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
path = '/Users/dingyunfei/Downloads/比赛/'
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)
(50000, 30)
Train_data.head()
|
SaleID |
name |
regDate |
model |
brand |
bodyType |
fuelType |
gearbox |
power |
kilometer |
... |
v_5 |
v_6 |
v_7 |
v_8 |
v_9 |
v_10 |
v_11 |
v_12 |
v_13 |
v_14 |
0 |
0 |
736 |
20040402 |
30.0 |
6 |
1.0 |
0.0 |
0.0 |
60 |
12.5 |
... |
0.235676 |
0.101988 |
0.129549 |
0.022816 |
0.097462 |
-2.881803 |
2.804097 |
-2.420821 |
0.795292 |
0.914762 |
1 |
1 |
2262 |
20030301 |
40.0 |
1 |
2.0 |
0.0 |
0.0 |
0 |
15.0 |
... |
0.264777 |
0.121004 |
0.135731 |
0.026597 |
0.020582 |
-4.900482 |
2.096338 |
-1.030483 |
-1.722674 |
0.245522 |
2 |
2 |
14874 |
20040403 |
115.0 |
15 |
1.0 |
0.0 |
0.0 |
163 |
12.5 |
... |
0.251410 |
0.114912 |
0.165147 |
0.062173 |
0.027075 |
-4.846749 |
1.803559 |
1.565330 |
-0.832687 |
-0.229963 |
3 |
3 |
71865 |
19960908 |
109.0 |
10 |
0.0 |
0.0 |
1.0 |
193 |
15.0 |
... |
0.274293 |
0.110300 |
0.121964 |
0.033395 |
0.000000 |
-4.509599 |
1.285940 |
-0.501868 |
-2.438353 |
-0.478699 |
4 |
4 |
111080 |
20120103 |
110.0 |
5 |
1.0 |
0.0 |
0.0 |
68 |
5.0 |
... |
0.228036 |
0.073205 |
0.091880 |
0.078819 |
0.121534 |
-1.896240 |
0.910783 |
0.931110 |
2.834518 |
1.923482 |
5 rows × 31 columns
Train_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')
Test_data.columns
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')
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
Train_data = outliers_proc(Train_data, 'power', scale=3)
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

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()
|
power_bin |
power |
0 |
5.0 |
60 |
1 |
NaN |
0 |
2 |
16.0 |
163 |
3 |
19.0 |
193 |
4 |
6.0 |
68 |
data = data.drop(['creatDate', 'regDate', 'regionCode'], axis=1)
print(data.shape)
data.columns
(199037, 39)
Index(['SaleID', 'bodyType', 'brand', 'fuelType', 'gearbox', 'kilometer',
'model', 'name', 'notRepairedDamage', 'offerType', 'power', 'price',
'seller', 'train', 'v_0', 'v_1', 'v_10', 'v_11', 'v_12', 'v_13', 'v_14',
'v_2', 'v_3', 'v_4', 'v_5', 'v_6', 'v_7', 'v_8', 'v_9', 'used_time',
'city', 'brand_amount', 'brand_price_max', 'brand_price_median',
'brand_price_min', 'brand_price_sum', 'brand_price_std',
'brand_price_average', 'power_bin'],
dtype='object')
data.to_csv('data_for_tree.csv', index=0)
data['power'].plot.hist()

Train_data['power'].plot.hist()

from sklearn import preprocessing
min_max_scaler = preprocessing.MinMaxScaler()
data['power'] = np.log(data['power'] + 1)
data['power'] = ((data['power'] - np.min(data['power'])) / (np.max(data['power']) - np.min(data['power'])))
data['power'].plot.hist()

data['kilometer'].plot.hist()

data['kilometer'] = ((data['kilometer'] - np.min(data['kilometer'])) /
(np.max(data['kilometer']) - np.min(data['kilometer'])))
data['kilometer'].plot.hist()

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)
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'))
0.5728285196051496
-0.4082569701616764
0.058156610025581514
0.3834909576057687
0.259066833880992
0.38691042393409447
data_numeric = data[['power', 'kilometer', 'brand_amount', 'brand_price_average',
'brand_price_max', 'brand_price_median']]
correlation = data_numeric.corr()
f , ax = plt.subplots(figsize = (7, 7))
plt.title('Correlation of Numeric Features with Price',y=1,size=16)
sns.heatmap(correlation,square = True, vmax=0.8)
