Call Me Hi Johnny~~

import pandas as pd from pandas import * import numpy as np df = DataFrame({‘key’:[‘b’,’b’,’a’,’c’,’a’,’b’],’data1’:range(6)}) result = pd.get_dummies(df[‘key’],prefix=’key’) print(resul

data = DataFrame({‘food’:[‘bacon’,’pull_pork’,’bacon’,’Pastrami’,’corned beef’,’Bacon’,’pastrami’,’honey ham’,’novs lox’], ‘ounces’:[4,3,12,6,7.5,8,3,5,6]}) print(data) meat_

import pandas as pd from pandas import * import numpy as np data = DataFrame({‘k1’:[‘one’]*3+[‘two’]*4,’k2’:[1,1,2,3,3,4,4]}) print(data) print(data.drop_duplicates())如果希望对指定的列进行重复值删除则

left1 = pd.DataFrame({‘key’:[‘a’,’b’,’a’,’a’,’b’,’c’],’value’:range(6)}) right1 = pd.DataFrame({‘group_val’:[3.5,7]},index = [‘a’,’b’]) print(left1) print(right1) result = pd.merge(left1,ri

df1 = pd.DataFrame({‘key’:[‘b’,’b’,’a’,’c’,’a’,’a’,’b’],’data1’:range(7)}) print(df1) df2 = pd.DataFrame({‘key’:[‘a’,’b’,’d’],’data2’:range(3)}) print(df2) result = pd.merge(df1,df2,on = ‘k

frame = pd.DataFrame({‘a’:range(3),’b’:range(0,3),’c’:[‘one’,’two’,’three’]}) result = frame.set_index(‘c’) print(result)

data = pd.Series(np.random.randn(10),index=[ [‘a’,’a’,’a’,’b’,’b’,’b’,’c’,’c’,’d’,’d’], [1,2,3,1,2,3,1,2,2,3] ]) print(data) print(data.index) data = pd.Series(np.random.ran

from numpy import nan as NA data = pd.Series([1,NA,3.5,NA,7]) print(data) print(data.dropna())以上是对于Serise,对于DataFrame来说，默认丢弃含有缺失值的行 from numpy import nan as NA data = pd.DataFrame([[1,6.

data = pd.DataFrame( {'Qu1':[1,3,4,3,4],'Qu2':[2,3,1,2,3],'Qu3':[1,5,2,4,4]})print(data)result = data.apply(pd.value_counts).fillna(0)print(result)

import pandas as pd from pandas import * import numpy as np df = DataFrame({‘key1’:[‘a’,’a’,’b’,’b’,’a’], ‘key2’:[‘one’,’two’,’one’,’two’,’one’], ‘data1’:

import pandas as pd from pandas import * import numpy as np df = DataFrame({‘key’:[‘b’,’b’,’a’,’c’,’a’,’b’],’data1’:range(6)}) result = pd.get_dummies(df[‘key’],prefix=’key’) print(resul

import matplotlib.pyplot as plt import pandas as pd import numpy as np fig = plt.figure() ax = fig.add_subplot(2,2,1) ax.plot(np.random.rand(100)) ticks = ax.set_xticks([0,25,50,75])

import matplotlib.pyplot as plt import tkinter import numpy as np import pandas as pd from pandas import Series,DataFrame data = {‘a’:[1,2,3], ‘c’:[4,5,6], ‘b’:[7,8

frame=pd.DataFrame(np.arange(12).reshape(4,3),columns=list(‘bde’),index=[‘one’,’two’,’three’,’four’]) print(frame) f = lambda x:x.max() -x.min() result = frame.apply(f) print(result) f

numpy中提供来用于合并数组的函数 arr = np.arange(12).reshape(3,4) print(arr) result = np.concatenate([arr,arr],axis=1) print(result) s1 = pd.Series([0,1],index=[‘a’,’b’]) s2 = pd.Series([2,3,4],in

ssh xxx@xx.xx.xx.xx -Lxx.xx.xx.xx:1234:xx.xx.xx.xx:8888

from dateutil.parser import parse a = parse(‘2011-01-03’) print(a) from dateutil.parser import parse a = parse(‘Jan 31,1997 10:45 PM’) print(a) from dateutil.parser import par...

class C: def init(self): print(‘enter C’) print(‘leave C’) class A: def init(self): print(“enter A”) print(“leave A”) class B(A): # A –...

import pandas as pd from pandas import * import numpy as np data = Series([1,-999,2,-999,-1000,3]) print(data.replace(-999,np.nan)) print(data.replace([-999,-1000],np.nan)) print(...

import pickle a1 = ‘apple’ b1 = {1: ‘One’, 2: ‘Two’, 3: ‘Three’} c1 = [‘fee’, ‘fie’, ‘foe’, ‘fum’] f1 = open(‘temp.pkl’, ‘wb’) pickle.dump(a1, f1, True) pickle.dump(b1, f1, True)

obj = pd.Series(range(4),index=[‘d’,’a’,’b’,’c’]) a = obj.sort_index() print(a) frame = pd.DataFrame(np.arange(8).reshape(2,4),index=[‘three’,’one’],columns=[‘d’,’a’,’b’,’c’]) a = frame.s

frame = pd.DataFrame(np.arange(12).reshape(4,3),columns=list(‘bde’),index=[‘one’,’two’,’three’,’four’]) print(frame) series2 = pd.Series(range(3),index=[‘b’,’e’,’f’]) print(frame + series2)上述

data = pd.DataFrame(np.arange(16).reshape(4,4),index = [‘one’,’two’,’three’,’four’],columns=[‘one’,’two’,’three’,’four’]) print(data) result = data.ix[‘three’,’three’] print(result)

import pandas as pd xiaoming=pd.DataFrame([1,2,3],index=[‘yellow’,’red’,’blue’],columns=[‘hat’]) print(xiaoming) hat_ranks=pd.get_dummies(xiaoming[‘hat’],prefix=’hat’) print(hat_ranks.head(

Serise上的画图 import matplotlib.pyplot as plt import pandas as pd from pandas import * import numpy as np s = Series(np.random.rand(10).cumsum(),index=np.arange(0,100,10)) s.plot() plt

这样我们就完成了整个文件在vi编辑器中的操作过程了。特别注意，在插入模式（Insert mode）中如果你想删除输错的字符用“backspace”是无效的哦，光标只会往前移动，并不会删除字符，在vi中直接在命令模式使用字符命令即可对文件内容进行修改：“x”：每按一次，删除光标所在位置所在位置的那个字符。“X”：大写的X，每按一次，删除光标所在位置的“前面”一个字符。当然如果你想在插入模式（Inse

在安装python的时候，按照下面的步骤进行，决对可以避开90%的坑 sudo apt-get install python3-dev libffi-dev libssl-dev wget https://www.python.org/ftp/python/3.6.0/Python-3.6.0.tgz tar xvf Python-3.6.0.tgz cd Python-3.6.0 .

因为奇怪，所以记录在这里 import pandas as pd df = pd.read_csv(‘test.txt’) print(df[[‘Names’,’Births’]])加入文件中有 Names 和 Births 这两个属性，我们需要把这两个属性输出出来，那我们要用[] 这个中括号把这两属性给括起来！

import numpy as np print(‘a = %d c = %d’%(1,2))

在文章中添加如下代码https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-MML-AM_CHTML">script>然后到Latex在线编辑网站http://www.codecogs.com/latex/eqneditor.php  编写就OK了

在实际使用的时候，经常会碰到对python字典的排序，首先要声明的是python字典是通过哈希映射来存储，不存在顺序关系，也就谈不上排序，我们这里所说的排序实际上是 对键值对的排序，排序后返回的结果是个列表。 对字典排序有两种方法。 第一种： import operator dic = {‘d’:2,’b’:4,’c’:1} b = sorted(dic.ite

import json dic = {‘崔’:1} file = open(‘testfile’,’w’,encoding=’utf8’) b = json.dumps(dic,ensure_ascii=False) print(type(b)) print(b) file.write(b)

a = [1,2,7,6,7,8] b = 7 c = a.index(b) print(c)

在做泰坦尼克 数据分析的时候遇到这样的一个函数subplot2grid 下面就简单实现一下关于这个函数的功能from matplotlib import pyplot as pltax1 = plt.subplot2grid((3,3), (0,0), colspan=3) ax2 = plt.subplot2grid((3,3), (1,0), colspan=2) ax3 = plt.su

最数据分析，通过直观的图来观察，无论是出自于分析还是呈现给别人看，都是很有必要的，所以就决定要学一学基本的绘图 以下是kaggle里著名的泰坦尼克号的数据分析，绘图的过程 import pandas as pd #数据分析 import numpy as np #科学计算 from pandas import Series,DataFrame data_train = p

from collections import defaultdict strings = (‘puppy’, ‘kitten’, ‘puppy’, ‘puppy’, ‘weasel’, ‘puppy’, ‘kitten’, ‘puppy’) counts = defaultdict(lambda: 0) for item in strings:

a = [1,2,3] a.extend([4]) print(a)

读取csv文件import csv with open(‘some.csv’, ‘r’) as f: # 采用b的方式处理可以省去很多问题 reader = csv.reader(f) for row in reader: # do something with row, such as row[0],row[1]import csv with

df = pd.read_csv(‘1.csv’) data = df.pop(‘c’) print(data) print(df) df.insert(0,’data’,data) print(df)

df = pd.read_csv(‘hahaha.csv’) df[df>0] = 1 print(df)