# 读入MySQL数据库数据
# 导入第三方模块
import pymysql

# 连接MySQL数据库
conn = pymysql.connect(host=‘localhost‘, user=‘root‘, password=‘test‘, 
                       database=‘test‘, port=3306, charset=‘utf8‘)
# 读取数据
user = pd.read_sql(‘select * from topy‘, conn)
# 关闭连接
conn.close()
# 数据输出
User

# 数据读取
sec_cars = pd.read_table(r‘C:UsersAdministratorDesktopsec_cars.csv‘, sep = ‘,‘)
# 预览数据的前五行
sec_cars.head()

# 查看数据的行列数
print(‘数据集的行列数：
‘,sec_cars.shape)

# 查看数据集每个变量的数据类型
print(‘各变量的数据类型：
‘,sec_cars.dtypes)

# 数据的描述性统计
sec_cars.describe()

# 数据读入
df = pd.read_excel(r‘C:UsersAdministratorDesktopdata_test05.xlsx‘)
# 缺失观测的检测
print(‘数据集中是否存在缺失值：
‘,any(df.isnull()))

# 删除法之记录删除
df.dropna()
# 删除法之变量删除
df.drop(‘age‘, axis = 1)

# 替换法之前向替换
df.fillna(method = ‘ffill‘)
# 替换法之后向替换
df.fillna(method = ‘bfill‘)

# 替换法之常数替换
df.fillna(value = 0)
# 替换法之统计值替换
df.fillna(value = {‘gender‘:df.gender.mode()[0], ‘age‘:df.age.mean(),     
                   ‘income‘:df.income.median()})

# 数据读入
df = pd.read_excel(r‘C:UsersAdministratorDesktopdata_test03.xlsx‘)

# 将birthday变量转换为日期型
df.birthday = pd.to_datetime(df.birthday, format = ‘%Y/%m/%d‘)

# 将手机号转换为字符串
df.tel = df.tel.astype(‘str‘)

# 新增年龄和工龄两列
df[‘age‘] = pd.datetime.today().year - df.birthday.dt.year
df[‘workage‘] = pd.datetime.today().year - df.start_work.dt.year

# 将手机号中间四位隐藏起来
df.tel = df.tel.apply(func = lambda x : x.replace(x[3:7], ‘****‘))
# 取出邮箱的域名
df[‘email_domain‘] = df.email.apply(func = lambda x : x.split(‘@‘)[1])

# 取出人员的专业信息
df[‘profession‘] = df.other.str.findall(‘专业：(.*?)，‘)
# 去除birthday、start_work和other变量
df.drop([‘birthday‘,‘start_work‘,‘other‘], axis = 1, inplace = True)

# 构造数据集df1和df2
df1 = pd.DataFrame({‘name‘:[‘张三‘,‘李四‘,‘王二‘], ‘age‘:[21,25,22], 
                  ‘gender‘:[‘男‘,‘女‘,‘男‘]})
df2 = pd.DataFrame({‘name‘:[‘丁一‘,‘赵五‘], ‘age‘:[23,22], ‘gender‘:[‘女‘,‘女‘]})
# 数据集的纵向合并
pd.concat([df1,df2] , keys = [‘df1‘,‘df2‘])

# 如果df2数据集中的“姓名变量为Name”
df2 = pd.DataFrame({‘Name‘:[‘丁一‘,‘赵五‘], ‘age‘:[23,22], ‘gender‘:[‘女‘,‘女‘]})
# 数据集的纵向合并
pd.concat([df1,df2])

# 构造数据集
df3 = pd.DataFrame({‘id‘:[1,2,3,4,5],‘name‘:[‘张三‘,‘李四‘,‘王二‘,‘丁一‘,‘赵五‘],
                  ‘age‘:[27,24,25,23,25],‘gender‘:[‘男‘,‘男‘,‘男‘,‘女‘,‘女‘]})
df4 = pd.DataFrame({‘Id‘:[1,2,2,4,4,4,5], ‘score‘:[83,81,87,75,86,74,88]
                  ‘kemu‘:[‘科目1‘,‘科目1‘,‘科目2‘,‘科目1‘,‘科目2‘,‘科目3‘,‘科目1‘]})
df5 = pd.DataFrame({‘id‘:[1,3,5],‘name‘:[‘张三‘,‘王二‘,‘赵五‘],
                  ‘income‘:[13500,18000,15000]})
# 三表的数据连接
# 首先df3和df4连接
merge1 = pd.merge(left = df3, right = df4, how = ‘left‘, left_on=‘id‘, right_on=‘Id‘)
merge1
# 再将连接结果与df5连接
merge2 = pd.merge(left = merge1, right = df5, how = ‘left‘)
merge2