数据分析第七章实践

import pandas as pd
datafile='C:/Users/Lenore/Desktop/data/air_data.csv'
resultfile='C:/Users/Lenore/Desktop/data/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)

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']
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('各年份会员入会人数_3042')
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))  #设置画布大小
plt.pie([male, female], labels=['男', '女'], colors=['lightskyblue', 'lightcoral'], autopct='%1.1f%%')
plt.title('会员性别比例_3042')
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))  #设置画布大小
plt.bar(range(3), [lv_four, lv_five, lv_six], width=0.4, alpha=0.8, color='skyblue')
#left：x轴的位置序列，一般采用arange函数产生一个序列；
#height：y轴的数值序列，也就是柱形图的高度，一般就是我们需要展示的数据；
#alpha：透明度
#width：为柱形图的宽度，一般这是为0.8即可；
#color或facecolor：柱形图填充的颜色；
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_3042')
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'], boxprops={'facecolor': 'lightblue'}) #设置填充颜色
plt.title('会员年龄分布箱型图_3042')
#显示y坐标轴的底线
plt.grid(axis='y')
plt.show()
plt.close()

 

 

 

 

 

 

 

 

lte = data['LAST_TO_END']
fc = data['FLIGHT_COUNT']
skc = data['SEG_KM_SUM']
#绘制最后乘机至结束时长箱型图
fig = plt.figure(figsize=(5, 8))
plt.boxplot(lte, patch_artist=True, labels=['时长'], boxprops={'facecolor': 'lightblue'})
plt.title('会员最后乘机至结束时长分布箱型图_3042')
plt.grid(axis='y')
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'], boxprops={'facecolor': 'lightblue'})
plt.title('会员飞行次数分布箱型图_3042')
plt.grid(axis='y')
plt.show()
plt.close()

#绘制客户总飞行公里数箱型图
fig = plt.figure(figsize=(5, 10))
plt.boxplot(skc, patch_artist=True, labels=['总飞行公里数'], boxprops={'facecolor': 'lightblue'})
plt.title('客户总飞行公里数箱型图_3042')
plt.grid(axis='y')
plt.show()
plt.close()

 

 

 

 

 

 

#积分信息类别
#提取会员积分兑换次数
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('会员兑换积分次数分布直方图_3042')
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'], boxprops={'facecolor': 'lightblue'})
plt.title('客户总累计积分箱型图_3042')
plt.grid(axis='y')
plt.show()
plt.close()

 

 

 

 

#提取属性并合并为新数据集
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_3042：\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.title('热力图_3042')
plt.show()
plt.close

 

 

 

 

import numpy as np
import pandas as pd

datafile = 'C:/Users/Lenore/Desktop/data/air_data.csv'  #原始数据路径
cleanedfile = 'C:/Users/Lenore/Desktop/data/data_cleaned.csv'  #数据清洗后的保存路径

airline_data = pd.read_csv(datafile, encoding='utf-8')
print('原始数据的形状_3042：', 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_3042：', airline_notnull.shape)
#只保留票价非零的，或者平均折扣率不为0且与总飞行公里数大于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('经过清洗后的数据的形状为_3042：', airline.shape)

airline.to_csv(cleanedfile)  #保存清洗后的数据

 

 

import pandas as pd
import numpy as np
#读取清洗后的数据
cleanedfile = 'C:/Users/Lenore/Desktop/data/data_cleaned.csv'  #数据清洗后的保存路径
airline = pd.read_csv(cleanedfile, encoding='utf-8')
#选取需求属性
airline_selection = airline[['LOAD_TIME','FFP_DATE','LAST_TO_END','FLIGHT_COUNT','SEG_KM_SUM','avg_discount']]
print('筛选的属性前5行为_3042：')
airline_selection.head()

 

 

#构造属性
from datetime import datetime

airline_selection['L1'] = pd.to_datetime(airline_selection['LOAD_TIME']) - pd.to_datetime(airline_selection['FFP_DATE'])
L = []
for i in airline_selection['L1']:
    a = int(str(i)[:4])/30
    L.append(a)
airline_selection['L'] = L
airline_selection.drop('L1', axis=1, inplace =True) # 删除中间变量
airline_selection.drop(airline_selection.columns[:2], axis=1, inplace =True) # 去掉不需要的u'LOAD_TIME', u'FFP_DATE'
airline_selection.rename(columns={'LAST_TO_END':'R','FLIGHT_COUNT':'F','SEG_KM_SUM':'M','avg_discount':'C'},inplace=True)
airline_selection.head()

#查看5个指标的取值范围
def f(x):
    return pd.Series([x.min(),x.max()], index=['min','max'])
d = airline_selection.apply(f)

# 5个指标的取值范围数据差异较大，为了消除数量级数据带来的影响，需要对数据进行标准化处理
from sklearn.preprocessing import StandardScaler
data = StandardScaler().fit_transform(airline_selection)
data = pd.DataFrame(data)
data.columns = ['Z' + i for i in airline_selection.columns]
data =data.iloc[:,[4,0,1,2,3]]   # 列进行排序
np.savez('C:/Users/Lenore/Desktop/data/airline_scale.npz',data)
data.head()

 

 

import pandas as pd
import numpy as np
from sklearn.cluster import KMeans

#读取标准化后的数据
airline_scale = np.load('C:/Users/Lenore/Desktop/data/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树木
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)

 

 

%matplotlib inline
import matplotlib.pyplot as plt

# 客户分群雷达图
labels = ['ZL','ZR','ZF','ZM','ZC']
legen = ['客户群' + str(i + 1) for i in cluster_center.index] # 客户群命名
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
plt.title('客户特征分析雷达图_3042')
plt.legend(legen)
plt.show()
plt.close