数据挖掘零基础--task2数据分析

EDA数据探索性分析

内容摘要

1. 载入库
2. 载入数据
3. 数据总览
4. 缺失与异常
5. 预测值分布
6. 类别特征和数字特征，并对类别特征查看unique分布
7. 数字特征分析及可视化
8. 类型特征分析及可视化
9. 用pandas_profiling生成数据报告

对各种python数据库的安装与载入

使用jupyter notebook
其中绝大多数可以使用pip install指令在cmd界面进行安装，不能的附地址和安装方法
pandas https://pypi.org/project/pandas/#files
numpy https://pypi.org/project/numpy/#files
下载的文件转移至python内的lib下的package文件夹，并调用pip安装
其他的三个包可以直接使用cmd安装

导入部分

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

设置路径，载入数据集

path = '路径'
Train_data = pd.read_csv(path+'文件名.文件格式', sep=' ')
Test_data = pd.read_csv(path+'文件名.文件格式', sep=' ')
Train_data.describe()

之后的文件名以train_data和test_data为例

数据总览

Train_data.head().append(Train_data.tail())
Train_data.shape

获得的表中看到个数count、平均值mean、方差std、最小值min、中位数25% 50% 75% 、以及最大值 这几种数据，以便获得总览

Train_data.info()

<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

缺失与异常

Train_data.isnull().sum()

也可以使用可视化

# 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))

预测值

Train_data['price']

Train_data['price'].value_counts()

总体分布情况

## 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)

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']

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())

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)

可视化各个数字特征

## 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)

类型特征分析

## 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")

## 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")

pandas_profiling生成数据报告

import pandas_profiling

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