利用过滤器来实现忽略警告语句。
import warnings
warnings.filterwarnings('ignore')

# GBDT
from sklearn.ensemble import GradientBoostingRegressor
# XGBoost
import xgboost as xgb
# LightGBM
import lightgbm as lgb

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import KFold
from sklearn.metrics import r2_score
from sklearn.preprocessing import LabelEncoder
import pickle
import multiprocessing
from sklearn.preprocessing import StandardScaler
ss = StandardScaler() 
from sklearn.model_selection import StratifiedKFold
from sklearn.linear_model import ElasticNet, Lasso,  BayesianRidge, LassoLarsIC,LinearRegression,LogisticRegression
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import RobustScaler
from sklearn.model_selection import train_test_split
from sklearn.ensemble import IsolationForest

导入数据

#载入数据
data_train = pd.read_csv('./data/train_data.csv')
data_train['Type'] = 'Train'
data_test = pd.read_csv('./data/test_a.csv')
data_test['Type'] = 'Test'
data_all = pd.concat([data_train, data_test], ignore_index=True)

缺失值处理方法
第一种：替换非统一格式，如“–”
第二种：使用LabelEncoder().fit_transform()函数拟合标签数据，将其标准化
第三种：用众数替换（pandas的mode()函数）
第四种：空值填充fillna()，可用平均值，中位数，还可以使用前/后向填充
第五种：处理年月日格式时间
第六种：去除无用特征

def preprocessingData(data):
    # 填充缺失值,这里的未知方式也算一种类型
    data['rentType'][data['rentType'] == '--'] = '未知方式'
    
    # 转换object类型数据   
    columns = ['rentType','communityName','houseType', 'houseFloor', 'houseToward', 'houseDecoration',  'region', 'plate']
    
    #fit_transform()的作用就是先拟合数据，然后转化它将其转化为标准形式
    for feature in columns:
        data[feature] = LabelEncoder().fit_transform(data[feature])

    # 将buildYear列转换为整型数据，mode()函数提取众数
    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')  #转换为int类型

    # 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):
        #split() 通过指定分隔符对字符串进行切片，如果参数 num 有指定值，则分隔 num+1 个子字符串
        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))  #apply间接调用函数
    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)

部分结果：

data_train.loc[:, ['rentType', 'buildYear', 'pv', 'month']]

在这里插入图片描述

2 异常值处理

异常检测算法
孤立随机森林方法，见博客：异常检测算法

# clean data
def IF_drop(train):
    #异常点检测，孤立森林算法
    #contamination是用户设置样本中异常点的比例
    IForest = IsolationForest(contamination=0.01) 
    #fit(X)： Fit estimator.（无监督）
    IForest.fit(train["tradeMoney"].values.reshape(-1,1))  # reshape(-1,1)转换为1列，reshape(1,-1)是1行
    #predict(X)：返回值：+1 表示正常样本， -1表示异常样本。
    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)

结果：

Int64Index([   62,    69,   128,   131,   146,   228,   246,   261,   266,
              277,
            ...
            39228, 39319, 39347, 39352, 39434, 39563, 41080, 41083, 41233,
            41241],
           dtype='int64', length=450)

丢弃部分异常值

def dropData(train):
    # 丢弃部分异常值
    train = train[train.area <= 200]
    train = train[(train.tradeMoney <=16000) & (train.tradeMoney >=700)]
    train.drop(train[(train['totalFloor'] == 0)].index, inplace=True)
    return train  
#数据集异常值处理
data_train = dropData(data_train)

去除异常值后的分布图

# 处理异常值后再次查看面积和租金分布图
plt.figure(figsize=(15,5))
sns.boxplot(data_train.area)
plt.show()
plt.figure(figsize=(15,5))
sns.boxplot(data_train.tradeMoney),
plt.show()

结果：
在这里插入图片描述

3 深度清洗

通过region的每个值，对数据进行进一步清洗
在这里直接运行源码会报错，因为在缺失值处理中，将rentType和region标准化了（索引不到RG00001），可以将标准化过程放在后面。

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['tradeMoney']>20000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00008') & (data['tradeMoney']<2000)&(data['area']>80)].index,inplace=True)
    data.drop(data[(data['region']=='RG00009') & (data['tradeMoney']>40000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00009') & (data['area']>300)].index,inplace=True)
    data.drop(data[(data['region']=='RG00009') & (data['area']>100)&(data['tradeMoney']<2000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00011') & (data['tradeMoney']<10000)&(data['area']>390)].index,inplace=True)
    data.drop(data[(data['region']=='RG00012') & (data['area']>120)&(data['tradeMoney']<5000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00013') & (data['area']<100)&(data['tradeMoney']>40000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00013') & (data['area']>400)&(data['tradeMoney']>50000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00013') & (data['area']>80)&(data['tradeMoney']<2000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00014') & (data['area']>300)&(data['tradeMoney']>40000)].index,inplace=True)
    data.drop(data[(data['region']=='RG00014') & (data['tradeMoney']<1300)&(data['area']>80)].index,inplace=True)
    data.drop(data[(data['region']=='RG00014') & (data['tradeMoney']<8000)&(data['area']>200)].index,inplace=True)
    data.drop(data[(data['region']=='RG00014') & (data['tradeMoney']<1000)&(data['area']>20)].index,inplace=True)
    data.drop(data[(data['region']=='RG00014') & (data['tradeMoney']>25000)&(data['area']>200)].index,inplace=True)
    data.drop(data[(data['region']=='RG00014') & (data['tradeMoney']<20000)&(data['area']>250)].index,inplace=True)
    data.drop(data[(data['region']=='RG00005') & (data['tradeMoney']>30000)&(data['area']<100)].index,inplace=True)
    data.drop(data[(data['region']=='RG00005') & (data['tradeMoney']<50000)&(data['area']>600)].index,inplace=True)
    data.drop(data[(data['region']=='RG00005') & (data['tradeMoney']>50000)&(data['area']>350)].index,inplace=True)
    data.drop(data[(data['region']=='RG00006') & (data['tradeMoney']>4000)&(data['area']<100)].index,inplace=True)
    data.drop(data[(data['region']=='RG00006') & (data['tradeMoney']<600)&(data['area']>100)].index,inplace=True)
    data.drop(data[(data['region']=='RG00006') & (data['area']>165)].index,inplace=True)
    data.drop(data[(data['region']=='RG00012') & (data['tradeMoney']<800)&(data['area']<30)].index,inplace=True)
    data.drop(data[(data['region']=='RG00007') & (data['tradeMoney']<1100)&(data['area']>50)].index,inplace=True)
    data.drop(data[(data['region']=='RG00004') & (data['tradeMoney']>8000)&(data['area']<80)].index,inplace=True)
    data.loc[(data['region']=='RG00002')&(data['area']>50)&(data['rentType']=='合租'),'rentType']='整租'
    data.loc[(data['region']=='RG00014')&(data['rentType']=='合租')&(data['area']>60),'rentType']='整租'
    data.drop(data[(data['region']=='RG00008')&(data['tradeMoney']>15000)&(data['area']<110)].index,inplace=True)
    data.drop(data[(data['region']=='RG00008')&(data['tradeMoney']>20000)&(data['area']>110)].index,inplace=True)
    data.drop(data[(data['region']=='RG00008')&(data['tradeMoney']<1500)&(data['area']<50)].index,inplace=True)
    data.drop(data[(data['region']=='RG00008')&(data['rentType']=='合租')&(data['area']>50)].index,inplace=True)
    data.drop(data[(data['region']=='RG00015') ].index,inplace=True)
    data.reset_index(drop=True, inplace=True)
    return data

data_train = cleanData(data_train)

# 转换object类型数据   
columns = ['region', 'rentType', 'communityName','houseType', 'houseFloor', 'houseToward', 'houseDecoration', 'plate']
#fit_transform()的作用就是先拟合数据，然后转化它将其转化为标准形式
for feature in columns:
    data_train[feature] = LabelEncoder().fit_transform(data_train[feature])

data_train