import numpy as np import pandas as pd import matplotlib.pyplot as plt import seaborn as sns %matplotlib inline

air_data_path = 'air_data.csv' # 读取原始数据，指定UTF-8编码 air_data = pd.read_csv(air_data_path,encoding='utf-8') # 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 = air_data.describe(percentiles=[],include='all').T # describe()函数自动计算非空值数，需要手动计算空值数 explore['null'] = len(air_data)-explore['count'] explore = explore[['null', 'max', 'min']] # # 表头重命名 explore.columns = [u'空值数', u'最大值', u'最小值'] explore

from datetime import datetime # 提取入会年份,apply将一个函数作用于DataFrame中的每个行或者列 ffp = air_data['FFP_DATE'].apply(lambda x:datetime.strptime(x,'%Y/%m/%d')) # map应用于Series结构中的每个元素 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.hist(ffp_year, bins='auto', color='#0504aa') plt.xlabel('年份') plt.ylabel('入会人数') plt.title('各年份会员入会人数')

# 提取会员不同性别人数 male = pd.value_counts(air_data['GENDER'])['男'] female = pd.value_counts(air_data['GENDER'])['女'] fig = plt.figure(figsize=(7,4)) # autopct 控制饼图内百分比设置 plt.pie([male,female],labels=['男','女'], colors=['lightskyblue', 'lightcoral'], autopct='%1.1f%%') plt.title('会员性别比例')

lv_four = pd.value_counts(air_data['FFP_TIER'])[4] lv_five = pd.value_counts(air_data['FFP_TIER'])[5] lv_six = pd.value_counts(air_data['FFP_TIER'])[6] fig = plt.figure(figsize = (8 ,5)) plt.bar(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('会员各级别人数')

age = air_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('会员年龄分布箱线图') # 显示y坐标轴的底线 plt.grid(axis='y')

# 乘机信息类别 lte = air_data['LAST_TO_END'] fc = air_data['FLIGHT_COUNT'] sks = air_data['SEG_KM_SUM'] 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('会员最后乘机至结束时长分布箱线图') # 显示y坐标轴的底线 plt.grid(axis='y')

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('会员飞行次数分布箱线图') # 显示y坐标轴的底线 plt.grid(axis='y')

fig = plt.figure(figsize = (5 ,10)) 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('客户总飞行公里数箱线图') # 显示y坐标轴的底线 plt.grid(axis='y')

# 提取会员积分兑换次数 ec = air_data['EXCHANGE_COUNT'] fig = plt.figure(figsize = (8 ,5)) # 设置画布大小 plt.hist(ec, bins=5, color='#0504aa') plt.xlabel('兑换次数') plt.ylabel('会员人数') plt.title('会员兑换积分次数分布直方图')

# 提取会员总累计积分 ps = air_data['Points_Sum'] 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('客户总累计积分箱线图') # 显示y坐标轴的底线 plt.grid(axis='y')

# 提取属性并合并为新数据集 data_corr = air_data[['FFP_TIER','FLIGHT_COUNT','LAST_TO_END', 'SEG_KM_SUM','EXCHANGE_COUNT','Points_Sum']] # 填充age age1 = air_data['AGE'].fillna(0) data_corr.loc[:,'AGE'] = age1.astype('int64') data_corr.loc[:,'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 plt.subplots(figsize=(10, 10)) sns.heatmap(dt_corr, annot=True, vmax=1, square=True, cmap='Blues')

cleanedfile = './data_cleaned.csv' # 数据清洗后保存的文件路径 # 读取数据 airline_data = pd.read_csv(air_data_path,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 # 去除年龄大于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) # 保存清洗后的数据

# 读取数据清洗后的数据 cleanedfile = './data_cleaned.csv' # 数据清洗后保存的文件路径 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())

# 构造属性L 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 # 合并属性 airline_features = pd.concat([L,airline_selection.iloc[:,2:]],axis = 1) airline_features.columns = ['L','R','F','M','C'] 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('./airline_scale.npz',data) print('标准化后LRFMC五个属性为：\n',data[:5,:])

from sklearn.cluster import KMeans # 导入kmeans算法 # 读取标准化后的数据 airline_scale = np.load('./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,n_jobs=4,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)

# 客户分群雷达图 labels = ['ZL','ZR','ZF','ZM','ZC'] legen = [' customers' + 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 ax.set_thetagrids(angle * 180 / np.pi, labels) plt.title('Customer Profile Analysis') plt.legend(legen)