Datawhale练习之二手车价格预测

#coding:utf-8
#导入warnings包，利用过滤器来实现忽略警告语句。
import warnings
warnings.filterwarnings('ignore')
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import missingno as msno

## 1) 载入训练集和测试集；
path = './'
Train_data = pd.read_csv(path+'car_train_0110.csv', sep=' ')
Test_data = pd.read_csv(path+'car_testA_0110.csv', sep=' ')

## 2) 简略观察数据(head()+shape)
Train_data.head().append(Train_data.tail())

Train_data.shape，Test_data.shape

Train_data.shape，Test_data.shape

Train_data.isnull().sum()

# find na 
tmp = df_train.isnull().any()
tmp[tmp.values==True]

Train_data.isnull().sum().plot( kind= 'bar')

msno.matrix(Train_data.sample(250))

msno.bar(Train_data.sample(250),labels= True)

msno.heatmap(Train_data.sample(250))

Train_data.info()

特征分为类别特征和数字特征

Train_data['price']

Train_data['price'].value_counts()

## 1) 总体分布概况（无界约翰逊分布等）
import scipy.stats as st
y = Train_data['price']
plt.figure(1); plt.title('Johnson SU')
sns.distplot(y, kde=False, fit=st.johnsonsu)
plt.figure(2); plt.title('Normal')
sns.distplot(y, kde=False, fit=st.norm)
plt.figure(3); plt.title('Log Normal')
sns.distplot(y, kde=False, fit=st.lognorm)

## 2) 查看skewness and kurtosis
sns.distplot(Train_data['price']);
print("Skewness: %f" % Train_data['price'].skew())
print("Kurtosis: %f" % Train_data['price'].kurt())

Train_data.skew()

Train_data.kurt()

## 3) 查看预测值的具体频数
plt.hist(Train_data['price'], orientation = 'vertical',histtype = 'bar', color ='red')
plt.show()

# log变换之后的分布较均匀，可以进行log变换进行预测，这也是预测问题常用的trick
plt.hist(np.log(1+Train_data['price']), orientation = 'vertical',histtype = 'bar', color ='red') 
plt.show()

Y_train = Train_data['price']

numeric_features = ['power', 'kilometer', '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' ]
categorical_features = ['name', 'model', 'brand', 'bodyType', 'fuelType', 'gearbox', 'notRepairedDamage', 'regionCode',]

# 特征nunique分布
for cat_fea in categorical_features:
    print(cat_fea + "的特征分布如下：")
    print("{}特征有个{}不同的值".format(cat_fea, Train_data[cat_fea].nunique()))
    print(Train_data[cat_fea].value_counts())

numeric_features.append('price')
numeric_features

price_numeric = Train_data[numeric_features]
correlation = price_numeric.corr()
correlation

print(correlation['price'].sort_values(ascending = False),'\n')

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)

del price_numeric['price']

## 2) 查看几个特征得 偏度和峰值
for col in numeric_features:
    print('{:15}'.format(col), 
          'Skewness: {:05.2f}'.format(Train_data[col].skew()) , 
          '   ' ,
          'Kurtosis: {:06.2f}'.format(Train_data[col].kurt())  
         )

## 3) 每个数字特征得分布可视化
f = pd.melt(Train_data, value_vars=numeric_features)
g = sns.FacetGrid(f, col="variable",  col_wrap=2, sharex=False, sharey=False)
g = g.map(sns.distplot, "value")

## 4) 数字特征相互之间的关系可视化
sns.set()
columns = ['price', 'v_12', 'v_8' , 'v_0', 'power', 'v_5',  'v_2', 'v_6', 'v_1', 'v_14']
sns.pairplot(Train_data[columns],size = 2 ,kind ='scatter',diag_kind='kde')
plt.show()

## 5) 多变量互相回归关系可视化
fig, ((ax1, ax2), (ax3, ax4), (ax5, ax6), (ax7, ax8), (ax9, ax10)) = plt.subplots(nrows=5, ncols=2, figsize=(24, 20))
# ['v_12', 'v_8' , 'v_0', 'power', 'v_5',  'v_2', 'v_6', 'v_1', 'v_14']
v_12_scatter_plot = pd.concat([Y_train,Train_data['v_12']],axis = 1)
sns.regplot(x='v_12',y = 'price', data = v_12_scatter_plot,scatter= True, fit_reg=True, ax=ax1)
v_8_scatter_plot = pd.concat([Y_train,Train_data['v_8']],axis = 1)
sns.regplot(x='v_8',y = 'price',data = v_8_scatter_plot,scatter= True, fit_reg=True, ax=ax2)
v_0_scatter_plot = pd.concat([Y_train,Train_data['v_0']],axis = 1)
sns.regplot(x='v_0',y = 'price',data = v_0_scatter_plot,scatter= True, fit_reg=True, ax=ax3)
power_scatter_plot = pd.concat([Y_train,Train_data['power']],axis = 1)
sns.regplot(x='power',y = 'price',data = power_scatter_plot,scatter= True, fit_reg=True, ax=ax4)
v_5_scatter_plot = pd.concat([Y_train,Train_data['v_5']],axis = 1)
sns.regplot(x='v_5',y = 'price',data = v_5_scatter_plot,scatter= True, fit_reg=True, ax=ax5)
v_2_scatter_plot = pd.concat([Y_train,Train_data['v_2']],axis = 1)
sns.regplot(x='v_2',y = 'price',data = v_2_scatter_plot,scatter= True, fit_reg=True, ax=ax6)
v_6_scatter_plot = pd.concat([Y_train,Train_data['v_6']],axis = 1)
sns.regplot(x='v_6',y = 'price',data = v_6_scatter_plot,scatter= True, fit_reg=True, ax=ax7)
v_1_scatter_plot = pd.concat([Y_train,Train_data['v_1']],axis = 1)
sns.regplot(x='v_1',y = 'price',data = v_1_scatter_plot,scatter= True, fit_reg=True, ax=ax8)
v_14_scatter_plot = pd.concat([Y_train,Train_data['v_14']],axis = 1)
sns.regplot(x='v_14',y = 'price',data = v_14_scatter_plot,scatter= True, fit_reg=True, ax=ax9)
v_13_scatter_plot = pd.concat([Y_train,Train_data['v_13']],axis = 1)
sns.regplot(x='v_13',y = 'price',data = v_13_scatter_plot,scatter= True, fit_reg=True, ax=ax10)

.value_counts()

## 1) unique分布
for fea in categorical_features:
    print(Train_data[fea].nunique())
categorical_features

## 2) 类别特征箱形图可视化
# 因为 name和 regionCode的类别太稀疏了，这里我们把不稀疏的几类画一下
categorical_features = ['model',
 'brand',
 'bodyType',
 'fuelType',
 'gearbox',
 'notRepairedDamage']
for c in categorical_features:
    Train_data[c] = Train_data[c].astype('category')
    if Train_data[c].isnull().any():
        Train_data[c] = Train_data[c].cat.add_categories(['MISSING'])
        Train_data[c] = Train_data[c].fillna('MISSING')
def boxplot(x, y, **kwargs):
    sns.boxplot(x=x, y=y)
    x=plt.xticks(rotation=90)
f = pd.melt(Train_data, id_vars=['price'], value_vars=categorical_features)
g = sns.FacetGrid(f, col="variable",  col_wrap=2, sharex=False, sharey=False, size=5)
g = g.map(boxplot, "value", "price")

Train_data.columns

## 3) 类别特征的小提琴图可视化
catg_list = categorical_features
target = 'price'
for catg in catg_list :
    sns.violinplot(x=catg, y=target, data=Train_data)
    plt.show()

categorical_features = ['model',
 'brand',
 'bodyType',
 'fuelType',
 'gearbox',
 'notRepairedDamage']

## 4) 类别特征的柱形图可视化
def bar_plot(x, y, **kwargs):
    sns.barplot(x=x, y=y)
    x=plt.xticks(rotation=90)
f = pd.melt(Train_data, id_vars=['price'], value_vars=categorical_features)
g = sns.FacetGrid(f, col="variable",  col_wrap=2, sharex=False, sharey=False, size=5)
g = g.map(bar_plot, "value", "price")

##  5) 类别特征的每个类别频数可视化(count_plot)
def count_plot(x,  **kwargs):
    sns.countplot(x=x)
    x=plt.xticks(rotation=90)
f = pd.melt(Train_data,  value_vars=categorical_features)
g = sns.FacetGrid(f, col="variable",  col_wrap=2, sharex=False, sharey=False, size=5)
g = g.map(count_plot, "value")

import pandas_profiling

pfr = pandas_profiling.ProfileReport(Train_data)
pfr.to_file("./example.html")