py，时间模块

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
# -*- coding: utf-8 -*-
"""
Created on Wed Dec 15 20:51:04 2021

@author: 62669
"""
# In[1]:
import pandas as pd
import datetime
import re
import numpy as np
from presto_cli import presto_client
import win32com.client as win32
import time as tm
from datetime import datetime
import datetime
#处理工作中遇到的
# In[1]:

#字段类型转换问题
wo['放款时效'] = wo['放款时效'].astype('float64')
wo['give_time'] = pd.to_datetime(wo['give_time'],format='%Y-%m-%d',errors='coerce')

#日期格式处理问题
today = datetime.date.today()
current_month_first= today.replace(day=1)
last_month_last = current_month_first - datetime.timedelta(days=1)
last_month_first = last_month_last.replace(day=1)
print(last_month_first.strftime("%Y-%m"))

def make_week(dt):
    if dt.day <= 7 :
        rn = str(dt.year) + str(dt.month) + '第1周'
    elif dt.day >7 and dt.day<=14:
        rn = str(dt.year) + str(dt.month) + '第2周'
    elif dt.day >14 and dt.day<=21:
        rn = str(dt.year) + str(dt.month) + '第3周'
    else :
        rn = str(dt.year) + str(dt.month) + '第4周'
    return rn
wo['give_time_day'] = wo['give_time'].map(lambda x:x.date())
wo['give_time_month'] =wo['give_time'].map(lambda x:x.date().replace(day=1))  
#wo['give_time'] =xs[i].map(lambda x:x.date()).map(make_week)

#groupby问题
wo["fk_shixiao_0"] = wo['放款时效'].apply( lambda x: 1 if x<=0.5  else 0 )
wo3 = wo.groupby(['give_time_month'])['fk_shixiao_0'].mean().reset_index()
tmp1 = xs.groupby([col_2])['shenhe_shixiao'].quantile(0.5).reset_index()

#merge问题
fk = pd.merge(fk,wo4,how='left',left_on=['give_time_month'],right_on=['give_time_month'])  


import numpy as np
import pandas as pd
import datetime

today = datetime.date.today()
type(today)
a=str(today)

now = datetime.datetime.now()
print(type(now))

t1 = datetime.datetime(2019,10,22)

t2 = datetime.datetime(2019,10,22,11,45,36)

t2-t1

print( t2-t1 )

tx = datetime.timedelta(100)

print(t2-tx)

from dateutil.parser import parse

date ='20170501'
date2 ='21/12/2019'

print(parse(date),type(parse(date)))

########pandas timestamp

date2 ='21/12/2019'
t1 = pd.Timestamp(date2)

t2 = pd.to_datetime(date2)

date3 =['21/12/2019','22/12/2019','23/12/2019','aa']
a = pd.to_datetime(date3,errors='ignore')
print(pd.to_datetime(date3,errors='ignore'))
print(pd.to_datetime(date3,errors='coerce'))
print(pd.to_datetime(date3,errors='ignore'))


ex = pd.date_range('2000-1-1', periods=1000, freq='M')
print(ex)

ex.date

#6字符串转换成datetime格式: strptime
df_data1  = pd.DataFrame(columns=['date','values'])
df_data1['date'] = ['2019-01-01','2019-01-02','2019-01-03','2019-01-04','2019-01-05']
df_data1['values'] = np.random.randn(5)

type(df_data1['date'][2])

df_data1['date1'] = df_data1['date'].map(lambda x:datetime.datetime.strptime(x,'%Y-%m-%d'))
df_data1
df_data1.info()

#6datetime变回string格式: strftime
df_data  = pd.DataFrame(columns=['date','values'])
df_data['date'] = pd.date_range('2019/01/01',periods=5)
df_data['values'] = np.random.randn(5)
df_data

df_data.info()

df_data['date1'] = df_data['date'].apply(lambda x:x.strftime('%Y-%m')) #datetime格式转成str




# -*- coding: utf-8 -*-
"""
Created on Thu Feb 11 11:55:42 2021

@author: 62669
"""
import pandas as pd
import numpy as np

pt = r'F:a_houdashi_workbbb_python学习pandas操作清洗1.xlsx'
t = pd.read_excel(pt,skiprows=1)

t.isnull()
t['分数'].isnull()

t.head()

t.dropna(axis="columns",how="all",inplace=True)
t.dropna(axis="index",how="all",inplace=True)

t.fillna({'分数':0})
t.loc[:,'分数'] = t['分数'].fillna(0)
t['分数'] = t['分数'].fillna(0)

t.loc[:,'姓名'] = t['姓名'].fillna(method='ffill')
t['姓名'] = t['姓名'].fillna(method='ffill')

#设置筛选条件
con= t['姓名']=='小明' 

t.loc[con,'新分数']=t['分数']*2
t[con].head()

tt = t[con].copy()
tt['新分数']=tt['分数']*2

#排序
t['分数'].sort_values()

t.sort_values(by=['分数'],ascending=False)
t.sort_values(by=['分数'],ascending=True)
t.sort_values(by=['分数','姓名'],ascending=True)