数据分析第三次作业

#7-1对数据进行基本的探索
#返回缺失值个数以及最大、最小值
import pandas as pd
datafile="D:/数据分析/air_data.csv"
resultfile="D:/数据分析/explore.csv"
data=pd.read_csv(datafile,encoding='utf-8')
explore=data.describe(percentiles=[],include='all').T
explore['null']=len(data)-explore['count']
explore=explore[['null','max','min']]
explore.columns=[u'空值数',u'最大值',u'最小值']
explore.to_csv(resultfile)

#7-2探索客户的基本信息分布情况
from datetime import datetime
import matplotlib.pyplot as plt
ffp=data['FFP_DATE'].apply(lambda x:datetime.strptime(x,'%Y/%m/%d'))
ffp_year=ffp.map(lambda x:x.year)

fig=plt.figure(figsize=(8,5))
plt.rcParams['font.sans-serif']='SimHei'
plt.rcParams['axes.unicode_minus']=False
plt.hist(ffp_year,bins='auto',color='#0504aa')
plt.xlabel('年份')
plt.ylabel('入会人数')
plt.title('学号3108各年份会员入会人数')
plt.show()
plt.close


male=pd.value_counts(data['GENDER'])['男']
female=pd.value_counts(data['GENDER'])['女']

fig=plt.figure(figsize=(7,4))
plt.pie([male,female],labels=['男','女'],colors=['lightskyblue','lightcoral'],autopct='%1.1f%%')
plt.title('学号3108会员性别比例')
plt.show()
plt.close


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]

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('学号3108会员各级别人数')
plt.show()
plt.close()

age=data['AGE'].dropna()
age=age.astype('int64')

fig=plt.figure(figsize=(5,10))
plt.boxplot(age,
            patch_artist=True,
            labels=['会员年龄'],
            boxprops={'facecolor':'lightblue'})
plt.title('学号3108会员年龄分布箱型图')
plt.grid(axis='y')
plt.show()
plt.close

 

 

 

 

 

 

 

 

 

 

#7-3
lte=data['LAST_TO_END']
fc=data['FLIGHT_COUNT']
sks=data['SEG_KM_SUM']

fig=plt.figure(figsize=(5,8))

plt.boxplot(lte,
            patch_artist=True,
            labels=['时长'],
            boxprops={'facecolor':'lightblue'})
plt.title('学号3108会员最后乘机至结束时长分布箱型图')
plt.grid(axis='y')
plt.show()
plt.close

fig=plt.figure(figsize=(5,8))
plt.boxplot(fc,
            patch_artist=True,
            labels=['飞行次数'],
            boxprops={'facecolor':'lightblue'})
plt.title('学号3108会员飞行次数分布箱型图')
plt.grid(axis='y')
plt.show()
plt.close

fig=plt.figure(figsize=(5,10))
plt.boxplot(sks,
            patch_artist=True,
            labels=['总飞行公里数'],
            boxprops={'facecolor':'lightblue'})
plt.title('学号3108客户总飞行公里数箱型图')
plt.grid(axis='y')
plt.show()
plt.close

 

 

 

 

 

 

#7-4
ec=data['EXCHANGE_COUNT']
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('学号3108会员兑换积分次数分布直方图')
plt.show()
plt.close

ps=data['Points_Sum']
fig=plt.figure(figsize=(5,8))
plt.boxplot(ps,
            patch_artist=True,
            labels=['总累计积分'],
            boxprops={'facecolor':'lightblue'})
plt.title('学号3108客户总累计积分箱型图')
plt.grid(axis='y')
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

dt_corr=data_corr.corr(method='pearson')
print('学号3108相关性矩阵为：\n',dt_corr)

import seaborn as sns
plt.subplots(figsize=(10,10))
sns.heatmap(dt_corr,annot=True,vmax=1,square=True,cmap='Blues')
plt.title('学号3108')
plt.show()
plt.close

 

 

 

 

#7-6
import numpy as np
import pandas as pd

datafile="D:/数据分析/air_data.csv"
cleanedfile="D:/数据分析/data_cleaned.csv"

airline_data=pd.read_csv(datafile,encoding='utf-8')
print('3108原始数据的形状为：',airline_data.shape)

airline_notnull=airline_data.loc[airline_data['SUM_YR_1'].notnull()&
                                 airline_data['SUM_YR_2'].notnull(),:]
print('3108删除缺失记录后数据的形状为：',airline_notnull.shape)

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
airline=airline_notnull[(index1|index2)&index3&~index4]
print('3108数据清洗后数据的形状为：',airline.shape)
airline.to_csv(cleanedfile)

 

 

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

cleanedfile="D:\数据分析\data_cleaned.csv"
airline=pd.read_csv(cleanedfile,encoding='utf-8')
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构造属性工
L= pd.to_datetime(airline_selection['LOAD_TIME']) - \
   pd.to_datetime(airline_selection['FFP_DATE'])
L= L.astype('str').str.split().str[0]
I= L.astype('int')/30
#合并属性
airline_features = pd.concat([L,airline_selection.iloc[:,2:]],axis=1)
print('构建的LRFMC属性前5行为:\n',airline_features.head())
# 数据标准化
from sklearn.preprocessing import StandardScaler
data = StandardScaler().fit_transform(airline_features)
np.savez('D:/数据分析/airline_scale.npz',data)
print('标准化后LREMC 5个属性为:\n',data[:5,:])

 

 

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

# 读取标准化后的数据
airline_scale = np.load('D:/数据分析/airline_scale.npz')['arr_0']
k = 5  # 确定聚类中心数

# 构建模型，随机种子设为123
kmeans_model = KMeans(n_clusters = k,random_state=123)
fit_kmeans = kmeans_model.fit(airline_scale)  # 模型训练

# 查看聚类结果
kmeans_cc = kmeans_model.cluster_centers_  # 聚类中心
print('各类聚类中心为：\n',kmeans_cc)
kmeans_labels = kmeans_model.labels_  # 样本的类别标签
print('各样本的类别标签为：\n',kmeans_labels)
r1 = pd.Series(kmeans_model.labels_).value_counts()  # 统计不同类别样本的数目
print('最终每个类别的数目为：\n',r1)
# 输出聚类分群的结果
cluster_center = pd.DataFrame(kmeans_model.cluster_centers_,\
             columns = ['ZL','ZR','ZF','ZM','ZC'])   # 将聚类中心放在数据框中
cluster_center.index = pd.DataFrame(kmeans_model.labels_ ).\
                  drop_duplicates().iloc[:,0]  # 将样本类别作为数据框索引
print(cluster_center)

 

 

# 7-10客户分群雷达图
import matplotlib.pyplot as plt
labels = ['ZL','ZR','ZF','ZM','ZC']

legen = [' 客户群' + str(i + 1) for i in cluster_center.index]  # 客户群命名，作为雷达图的图例
lstype = ['-','--',(0, (3, 5, 1, 5, 1, 5)),':','-.']
kinds = list(cluster_center.iloc[:, 0])
# 由于雷达图要保证数据闭合，因此再添加L列，并转换为 np.ndarray
cluster_center = pd.concat([cluster_center, cluster_center[['ZL']]], axis=1)
centers = np.array(cluster_center.iloc[:, 0:])

# 分割圆周长，并让其闭合
n = len(labels)
angle = np.linspace(0, 2 * np.pi, n, endpoint=False)
angle = np.concatenate((angle, [angle[0]]))

# 绘图
fig = plt.figure(figsize = (8,6))
ax = fig.add_subplot(111, polar=True)  # 以极坐标的形式绘制图形
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号 
# 画线
for i in range(len(kinds)):
    ax.plot(angle, centers[i], linestyle=lstype[i], linewidth=2, label=kinds[i])
# 添加属性标签
labels = labels.append(pd.Index(labels)) #添加多 第一个标签
ax.set_thetagrids(angle * 180 / np.pi, labels)

plt.title('学号3108客户特征分析雷达图')
plt.legend(legen)
plt.show()
plt.close