python数据分析与挖掘实战第七章

标签：数据分析 plt pd python labels airline 第七章 import data

#代码7-1 数据探索
import pandas as pd
datafile = 'data3/air_data.csv' #航空原始数据，第一行为属性标签
resultfile = 'data3/explore.csv'  #数据探索结果表

data = pd.read_csv(datafile,encoding = 'utf-8')#读取原始数据，指定UTF-8编码（需要用文本编译器将数据转换为UTF-8编码）

#包括对数据的基本描述，percentiles参数是指定计算多少的分位数表（如1/4分位数、中位数等）
explore = data.describe(percentiles = [], include = 'all').T
explore['null'] = len(data)-explore['count']#describe()函数自动计算非空值数，需要手动计算空值数

explore = explore[['null','max','min']]
explore.columns = [u'空值数',u'最大值',u'最小值'] #表头重命名
'''
这里只选取部分探索结果。
describe()函数自动计算的字段有count(非空值数)、unique(唯一值数)、top(频数最高者)、freq(最高频数)、mean(平均值)、
std(方差)、min(最小值)、50%(中位数)、max(最大值)
'''
explore.to_csv(resultfile) #导出结果

#代码7-2 探索客户的基本信息发布情况
#客户信息类别
#提取会员入会年份
import matplotlib.pyplot as plt
from datetime import datetime
ffp = data['FFP_DATE'].apply(lambda x:datetime.strptime(x,'%Y/%m/%d'))
ffp_year = ffp.map(lambda x : x.year)
#绘制各年份会员入会人数直方图
fig = plt.figure(figsize=(8,5))             #设置画布大小
plt.rcParams['font.sans-serif'] = 'SimHei'  # 设置中文显示
plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号
plt.hist(ffp_year,bins='auto',color='#0504aa')
plt.xlabel('年份')
plt.ylabel('入会人数')
plt.title('3107各年份会员入会人数')
plt.show()
plt.close

#提取会员不同性别人数
male = pd.value_counts(data['GENDER'])['男']
female = pd.value_counts(data['GENDER'])['女']
#绘制会员性别比例饼图
fig = plt.figure(figsize = (7,4))
plt.pie([male,female],labels=['男','女'],colors=['lightskyblue','lightcoral'],autopct='%1.1f%%')
plt.title('3107会员性别比例')
plt.show()
plt.close()

#提取不同级别会员的人数
lv_four = pd.value_counts(data['FFP_TIER'])[4]
lv_five = pd.value_counts(data['FFP_TIER'])[5]
lv_six = pd.value_counts(data['FFP_TIER'])[6]
#绘制会员各级别人数条形图
fig = plt.figure(figsize=(8,5))
plt.bar(x=range(3), height=[lv_four,lv_five,lv_six],width=0.4,alpha=0.8,color='skyblue')
plt.xticks([index for index in range(3)],['4','5','6'])
plt.xlabel('会员等级')
plt.ylabel('会员人数')
plt.title('3107会员各级别人数')
plt.show()
plt.close

#提取会员年龄
age = data['AGE'].dropna()
age = age.astype('int64')
#绘制会员年龄分布箱型图
fig = plt.figure(figsize=(5,10))
plt.boxplot(age,patch_artist=True,
            labels=['会员年龄'],    #设置x轴标题
            boxprops={'facecolor' : 'lightblue'})  #设置填充颜色
plt.title('3107会员年龄分布箱型图')
plt.grid(axis='y') #显示y坐标轴的底线
plt.show()
plt.close

 

#代码7-3 探索客户乘机信息分布情况
lte = data['LAST_TO_END']
fc = data['FLIGHT_COUNT']
sks = data['SEG_KM_SUM']

#绘制最后乘机至结束时长分布箱型图
fig = plt.figure(figsize=(5,8))
plt.boxplot(lte,
            patch_artist=True,
            labels=['时长'],    #设置x轴标题
            boxprops={'facecolor' : 'lightblue'})  #设置填充颜色
plt.title('3107客户最后乘机至结束时长分布箱型图')
plt.grid(axis='y') #显示y坐标轴的底线
plt.show()
plt.close

#绘制客户飞行次数箱型图
fig = plt.figure(figsize=(5,8))
plt.boxplot(fc,
            patch_artist=True,
            labels=['飞行次数'],    #设置x轴标题
            boxprops={'facecolor' : 'lightblue'})  #设置填充颜色
plt.title('3107客户飞行次数分布箱型图')
plt.grid(axis='y') #显示y坐标轴的底线
plt.show()
plt.close

#绘制客户总飞行公里数箱型图
fig = plt.figure(figsize=(5,8))
plt.boxplot(sks,
            patch_artist=True,
            labels=['总飞行公里数'],    #设置x轴标题
            boxprops={'facecolor' : 'lightblue'})  #设置填充颜色
plt.title('3107客户总飞行公里数分布箱型图')
plt.grid(axis='y') #显示y坐标轴的底线
plt.show()
plt.close

 

#代码7-4 
ec = data['EXCHANGE_COUNT']
#绘制会员兑换积分次数直方图
fig = plt.figure(figsize=(8,5))
plt.hist(ec,bins=5,color='#0504aa')
plt.xlabel('兑换次数')
plt.ylabel('会员人数')
plt.title('3107会员兑换积分次数分布直方图')
plt.show()
plt.close

#提取会员总累计积分
ps = data['Points_Sum']
#绘制会员总累计积分箱型图
fig = plt.figure(figsize=(5,8))
plt.boxplot(ps,
            patch_artist=True,
            labels=['总累计积分'],    #设置x轴标题
            boxprops={'facecolor' : 'lightblue'})  #设置填充颜色
plt.title('3107客户总累计积分箱型图')
plt.grid(axis='y') #显示y坐标轴的底线
plt.show()
plt.close

#7—5
data_corr = data[['FFP_TIER','FLIGHT_COUNT','LAST_TO_END',
                  'SEG_KM_SUM','EXCHANGE_COUNT','Points_Sum']]
age1 = data['AGE'].fillna(0)
data_corr['AGE'] = age1.astype('int64')
data_corr['ffp_year'] = ffp_year

#计算相关性矩阵
dt_corr = data_corr.corr(method = 'pearson')
print('相关性矩阵为:\n',dt_corr)

#绘制热力图
import seaborn as sns
plt.subplots(figsize=(10,10))
sns.heatmap(dt_corr,annot=True,vmax=1,square=True,cmap='Blues')
plt.show()
plt.close

#代码7-6 清洗空值与异常值
import numpy as np
import pandas as pd
​
datafile = 'data3/air_data.csv'
cleanedfile = 'data3/data_cleaned.csv'
​
airline_data = pd.read_csv(datafile,encoding = 'utf-8')
print('原始数据的形状为:', airline_data.shape)
​
#去除票价为空的记录
airline_notnull = airline_data.loc[airline_data['SUM_YR_1'].notnull() & 
                                   airline_data['SUM_YR_2'].notnull(),:]
print('删除缺失记录后数据的形状为:',airline_notnull.shape)
​
#只保留票价非零的，或者平均折扣率不为0且总飞行公里数大于0的记录
index1 = airline_notnull['SUM_YR_1'] != 0
index2 = airline_notnull['SUM_YR_2'] != 0
index3 = (airline_notnull['SEG_KM_SUM'] > 0) & (airline_notnull['avg_discount'] != 0)
index4 = airline_notnull['AGE'] > 100   #去除年龄>100的记录
airline = airline_notnull[(index1 | index2) & index3 & ~index4]
print('数据清洗后数据的形状为:',airline.shape)
​
airline.to_csv(cleanedfile)

#7-7
import numpy as np
import pandas as pd

cleanedfile = 'data3/data_cleaned.csv'
airline = pd.read_csv(cleanedfile,encoding = 'utf-8')
#选取需求属性
airline_selection = airline[['FFP_DATE','LOAD_TIME','LAST_TO_END',
                             'FLIGHT_COUNT','SEG_KM_SUM','avg_discount']]
print('筛选的属性前5行为:\n',airline_selection.head())

#7-8
import pandas as pd
L=pd.to_datetime(airline_selection['LOAD_TIME'])-pd.to_datetime(airline_selection['FFP_DATE'])
L=L.astype('str').str.split().str[0]
L=L.astype('int')/30

airline_features=pd.concat([L,airline_selection.iloc[:,2:]],axis=1)
print('3107构建的LRFMC属性前5行为：\n',airline_features.head())

from sklearn.preprocessing import StandardScaler
airline_features.columns = airline_features.columns.astype(str)
data=StandardScaler().fit_transform(airline_features)
np.savez('data3/airline_scale.npz',data)
print('3107标准化后LRFMC 5个属性为：\n',data[:5,:])

#7-9
import pandas as pd
import numpy as np
from sklearn.cluster import KMeans

airline_scale=np.load('data3/airline_scale.npz')['arr_0']
k=5

kmeans_model=KMeans(n_clusters=k,random_state=123)
fit_kmeans=kmeans_model.fit(airline_scale)

kmeans_cc=kmeans_model.cluster_centers_
print('3107各类聚类中心为：\n',kmeans_cc)
kmeans_labels=kmeans_model.labels_
print('各样本的类别标签为：\n',kmeans_labels)
r1=pd.Series(kmeans_model.labels_).value_counts()
print('最终每个类别的数目为：\n',r1)

cluster_center=pd.DataFrame(kmeans_model.cluster_centers_,columns=['ZL','ZR','ZF','ZM','ZC'])
cluster_center.index=pd.DataFrame(kmeans_model.labels_).drop_duplicates().iloc[:,0]
print(cluster_center)

#7-10
%matplotlib inline
import matplotlib.pyplot as plt
labels=['ZL','ZR','ZF','ZM','ZC']
legen=['客户群'+str(i+1) for i in cluster_center.index]
lstype=['-','--',(0,(3,5,1,5,1,5)),':','-.']
kinds=list(cluster_center.iloc[:,0])
cluster_center=pd.concat([cluster_center,cluster_center[['ZL']]],axis=1)
centers=np.array(cluster_center.iloc[:,0:])
n=len(labels)
angle=np.linspace(0,2*np.pi,n,endpoint=False)
angle=np.concatenate((angle,[angle[0]]))

fig=plt.figure(figsize=(8,6))
ax=fig.add_subplot(111,polar=True)
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False

for i in range(len(kinds)):
    ax.plot(angle,centers[i],linestyle=lstype[i],linewidth=2,label=kinds[i])
#ax.set_thetagrids(angle*180/np.pi,labels)
plt.title('3107客户特征分析雷达图')
plt.legend(legen)
plt.show()
plt.close

#客户流失分析
import pandas as pd

input_file = 'data3/data_cleaned.csv'
output_file = 'data3/selected.xls'
data = pd.read_csv(input_file)
#选取特征
data['单位里程票价'] = (data['SUM_YR_1'] + data['SUM_YR_2'])/data['SEG_KM_SUM']
data['单位里程积分'] = (data['P1Y_BP_SUM'] + data['L1Y_BP_SUM'])/data['SEG_KM_SUM']
data['飞行次数比例'] = data['L1Y_Flight_Count'] / data['P1Y_Flight_Count'] #第二年飞行次数与第一年飞行次数的比例

data = data[data['FLIGHT_COUNT'] > 6]  #筛选出老客户(飞行次数大于6次的为老客户)
#选择特征
data = data[['FFP_TIER','飞行次数比例','AVG_INTERVAL','avg_discount','EXCHANGE_COUNT',
             'Eli_Add_Point_Sum','单位里程票价','单位里程积分']]

data.to_excel(output_file,index=None)

import pandas as pd
input_file = 'data3/selected.xls'
output_file = 'data3/classfication.xls'
data = pd.read_excel(input_file)
data['客户类型'] = None
for i in range(len(data)):
    if data['飞行次数比例'][i] < 0.5:
        data['客户类型'][i] = 0 #0代表已流失
    if (data['飞行次数比例'][i] >= 0.5) & (data['飞行次数比例'][i] < 0.9) : 
        data['客户类型'][i] = 1 #1代表准流失 
    if data['飞行次数比例'][i] >= 0.9:
        data['客户类型'][i] = 2 #2代表未流失
#导出
data.to_excel(output_file,index=None)

import pandas as pd

input_file = 'data3/classfication.xls'
output_file = 'data3/std.xls'
data = pd.read_excel(input_file)

#去掉飞行次数比例
data = data[['FFP_TIER','AVG_INTERVAL','avg_discount','EXCHANGE_COUNT',
             'Eli_Add_Point_Sum','单位里程票价','单位里程积分','客户类型']]

#标准化
data.loc[:,:'单位里程积分'] = (data.loc[:,:'单位里程积分'] - data.loc[:,:'单位里程积分'].mean(axis = 0)) \
/ (data.loc[:,:'单位里程积分'].std(axis = 0))

data.to_excel(output_file,index=None)

import matplotlib.pyplot as plt
datafile='data3/std.xls'
data=pd.read_excel(datafile)

ls=pd.value_counts(data['客户类型'])[0]
zls=pd.value_counts(data['客户类型'])[1]
wls=pd.value_counts(data['客户类型'])[2]

fig=plt.figure(figsize=(7,4))
plt.rcParams['font.sans-serif']='SimHei'
plt.rcParams['axes.unicode_minus']=False
plt.pie([ls,zls,wls],labels=['0','1','2'],colors=['lightskyblue','lightcoral','lightgreen'],autopct='%1.1f',shadow=True)
plt.title('客户流失准流失未流失的比例3107')
plt.show()
plt.close

标签：数据分析,plt,pd,python,labels,airline,第七章,import,data
From： https://www.cnblogs.com/pcr-2020310143107/p/17209803.html