#查找index函数的帮助
Help (Str.index)
#for循环和break语句
From math import sqrt
For I in Range (2,101):
Flag=1
K=int (sqrt (i))
For j in Range (2,k+1):
If i%j==0:
Flag=0
Break
if (flag):
Print I
#continue语句, the statement that satisfies the condition to jump out of continue
Suma=0
I=1
While i<=5:
Suma+=i
I+=1
If i==3:
Continue
print ' i=%d,sum=%d '% (I,suma)
#循环中的else语句
K=5
For I in Range (1,10):
If k==3:
Break
Else
Print I
#自定义函数/footage 1-100 Prime
From math import sqrt
def isprime (x):
If x==1:
Return False
K=int (sqrt (x))
For j in Range (2,k+1):
If x%j==0:
Return False
Return True
For I in Range (2,101):
If IsPrime (i):
Print I
def f (x,y=true): #默认参数要放在参数列表的最后
' x and Y both correct words or not '
If y:
Print x, ' and y both correct '
Print x, ' is Ok '
F (68)
F (68,false)
#传递函数
def addme2me (x):
Return (X+X)
def self (f,y):
Print f (Y)
Self (addme2me,2.2)
#lambda函数
My_add=lambda X,y:x+y
My_add (5,6)
#数据获取与表示
F=open (R ' E:\360Downloads\firstpro.txt ', ' W ') #新建一个文件
F.write (' Hello,world ') #f为对象, write writes to file
F.close ()
F=open (R ' E:\360Downloads\firstpro.txt ', ' R ') #r代表读出
P1=f.read (5) #5代表读出的字节数
P2=f.read ()
Print P1,P2
F.close
F1=open (R ' E:\360Downloads\companies.txt ')
Cname=f1.readlines ()
For I in range (0,len (CNAME)):
Cname[i]=str (i+1) + "+cname[i"
F1.close
F2=open (R ' E:\360Downloads\scompanies.txt ', ' W ')
F2.writelines (CNAME)
F2.close ()
#网络数据获取
Import Urllib
R=urllib.urlopen (' http://z.cn/')
Html=r.read
#序列
#标准类型运算符
' Apple ' < ' banana '
[1,2,3]!=[4,5,6] #值比较
atuple= (' Ba ', 126.4)
Btuple=atuple
Btuple is not atuple# object identity comparison
(' 86.40 ' < ' 122.64 ') and (' Apple ' < ' banana ') #布尔运算
#序列类型运算符
week=[' Mondy ', ' Tuesday ', ' Wednesday ', ' Thursday ', ' firday ', ' satuday ', ' Sunday '
Print week[1],week[-2], ' \ n ', week[1:4], ' \ n ', week[:6], ' \ n ', week[::-1] #序列值的序号是从0开始到N-1 or from 1 to n
' Apple '
' Ba ' in (' Ba ', ' the Boeingcompany ')
#序列类型转换工厂函数
List (' Hello,world ') #将字符串转成列表
Tuple (' Hello,world ') #将字符串转成元组
#字符串
s1= "' Hello
A
' B '
world! ""
S1 #三引号可以保持里面字符串的原貌
S2=r ' d:\python\a.py '
S2
ccode=[' AXP ', ' ba ', ' cat ', ' csco ', ' CVX ']
cprice=[' 86.40 ', ' 122.64 ', ' 99.44 ', ' 23.78 ', ' 115.91 ']
For I in range (5):
print '%d%8s:%8s '% (I,ccode[i],cprice[i]) #%8s refers to 8 characters
print ' I get%d%%! '%32 #两个 percent will leave a
Astr= ' What does your think of this saying "no pain,no gain"? '
Tempstr=astr.split (' \ "') [1] #\" is an escape character
If Tempstr.istitle ():
print ' It is title format '
Else
print ' It is not title format '
Print Tempstr.title ()
Astr= ' \101\t\x41\n ' #\ octal number 000 represents the character \ t represents a horizontal tab
Print Astr
#列表
JSCORES=[9,9,8.5,10,7,8,8,9,8,10]
Ascore=9
Jscores.sort ()
Jscores.pop () #去掉最高分
Jscores.pop (0) #去掉最低分
Jscores.append (Ascore) #合并
Avescore=sum (jscores)/len (jscores)
Print Avescore
week=[' Monday ', ' Tuesday ', ' Wednesday ', ' Thursday ', ' Firday ']
weekend=[' Saturday ', ' Sunday ']
Week.extend (Weekend) #extend合并函数
For I,J in Enumerate (week): #enumerate函数 produces a sequence starting from 0
Print I+1,j
numlist=[3,11,5,8,16,1]
Numlist.sort (reverse=true) #按逆序排列
Numlist
fruitlist=[' apple ', ' banana ', ' pear ', ' lemon ', ' avocado '
Fruitlist.sort (Key=len)
Fruitlist #按字符长度排序
#列表解析
[X**2 for X in range (10)]
[X**2 for X in range (ten) if X**2<50]
[(x+1,y+1) for x in range (2) for Y in range (2)]
#元组
Atruple= (a)
Atruple
Atruple[1:]
Len (atruple)
btruple= ([' Monday ', 1],2,3)
BTRUPLE[0][1]
, #创建元组2014
alist=[' AXP ', ' ba ', ' Cat ']
atruple= (' AXP ', ' ba ', ' cat ')
Alist[1]= ' Alibaba '
Atruple[1]= ' Alibaba ' #元组是不可变的, the list is mutable
alist=[3,5,2,4]
Alist.sort () #改变原来列表
Alist
alist=[3,5,2,4]
Sorted (alist) #sorted只是新生成一个列表的副本, the original list has not changed
Alist
#但元组就只能使用sorted, cannot use sort, because tuples cannot be changed
Atruple= (3,5,2,4)
Atruple.sort #会报错
def func (args1,args2= ' World '): #元组作为函数形式的参数
Print ARGS1,ARGS2
Func (' Hello ',)
Func (args2= ' Apple ', args1= ' hello ')
def func (Args1,*args):
Print ARGS1
Print args
Func (' Hello, ', ' Wangdachui ', ' Liuyuan ', ' Linlin ')
#返回值类型为元组的函数enumerate (), coerce ()
#字典
ainfo={' Wangdachui ':, ' Niuyun ': +, ' linlin ': ' #直接创建字典
info=[(' Wangdachui ', +), (' Niuyun ', +), (' Linlin ', 3000)]
Binfo=dict (Info) #利用dict函数创建字典
Cinfo=dict ([[' Wangdachui ', 3000],[' Niuyun ', 2000],[' Linlin ', 3000]])
Dinfo=dict (wangdachui=3000,niuyun=2000,linlin=3000)
Adict={}.fromkeys (' Wangdachui ', ' Niuyun ', ' Linlin '), #fromkeys函数将所有的keys初始值设置为3000
Adict
plist=[(' AXP ', ' American Express ', ' 86.40 '), (' Ba ', ' the ' Boeing Company ', ' 122.64 '), (' Cat ', ' Caterpillar Inc. ', ' 99.44 ')]
Alist[]
Blist[]
For I in range (2):
ASTR=PLIST[I][0]
BSTR=PLIST[I][2]
Alist.append (ASTR)
Blist.append (BSTR)
Adict=dict (Zip (alist,blist)) #zip函数
#字典的使用
#字典的基本操作
ainfo={' Wangdachui ':, ' Niuyun ': +, ' Linglin ': 4500, ' Tianqi ': 8000}
ainfo[' Niuyun '] #键值查找
ainfo[' Niuyun ']=9999# update
Ainfo
ainfo[' Funyun ']=1000# find
' Mayun ' in Ainfo #成员判断
Del Ainfo #删除字典
ainfo={' Wangdachui ':, ' Niuyun ': +, ' Linglin ': 4500, ' Tianqi ': 8000}
For key in Ainfo.keys ():
print ' name=%s,salary=%s '% (Key,ainfo[key])
"Niuyun ' s salary is% (Niuyun) s."%ainfo #% (key) format specifier% Dictionary object name
ainfo={' Wangdachui ':, ' Niuyun ': +, ' Linglin ': 4500, ' Tianqi ': 8000}
Ainfo.keys ()
Ainfo.values ()
ainfo={' Wangdachui ':, ' Niuyun ': +, ' Linglin ': 4500, ' Tianqi ': 8000}
binfo={' Wangdachui ':, ' Niuyun ': 9999, ' Linglin ': 4500, ' Wangzi ': 8000}
Ainfo.update (binfo) #update函数 Quick Change
Ainfo
astock={' AXP ': 86.4, ' BA ': 122.64}
Bstock=astock
astock={} #此时只会讲astock清空, the bstock will not be emptied and the clear function will be used to delete the associated
Bstock
Astock.clear ()
Bstock
#字典作为函数的形式参数
def func (ARGS1,*ARGST,**ARGSD): #一个 * is a variable long positional parameter, * * variable long keyword parameter
Print ARGS1
Print Argst
Print ARGSD
Func (' Hello ', ' Wangdachui ', ' Niuyun ', ' Linglin ', a1=1,a2=2,a3=3)
#集合
names=[' Wangdachui ', ' Niuyun ', ' Wangzi ', ' Wangdachui ', ' lingling ', ' Niuyun ']
Namesset=set (names) #set删除重复对象 because the elements of the collection are not duplicated
Namesset
Aset=set (' Hello ')
Aset
Fset=frozenset (' Hello ')
Fset
#集合比较
Aset=set (' Sunrise ')
Bset=set (' Sunset ')
' U ' in Aset
Aset==bset
Set (' Sun ') <aset
Aset&bset #集合关系运算
Aset|bset
Aset-bset
Aset^bset #不能同时属于两个集合
Aset-=set (' Sun ') #运算符可复合
#集合内建函数
Aset=set (' Sunrise ')
Bset=set (' Sunset ')
Aset.issubset (bset) #是否为子集
Aset.intersection (bset) #交集
Aset.difference (bset) #差补
Cset=aset.copy () #拷贝
#面向可变集合的函数
Aset=set (' Sunrise ')
Aset.add ('! ')
Aset
Aset.update (' Yeah ')
Aset.remove ('! ')
Aset.clear ()
#扩展库scipy
Import NumPy as NP
Xarray=np.ones ((3,4)) #生产3 all 1 matrix
Xarry
From scipy import Linalg
Arr=np.array ([[1,2],[3,4]])
Linalg.det (arr)
#ndarry
From numpy Import *
Aarray=array ([i])
Aarray
Barray=array ([(+), (4,5,6)])
Barray
Zeros ((2,2))
Arange (1,5,0.5)
Aarray=array ([(+), (4,5,6)])
Sin (aarray)
Aarray.shape #数组的维度
Barray=aarray.reshape (3,2)
Barray
Aarray.sum ()
Aarray.sum (axis=0) #通过设置参数, row, column sum
Aarray.sum (Axis=1)
Carray=array ([1,3,5])
Carray[:1] #切片功能
Darray=array ([2,4,6])
Earray=array ([7,8,9])
where (Carray>2,darray,earray) #where函数
def fun (x, y):
Return (x+1) * (y+1)
Arr=fromfunction (fun, (9,9)) #fromfunction函数
Arr
#ufunc函数能对数组中每个元素进行操作, including functions such as add
Import NumPy as NP
A=np.arange (1,5)
B=np.arange (2,6)
Np.add (A, B)
Np.add.accumulate ([2,3,8])
Np.multiply.accumulate ([2,3,8])
#series
#series objects similar to one-dimensional arrays, consisting of data and indexes
from pandas import series
Import pandas as PD
ASER=PD. Series ([1,2.0, ' a '])
BSER=PD. Series ([' Apple ', ' peach ', ' lemon '],index=[1,2,3])
Bser.index
bser.values
aser[' a ']
import numpy as NP
Np.exp (aser)
#series数据对齐
data={' AXP ': ' ', ' csco ': ' 122 ', ' BA ': ' 94 '}
sindex=[' AXP ', ' Csco ', ' AAPL ']
ASER=PD. Series (data,index=sindex)
Aser
Pd.isnull (aser)
#series的name属性
aser.name= ' cnames '
Aser.index.name= ' volume '
aser
#dataframe表结构
#大致可以看成共享一个index的series的集合
data={' name ': [' Wangdachui ', ' Linlin ', ' Niuyun '], ' pay ': [4000,5000,6000]}
FRAME=PD. DataFrame (data)
frame[' name ']
Frame.pay
Frame.ix[2] #索引所对应的数据
#dataframe对象的修改和删除
frame[' name ']= ' Admin ' #对name下的所有元素进行更改
del frame[' pay ']
frame
frame.index.name= ' no '
#便捷数据获取
# Convenient network data yahoo Finance
from matplotlib.finance import Quotes_historical_yahoo
from datetime import Date
Import pandas as PD
Today=date.today ()
start= (today.year-1,today.month,today.day)
Quotes=quotes_historical_yahoo (' AXP ' , Start,today)
DF=PD. DataFrame (quotes)
Print df
#自然语言工具包NLTK
from Nltk.corpus Import Gutenberg
Import NLTK
Print Gutenberg.fileids ()
#数据准备
From matplotlib.finance import Quotes_historical_yahoo
From datetime import Date
Import Pandas as PD
Today=date.today ()
Start= (Today.year-1,today.month,today.day)
Quotes=quotes_historical_yahoo (' AXP ', start,today)
fields=[' Date ', ' open ', ' close ', ' High ', ' low ', ' volume '
QUOTESDF=PD. DataFrame (Quotes,columns=fields) #通过columns数据加属性名
QUOTESDF=PD. DataFrame (Quotes,index=range (1,len (quotes) +1,columns=fields)
Print QUOTESDF
From datetime import Date
From datetime import datetime
Y=datetime.strftime (x, '%y-%m-%d ') #将日期转换成固定格式
Import Pandas as PD
Dates=pd.date_range (' 20141001 ', periods=7) #自己创建时间序列
Dates
#数据显示
Djidf.index
Djidf.columns
Djidf.values
djidf.describe# Display Data Description
Djidf.head (5) #显示前五行数据
Djidf.tail (5)
#数据选择
Quotesdf[u ' 2013-12-02 ': U ' 2013-12-06 '] #dataframe可以使用索引选择
djidf[' Code ']
Djidf.loc[1:5,] #通过loc通过标签选择数据, the first parameter is the row label, the second argument is the column label
djidf.loc[:,[' code ', ' Lasttrade '] #前面这个: Required
djidf.loc[1:6,[0,2]] #通过的行位置, column position Selection tab
Quotesdf[quotesdf.index>=u ' 2014-01-01 ']
quotesdf[(quotesdf.index>=u ' 2014-01-01 ') & (quotesdf.close>=95)] #条件筛选
#简单统计预处理
Djidf.mean (columns= ' Lasttrade ') #最近一次成交价的平均值
djidf[djidf.lasttrade>=120].name# company name with the most recent transaction price greater than or equal to 120
Len (Quotesdf[quotesdf.close>quotesdf.open]) #股票涨的天数
Len (QUOTESDF)-131
Status=np.sign (Np.diff (quotesdf.close)) #np. diff The difference between two consecutive days of data
Status[np.where (status==1.)]. Size
Djidf.sort (columns= ' Lasttrade ') [27:].name# sort results list the top three company names, altogether is 30 records, so yes [27:]
t=quotesdf[(quotesdf.index>=u ' 2014-01-01 ') & (Quotesdf.index<=u ' 2014-02-01 ')]
Len (t) #统计2014年1月份的股票开盘天数
#分组
Tempdf.groupby (' month '). Count (). Month #每个月的股票开盘天数
Tempdf.groupby (' month '). SUM (). Volume #每个月的股票总成交量
G=tempdf.groupby (' month ')
gvolume=g[' volume ']
Print Gvolume.sum ()
#合并
#append追加 portrait
P=quotesdf[:2]
Q=quotesdf[u ' 2014-01-01 ': U ' 2014-01-05 '
P.append (q)
#concat连接
Pieces=[tempdf[:5],tempdf[len (Tempdf)-4:]]
Pd.concat (Pieces)
#两个不同逻辑结构的对象能否连接 portrait
Piece1=quotesdf[:3]
Piece2=tempdf[:3]
Pd.concat ([Piece1,piece2],ignore_index=true)
#join连接 Landscape
Pd.merge (djidf,akdf,on= ' code ')
Pd.merge. (djidf,akdf,on= ' Code '). Drop ([' Lasttrade '],axis=1)
#聚类分析
From Pylab Import *
From SCIPY.CLUSTER.VQ Import *
LIST1=[88,74,96,85]
LIST2=[92,99,95,94]
LIST3=[91,87,99,95]
LIST4=[78,99,97,81]
LIST5=[88,78,98,84]
LIST6=[100,95,100,92]
Data=vstack ((LIST1,LIST2,LIST3,LIST4,LIST5,LIST6))
Centroids,_=kmeans (data,2)
RESULT,_=VQ (Data,centroids)
Print result
Python Primer Base Code