#去重

df = df.drop_duplicates().reset_index(drop=True)

#删除某一列

df2=df2.drop(cols,axis=1)

#删除两行

df.drop(index=[0, 1])

#date转字符串

from datetime import datetime, date, time

d = date.fromisoformat('2018-09-22')

t = time.fromisoformat('16:28:22')

dt = datetime.fromisoformat('2018-09-22')

sdate = pd.to_datetime(ds).strftime('%Y-%m-%d')

st = "2019-01-20 00:00:00"

dt = datetime.datetime.strptime(st, '%Y-%m-%d %H:%M:%S')

st = "2019-01-20"

dt = datetime.datetime.strptime(st, '%Y-%m-%d')

start=pd.to_datetime('2017-01-01')

#修改类型

train['tf_status'] = t1['tf_status'].astype(np.int64)

#修改日期类型

df['ds'] = pd.to_datetime(df['ds'])

#修改字段名

df.rename(columns={'#studentid':'studentid'}, inplace = True)

#加年月

df['year']=df.datetime.apply(lambda x: x.year)

df['month'] = df.datetime.apply(lambda x: x.month)

df['year'] = df['year'].astype(np.int64)

df['month'] = df['month'].astype(np.int64)

#删除字段

df.drop(['#id'], axis=1, inplace=True)

#查看数据中顶部10%的数据

print(df.weeks.quantile(np.arange(.9,1,.01)))

#设置索引

df = df.set_index(['hetongdetailid'])

#判断空值

print("在 cat 列中总共有 %d 个空值." % df['cat'].isnull().sum())

print("在 review 列中总共有 %d 个空值." % df['review'].isnull().sum())

df[df.isnull().values==True]

df = df[pd.notnull(df['review'])]

#排序

df.sort_values(by="x1",ascending= False)

#模糊查询

df_remark_tf[df_remark_tf["content_method"].str.contains(keystring)]

#修改字段类型

df_appraise['deptid'] = df_appraise['deptid'].astype(np.int64)

#修改数据(https://blog.csdn.net/zhangchuang601/article/details/79583551)

df.loc[1,['name','age']] = ['bb',11]

df.iloc[1,2] = 19#修改某一无

df.loc[df[df.htid.isin(ids)].index,"y"]=1

#保存数据库

df.to_sql(name='predict',con=mysql_engine,if_exists = 'replace')

#生成日期

dt = datetime.datetime(year, month, 1)

#查看顶部10%数据分布

print(movie_rating_count['totalRatingCount'].quantile(np.arange(.9,1,.01)))

#-------plotly.express-------------------------

fig = px.line(df, x='date', y='y_true',

labels={'date':'日期', 'y_true':'话务量'},

markers=True)

fig.update_xaxes(tickformat = "%Y-%m-%d", hoverformat = "%Y-%m-%d")

fig.update_layout(title_text="热线部门日业务量趋势图", title_x=0.5)

fig.show()

----------------------------------

1、nohup command &

例如 nohup jupyter notebook &

2、找到进程PID(关闭在前面后台执行的进程的步骤，首先找到其进程PID)

ps -ef | grep xxxx

ps -ef 查看本机所有的进程；grep xxxx代表过滤找到条件xxxx的项目

3、kill掉进程

kill -9 具体的PID