二手车价格预测 | 构建AI模型并部署Web应用 ⛵

7,237 阅读11分钟

携手创作,共同成长!这是我参与「掘金日新计划 · 8 月更文挑战」的第N天,点击查看活动详情

一份来自『RESEARCH AND MARKETS』的二手车报告预计,从 2022 年到 2030 年,全球二手车市场将以 6.1% 的复合年增长率增长,到 2030 年达到 2.67 万亿美元。人工智能技术的广泛使用增加了车主和买家之间的透明度,提升了购买体验,极大地推动了二手车市场的增长。

基于机器学习对二手车交易价格进行预估,这一技术已经在二手车交易平台中广泛使用。在本篇内容中,ShowMeAI 会完整构建用于二手车价格预估的模型,并部署成web应用。

💡 数据分析处理&特征工程

本案例涉及的数据集可以在 kaggle汽车价格预测 获取,也可以在ShowMeAI的百度网盘地址直接下载。

🏆 实战数据集下载(百度网盘):公众号『ShowMeAI研究中心』回复『实战』,或者点击 这里 获取本文 [11] 构建AI模型并部署Web应用,预测二手车价格CarPrice 二手车价格预测数据集

ShowMeAI官方GitHubgithub.com/ShowMeAI-Hu…

① 数据探索

数据分析处理涉及的工具和技能,欢迎大家查阅ShowMeAI对应的教程和工具速查表,快学快用。

我们先加载数据并初步查看信息。

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import pickle
%matplotlib.inline

df=pd.read_csv('CarPrice_Assignment.csv')
df.head()

数据 Dataframe 的数据预览如下:

我们对属性字段做点分析,看看哪些字段与价格最相关,我们先计算相关性矩阵

df.corr()

再对相关性进行热力图可视化。

sns.set(rc={"figure.figsize":(20, 20)})
sns.heatmap(df.corr(), annot = True)

其中各字段和price的相关性如下图所示,我们可以看到其中有些字段和结果之间有非常强的相关性。

我们可以对数值型字段,分别和price目标字段进行绘图详细分析,如下:

for col in df.columns: 
    if df[col].dtypes != 'object':
        sns.lmplot(data = df, x = col, y = 'price')

可视化结果图如下:

我们把一些与价格相关性低(r<0.15)的字段删除掉:

df.drop(['car_ID'], axis = 1, inplace = True) 
to_drop = ['peakrpm', 'compressionratio', 'stroke', 'symboling']
df.drop(df[to_drop], axis = 1, inplace = True)

② 特征工程

特征工程涉及的方法技能,欢迎大家查阅ShowMeAI对应的教程文章,快学快用。

车名列包括品牌和型号,我们对其拆分并仅保留品牌:

df['CarName'] = df['CarName'].apply(lambda x: x.split()[0]) 

输出:

我们发现有一些车品牌的别称或者拼写错误,我们做一点数据清洗如下:

df['CarName'] = df['CarName'].str.lower()
df['CarName']=df['CarName'].replace({'vw':'volkswagen','vokswagen':'volkswagen','toyouta':'toyota','maxda':'mazda','porcshce':'porsche'})

再对不同车品牌的数量做绘图,如下:

sns.set(rc={'figure.figsize':(30,10)})
sns.countplot(data = df, x='CarName')

③ 特征编码&数据变换

下面我们要做进一步的特征工程:

  • 类别型特征

大部分机器学习模型并不能处理类别型数据,我们会手动对其进行编码操作。类别型特征的编码可以采用 序号编码 或者 独热向量编码(具体参见ShowMeAI文章 机器学习实战 | 机器学习特征工程最全解读),独热向量编码示意图如下:

  • 数值型特征

针对不同的模型,有不同的处理方式,比如幅度缩放和分布调整。

下面我们先将数据集的字段分为两类:类别型和数值型:

categorical = []
numerical = []
for col in df.columns:
   if df[col].dtypes == 'object':
      categorical.append(col)
   else:
      numerical.append(col)

下面我们使用pandas中的哑变量变换操作把所有标记为“categorical”的特征进行独热向量编码。

# 独热向量编码
x1 = pd.get_dummies(df[categorical], drop_first = False)
x2 = df[numerical]
X = pd.concat([x2,x1], axis = 1)
X.drop('price', axis = 1, inplace = True)

下面我们对数值型特征进行处理,首先我们看看标签字段price,我们先绘制一下它的分布,如下:

sns.histplot(data=df, x="price", kde=True) 

大家从图上可以看出这是一个有偏分布。我们对它做一个对数处理,以使其更接近正态分布。(另外一个考量是,如果我们以对数后的结果作为标签来建模学习,那还原回 price 的过程,会使用指数操作,这能保证我们得到的价格一定是正数) ,代码如下:

#修复偏态分布 
df["price_log"]=np.log(df["price"])
sns.histplot(data=df, x="price_log", kde=True)

校正过后的数据分布更接近正态分布了,做过这些基础处理之后,我们准备开始建模了。

💡 机器学习建模

① 数据集切分&数据变换

让我们拆分数据集为训练和测试集,并对其进行基本的数据变换操作:

#切分数据 
from sklearn.model_selection import train_test_split

y = df['price_log']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size= 0.333, random_state=1)
 
#特征工程-幅度缩放
from sklearn.preprocessing import StandardScaler
sc= StandardScaler()
X_train[:, :(len(x1.columns))]= sc.fit_transform(X_train[:, :(len(x1.columns))])
X_test[:, :(len(x1.columns))]= sc.transform(X_test[:, :(len(x1.columns))])

② 建模&调优

建模涉及的方法技能,欢迎大家查阅ShowMeAI对应的教程文章,快学快用。

我们这里的数据集并不大(样本数不多),基于模型复杂度和效果考虑,我们先测试 4 个模型,看看哪一个表现最好。

  • Lasso regression
  • Ridge regression
  • 随机森林回归器
  • XGBoost回归器

我们先从scikit-learn导入对应的模型,如下:

#回归模型 
from sklearn.linear_model import Lasso, Ridge
from sklearn.ensemble import RandomForestRegressor
import xgboost as xgb

③ 建模 pipeline

为了让整个建模过程更加紧凑简介,我们创建一个pipeline来训练和调优模型。 具体步骤为:

  • 使用随机超参数训练评估每个模型。
  • 使用网格搜索调优每个模型的超参数。
  • 用找到的最佳参数重新训练评估模型。

我们先从 scikit-learn 导入网格搜索:

from sklearn.model_selection import GridSearchCV

接着我们构建一个全面的评估指标函数,打印每个拟合模型的指标(R 平方、均方根误差和平均绝对误差等):

def metrics(model):
   res_r2 = []
   res_RMSE = []
   res_MSE = []
   model.fit(X_train, y_train)
   Y_pred = model.predict(X_test)   

   #计算R方
   r2 = round(r2_score(y_test, Y_pred),4)
   print( 'R2_Score: ', r2)
   res_r2.append(r2)   
   
   #计算RMSE
   rmse = round(mean_squared_error(np.exp(y_test),np.exp(Y_pred), squared=False), 2)
   print("RMSE: ",rmse)
   res_RMSE.append(rmse)   

   #计算MAE
   mse = round(mean_absolute_error(np.exp(y_test),np.exp(Y_pred)), 2)
   print("MAE: ", mse)
   res_MSE.append(mse)

下面要构建pipeline了:

# 候选模型
models={
   'rfr':RandomForestRegressor(bootstrap=False, max_depth=15, max_features='sqrt', min_samples_split=2, n_estimators=100),
   
   'lasso':Lasso(alpha=0.005, fit_intercept=True),
   
   'ridge':Ridge(alpha = 10, fit_intercept=True), 'xgb':xgb.XGBRegressor(bootstrap=True, max_depth=2, max_features = 'auto', min_sample_split = 2, n_estimators = 100)
}

# 不同的模型不同建模方法
for mod in models:
   if mod == 'rfr' or mod == 'xgb':
     print('Untuned metrics for: ', mod)
     metrics(models[mod])
     print('\n')
     print('Starting grid search for: ', mod)
     params = {
       "n_estimators"      : [10,100, 1000, 2000, 4000, 6000],
       "max_features"      : ["auto", "sqrt", "log2"],
       "max_depth"         : [2, 4, 8, 12, 15],
       "min_samples_split" : [2,4,8],
       "bootstrap": [True, False],
    }
    if mod == 'rfr':
       rfr = RandomForestRegressor()
       grid = GridSearchCV(rfr, params, verbose=5, cv=2)
       grid.fit(X_train, y_train)
       print("Best score: ", grid.best_score_ )
       print("Best: params", grid.best_params_)
    else:
       xgboost = xgb.XGBRegressor()
       grid = GridSearchCV(xgboost, params, verbose=5, cv=2)
       grid.fit(X_train, y_train)
       print("Best score: ", grid.best_score_ )
       print("Best: params", grid.best_params_)
   else:
      print('Untuned metrics for: ', mod)
      metrics(models[mod])
      print('\n')
      print('Starting grid search for: ', mod)
      params = {
         "alpha": [0.005, 0.05, 0.1, 1, 10, 100, 290, 500],
         "fit_intercept": [True, False]
      }
      if mod == 'lasso':
         lasso = Lasso()
         grid = GridSearchCV(lasso, params, verbose = 5, cv = 2)
         grid.fit(X_train, y_train)
         print("Best score: ", grid.best_score_ ) 
         print("Best: params", grid.best_params_)
      else:
         ridge = Ridge()
         grid = GridSearchCV(ridge, params, verbose = 5, cv = 2)
         grid.fit(X_train, y_train)
         print("Best score: ", grid.best_score_ )
         print("Best: params", grid.best_params_)

以下是随机调整模型的结果:

在未调超参数的情况下,我们看到差异不大的R方结果,但 Lasso 的误差最小。

我们再看看网格搜索的结果,以找到每个模型的最佳参数:

现在让我们将这些参数应用于每个模型,并查看结果:

调参后的结果相比默认超参数,都有提升,但 Lasso回归依旧有最佳的效果(与本例的数据集样本量和特征相关性有关),我们最终保留Lasso回归模型并存储模型到本地。

lasso_reg = Lasso(alpha = 0.005, fit_intercept = True)
pickle.dump(lasso_reg, open('model.pkl','wb'))

💡 web应用开发

下面我们把上面得到的模型部署到网页端,形成一个可以实时预估的应用,我们这里使用 gradio 库来开发 Web 应用程序,实际的web应用预估包含下面的步骤:

  • 用户在网页表单中输入数据
  • 处理数据(特征编码&变换)
  • 数据处理以匹配模型输入格式
  • 预测并呈现给用户的价格

① 基本开发

首先,我们导入原始数据集和做过数据处理(独热向量编码)的数据集,并保留它们各自的列。

# df的列
#Columns of the df
df = pd.read_csv('df_columns')
df.drop(['Unnamed: 0','price'], axis = 1, inplace=True)
cols = df.columns

# df的哑变量列
dummy = pd.read_csv('dummy_df')
dummy.drop('Unnamed: 0', axis = 1, inplace=True)
cols_to_use = dummy.columns

接下来,对于类别型特征,我们构建web应用端下拉选项:

# 构建应用中的候选值

# 车品牌首字母大写
cars = df['CarName'].unique().tolist()
carNameCap = []
for col in cars:
   carNameCap.append(col.capitalize())

#fueltype字段
fuel = df['fueltype'].unique().tolist()
fuelCap = []
for fu in fuel:
   fuelCap.append(fu.capitalize())

#carbod, engine type, fuel systems等字段
carb = df['carbody'].unique().tolist()
engtype = df['enginetype'].unique().tolist()
fuelsys = df['fuelsystem'].unique().tolist()

OK,我们会针对上面这些模型预估需要用到的类别型字段,开发下拉功能并添加候选项。

下面我们定义一个函数进行数据处理,并预估返回价格:

# 数据变换处理以匹配模型
def transform(data):
   # 数据幅度缩放
   sc = StandardScaler()
   
   # 导入模型
   model= pickle.load(open('model.pkl','rb'))
   
   # 新数据Dataframe
   new_df = pd.DataFrame([data],columns = cols)   
   # 区分类别型和数值型特征
   cat = []
   num = []
   for col in new_df.columns:
      if new_df[col].dtypes == 'object':
         cat.append(col)
      else:
         num.append(col)    
    x1_new = pd.get_dummies(new_df[cat], drop_first = False)
    x2_new = new_df[num]
    
    X_new = pd.concat([x2_new,x1_new], axis = 1)
    final_df = pd.DataFrame(columns = cols_to_use)
    final_df = pd.concat([final_df, X_new])
    final_df = final_df.fillna(0)
    X_new = final_df.values
    X_new[:, :(len(x1_new.columns))]= sc.fit_transform(X_new[:,
:(len(x1_new.columns))])    
    output = model.predict(X_new)
    return "The price of the car " + str(round(np.exp(output)[0],2)) + "$"

下面我们在gradio web应用程序中创建元素,我们会为类别型字段构建下拉菜单或复选框,为数值型字段构建输入框。 参考代码如下:

# 类别型
car = gr.Dropdown(label = "Car brand", choices=carNameCap)
# 数值型
curbweight = gr.Slider(label = "Weight of the car (in pounds)", minimum = 500, maximum = 6000)

现在,让我们在界面中添加所有内容:

一切就绪就可以部署了!

② 部署

下面我们把上面得到应用部署一下,首先我们对于应用的 ip 和端口做一点设定

export GRADIO_SERVER_NAME=0.0.0.0
export GRADIO_SERVER_PORT="$PORT"

大家确定使用pip安装好下述依赖:

numpy                            
pandas                             
scikit-learn                             
gradio                             
Flask                             
argparse                             
gunicorn                             
rq

接着运行 python WebApp.py 就可以测试应用程序了,WebApp.py内容如下:

import gradio as gr
import numpy as np
import pandas as pd
import pickle
from sklearn.preprocessing import StandardScaler

# 数据字典
asp = {
    'Standard':'std',
   'Turbo':'turbo'
}

drivew = {
    'Rear wheel drive': 'rwd',
    'Front wheel drive': 'fwd', 
    '4 wheel drive': '4wd'
}

cylnum = {
    2: 'two',
    3: 'three', 
    4: 'four',
    5: 'five', 
    6: 'six', 
    8: 'eight',
    12: 'twelve'
}

# 原始df字段名
df = pd.read_csv('df_columns')
df.drop(['Unnamed: 0','price'], axis = 1, inplace=True)
cols = df.columns

# 独热向量编码过后的字段名
dummy = pd.read_csv('dummy_df')
dummy.drop('Unnamed: 0', axis = 1, inplace=True)
cols_to_use = dummy.columns

# 车品牌名
cars = df['CarName'].unique().tolist()
carNameCap = []
for col in cars:
    carNameCap.append(col.capitalize())

# fuel
fuel = df['fueltype'].unique().tolist()
fuelCap = []
for fu in fuel:
    fuelCap.append(fu.capitalize())

#For carbod, engine type, fuel systme
carb = df['carbody'].unique().tolist() 
engtype = df['enginetype'].unique().tolist()
fuelsys = df['fuelsystem'].unique().tolist()

#Function to model data to fit the model
def transform(data):
    # 数值型幅度缩放
    sc= StandardScaler()

    # 导入模型
    lasso_reg = pickle.load(open('model.pkl','rb'))

    # 新数据Dataframe
    new_df = pd.DataFrame([data],columns = cols)

    # 切分类别型与数值型字段
    cat = []
    num = []
    for col in new_df.columns: 
        if new_df[col].dtypes == 'object': 
            cat.append(col)
        else: 
            num.append(col)

    # 构建模型所需数据格式
    x1_new = pd.get_dummies(new_df[cat], drop_first = False)
    x2_new = new_df[num]
    X_new = pd.concat([x2_new,x1_new], axis = 1)
    
    final_df = pd.DataFrame(columns = cols_to_use)
    final_df = pd.concat([final_df, X_new])
    final_df = final_df.fillna(0)
    final_df = pd.concat([final_df,dummy])

    X_new = final_df.values
    X_new[:, :(len(x1_new.columns))]= sc.fit_transform(X_new[:, :(len(x1_new.columns))])
    print(X_new[-1].reshape(-1, 1))
    output = lasso_reg.predict(X_new[-1].reshape(1, -1))
    return "The price of the car " + str(round(np.exp(output)[0],2)) + "$"

# 预估价格的主函数
def predict_price(car, fueltype, aspiration, doornumber, carbody, drivewheel, enginelocation, wheelbase, carlength, carwidth, 
                carheight, curbweight, enginetype, cylindernumber, enginesize, fuelsystem, boreratio, horsepower, citympg, highwaympg): 

    new_data = [car.lower(), fueltype.lower(), asp[aspiration], doornumber.lower(), carbody, drivew[drivewheel], enginelocation.lower(),
                wheelbase, carlength, carwidth, carheight, curbweight, enginetype, cylnum[cylindernumber], enginesize, fuelsystem, 
                boreratio, horsepower, citympg, highwaympg]
    
    return transform(new_data) 


car = gr.Dropdown(label = "Car brand", choices=carNameCap)

fueltype = gr.Radio(label = "Fuel Type", choices = fuelCap)

aspiration = gr.Radio(label = "Aspiration type", choices = ["Standard", "Turbo"])

doornumber = gr.Radio(label = "Number of doors", choices = ["Two", "Four"])

carbody = gr.Dropdown(label ="Car body type", choices = carb)

drivewheel = gr.Radio(label = "Drive wheel", choices = ['Rear wheel drive', 'Front wheel drive', '4 wheel drive'])

enginelocation = gr.Radio(label = "Engine location", choices = ['Front', 'Rear'])

wheelbase = gr.Slider(label = "Distance between the wheels on the side of the car (in inches)", minimum = 50, maximum = 300)

carlength = gr.Slider(label = "Length of the car (in inches)", minimum = 50, maximum = 300)

carwidth = gr.Slider(label = "Width of the car (in inches)", minimum = 50, maximum = 300)

carheight = gr.Slider(label = "Height of the car (in inches)", minimum = 50, maximum = 300)

curbweight = gr.Slider(label = "Weight of the car (in pounds)", minimum = 500, maximum = 6000)

enginetype = gr.Dropdown(label = "Engine type", choices = engtype)

cylindernumber = gr.Radio(label = "Cylinder number", choices = [2, 3, 4, 5, 6, 8, 12])

enginesize = gr.Slider(label = "Engine size (swept volume of all the pistons inside the cylinders)", minimum = 50, maximum = 500)

fuelsystem = gr.Dropdown(label = "Fuel system (link to ressource: ", choices = fuelsys)

boreratio = gr.Slider(label = "Bore ratio (ratio between cylinder bore diameter and piston stroke)", minimum = 1, maximum = 6)

horsepower = gr.Slider(label = "Horse power of the car", minimum = 25, maximum = 400)

citympg = gr.Slider(label = "Mileage in city (in km)", minimum = 0, maximum = 100)

highwaympg = gr.Slider(label = "Mileage on highway (in km)", minimum = 0, maximum = 100)

Output = gr.Textbox()

app = gr.Interface(title="Predict the price of a car based on its specs", 
                    fn=predict_price,
                    inputs=[car,
                            fueltype,
                            aspiration,
                            doornumber,
                            carbody,
                            drivewheel, 
                            enginelocation, 
                            wheelbase,
                            carlength, 
                            carwidth, 
                            carheight, 
                            curbweight,
                            enginetype, 
                            cylindernumber, 
                            enginesize,
                            fuelsystem,
                            boreratio,
                            horsepower, 
                            citympg, 
                            highwaympg
                            ],
                    outputs=Output)

app.launch()

最终的应用结果如下,可以自己勾选与填入特征进行模型预估!

参考资料