打卡

删除异常值

import pandas as pd
import numpy as npimport matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
from operator import itemgetter
train=pd.read_csv('train.csv', sep=' ')
test=pd.read_csv('testA.csv',sep='')
print(train.shape)
print(test.shape)
# 这里我包装了一个异常值处理的代码，可以随便调用。
def outliers_proc(data, col_name, scale=3):    """    用于清洗异常值，默认用 box_plot（scale=3）进行清洗    :param data: 接收 pandas 数据格式    :param col_name: pandas 列名    :param scale: 尺度    :return:    """    
def box_plot_outliers(data_ser, box_scale):        """        利用箱线图去除异常值        :param data_ser: 接收 pandas.Series 数据格式        :param box_scale: 箱线图尺度，        :return:        """        
iqr = box_scale * (data_ser.quantile(0.75) - data_ser.quantile(0.25))        
val_low = data_ser.quantile(0.25) - iqr        val_up = data_ser.quantile(0.75) + iqr        rule_low = (data_ser < val_low)        rule_up = (data_ser > val_up)        
return (rule_low, rule_up), (val_low,val_up)    
data_n = data.copy()    
data_series = data_n[col_name]    
rule, value = box_plot_outliers(data_series, box_scale=scale)    
index = np.arange(data_series.shape[0])[rule[0] | rule[1]]    
print("Delete numberis:{}".format(len(index)))    
data_n = data_n.drop(index)    data_n.reset_index(drop=True, inplace=True)    print("Now column number is: {}".format(data_n.shape[0]))    
index_low = np.arange(data_series.shape[0])[rule[0]]    
outliers = data_series.iloc[index_low]    print("Description of data less than the lower bound is:")    print(pd.Series(outliers).describe())    index_up = np.arange(data_series.shape[0])[rule[1]]    
outliers = data_series.iloc[index_up]    print("Description of data larger than the upper bound is:")    print(pd.Series(outliers).describe())        fig, ax = plt.subplots(1, 2, figsize=(10, 7))    
sns.boxplot(y=data[col_name], data=data, palette="Set1", ax=ax[0])    sns.boxplot(y=data_n[col_name], data=data_n, palette="Set1", ax=ax[1])    
return data_n
train = outliers_proc(train, 'power', scale=3)

特征构造

# 训练集和测试集放在一起，方便构造特征
train['train']=1test['train']=0data = pd.concat([train, test], ignore_index=True, sort=False)# 使用时间：data['creatDate'] - data['regDate']，反应汽车使用时间，一般来说价格与使用时间成反比# 不过要注意，数据里有时间出错的格式，所以我们需要 errors='coerce'
data['used_time'=(pd.to_datetime(data['creatDate'], format='%Y%m%d', errors='coerce') -                             pd.to_datetime(data['regDate'],format='%Y%m%d', errors='coerce')).dt.days
# 看一下空数据，有 15k 个样本的时间是有问题的，我们可以选择删除，也可以选择放着。
# 但是这里不建议删除，因为删除缺失数据占总样本量过大，7.5%
# 我们可以先放着，因为如果我们 XGBoost 之类的决策树，其本身就能处理缺失值，所以可以不用管；
data['used_time'].isnull().sum()
# 从邮编中提取城市信息，因为是德国的数据，所以参考德国的邮编，相当于加入了先验知识
data['city']=data['regionCode'].apply(lambda x : str(x)[:-3])
# 计算某品牌的销售统计量，同学们还可以计算其他特征的统计量
# 这里要以 train 的数据计算统计量train_gb = train.groupby("brand")
all_info={}for kind, kind_data in train_gb:    
info = {}   
kind_data = kind_data[kind_data['price'] > 0]    
info['brand_amount'] = len(kind_data)    info['brand_price_max']=kind_data.price.max()    
info['brand_price_median']=kind_data.price.median()    
info['brand_price_min']=kind_data.price.min()    
info['brand_price_sum']=kind_data.price.sum()    
info['brand_price_std']=kind_data.price.std()    
info['brand_price_average']=round(kind_data.price.sum() / (len(kind_data) + 1), 2)    all_info[kind] = info
brand_fe=pd.DataFrame(all_info).T.reset_index().rename(columns={"index": "brand"})
data = data.merge(brand_fe, how='left', on='brand')
bin = [i*10 for i in range(31)]
data['power_bin'] = pd.cut(data['power'], bin, labels=False)data[['power_bin','power']].head()
# 除此之外 还有我们刚刚构造的统计量特征：
# 'brand_amount', 'brand_price_average', 'brand_price_max',# 'brand_price_median', 'brand_price_min', 'brand_price_std',# 'brand_price_sum'# 这里不再一一举例分析了，直接做变换，
def max_min(x):   
        return (x - np.min(x)) / (np.max(x) - np.min(x))
 data['brand_amount']=((data['brand_amount'] - np.min(data['brand_amount'])) /                         (np.max(data['brand_amount']) - np.min(data['brand_amount'])))
 data['brand_price_average'] = ((data['brand_price_average'] - np.min(data['brand_price_average'])) /                                (np.max(data['brand_price_average']) - np.min(data['brand_price_average'])))
data['brand_price_max'] = ((data['brand_price_max'] - np.min(data['brand_price_max'])) /                            (np.max(data['brand_price_max']) - np.min(data['brand_price_max'])))
data['brand_price_median'] = ((data['brand_price_median'] - np.min(data['brand_price_median'])) /                              (np.max(data['brand_price_median']) - np.min(data['brand_price_median'])))
data['brand_price_min'] = ((data['brand_price_min'] - np.min(data['brand_price_min'])) /                            (np.max(data['brand_price_min']) - np.min(data['brand_price_min'])))
data['brand_price_std'] = ((data['brand_price_std'] - np.min(data['brand_price_std'])) /                            (np.max(data['brand_price_std']) - np.min(data['brand_price_std'])))
data['brand_price_sum'] = ((data['brand_price_sum'] - np.min(data['brand_price_sum'])) /                            (np.max(data['brand_price_sum']) - np.min(data['brand_price_sum'])))# 对类别特征进行
OneEncoderdata = pd.get_dummies(data, columns=['model', 'brand', 'bodyType', 'fuelType',                                     'gearbox', 'notRepairedDamage', 'power_bin'])print(data.shape)

特征筛选

# 相关性分析
print(data['power'].corr(data['price'], method='spearman'))print(data['kilometer'].corr(data['price'], method='spearman'))print(data['brand_amount'].corr(data['price'], method='spearman'))print(data['brand_price_average'].corr(data['price'], method='spearman'))print(data['brand_price_max'].corr(data['price'], method='spearman'))print(data['brand_price_median'].corr(data['price'], method='spearman'))