import smtplib
from email import (header)
from email.mime import (text, application, multipart)
import time

def sender_mail():
    smt_p = smtplib.SMTP()
    smt_p.connect(host='smtp.qq.com', port=25)
    sender, password = '[email protected]', "**************"
    smt_p.login(sender, password)
    receiver_addresses, count_num = [
        '[email protected]', '[email protected]'], 1
    for email_address in receiver_addresses:
        try:
            msg = multipart.MIMEMultipart()
            msg['From'] = "zhenguo"
            msg['To'] = email_address
            msg['subject'] = header.Header('这是邮件主题通知', 'utf-8')
            msg.attach(text.MIMEText(
                '这是一封测试邮件，请勿回复本邮件~', 'plain', 'utf-8'))
            smt_p.sendmail(sender, email_address, msg.as_string())
            time.sleep(10)
            print('第%d次发送给%s' % (count_num, email_address))
            count_num = count_num + 1
        except Exception as e:
            print('第%d次给%s发送邮件异常' % (count_num, email_address))
            continue
    smt_p.quit()

sender_mail()

def binarySearch(arr, left, right, x):
    while left <= right:

        mid = int(left + (right - left) / 2); # 找到中间位置。求中点写成(left+right)/2更容易溢出，所以不建议这样写

        # 检查x是否出现在位置mid
        if arr[mid] == x:
            print('found %d 在索引位置%d 处' %(x,mid))
            return mid

            # 假如x更大，则不可能出现在左半部分
        elif arr[mid] < x:
            left = mid + 1 #搜索区间变为[mid+1,right]
            print('区间缩小为[%d,%d]' %(mid+1,right))

        # 同理，假如x更小，则不可能出现在右半部分
        elif x<arr[mid]:
            right = mid - 1 #搜索区间变为[left,mid-1]
            print('区间缩小为[%d,%d]' %(left,mid-1))

    # 假如搜索到这里，表明x未出现在[left,right]中
    return -1

In [8]: binarySearch([4,5,6,7,10,20,100],0,6,5)
区间缩小为[0,2]
found 5 at 1
Out[8]: 1

In [9]: binarySearch([4,5,6,7,10,20,100],0,6,4)
区间缩小为[0,2]
区间缩小为[0,0]
found 4 at 0
Out[9]: 0

In [10]: binarySearch([4,5,6,7,10,20,100],0,6,20)
区间缩小为[4,6]
found 20 at 5
Out[10]: 5

In [11]: binarySearch([4,5,6,7,10,20,100],0,6,100)
区间缩小为[4,6]
区间缩小为[6,6]
found 100 at 6
Out[11]: 6

import requests
from lxml import etree
import pandas as pd
import re

url = 'https://www.weather.com.cn/weather1d/101010100.shtml#input'
with requests.get(url) as res:
    content = res.content
    html = etree.HTML(content)

location = html.xpath('//*[@id="around"]//a[@target="_blank"]/span/text()')
temperature = html.xpath('//*[@id="around"]/div/ul/li/a/i/text()')

['香河', '涿州', '唐山', '沧州', '天津', '廊坊', '太原', '石家庄', '涿鹿', '张家口', '保定', '三河', '北京孔庙', '北京国子监', '中国地质博物馆', '月坛公
园', '明城墙遗址公园', '北京市规划展览馆', '什刹海', '南锣鼓巷', '天坛公园', '北海公园', '景山公园', '北京海洋馆']

['11/-5°C', '14/-5°C', '12/-6°C', '12/-5°C', '11/-1°C', '11/-5°C', '8/-7°C', '13/-2°C', '8/-6°C', '5/-9°C', '14/-6°C', '11/-4°C', '13/-3°C'
, '13/-3°C', '12/-3°C', '12/-3°C', '13/-3°C', '12/-2°C', '12/-3°C', '13/-3°C', '12/-2°C', '12/-2°C', '12/-2°C', '12/-3°C']

df = pd.DataFrame({'location':location, 'temperature':temperature})
print('温度列')
print(df['temperature'])

df['high'] = df['temperature'].apply(lambda x: int(re.match('(-?[0-9]*?)/-?[0-9]*?°C', x).group(1) ) )
df['low'] = df['temperature'].apply(lambda x: int(re.match('-?[0-9]*?/(-?[0-9]*?)°C', x).group(1) ) )
print(df)

m = re.match(r'^(\d{3})-(\d{3,8})$', '010-12345')
print(m.group(0))
print(m.group(1))
print(m.group(2))

# 010-12345
# 010
# 12345

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from pyecharts.charts import Bar,Grid,Line
import pyecharts.options as opts
from pyecharts.globals import ThemeType

Out[89]:
        a  val
0  apple1  1.0
1  apple2  2.0
2  apple3  3.0
3  apple4  4.0
4  apple5  5.0

a  apple1  apple2  apple3  apple4  apple5
0     1.0     2.0     3.0     4.0     5.0

In [113]: pd.DataFrame(index=[0],columns=df.a,data=dict(zip(df.a,df.val)))
Out[113]:
a  apple1  apple2  apple3  apple4  apple5
0     1.0     2.0     3.0     4.0     5.0

In [116]: dict(zip(df.a,df.val))
Out[116]: {'apple1': 1.0, 'apple2': 2.0, 'apple3': 3.0, 'apple4': 4.0, 'apple5': 5.0}

import pandas as pd

movies = pd.read_csv('./data/movietweetings/movies.dat', delimiter='::', engine='python', header=None, names = ['Movie ID', 'Movie Title', 'Genre'])

   Movie ID                                        Movie Title  \
0         8      Edison Kinetoscopic Record of a Sneeze (1894)   
1        10                La sortie des usines Lumi猫re (1895)   
2        12                      The Arrival of a Train (1896)   
3        25  The Oxford and Cambridge University Boat Race ...   
4        91                         Le manoir du diable (1896)   
5       131                           Une nuit terrible (1896)   
6       417                      Le voyage dans la lune (1902)   
7       439                     The Great Train Robbery (1903)   
8       443        Hiawatha, the Messiah of the Ojibway (1903)   
9       628                    The Adventures of Dollie (1908)  
                                          Genre  
0                             Documentary|Short  
1                             Documentary|Short  
2                             Documentary|Short  
3                                           NaN  
4                                  Short|Horror  
5                           Short|Comedy|Horror  
6  Short|Action|Adventure|Comedy|Fantasy|Sci-Fi  
7                    Short|Action|Crime|Western  
8                                           NaN  
9                                  Action|Short  

users = pd.read_csv('./data/movietweetings/users.dat', delimiter='::', engine='python', header=None, names = ['User ID', 'Twitter ID'])
print(users.head())

   User ID  Twitter ID
0        1   397291295
1        2    40501255
2        3   417333257
3        4   138805259
4        5  2452094989
5        6   391774225
6        7    47317010
7        8    84541461
8        9  2445803544
9       10   995885060

ratings = pd.read_csv('./data/movietweetings/ratings.dat', delimiter='::', engine='python', header=None, names = ['User ID', 'Movie ID', 'Rating', 'Rating Timestamp'])
print(ratings.head())

   User ID  Movie ID  Rating  Rating Timestamp
0        1    111161      10        1373234211
1        1    117060       7        1373415231
2        1    120755       6        1373424360
3        1    317919       6        1373495763
4        1    454876      10        1373621125
5        1    790724       8        1374641320
6        1    882977       8        1372898763
7        1   1229238       9        1373506523
8        1   1288558       5        1373154354
9        1   1300854       8        1377165712

import pandas as pd

movies = pd.read_csv('./data/movietweetings/movies.dat', delimiter='::', engine='python', header=None, names = ['Movie ID', 'Movie Title', 'Genre'])
users = pd.read_csv('./data/movietweetings/users.dat', delimiter='::', engine='python', header=None, names = ['User ID', 'Twitter ID'])
ratings = pd.read_csv('./data/movietweetings/ratings.dat', delimiter='::', engine='python', header=None, names = ['User ID', 'Movie ID', 'Rating', 'Rating Timestamp'])

mask = movies.Genre.str.contains('comedy',case=False,na=False)

0    False
1    False
2    False
3    False
4    False
5     True
6     True
7    False
8    False
9    False
Name: Genre, dtype: bool

comedy = movies[mask]
comdey_ids = comedy['Movie ID']

5      131
6      417
15    2354
18    3863
19    4099
20    4100
21    4101
22    4210
23    4395
25    4518
Name: Movie ID, dtype: int64

5      131
6      417
15    2354
18    3863
19    4099
20    4100
21    4101
22    4210
23    4395
25    4518
Name: Movie ID, dtype: int64

   User ID  Movie ID  Rating  Rating Timestamp
0        1    111161      10        1373234211
1        1    117060       7        1373415231
2        1    120755       6        1373424360
3        1    317919       6        1373495763
4        1    454876      10        1373621125
5        1    790724       8        1374641320
6        1    882977       8        1372898763
7        1   1229238       9        1373506523
8        1   1288558       5        1373154354
9        1   1300854       8        1377165712

combine = ratings.join(comedy, on='Movie ID', rsuffix='2')

combine = ratings.join(comedy.set_index('Movie ID'), on='Movie ID')
print(combine.head(10))

   User ID  Movie ID  Rating  Rating Timestamp Movie Title Genre
0        1    111161      10        1373234211         NaN   NaN
1        1    117060       7        1373415231         NaN   NaN
2        1    120755       6        1373424360         NaN   NaN
3        1    317919       6        1373495763         NaN   NaN
4        1    454876      10        1373621125         NaN   NaN
5        1    790724       8        1374641320         NaN   NaN
6        1    882977       8        1372898763         NaN   NaN
7        1   1229238       9        1373506523         NaN   NaN
8        1   1288558       5        1373154354         NaN   NaN
9        1   1300854       8        1377165712         NaN   NaN

mask = pd.notnull(combine['Genre'])

result = combine[mask]
print(result.head())

    User ID  Movie ID  Rating  Rating Timestamp             Movie Title  \
12        1   1588173       9        1372821281      Warm Bodies (2013)   
13        1   1711425       3        1372604878        21 & Over (2013)   
14        1   2024432       8        1372703553   Identity Thief (2013)   
17        1   2101441       1        1372633473  Spring Breakers (2012)   
28        2   1431045       7        1457733508         Deadpool (2016)   

                             Genre  
12           Comedy|Horror|Romance  
13                          Comedy  
14    Adventure|Comedy|Crime|Drama  
17              Comedy|Crime|Drama  
28  Action|Adventure|Comedy|Sci-Fi  

    User ID  Movie ID  Rating  Rating Timestamp             Movie Title  \
12        1   1588173       9        1372821281      Warm Bodies (2013)   
13        1   1711425       3        1372604878        21 & Over (2013)   
14        1   2024432       8        1372703553   Identity Thief (2013)   
17        1   2101441       1        1372633473  Spring Breakers (2012)   
28        2   1431045       7        1457733508         Deadpool (2016)   

                             Genre  
12           Comedy|Horror|Romance  
13                          Comedy  
14    Adventure|Comedy|Crime|Drama  
17              Comedy|Crime|Drama  
28  Action|Adventure|Comedy|Sci-Fi  

score_as_movie = result.groupby('Movie ID').mean()

               User ID  Rating  Rating Timestamp
Movie ID                                        
131       34861.000000     7.0      1.540639e+09
417       34121.409091     8.5      1.458680e+09
2354       6264.000000     8.0      1.456343e+09
3863      43803.000000    10.0      1.430439e+09
4099      25084.500000     7.0      1.450323e+09

score_as_movie.sort_values(by='Rating', ascending = False,inplace=True)
score_as_movie

	User ID	Rating	Rating Timestamp
Movie ID			
7134690	30110.0	10.0	1.524974e+09
416889	1319.0	10.0	1.543320e+09
57840	23589.0	10.0	1.396802e+09
5693562	50266.0	10.0	1.511024e+09
5074	43803.0	10.0	1.428352e+09

watchs = result.groupby('Movie ID').agg(['count'])
watchs2 = watchs['Rating']['count']

print(watchs2.head(20))

Movie ID
131      1
417     22
2354     1
3863     1
4099     2
4100     1
4101     1
4210     1
4395     1
4518     1
4546     2
4936     2
5074     1
5571     1
6177     1
6414     3
6684     1
6689     1
7145     1
7162     2
Name: count, dtype: int64

watchs2.describe()

count    10740.000000
mean        20.192086
std         86.251411
min          1.000000
25%          1.000000
50%          2.000000
75%          7.000000
max       1843.000000
Name: count, dtype: float64

fig = plt.figure(figsize=(12,8))
histn = plt.hist(watchs2[watchs2 <=19],19,histtype='step')
plt.scatter([i+1 for i in range(len(histn[0]))],histn[0])

array([4383., 1507.,  787.,  541.,  356.,  279.,  209.,  163.,  158.,
        118.,  114.,   90.,  104.,   81.,   80.,   73.,   62.,   65.,
         52.])

sum(histn[0]) # 9222

n3 = result.groupby('Movie ID').agg(['count','mean','std'])
n3r = n3[n3['Rating']['count']>=20]['Rating']

	count	mean	std
Movie ID			
417	22	8.500000	1.263027
12349	68	8.485294	1.227698
15324	20	8.350000	1.039990
15864	51	8.431373	1.374844
17925	44	8.636364	1.259216

nmin = (1.96**2*n3r['std']**2) / ( (n3r['mean']*0.025)**2 )

Movie ID
417         135.712480
12349       128.671290
15324        95.349276
15864       163.434005
17925       130.668350

n3s = n3r[ n3r['count'] >= nmin ]

count	mean	std
Movie ID			
53604	129	8.635659	1.230714
57012	207	8.449275	1.537899
70735	224	8.839286	1.190799
75686	209	8.095694	1.358885
88763	296	8.945946	1.026984
...	...	...	...
6320628	860	7.966279	1.469924
6412452	276	7.510870	1.389529
6662050	22	10.000000	0.000000
6966692	907	8.673649	1.286455
7131622	1102	7.851180	1.751500
173 rows × 3 columns

n3s_sort = n3s.sort_values(by='mean',ascending=False)

	count	mean	std
Movie ID			
6662050	22	10.000000	0.000000
4921860	48	10.000000	0.000000
5262972	28	10.000000	0.000000
5512872	353	9.985836	0.266123
3863552	199	9.010050	1.163372
...	...	...	...
1291150	647	6.327666	1.785968
2557490	546	6.307692	1.858434
1478839	120	6.200000	0.728761
2177771	485	6.150515	1.523922
1951261	1091	6.083410	1.736127
173 rows × 3 columns

ms = movies.drop_duplicates(subset=['Movie ID'])
ms = ms.set_index('Movie ID')
n3s_final = n3s_drops.join(ms,on='Movie ID')

Movie Title
Five Minutes (2017)
MSG 2 the Messenger (2015)
Avengers: Age of Ultron Parody (2015)
Be Somebody (2016)
Bajrangi Bhaijaan (2015)
Back to the Future (1985)
La vita 鐚?bella (1997)
The Intouchables (2011)
The Sting (1973)
Coco (2017)
Toy Story 3 (2010)
3 Idiots (2009)
Green Book (2018)
Dead Poets Society (1989)
The Apartment (1960)
P.K. (2014)
The Truman Show (1998)
Am鑼卨ie (2001)
Inside Out (2015)
Toy Story 4 (2019)
Toy Story (1995)
Finding Nemo (2003)
Dr. Strangelove or: How I Learned to Stop Worrying and Love the Bomb (1964)
Home Alone (1990)
Zootopia (2016)
Up (2009)
Monsters, Inc. (2001)
La La Land (2016)
Relatos salvajes (2014)
En man som heter Ove (2015)
Snatch (2000)
Lock, Stock and Two Smoking Barrels (1998)
How to Train Your Dragon 2 (2014)
As Good as It Gets (1997)
Guardians of the Galaxy (2014)
The Grand Budapest Hotel (2014)
Fantastic Mr. Fox (2009)
Silver Linings Playbook (2012)
Sing Street (2016)
Deadpool (2016)
Annie Hall (1977)
Pride (2014)
In Bruges (2008)
Big Hero 6 (2014)
Groundhog Day (1993)
The Breakfast Club (1985)
Little Miss Sunshine (2006)
Deadpool 2 (2018)
The Terminal (2004)

x = n3s_final['Movie Title'][:10].tolist()[::-1]
y = n3s_final['count'][:10].tolist()[::-1]
bar = (
    Bar()
    .add_xaxis(x)
    .add_yaxis('评论数',y,category_gap='50%')
    .reversal_axis()
    .set_global_opts(title_opts=opts.TitleOpts(title="喜剧电影被评论次数"),
                    toolbox_opts=opts.ToolboxOpts(),)
)
grid = (
    Grid(init_opts=opts.InitOpts(theme=ThemeType.LIGHT))
    .add(bar, grid_opts=opts.GridOpts(pos_left="30%"))
)
grid.render_notebook()

x = n3s_final['Movie Title'][:10].tolist()[::-1]
y = n3s_final['mean'][:10].round(3).tolist()[::-1]
bar = (
    Bar()
    .add_xaxis(x)
    .add_yaxis('平均得分',y,category_gap='50%')
    .reversal_axis()
    .set_global_opts(title_opts=opts.TitleOpts(title="喜剧电影平均得分"),
                    xaxis_opts=opts.AxisOpts(min_=8.0,name='平均得分'),
                    toolbox_opts=opts.ToolboxOpts(),)
)
grid = (
    Grid(init_opts=opts.InitOpts(theme=ThemeType.MACARONS))
    .add(bar, grid_opts=opts.GridOpts(pos_left="30%"))
)
grid.render_notebook()

In [8]: s = pd.Series(list('ABCA'))
In [9]: pd.get_dummies(s)
Out[9]:
   A  B  C
0  1  0  0
1  0  1  0
2  0  0  1
3  1  0  0

In [5]: s = pd.Series(list('abaccd'))
In [6]: pd.get_dummies(s)
Out[6]:
   a  b  c  d
0  1  0  0  0
1  0  1  0  0
2  1  0  0  0
3  0  0  1  0
4  0  0  1  0
5  0  0  0  1

d:\source\test\settingwithcopy.py:9: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy 

tmp = df[df.a<4]
tmp['c'] = 200

import pandas as  pd

df = pd.DataFrame({'a':[1,3,5],'b':[4,2,7]},index=['a','b','c'])
df.loc[df.a<4,'c'] = 100
print(df)
print('it\'s ok')

tmp = df[df.a<4]
tmp['c'] = 200
print('-----tmp------')
print(tmp)
print('-----df-------')
print(df)

   a  b      c
a  1  4  100.0
b  3  2  100.0
c  5  7    NaN
it's ok
d:\source\test\settingwithcopy.py:9: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy     
  tmp['c'] = 200
-----tmp------
   a  b    c
a  1  4  200
b  3  2  200
-----df-------
   a  b      c
a  1  4  100.0
b  3  2  100.0
c  5  7    NaN

import numpy as np

url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
wid = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[1])

array([3.5, 3. , 3.2, 3.1, 3.6, 3.9, 3.4, 3.4, 2.9, 3.1, 3.7, 3.4, 3. ,
       3. , 4. , 4.4, 3.9, 3.5, 3.8, 3.8, 3.4, 3.7, 3.6, 3.3, 3.4, 3. ,
       3.4, 3.5, 3.4, 3.2, 3.1, 3.4, 4.1, 4.2, 3.1, 3.2, 3.5, 3.1, 3. ,
       3.4, 3.5, 2.3, 3.2, 3.5, 3.8, 3. , 3.8, 3.2, 3.7, 3.3, 3.2, 3.2,
       3.1, 2.3, 2.8, 2.8, 3.3, 2.4, 2.9, 2.7, 2. , 3. , 2.2, 2.9, 2.9,
       3.1, 3. , 2.7, 2.2, 2.5, 3.2, 2.8, 2.5, 2.8, 2.9, 3. , 2.8, 3. ,
       2.9, 2.6, 2.4, 2.4, 2.7, 2.7, 3. , 3.4, 3.1, 2.3, 3. , 2.5, 2.6,
       3. , 2.6, 2.3, 2.7, 3. , 2.9, 2.9, 2.5, 2.8, 3.3, 2.7, 3. , 2.9,
       3. , 3. , 2.5, 2.9, 2.5, 3.6, 3.2, 2.7, 3. , 2.5, 2.8, 3.2, 3. ,
       3.8, 2.6, 2.2, 3.2, 2.8, 2.8, 2.7, 3.3, 3.2, 2.8, 3. , 2.8, 3. ,
       2.8, 3.8, 2.8, 2.8, 2.6, 3. , 3.4, 3.1, 3. , 3.1, 3.1, 3.1, 2.7,
       3.2, 3.3, 3. , 2.5, 3. , 3.4, 3. ])
      

smax = np.max(wid)
smin = np.min(wid)

In [51]: smax,smin
Out[51]: (4.4, 2.0)

s = (wid - smin) / (smax - smin)

np.set_printoptions(precision=3)  

import seaborn as sns
sns.distplot(s,kde=False,rug=True)

sns.distplot(s,hist=True,kde=True,rug=True)

from scipy import stats
sns.distplot(s, kde=False, fit = stats.gamma)

from scipy import stats
sns.distplot(s, kde=False, fit = stats.dgamma)

import pandas as pd
import numpy as np

df = pd.read_csv("big_data.csv", 
skiprows = 
lambda x: x>0 and np.random.rand() > 0.01)

print("The shape of the df is {}. 
It has been reduced 100 times!".format(df.shape))

from flask import Flask

App = Flask(__name__)

@App.route('/')
def index():
    return "hello world"

if __name__ == "__main__":
    App.run(debug=True)

* Debug mode: on
 * Restarting with stat
 * Debugger is active!
 * Debugger PIN: 663-788-611
 * Running on http://127.0.0.1:5000/ (Press CTRL+C to quit)

27.0.0.1 - - [03/Feb/2020 21:26:50] "GET / HTTP/1.1" 200 -

import sqlite3

conn = sqlite3.connect("test.db")

c = conn.cursor()

c.execute('''CREATE TABLE books
      (id int primary key,
       sort int,
       name text,
       price real)''')

c.execute('''CREATE TABLE IF NOT EXISTS books
      (id int primary key,
       sort int,
       name text,
       price real)''')

c.execute('''INSERT INTO books VALUES
       (1, 
       1, 
       'computer science',
       39.0)''')

books = [(2, 2, 'Cook book', 68),
         (3, 2, 'Python intro', 89),
         (4, 3, 'machine learning', 59),
         ]


c.executemany('INSERT INTO books VALUES (?, ?, ?, ?)', books)

conn.commit()

conn.close()
print('Done')

@main_blue.route('/', methods=['GET', 'POST'])
def index():
    form = TestForm()
    print('test')

import qrcode

# 二维码内容
data = "https://www.zglg.work/wp-content/uploads/2020/10/image-3.png"
# 生成二维码
img = qrcode.make(data=data)
# 直接显示二维码
img.show()
# 保存二维码为文件
img.save("我的微信.jpg")

import qrcode

# 实例化二维码生成类
qr = qrcode.QRCode(border=2)
# 设置二维码数据
data = "https://www.zglg.work/wp-content/uploads/2020/10/image-3.png"
qr.add_data(data=data)
# 启用二维码颜色设置
qr.make(fit=True)
img = qr.make_image(fill_color="orange", back_color="white")

# 显示二维码
img.show()