python程式設計規則與技巧-（持續記錄）

一、頭檔案

基本子產品導入

import pandas as pd
import numpy as np
import cv2
import os
import matplotlib.pyplot as plt
import re
           

機器學習子產品：

from sklearn.cross_validation import train_test_split  #分資料
import mglearn 
from sklearn.linear_model import Ridge 
from sklearn import datasets, linear_model
from sklearn.linear_model import LogisticRegression
from sklearn.svm import LinearSVC
from mglearn import plot_2d_separator
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error
           

深度學習子產品：

from keras.models import Sequential
from keras.layers import Dense,Dropout,Flatten,Conv2D,MaxPooling2D
from keras.models import load_model

           

讀取檔案方法，好多包都可讀取檔案：

C:/pypractise/fangzhen2/cj.csv

text = open('test_txt/14.txt','r')
q = text.read()

data=pd.read_csv('C:/pypractise/3/Advertising.csv')


           

讀取檔案清單，以便在依次周遊檔案

def get_imglist(path):
    return [os.path.join(path,f) for f in os.listdir(path) if f.endswith('.jpg')]
           

寫入exls 大檔案可用

def data_w(datas):
    f= xlsxwriter.Workbook('demo1.xlsx')#建立一個excel檔案
    sheet1= f.add_worksheet(u'sheet1')
    i = 0
    j = 0
    for data in datas[0]:        
        sheet1.write(i,j,data)
        i=i+2
    i = 1
    j = 0
    for data1 in datas[1]:
        sheet1.write(i,j,data1)
        i=i+2
    f.close()
           

将檔案寫進行excel表格中：

def data_write(datas):
    f = xlwt.Workbook()
    sheet1 = f.add_sheet(u'ex.xls',cell_overwrite_ok=True) #建立sheet

    #将資料寫入第 i 行，第 j 列
    i = 0    #行
    j = 0   #列
    for data in datas:        
        sheet1.write(i,j,data)
        i=i+1
#    i=1
#    for data1 in datas[1]:
#        sheet1.write(i,j,data1)
#        i=i+2
    f.save('ex.xls') #儲存檔案
           

将檔案txt的寫到csv中；

def data_write():
    '''
    函數為将txt資料寫入到csv中
    '''    
    with open('shuju.csv', 'w+',newline='') as csvfile:
        spamwriter = csv.writer(csvfile, dialect='excel')
        # 讀要轉換的txt檔案，檔案每行各詞間以@@@字元分隔
        with open('che.txt', 'r',encoding='utf-8') as filein:
            for line in filein:
                line_list = line.strip('\n').split(' ')
                spamwriter.writerow(line_list)
           

正則語句切分. 文獻去頭尾;

#(\.(?=\s+(?:[A-Z])))|(\). )|(\.[ 0-9|A-Z])|(ACKNOWLEDGMENTS.*$)|(.*AUTHOR INFORMATION*$)|(REFERENCES.*$)|(References.*$)|(\?+)|(^.*ABSTRACT:)|(^.*INTRODUCTION )| (^.*CONSPECTUS:)
#正則規則去除開頭結尾和*？
# 切分 \.(?=[\d+](?=\s+(?:[A-Z])))|\.(?=\s+(?:[A-Z])))
# 删除開頭結尾 (ACKNOWLEDGMENTS.*$)|(AUTHOR.INFORMATION.*$)|(REFERENCES.*$)|(References.*$)|(^.*ABSTRACT:)|(^.*INTRODUCTION )| (^.*CONSPECTUS:)|(ASSOCIATED.CONTENT.*$)
#替換 ？和* (\?+)|(\*+)
re.sub(pattern1,'',q)
re.compile(r' ')
           

調用API翻譯 百度：

ID自己的号

def fanyi(yuju):
   
    '''
    出入Q 傳回src 和dst
    '''
    
    myurl = '/api/trans/vip/fieldtranslate'   #分網頁
    appid = '    '
    secretKey =  '   '
    
    q = yuju
    q.encode(encoding = 'utf-8')
    salt = random.randint(32768, 65536)
    salt = str(salt)
    domain = 'medicine'
    sign = appid + q + salt + domain + secretKey   #簽名
    
    m1 = hashlib.md5()  #建立一個md5加密模式的hash對象
    m1.update(sign.encode(encoding = 'utf-8'))  #跟新對象
    sign = m1.hexdigest()  #傳回摘要
    
    fromLang = 'en'
    toLang = 'zh'
    httpClient = None
    
    myurl = myurl+'?q='+parse.quote(q)+'&from='+fromLang+'&to='+toLang+'&appid='+appid+'&salt='+salt+'&domain='+'medicine'+'&sign='+sign 

    try:
        httpClient = http.client.HTTPConnection('api.fanyi.baidu.com')    #主網頁
        httpClient.request('GET', myurl)
        response = httpClient.getresponse()
        html = response.read().decode('utf-8')
        html = json.loads(html)    #傳回翻譯結果
#        ds1t = html["trans_result"][0]["dst"]
#        src1 = html["trans_result"][0]["src"]
    except Exception as e:
        print(e)
    finally:
        if httpClient:
            httpClient.close()
    return html
           

畫圖方法：

一般的畫出來：

plt.title("ATP curve")     #設定标題
plt.xlim(xmax=2500,xmin=-250)    #設定x y軸的大小
plt.ylim(ymax=220,ymin=0)
plt.figure()
plt.plot(range(len(y_pred)),y_pred,'b',label='predict')
plt.plot(range(len(y_pred)),y_test,'r',label='test')
plt.legend(loc="upper right")    #圖示的位置
plt.xlabel("the number of sales")
plt.ylabel("value of sales")
plt.show()