天池二手车拍卖赛题理解之数据分析

天池二手车交易价格预测赛题理解之数据分析常见操作

原文链接：Datawhale 零基础入门数据挖掘-Task2 数据分析

本文为个人阅读笔记，仅记录阅读过程中遇到的新知识。

1. 需要的数据处理包

#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

2. 读取.csv文件

path = './datalab/231784/'
Train_data = pd.read_csv(path+'used_car_train_20200313.csv', sep=' ')

3. 简要观察数据

##简略观察数据(head()+shape)
Train_data.head().append(Train_data.tail()) #为什么要这样操作？

## describe:相关统计量
Train_data.describe()

## info():数据类型
Train_data.info()
Test_data.info()

4. 统计每列缺省值情况并可视化

##统计每列的存在nan情况
Train_data.isnull().sum()

#nan可视化
missing = Train_data.isnull().sum()
missing = missing[missing > 0]
missing.sort_values(inplace=True)
missing.plot.bar()

# 可视化看下缺省值
msno.matrix(Train_data.sample(250))
msno.bar(Train_data.sample(1000))

5. 通过无界约翰逊分布查看总体分布概况

import scipy.stats as st
y = Train_data['price']
plt.figure(1); plt.title('Johnson SU')
sns.distplot(y, kde=False, fit=st.johnsonsu)

6. 查看skewness and kurtosis

sns.distplot(Train_data['price']);
print("Skewness: %f" % Train_data['price'].skew())
print("Kurtosis: %f" % Train_data['price'].kurt())
sns.distplot(Train_data.skew(),color='blue',axlabel ='Skewness')
sns.distplot(Train_data.kurt(),color='orange',axlabel ='Kurtness')

7. 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 z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(Train_data['price']), orientation = 'vertical',histtype = 'bar', color ='red') 
plt.show()

8. 相关性分析

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

9. 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()

10. 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)

11. 类别特征箱形图可视化

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")

12. 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()

13. 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")

14. 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")

15. 用pandas_profiling生成数据报告

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