零基础入门数据挖掘：Task3 特征工程

特征工程就是把数据和预测建模之间通过这个数据的特点来构造一个特征，将他们联系起来。这之中也包括分析匿名数据的特征。

首先导入库和数据

#各种科学计数库可视化库
import pandas as pd
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
from operator import itemgetter

%matplotlib inline

#导入数据
path = './datalab/231784/'
Train_data = pd.read_csv(path+'used_car_train_20200313.csv', sep=' ')
Test_data = pd.read_csv(path+'used_car_testA_20200313.csv', sep=' ')
print(Train_data.shape)
print(Test_data.shape)

(150000, 31) 一万五千行，每组31列（多一列编号，没有价值）
(50000, 30)五千行 30列
看一下数据情况

Train_data.head()
Train_data.columns
Test_data.columns

Index([‘SaleID’, ‘name’, ‘regDate’, ‘model’, ‘brand’, ‘bodyType’, ‘fuelType’,
‘gearbox’, ‘power’, ‘kilometer’, ‘notRepairedDamage’, ‘regionCode’,
‘seller’, ‘offerType’, ‘creatDate’, ‘price’, ‘v_0’, ‘v_1’, ‘v_2’, ‘v_3’,
‘v_4’, ‘v_5’, ‘v_6’, ‘v_7’, ‘v_8’, ‘v_9’, ‘v_10’, ‘v_11’, ‘v_12’,
‘v_13’, ‘v_14’],
dtype=‘object’)
Index([‘SaleID’, ‘name’, ‘regDate’, ‘model’, ‘brand’, ‘bodyType’, ‘fuelType’,
‘gearbox’, ‘power’, ‘kilometer’, ‘notRepairedDamage’, ‘regionCode’,
‘seller’, ‘offerType’, ‘creatDate’, ‘v_0’, ‘v_1’, ‘v_2’, ‘v_3’, ‘v_4’,
‘v_5’, ‘v_6’, ‘v_7’, ‘v_8’, ‘v_9’, ‘v_10’, ‘v_11’, ‘v_12’, ‘v_13’,
‘v_14’],
dtype=‘object’)

下面借用一下大佬的代码

# 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 number is: {}".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

  Delete number is: 963

Now column number is: 149037
Description of data less than the lower bound is:
count 0.0
mean NaN
std NaN
min NaN
25% NaN
50% NaN
75% NaN
max NaN
Name: power, dtype: float64
Description of data larger than the upper bound is:
count 963.000000
mean 846.836968
std 1929.418081
min 376.000000
25% 400.000000
50% 436.000000
75% 514.000000
max 19312.000000
Name: power, dtype: float64
下面开始特征构造

Train_data['train']=1
Test_data['train']=0

data = pd.concat([Train_data, Test_data], ignore_index=True)
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

data['used_time'].isnull().sum()

15072

data['city'] = data['regionCode'].apply(lambda x : str(x)[:-3])
data = data

Train_gb = Train_data.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()

![在这里插入图片描述](https://img-blog.csdnimg.cn

#开始做变换
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'])))

data = pd.get_dummies(data, columns=['model', 'brand', 'bodyType', 'fuelType',
                                     'gearbox', 'notRepairedDamage', 'power_bin'])

print(data.shape)
data.columns

(199037, 370)

Index([‘SaleID’, ‘kilometer’, ‘name’, ‘offerType’, ‘power’, ‘price’, ‘seller’,
‘train’, ‘v_0’, ‘v_1’,
…
‘power_bin_20.0’, ‘power_bin_21.0’, ‘power_bin_22.0’, ‘power_bin_23.0’,
‘power_bin_24.0’, ‘power_bin_25.0’, ‘power_bin_26.0’, ‘power_bin_27.0’,
‘power_bin_28.0’, ‘power_bin_29.0’],
dtype=‘object’, length=370)

data.to_csv('data_for_lr.csv', index=0)

看一下结果

from mlxtend.plotting import plot_sequential_feature_selection as plot_sfs
import matplotlib.pyplot as plt
fig1 = plot_sfs(sfs.get_metric_dict(), kind='std_dev')
plt.grid()
plt.show()