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 = './data/'
## 1) 载入训练集和测试集；
train = pd.read_csv(path+'train.csv', sep=' ')
test = pd.read_csv(path+'testA.csv', sep=' ')
print(train.shape)
print(test.shape)

train.head()

train.columns

# 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

# 我们可以删掉一些异常数据，以 power 为例。  
# 这里删不删同学可以自行判断
# 但是要注意 test 的数据不能删 = = 不能掩耳盗铃是不是

train = outliers_proc(train, '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

# 训练集和测试集放在一起，方便构造特征
train['train']=1
test['train']=0
data = 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')


# 数据分桶 以 power 为例
# 这时候我们的缺失值也进桶了，
# 为什么要做数据分桶呢，原因有很多，= =
# 1. 离散后稀疏向量内积乘法运算速度更快，计算结果也方便存储，容易扩展；
# 2. 离散后的特征对异常值更具鲁棒性，如 age>30 为 1 否则为 0，对于年龄为 200 的也不会对模型造成很大的干扰；
# 3. LR 属于广义线性模型，表达能力有限，经过离散化后，每个变量有单独的权重，这相当于引入了非线性，能够提升模型的表达能力，加大拟合；
# 4. 离散后特征可以进行特征交叉，提升表达能力，由 M+N 个变量编程 M*N 个变量，进一步引入非线形，提升了表达能力；
# 5. 特征离散后模型更稳定，如用户年龄区间，不会因为用户年龄长了一岁就变化

# 当然还有很多原因，LightGBM 在改进 XGBoost 时就增加了数据分桶，增强了模型的泛化性

bin = [i*10 for i in range(31)]
data['power_bin'] = pd.cut(data['power'], bin, labels=False)
data[['power_bin', 'power']].head()

# 利用好了，就可以删掉原始数据了
data = data.drop(['creatDate', 'regDate', 'regionCode'], axis=1)

print(data.shape)
data.columns

# 目前的数据其实已经可以给树模型使用了，所以我们导出一下
data.to_csv('data_for_tree.csv', index=0)

# 我们可以再构造一份特征给 LR NN 之类的模型用
# 之所以分开构造是因为，不同模型对数据集的要求不同
# 我们看下数据分布：
data['power'].plot.hist()

# 我们刚刚已经对 train 进行异常值处理了，但是现在还有这么奇怪的分布是因为 test 中的 power 异常值，
# 所以我们其实刚刚 train 中的 power 异常值不删为好，可以用长尾分布截断来代替
train['power'].plot.hist()

# 我们对其取 log，在做归一化
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()

# km 的比较正常，应该是已经做过分桶了
data['kilometer'].plot.hist()

# 所以我们可以直接做归一化
data['kilometer'] = ((data['kilometer'] - np.min(data['kilometer'])) / 
                        (np.max(data['kilometer']) - np.min(data['kilometer'])))
data['kilometer'].plot.hist()

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

print(data.shape)
data.columns

(199037, 370)
Index(['SaleID', 'name', 'power', 'kilometer', 'seller', 'offerType', 'price',
,       'v_0', 'v_1', 'v_2',
,       ...
,       '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)

# 这份数据可以给 LR 用
data.to_csv('data_for_lr.csv', index=0)

# 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'))


0.5728285196051496

-0.4082569701616764

0.058156610025581514

0.3834909576057687

0.259066833880992

0.38691042393409447

# 当然也可以直接看图
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)

!pip install mlxtend


# k_feature 太大会很难跑，没服务器，所以提前 interrupt 了
from mlxtend.feature_selection import SequentialFeatureSelector as SFS
from sklearn.linear_model import LinearRegression
sfs = SFS(LinearRegression(),
           k_features=10,
           forward=True,
           floating=False,
           scoring = 'r2',
           cv = 0)
x = data.drop(['price'], axis=1)
numerical_cols = x.select_dtypes(exclude = 'object').columns
x = x[numerical_cols]
x = x.fillna(0)
y = data['price'].fillna(0)
sfs.fit(x, y)
sfs.k_feature_names_ 

('kilometer',
, 'v_0',
, 'v_3',
, 'v_7',
, 'train',
, 'used_time',
, 'brand_price_average',
, 'brand_price_std',
, 'model_167.0',
, 'gearbox_1.0')

# 画出来，可以看到边际效益
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()

import pandas as pd
import numpy as np
import warnings
warnings.filterwarnings('ignore')

def reduce_mem_usage(df):
    """ iterate through all the columns of a dataframe and modify the data type
        to reduce memory usage.        
    """
    start_mem = df.memory_usage().sum() 
    print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))
    
    for col in df.columns:
        col_type = df[col].dtype
        
        if col_type != object:
            c_min = df[col].min()
            c_max = df[col].max()
            if str(col_type)[:3] == 'int':
                if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:
                    df[col] = df[col].astype(np.int8)
                elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:
                    df[col] = df[col].astype(np.int16)
                elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:
                    df[col] = df[col].astype(np.int32)
                elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:
                    df[col] = df[col].astype(np.int64)  
            else:
                if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:
                    df[col] = df[col].astype(np.float16)
                elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:
                    df[col] = df[col].astype(np.float32)
                else:
                    df[col] = df[col].astype(np.float64)
        else:
            df[col] = df[col].astype('category')

    end_mem = df.memory_usage().sum() 
    print('Memory usage after optimization is: {:.2f} MB'.format(end_mem))
    print('Decreased by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))
    return df

sample_feature = reduce_mem_usage(pd.read_csv('data_for_tree.csv'))

Memory usage of dataframe is 62099672.00 MB

Memory usage after optimization is: 16520303.00 MB

Decreased by 73.4%

continuous_feature_names = [x for x in sample_feature.columns if x not in ['price','brand','model','brand']]

sample_feature = sample_feature.dropna().replace('-', 0).reset_index(drop=True)
sample_feature['notRepairedDamage'] = sample_feature['notRepairedDamage'].astype(np.float32)
train = sample_feature[continuous_feature_names + ['price']]

train_X = train[continuous_feature_names]
train_y = train['price']

from sklearn.linear_model import LinearRegression

model = LinearRegression(normalize=True)

model = model.fit(train_X, train_y)

'intercept:'+ str(model.intercept_)

查看训练的线性回归模型的截距（intercept）与权重(coef)

sorted(dict(zip(continuous_feature_names, model.coef_)).items(), key=lambda x:x[1], reverse=True)

from matplotlib import pyplot as plt

subsample_index = np.random.randint(low=0, high=len(train_y), size=50)

plt.scatter(train_X['v_9'][subsample_index], train_y[subsample_index], color='black')
plt.scatter(train_X['v_9'][subsample_index], model.predict(train_X.loc[subsample_index]), color='blue')
plt.xlabel('v_9')
plt.ylabel('price')
plt.legend(['True Price','Predicted Price'],loc='upper right')
print('The predicted price is obvious different from true price')
plt.show()

import seaborn as sns
print('It is clear to see the price shows a typical exponential distribution')
plt.figure(figsize=(15,5))
plt.subplot(1,2,1)
sns.distplot(train_y)
plt.subplot(1,2,2)
sns.distplot(train_y[train_y < np.quantile(train_y, 0.9)])

train_y_ln = np.log(train_y + 1)

import seaborn as sns
print('The transformed price seems like normal distribution')
plt.figure(figsize=(15,5))
plt.subplot(1,2,1)
sns.distplot(train_y_ln)
plt.subplot(1,2,2)
sns.distplot(train_y_ln[train_y_ln < np.quantile(train_y_ln, 0.9)])


model = model.fit(train_X, train_y_ln)

print('intercept:'+ str(model.intercept_))
sorted(dict(zip(continuous_feature_names, model.coef_)).items(), key=lambda x:x[1], reverse=True)

plt.scatter(train_X['v_9'][subsample_index], train_y[subsample_index], color='black')
plt.scatter(train_X['v_9'][subsample_index], np.exp(model.predict(train_X.loc[subsample_index])), color='blue')
plt.xlabel('v_9')
plt.ylabel('price')
plt.legend(['True Price','Predicted Price'],loc='upper right')
print('The predicted price seems normal after np.log transforming')
plt.show()

from sklearn.model_selection import cross_val_score
from sklearn.metrics import mean_absolute_error,  make_scorer

def log_transfer(func):
    def wrapper(y, yhat):
        result = func(np.log(y), np.nan_to_num(np.log(yhat)))
        return result
    return wrapper

scores = cross_val_score(model, X=train_X, y=train_y, verbose=1, cv = 5, scoring=make_scorer(log_transfer(mean_absolute_error)))

使用线性回归模型，对未处理标签的特征数据进行五折交叉验证
print('AVG:', np.mean(scores))
使用线性回归模型，对处理过标签的特征数据进行五折交叉验证
scores = cross_val_score(model, X=train_X, y=train_y_ln, verbose=1, cv = 5, scoring=make_scorer(mean_absolute_error))

print('AVG:', np.mean(scores))
AVG: 0.1932530155796405

scores = pd.DataFrame(scores.reshape(1,-1))
scores.columns = ['cv' + str(x) for x in range(1, 6)]
scores.index = ['MAE']
scores

import datetime
sample_feature = sample_feature.reset_index(drop=True)
split_point = len(sample_feature) // 5 * 4
train = sample_feature.loc[:split_point].dropna()
val = sample_feature.loc[split_point:].dropna()

train_X = train[continuous_feature_names]
train_y_ln = np.log(train['price'] + 1)
val_X = val[continuous_feature_names]
val_y_ln = np.log(val['price'] + 1)
model = model.fit(train_X, train_y_ln)
mean_absolute_error(val_y_ln, model.predict(val_X))

0.19577667149549233

from sklearn.model_selection import learning_curve, validation_curve

? learning_curve 查看功能

def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,n_jobs=1, train_size=np.linspace(.1, 1.0, 5 )):  
    plt.figure()  
    plt.title(title)  
    if ylim is not None:  
        plt.ylim(*ylim)  
    plt.xlabel('Training example')  
    plt.ylabel('score')  
    train_sizes, train_scores, test_scores = learning_curve(estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_size, scoring = make_scorer(mean_absolute_error))  
    train_scores_mean = np.mean(train_scores, axis=1)  
    train_scores_std = np.std(train_scores, axis=1)  
    test_scores_mean = np.mean(test_scores, axis=1)  
    test_scores_std = np.std(test_scores, axis=1)  
    plt.grid()#区域  
    plt.fill_between(train_sizes, train_scores_mean - train_scores_std,  
                     train_scores_mean + train_scores_std, alpha=0.1,  
                     color="r")  
    plt.fill_between(train_sizes, test_scores_mean - test_scores_std,  
                     test_scores_mean + test_scores_std, alpha=0.1,  
                     color="g")  
    plt.plot(train_sizes, train_scores_mean, 'o-', color='r',  
             label="Training score")  
    plt.plot(train_sizes, test_scores_mean,'o-',color="g",  
             label="Cross-validation score")  
    plt.legend(loc="best")  
    return plt  

plot_learning_curve(LinearRegression(), 'Liner_model', train_X[:1000], train_y_ln[:1000], ylim=(0.0, 0.5), cv=5, n_jobs=1)