第三周

标签：plt 第三周 会员 airline pd csv data

import pandas as pd

datafile= 'air_data.csv'  # 航空原始数据,第一行为属性标签
resultfile = 'explore.csv'  # 数据探索结果表

data = pd.read_csv(datafile,encoding='utf-8')

# 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  # T是转置，转置后更方便查阅
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 = ['null', 'max', 'min']  # 表头重命名


explore.to_csv(resultfile)  # 导出结果

 

import pandas as pd
import matplotlib.pyplot as plt 

datafile= 'air_data.csv'  # 航空原始数据,第一行为属性标签

# 读取原始数据，指定UTF-8编码（需要用文本编辑器将数据装换为UTF-8编码）
data = pd.read_csv(datafile, encoding = 'utf-8')
explore = data.describe(percentiles = [], include = 'all').T  # T是转置，转置后更方便查阅
print(explore)

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
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3145')
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3145')
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(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('会员各级别人数3145')
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('会员年龄分布箱线图3145')
# 显示y坐标轴的底线
plt.grid(axis='y')
plt.show()
plt.close

 

 

# 乘机信息类别
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箱线图
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('会员最后乘机至结束时长分布箱线图3145')
# 显示y坐标轴的底线
plt.grid(axis='y')
plt.show()
plt.close

# 绘制客户飞行次数箱线图
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('会员飞行次数分布箱线图3145')
# 显示y坐标轴的底线
plt.grid(axis='y')
plt.show()
plt.close

# 绘制客户总飞行公里数箱线图
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3145')
# 显示y坐标轴的底线
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))  # 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3145')
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线图
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('客户总累计积分箱线图3145')
# 显示y坐标轴的底线
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('相关性矩阵为：\n',dt_corr)

# 绘制热力图
import seaborn as sns
plt.subplots(figsize=(10, 10)) # 设置画面大小 
sns.heatmap(dt_corr, annot=True, vmax=1, square=True, cmap='Blues') 
plt.title('相关性热力图3145')
plt.show()
plt.close

import numpy as np
import pandas as pd

datafile = 'air_data.csv'  # 航空原始数据路径
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(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

 

 

二、电信用户分类

 

 

import pandas as pd

data=pd.read_csv('WA_Fn-UseC_-Telco-Customer-Churn.csv')
#设置显示所有的列
pd.set_option('display.max_columns',None)
#设置显示所有的行
data.head()
data.info()
data.columns=['用户ID','性别','老年人' ,'是否有配偶' ,'是否经济独立' ,'客户的入网时间','是否开通电话服务业务' ,'是否开通了多线业务'
,'是否开通互联网服务' ,'是否开通网络安全服务','是否开通在线备份业务','是否开通了设备保护业务','是否开通了技术支持服务','是否开通网络电视'
,'是否开通网络电影','签订合同年限' ,'是否开通电子账单','付款方式','月费用','总费用','该用户是否流失']
data.head()
data['总费用'].value_counts()
for i in data.columns:
    test=data[i].value_counts()
    print('[{0}行数是：{1}'.format(i,test.sum()))
    print('[{0}内容是：\n{1}\n'.format(i,test))
data['总费用']=data['总费用'].apply(pd.to_numeric, errors="coerce")
data[data['总费用'].isnull()][['客户的入网时间','总费用']]
data['总费用'].fillna(data[data['总费用'].isnull()]['月费用'],axis=0,inplace=True)
data['客户的入网时间'].replace(to_replace=0,value=1,inplace=True)
data.info()

import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False
plt.pie(data['该用户是否流失'].value_counts(),labels=['未流失','流失'],autopct='%.2f%%',explode=(0.1,0))
plt.title('用户流失占比3145')

 

 

 

import sklearn
model=[DecisionTreeClassifier(random_state=120)  #决策树、随机森林、K近邻、逻辑回归四个模型
      , RandomForestClassifier(random_state=120)
      ,KNeighborsClassifier()
      , LogisticRegression(max_iter=1000)]
for clf in model:
    clf.fit(Xtrain,ytrain)
    y_pre=clf.predict(Xtest)
    precision = precision_score(ytest, y_pre) 
    accuracy = accuracy_score(ytest, y_pre)
    
    print(clf,'\n \n',classification_report(ytest,y_pre)
         ,'\n \n Precision Score:', precision
         ,'\n Accuracy Score::',accuracy
          ,'\n\n')
#运行结果：
DecisionTreeClassifier(ccp_alpha=0.0, class_weight=None, criterion='gini',
                       max_depth=None, max_features=None, max_leaf_nodes=None,
                       min_impurity_decrease=0.0, min_impurity_split=None,
                       min_samples_leaf=1, min_samples_split=2,
                       min_weight_fraction_leaf=0.0, presort='deprecated',
                       random_state=120, splitter='best')

figure,ax=plt.subplots(1,4,figsize=(30,4))
for i in range(4):
train_sizes, train_scores, valid_scores=learning_curve(model[i],over_X,over_y, cv=5,random_state=10)
train_std=train_scores.mean(axis=1)
test_std=valid_scores.mean(axis=1)
ax[i].plot(train_sizes,train_std,color='red',label='train_scores')
ax[i].plot(train_sizes,test_std,color='blue',label='test_scores')
plt.legend()

 

标签：plt,第三周,会员,airline,pd,csv,data
From： https://www.cnblogs.com/lijieying/p/17209188.html