Datawhale-Task2 数据分析

学习目标：

零基础入门数据挖掘-Task2 数据分析（熟悉数据，分析数据，处理数据）

学习心得：

基于二手车交易数据，对其数据进行处理得出相关需要的数据。在这个过程中加深我对数据集的认识，以及在下次面对数据集时可以进行一些简单的机器学习，处理数据，或者时使用深度学习的使用。经过一系列的处理加深预测数据的可信度和准确度。

学习内容：

1、 选择相应的开发环境，安装所需要的可视化库。
2、载入数据（数据下载地址：https://tianchi.aliyun.com/competition/entrance/231784/introduction?spm=5176.12281957.1004.1.38b02448ausjSX）
3、 对数据的缺失值和异常进行相关处理。
4、 了解预测值得分布，以及了解类别特征和数字特征，并对类别进行查看分布。
5、对其进行分析得出相关数据的报告。

部分代码：

1、 相关模块的安装（主要是使用pip install,要是有兴趣的也可以去官网下载好库包，然后放在工具包里即可使用 ）

#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、 数据载入

## 1) 载入训练集和测试集；
Train_data = pd.read_csv('train.csv', sep=' ')
Test_data = pd.read_csv('testA.csv', sep=' ')

3、使用describe方法计算数据相关的数字特征。

## 1) 通过describe()来熟悉数据的相关统计量
Train_data.describe()

4、判断异常数据和缺失值

## 1) 查看每列的存在nan情况
Train_data.isnull().sum()
Test_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))
msno.matrix(Test_data.sample(250))
msno.bar(Test_data.sample(1000))

## 2) 查看异常值检测
Train_data.info()
Train_data['notRepairedDamage'].value_counts()
Train_data['notRepairedDamage'].replace('-', np.nan, inplace=True)
Train_data['notRepairedDamage'].value_counts()
Train_data.isnull().sum()
Test_data['notRepairedDamage'].value_counts()
Test_data['notRepairedDamage'].replace('-', np.nan, inplace=True)
Train_data["seller"].value_counts()
Train_data["offerType"].value_counts()

5、了解预测值的分布

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()
sns.distplot(Train_data.skew(),color='blue',axlabel ='Skewness')
sns.distplot(Train_data.kurt(),color='orange',axlabel ='Kurtness')


## 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 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()

6、特征分为类别特征和数字特征，并对类别特征查看unique分布

# 分离label即预测值
Y_train = Train_data['price']

# 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())


# 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, Test_data[cat_fea].nunique()))
    print(Test_data[cat_fea].value_counts())

7、数字特征分析

numeric_features.append('price')
numeric_features
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')


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

8、多变量之间关系可视化

## 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)

9、 类别特征分析

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

## 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")

10、用pandas_profiling生成数据报告

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