Day-2

最新推荐文章于 2024-07-15 19:47:57 发布

仅用于个人纪录

最新推荐文章于 2024-07-15 19:47:57 发布

阅读量97

点赞数

分类专栏： python datawhale

本文链接：https://blog.csdn.net/weixin_43444314/article/details/103897829

版权

python 同时被 2 个专栏收录

84 篇文章 1 订阅

订阅专栏

datawhale

7 篇文章 0 订阅

订阅专栏

缺失值分析

#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

#载入数据
data_train = pd.read_csv('./train_data.csv')#将数据通过pandas读取成为DataFrame类型的数据结构
data_train['Type'] = 'Train'
data_test = pd.read_csv('./test_a.csv')
data_test['Type'] = 'Test'
data_all = pd.concat([data_train, data_test], ignore_index=True)

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())#找出众数
    data.loc[data[data['buildYear'] == '暂无信息'].index, 'buildYear'] = buildYearmean.iloc[0, 0]#loc是按照索引的值来选取来选取，iloc就是按照索引的位置来进行选取，iloc不关心索引的具体值是多少，只关心位置是多少，所以使用iloc时方括号中只能使用数值。
    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)
print(data_train)

输出为

         area  rentType  houseType  houseFloor  ...  tradeMoney   Type  month  day
0       68.06         2         12           1  ...      2000.0  Train     11   28
1      125.55         2         28           0  ...      2000.0  Train     12   16
2      132.00         2         28           1  ...     16000.0  Train     12   22
3       57.00         2          4           0  ...      1600.0  Train     12   21
4      129.00         2         29           1  ...      2900.0  Train     11   18
...       ...       ...        ...         ...  ...         ...    ...    ...  ...
41435   10.00         0         39           2  ...      2190.0  Train      2    5
41436    7.10         0         24           0  ...      2090.0  Train      1   22
41437    9.20         0         39           2  ...      3190.0  Train      2    8
41438   14.10         0         39           1  ...      2460.0  Train      3   22
41439   33.50         2          4           0  ...      3000.0  Train     10   21

[41440 rows x 51 columns]
[Finished in 12.1s]

异常值处理

# clean data
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)

输出为

Int64Index([   62,    69,   128,   131,   246,   261,   266,   297,   308,
              313,
            ...
            39224, 39228, 39319, 39347, 39352, 39434, 39563, 41080, 41083,
            41233],
           dtype='int64', length=401)

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)

# 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)#绘制箱型图，注意箱型图的理解
plt.show()
plt.figure(figsize=(15,5))
sns.boxplot(data_train.tradeMoney),
plt.show()

在这里插入图片描述

这个是深度清洗


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)

仅用于个人纪录

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
Day-2

缺失值分析#coding:utf-8#导入warnings包，利用过滤器来实现忽略警告语句。import warningswarnings.filterwarnings('ignore')# GBDTfrom sklearn.ensemble import GradientBoostingRegressor# XGBoostimport xgboost as xgb# Ligh...
复制链接

扫一扫