呜啦吧哈的博客

from collections import Countern = ['a','b','c','a','d','d']m = dict(Counter(n))输出键是元素,值是元素出现的次数print(m){'a': 2, 'b': 1, 'c': 1, 'd': 2}

提取表格#%%从pdf中提取表格import tabuladf = tabula.read_pdf("E:\\testdata\\zhushengnan\\Controlled Substances by CSA Schedule-17.pdf", pages='all')表头处理import pandas as pddf_result = []for df_1 in df: column = df_1.columns.values.tolist() df_c .

import osimport os.pathimport win32com.client as win32## 根目录rootdir = u'E:\\testdata\\combine\\2020Q1'# 三个参数：父目录；所有文件夹名（不含路径）；所有文件名for parent, dirnames, filenames in os.walk(rootdir): for ...

delete T from(select ROW_NUMBER() over(partition by [AproveNo] order by [date] desc) as row_number, *from ku.dbo.biao) T where T.row_number>1;

有道http://fanyi.youdao.com/translate?&doctype=json&type=AUTO&i=要翻译的文本搜狗https://deepi.sogou.com/doccenter/texttranslatedoc?fr=process，接入文档url = "http://fanyi.sogou.com:80/reventondc/...

import numpy as npy = np.bincount(array([1, 0, 1]))##理解：最大值为1，所以输出有1+1=2个>array([1, 2], dtype=int64)##索引0出现1次，索引1出现2次，所以输出[1,2]np.bincount(np.array([y_train[i] for i in small_k])).argsor...

有值为yes，无值为no（可用于缺失值处理）def set_Cabin_type(df): df.loc[ (df.Cabin.notnull()), 'Cabin' ] = "Yes" df.loc[ (df.Cabin.isnull()), 'Cabin' ] = "No" return df...

import pandas as pddf = {'id':['a','a','b','c','c'], 'en':['apple','app','w','cf','as']}df = pd.DataFrame(df)grouped = df.groupby('id')result = grouped['en'].unique()result2 = ...

1、解决matplotlib图例中文乱码?2、升级pippython -m pip install --upgrade pip遇到 could not install packages due to an environmenterror：在install后加上--userpython -m pip install --user --upgrade pip...

#格式化字符串name = 'jenny'a = "%s is 好人" % name

管理员身份运行创建python3.6.5环境conda create --name py365 python=3.6.5 激活环境conda activate py365查看python版本python --version安装tensorflowconda install tensorflow安装deepchempip install deepchem安装deep...

#筛选当天更新数据，并通过Rank排序select *from table where DATEDIFF (dd,FDate,GETDATE())=0 order by Rank #筛选当天更新数据，并通过Rank倒序select *from table where DATEDIFF (dd,FDate,GETDATE())=0 order by Rank desc #修改值u...

创建dataframedf1 = pd.DataFrame(data1, columns = ["a", "b"])ndarray转化为DataFrameIn：type(y）Out：numpy.ndarrayfrom pandas import DataFramepre = DataFrame(y,columns=['pre'])import pandas a...

去除标点test['clean'] = test.content.apply(lambda x:re.sub(r'[\s+\.\!\/_,$%^*(+\"\')]+|[+——()?【】“”！，。？、~@#￥%……&*（）]+:：', " ",x))取出中文chapter['ch'] = chapter.content.apply(lambda x:re.sub(r'[...

转为refworks格式import pandas as pd#from pandas.core.frame import DataFrame"""读取csv文件"""rawdata = pd.read_csv('E:\\testdata\\co2000.csv',encoding = "utf-8")"""将含有NaN的行去掉"""#dat

import pymssqlimport pandas as pdimport re###连接sql sever并读取数据到dataframeconn = pymssql.connect('WIN****', 'sa', '*****', 'jsontest')cursor = conn.cursor()sql = "select drugid,pclass,pName,pNam...

参考来源：https://www.cnblogs.com/webRobot/p/5407193.htmlimport requests,bs4####单词去除空格，名词符号####def word_format(word): #去掉空格 word1 = word.strip() word2 = word1.replace("\n",'') word3 ...

环境：python3原始表：拆分后的表：import pandas as pd#from pandas.core.frame import DataFrame"""读取文件"""rawdata = pd.read_csv('E:\\testdata\\test1.csv',encoding = "GBK")rawdata2