TASK2:数据分析
摘自 AI蜗牛车 在Datawhale 数据挖掘入门:数据分析部分的讲义
赛题:零基础入门数据挖掘 - 二手车交易价格预测
地址:https://tianchi.aliyun.com/competition/entrance/231784/introduction?spm=5176.12281957.1004.1.38b02448ausjSX
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;
Train_data = pd.read_csv('datalab/231784/used_car_train_20200313.csv', sep=' ')
Test_data = pd.read_csv('datalab/231784/used_car_testA_20200313.csv', sep=' ')
备注:如果出现无法加载数据的问题,可以重新挂载一下数据,在前面使用一个新块确认一下路径:!ls datalab/ 输出应该为231784才对。
## 2) 简略观察数据(head()+shape)
Train_data.head().append(Train_data.tail())
Test_data.head().append(Test_data.tail())
Train_data.shape
输出:(150000,31)
Test_data.shape
输出:(50000,30)
Train_data.describe()
## 2) 通过info()来熟悉数据类型
Train_data.info()
输出:
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 150000 entries, 0 to 149999
Data columns (total 31 columns):
SaleID 150000 non-null int64
name 150000 non-null int64
regDate 150000 non-null int64
model 149999 non-null float64
brand 150000 non-null int64
bodyType 145494 non-null float64
fuelType 141320 non-null float64
gearbox 144019 non-null float64
power 150000 non-null int64
kilometer 150000 non-null float64
notRepairedDamage 150000 non-null object
regionCode 150000 non-null int64
seller 150000 non-null int64
offerType 150000 non-null int64
creatDate 150000 non-null int64
price 150000 non-null int64
v_0 150000 non-null float64
v_1 150000 non-null float64
v_2 150000 non-null float64
v_3 150000 non-null float64
v_4 150000 non-null float64
v_5 150000 non-null float64
v_6 150000 non-null float64
v_7 150000 non-null float64
v_8 150000 non-null float64
v_9 150000 non-null float64
v_10 150000 non-null float64
v_11 150000 non-null float64
v_12 150000 non-null float64
v_13 150000 non-null float64
v_14 150000 non-null float64
dtypes: float64(20), int64(10), object(1)
memory usage: 35.5+ MB
Test_data.info()
输出:
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 50000 entries, 0 to 49999
Data columns (total 30 columns):
SaleID 50000 non-null int64
name 50000 non-null int64
regDate 50000 non-null int64
model 50000 non-null float64
brand 50000 non-null int64
bodyType 48587 non-null float64
fuelType 47107 non-null float64
gearbox 48090 non-null float64
power 50000 non-null int64
kilometer 50000 non-null float64
notRepairedDamage 50000 non-null object
regionCode 50000 non-null int64
seller 50000 non-null int64
offerType 50000 non-null int64
creatDate 50000 non-null int64
v_0 50000 non-null float64
v_1 50000 non-null float64
v_2 50000 non-null float64
v_3 50000 non-null float64
v_4 50000 non-null float64
v_5 50000 non-null float64
v_6 50000 non-null float64
v_7 50000 non-null float64
v_8 50000 non-null float64
v_9 50000 non-null float64
v_10 50000 non-null float64
v_11 50000 non-null float64
v_12 50000 non-null float64
v_13 50000 non-null float64
v_14 50000 non-null float64
dtypes: float64(20), int64(9), object(1)
memory usage: 11.4+ MB
## 1) 查看每列的存在nan情况
Train_data.isnull().sum()
Test_data.isnull().sum()
#可视化:
# 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))
此外对于类似于notRepairedDamage这一类的缺省,首先需要替换其中的“-”为nan
Train_data['notRepairedDamage'].value_counts()
将特殊符号转化为nan
Train_data['notRepairedDamage'].replace('-', np.nan, inplace=True)
替换以后检查一下
Train_data['notRepairedDamage'].value_counts()
处理倾斜特别严重的参考量
比如:
Train_data["seller"].value_counts()
Train_data["offerType"].value_counts()
特征都存在严重倾斜。
应对办法为暂时删除。
del Train_data["seller"]
del Train_data["offerType"]
del Test_data["seller"]
del Test_data["offerType"]
Train_data['price']
Train_data['price'].value_counts()
观察预测值的分布情况:
## 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)
价格不服从正态分布,所以在进行回归之前,它必须进行转换。虽然对数变换做得很好,但最佳拟合是无界约翰逊分布
查看分布中的偏度和峰度
## 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())
训练数据的偏度和峰度
Train_data.skew(), Train_data.kurt()
绘制偏度和峰度:
sns.distplot(Train_data.skew(),color='blue',axlabel ='Skewness')
sns.distplot(Train_data.kurt(),color='orange',axlabel ='Kurtness')
查看预测值的频数
## 3) 查看预测值的具体频数
plt.hist(Train_data['price'], orientation = 'vertical',histtype = 'bar', color ='red')
plt.show()
查看频数, 大于20000得值极少,其实这里也可以把这些当作特殊得值(异常值)直接用填充或者删掉,再前面进行
# 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()
# 这个区别方式适用于没有直接label coding的数据
# 这里不适用,需要人为根据实际含义来区分
# 数字特征
# numeric_features = Train_data.select_dtypes(include=[np.number])
# numeric_features.columns
# # 类型特征
# categorical_features = Train_data.select_dtypes(include=[np.object])
# categorical_features.column
#手动分割特征:
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')
Train_data.head()
## 1) 相关性分析
price_numeric = Train_data[numeric_features]
correlation = price_numeric.corr()
print(correlation['price'].sort_values(ascending = False),'\n')
做出相关性矩阵图
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()
Train_data.columns
Y_train
## 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)
## 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()
## 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")
用pandas_profiling生成一个较为全面的可视化和数据报告(较为简单、方便) 最终打开html文件即可
import pandas_profiling
pfr = pandas_profiling.ProfileReport(Train_data)
pfr.to_file("./example.html")
总结:
数据探索有利于我们发现数据的一些特性,数据之间的关联性,对于后续的特征构建是很有帮助的。
对于数据的初步分析(直接查看数据,或.sum(), .mean(),.descirbe()等统计函数)可以从:样本数量,训练集数量,是否有时间特征,是否是时序问题,特征所表示的含义(非匿名特征),特征类型(字符类似,int,float,time),特征的缺失情况(注意缺失的在数据中的表现形式,有些是空的有些是”NAN”符号等),特征的均值方差情况。
分析记录某些特征值缺失占比30%以上样本的缺失处理,有助于后续的模型验证和调节,分析特征应该是填充(填充方式是什么,均值填充,0填充,众数填充等),还是舍去,还是先做样本分类用不同的特征模型去预测。
对于异常值做专门的分析,分析特征异常的label是否为异常值(或者偏离均值较远或者事特殊符号),异常值是否应该剔除,还是用正常值填充,是记录异常,还是机器本身异常等。
对于Label做专门的分析,分析标签的分布情况等。
进步分析可以通过对特征作图,特征和label联合做图(统计图,离散图),直观了解特征的分布情况,通过这一步也可以发现数据之中的一些异常值等,通过箱型图分析一些特征值的偏离情况,对于特征和特征联合作图,对于特征和label联合作图,分析其中的一些关联性。