[Python] 练习代码

100 阅读 0 评论 66 点赞

我是靠谱客的博主清爽荔枝，这篇文章主要介绍[Python] 练习代码，现在分享给大家，希望可以做个参考。

复制代码

# from random import randrange
# num = int(input('摇几次骰子: '))
# sides=int(input('筛子有几个面: '))
# sum=0
# for i in range(num):
#
sum+= randrange(sides)+1
# print('最终的点数和是 ',sum,'平均点数是:',sum/num)
# from random import shuffle
# from pprint import pprint
# values=list(range(1,11))+'Jack Queen King'.split()
#并入列表中
# card_suits='diamonds clubs hearts spades'.split()
# value_suit=['{} of {}'.format(v,c) for v in values for c in card_suits]
# shuffle(value_suit)
#打乱顺序
# pprint(value_suit[:12])
# while value_suit:
#
input(value_suit.pop())

f=open('a123.txt','a')
f.write('hello aaaaaaaaaaaaadddddddddddddddddd')
f.close()
f=open('a123.txt','r')
for i in range(10):
print(f.readline(),end='')
f = open('a123.txt','a')
f.write('Thisnis nonhaikou')
f.close()
def process(string):
print('处理中...',string)
# with open('a123.txt','r') as f:
#
while True:
#
line=f.readline()
#
if not line:
#
break
#
process(line)
with open('a123.txt','r') as f:
for line in f:
process(line)
with open('a123.txt','r') as f:
for line in f.readlines():
process(line)
def triangles():
row = [1]
while True:
yield(row)
row = [1] + [row[k] + row[k + 1] for k in range(len(row) - 1)] + [1]
n = 0
results = []
for t in triangles():
print(t)
results.append(t)
n = n + 1
if n == 10:
break
if results == [
[1],
[1, 1],
[1, 2, 1],
[1, 3, 3, 1],
[1, 4, 6, 4, 1],
[1, 5, 10, 10, 5, 1],
[1, 6, 15, 20, 15, 6, 1],
[1, 7, 21, 35, 35, 21, 7, 1],
[1, 8, 28, 56, 70, 56, 28, 8, 1],
[1, 9, 36, 84, 126, 126, 84, 36, 9, 1]
]:
print('测试通过!')
else:
print('测试失败!')
' a test module '
__author__ = 'Michael Liao'
import sys
def test():
args = sys.argv
if len(args)==1:
print('Hello, world!')
elif len(args)==2:
print('Hello, %s!' % args[1])
else:
print('Too many arguments!')
if __name__=='__main__':
test()
class Student(object):
pass
bart = Student()
bart.name='jojo'
bart.name
class Student(object):
def __init__(self, name, score):
self.name = name
self.score = score
def get_grade(self):
if self.score >= 90:
return 'A'
elif self.score >= 60:
return 'B'
else:
return 'C'
gg=Student('aaa',100)
gg.get_grade()
for c in "python":
if c=='t':
continue
print(c,end=' ')
s='python'
while s !='':
for c in s:
print(c,end='')
s=s[:-1]
import random
from pprint import pprint
pprint(random.seed(10))
random.random()
from random import random
from time import perf_counter
DARTS=1000*10000
hits=0.0
start=perf_counter()
for i in range(1,DARTS+1):
x,y=random(),random()
dist=pow(x**2+y**2,0.5)
if dist <= 1:
hits=hits+1
pi = 4*(hits/DARTS)
print("圆周率值是:{}".format(pi))
print('运行时间是:{:.20f}s'.format(perf_counter()-start))
import requests
r=requests.get('http://www.shipxy.com/')
r.status_code
r.text
for i in range(1,5):
for j in range(1,5):
for k in range(1,5):
if (i!=j)and(j!=k)and(k!=i):
print(i,j,k)
profit = int(input('输入发放的利润值(万元): '))
if 0 <= profit <10:
print('提成为:',profit*0.1,'万元')
if 10 <= profit < 20:
print('提成为:',(profit-10)*0.075+10*0.1,'万元')
if 20 <= profit < 40:
print('提成为:',(profit-20)*0.05+10*0.075+10*0.1,'万元')
if 40 <= profit < 60:
print('提成为:',(profit-40)*0.03+20*0.05+10*0.075+10*0.1,'万元')
if 60 <= profit < 100:
print('提成为:',(profit-60)*0.015+20*0.03+20*0.05+10*0.075+10*0.1,'万元')
if profit >= 100:
print('提成为:',(profit-100)*0.01+40*0.015+20*0.03+20*0.05+10*0.075+10*0.1,'万元')
profit = int(input('输入企业的利润值(万元): '))
gap = [100,60,40,20,10,0]
ratio =[0.01,0.015,0.03,0.05,0.075,0.1]
bonus=0
for idx in range(0,6):
if profit >= gap[idx]:
bonus += (profit-gap[idx])*ratio[idx]
profit=gap[idx]
print('提成为:',bonus,'万元')
profit = int(input('输入企业的利润值(万元): '))
def get_bonus(profit):
bonus = 0
if 0 <= profit <= 10:
bonus = 0.1*profit
elif (profit > 10) and (profit <= 20):
bonus = (profit-10)*0.075 + get_bonus(10)
elif (profit > 20) and (profit <= 40):
bonus = (profit-20)*0.05 + get_bonus(20)
elif (profit > 40) and (profit <= 60):
bonus = (profit-40)*0.03 + get_bonus(40)
elif (profit > 60) and (profit <= 100):
bonus = (profit-60)*0.015 + get_bonus(60)
elif (profit >100):
bonus = (profit-100)*0.01 + get_bonus(100)
else:
print("利润输入值不能为负")
return bonus
if __name__ == '__main__':
print('提成为:',get_bonus(profit),'万元')
'''
分析：
x + 100 = m^2
x + 100 + 168 = n^2
n^2 - m^2 = 168
(n + m) * (n - m) = 168
n > m >= 0
n - m 最小值为 1
n + m 最大为 168
n 最大值为 168
m 最大值为 167
'''
def _test():
for m in range(0, 168):
for n in range(m + 1, 169):
#print('n=%s,m=%s' % (n, m))
if (n + m) * (n - m) == 168:
print("该数为:" + str(n * n - 168 - 100))
print("该数为:" + str(m * m - 100))
print('n为%s,m为%s' % (n, m))
if __name__ == '__main__':
_test()
def test1():
for n in range(0,168):
for m in range(n,169):
if (m+n)*(m-n) == 168:
print("这个整数是: ",str(n*n-100))
if __name__ =='__main__':
test1()
import pandas as pd
df = pd.read_csv(r'c:UsersclementeDesktopalltrain.csv',index_col='Id')
df.head()
for i in range(0,7):
for j in range(0,7):
for k in range(0,7):
for g in range(0,7):
for h in range(0,7):
while (i!=j) and(i!=g) and(g!=h)and(h!=k)and(k!=i):
if (i+j+k+g+h)==15:
print (i,j,k,g,h)
import random
def gen5num():
alldigit=[0,1,2,3,4,5,6,0]
first=random.randint(0,6)
#randint包含两端,0和6

alldigit.remove(first)
second=random.choice(alldigit)
alldigit.remove(second)
third=random.choice(alldigit)
alldigit.remove(third)
forth=random.choice(alldigit)
alldigit.remove(forth)
fiveth=random.choice(alldigit)
alldigit.remove(fiveth)
if (first+second+third+forth+fiveth)==15:
return first,second,third,forth,fiveth
if __name__=='__main__':
for i in range(100):
print(gen5num())
#!/usr/bin/env python3
#coding=utf-8
from itertools import permutations
t = 0
for i in permutations('0123456',5):
print(''.join(i))
t += 1
print("不重复的数量有:%s"%t)
def sum_1():
"""
aaaddd
"""
for i in '01234567':
p += int(i)
print(sum(p))
sum_1()
np.*load*?
#题目：数组中找出两个元素之和 等于给定的整数
# 思路：
# 1、将数组元素排序；
# 2、array[i]与a[j](j的取值：i+1到len_array-1) 相加；
# 3、如两两相加＜整数继续，如＝整数则输出元素值；
# 4、如＞则直接退出，i+1 开始下一轮相加比较
def addData(array, sumdata):
"""
aaaadddd
"""
temp_array = array
temp_sumdata = sumdata
print ("sumdata: {}".format(temp_sumdata))
sorted(temp_array)
len_temp_array = len(temp_array)
# 计数符合条件的组数
num = 0
for i in range(0, len_temp_array-1):
for j in range(i+1, len_temp_array):
for k in range(j+1,len_temp_array):
if temp_array[i] + temp_array[j] + temp_array[k] < temp_sumdata:
continue
elif temp_array[i] + temp_array[j] + temp_array[k] == temp_sumdata:
num += 1
print("Group {} :".format(num))
print("下标：{}, 元素值： {}".format(i, temp_array[i]))
else:
break
if __name__=="__main__":
test_array = [0,1,2,3,4,5,6,0]
test_sumdata = 4
addData(test_array, test_sumdata)
#题目：数组中找出两个元素之和 等于给定的整数
# 思路：
# 1、将数组元素排序；
# 2、array[i]与a[j](j的取值：i+1到len_array-1) 相加；
# 3、如两两相加＜整数继续，如＝整数则输出元素值；
# 4、如＞则直接退出，i+1 开始下一轮相加比较
import numpy as np
names=np.array(['Bob','Joe','Will','Bob','Will','Joe','Joe'])
data=np.random.randn(7,4)
names
data
names == 'Bob'
data[names=='Bob']
arr[[4,3,0,6]]
import matplotlib.pyplot as plt
points = np.arange(-5,5,0.01)
xs,ys=np.meshgrid(points,points)
z=np.sqrt(xs**2+ys**2)
plt.imshow(z,cmap=plt.cm.gray)
plt.colorbar()
plt.title("图像
$sqrt{x^2+y^2}$")
import pandas as pd
obj=pd.Series(range(3),index=["a","b","c"])
index=obj.index
index[1]='d'
import numpy as np
import pandas as pd
data=pd.DataFrame(np.arange(16).reshape(4,4),index=[1,2,3,4],columns=["one","two","three","forth"])
data<3
df1=pd.DataFrame({"A":[1,2]})
df1
obj=pd.Series(["a","a","b","c"]*4)
obj
obj.describe()
import json
result = json.loads(obj)
result
import pandas as pd
ages=[12,34,23,45,67,30,20,55,98,30,43]
bins=[1,20,30,40,50,100]
cats=pd.cut(ages,bins)
cats
cats.codes
pd.value_counts(cats)
DataF=pd.DataFrame(np.arange(5*4).reshape((5,4)))
DataF
sample_1=np.random.permutation(5*4)
sample_1.reshape(5,4)
df=pd.DataFrame({'key':['b','b','a','c','a','b'],'data1':range(6)})
df
df[["data1"]]
import pandas as pd
left=pd.DataFrame({'key1':['foo','foo','bar'],'key2':['one','two','one'],'lval':[1,2,3]})
right=pd.DataFrame({'key1':['foo','foo','bar','bar'],'key2':['one','one','one','two'],'rval':[4,5,6,7]})
pd.merge(left,right,on=['key1'])
import matplotlib.pyplot as plt
import numpy as np
data=np.arange(10000)
plt.plot(data)
fig=plt.figure()
ax1=fig.add_subplot(2,2,1)
ax2=fig.add_subplot(2,2,2)
ax3=fig.add_subplot(2,2,3)
ax1.hist(np.random.randn(100),bins=20,color='k',alpha=0.5)
ax2.scatter(np.arange(30),np.arange(30)+3*np.random.randn(30))
ax3.plot(np.random.randn(50).cumsum(),drawstyle='steps-post')
fig=plt.figure()
ax=fig.add_subplot(1,1,1)
rect=plt.Rectangle((0.5,0.8),0.4,0.4,color='g',alpha=0.4)
ax.add_patch(rect)
plt.savefig("真的.svg",bbox_inches='tight')
s=pd.Series(np.random.randn(10).cumsum())
s.plot()
s=pd.Series(np.random.randn(10).cumsum(),index=np.arange(0,100,10))
s.plot()
df=pd.DataFrame(np.random.randn(10,4).cumsum(0),columns=['A','B','C','D'],index=np.arange(0,100,10))
df.plot()
fig,axes=plt.subplots(2,1)
data=pd.Series(np.random.rand(16),index=list("abcdefghijklmnop"))
data.plot.bar(ax=axes[0],color='k',alpha=0.7)
data.plot.barh(ax=axes[1],color='g',alpha=0.7)
plt.show()
df=pd.DataFrame(np.random.rand(6,4),index=['one','two','three','four','five','six'],columns=pd.Index(['A','B','C','D'],name='Genus'))
df
df.plot.bar()
df.plot.barh(stacked=True,alpha=0.5)
tips=pd.read_csv('tips.csv')
party_counts = pd.crosstab(tips['day'],tips['size'])
party_counts
party_counts=party_counts.loc[:,2:5]
party_counts
party_counts.sum(1)
party_pcts= party_counts.div(party_counts.sum(1),axis=0)
party_pcts.plot.bar()
import seaborn as sns
tips=pd.read_csv('tips.csv')
tips['tip_pct']=tips['tip']/(tips['total_bill']-tips['tip'])
tips.head()
sns.barplot(x='tip_pct',y='day',data=tips,orient='h')
sns.barplot(x='tip_pct',y='day',hue='time',data=tips,orient='h')
sns.set(style='whitegrid')
tips['tip_pct'].plot.hist(bins=50)
tips['total_bill'].plot.hist(bins=50)
tips['tip_pct'].plot.density()
tips['total_bill'].plot.density()
comp1=np.random.normal(0,1,size=200)
comp2=np.random.normal(10,2,size=200)
values=pd.Series(np.concatenate([comp1,comp2]))
sns.distplot(values,bins=101,color='k')
macro=pd.read_csv('macrodata.csv')
data=macro[['cpi','m1','tbilrate','unemp']]
trans_data=np.log(data).diff().dropna()
trans_data.head()
trans_data[-5:]
sns.regplot("m1","unemp",data=trans_data)
plt.title('Changes in log {} versus log {}'.format('m1','unemp'))
sns.set(style="ticks", color_codes=True)
sns.pairplot(trans_data,diag_kind='kde',kind='reg')
sns.pairplot(trans_data,diag_kind='hist',kind='reg')
sns.factorplot(x='day',y='tip_pct',row='time',hue='smoker',kind='box',data=tips[tips.tip_pct<0.5])
tips.describe()
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
df=pd.DataFrame({'key1':['a','a','b','b','a'],'key2':['one','two','one','two','one'],'data1':np.random.randn(5),'data2':np.random.randn(5)})
df
group_1=df['data1'].groupby(df['key1'])
group_1.describe()
group_2=df['data1'].groupby([df['key1'],df['key2']]).mean()
group_2
states=np.array(['Ohio','California','California','Ohio','Ohio'])
years=np.array([2005,2005,2006,2005,2006])
df['data1'].groupby([states,years]).mean()
dict(list(df.groupby('key1')))
try:
year=input("输入年份:")
month=input("输入月份: ")
day=input("输入日期号: ")
finally:
print("正在计算")
months2days=[0,31,59,90,120,151,181,212,243,273,304,334]
# 闰年
if int(year) % 4 ==0:
for i in range(2,12,1):
months2days[i] +=1
month_index=[]
for j in range(12):
month_index.append(i+1)
dict_md=dict(zip(month_index,months2days))
whichday=dict_md[int(month)]+int(day)
print('结果是: 第{}天'.format(whichday))
def unsortedSearch(list, i, u):
found = False
pos = 0
pos2 = 0
while pos < len(list) and not found:
if int(list[pos]) < int(u) :
if int(list[pos2]) > int(i):
found = True
pos2 = pos2 + 1
pos = pos + 1
return found
unsortedList = ['1', '3', '4', '2', '6', '9', '2', '1', '3', '7']
num1 = '3'
num2 = '5'
isItThere = unsortedSearch(unsortedList, num1, num2)
if isItThere:
print ("There is a number between those values")
else:
print ("There isn't a number between those values")
def get_nums():
nums=[]
n=int(input("一共有几个整数?"))
for i in range(n):
x=int(input('请按次随机输入第{}个整数(剩余{}次输入)：'.format(i+1,n-i)))
nums.append(x)
return nums
if __name__=='__main__':
list_nums=get_nums()
def BubbleSort(nums):
#冒泡法
print('初始整数集合为:{}'.format(nums))
for i in range(len(nums)-1):
for j in range(len(nums)-i-1):
if nums[j]>nums[j+1]:
nums[j],nums[j+1]=nums[j+1],nums[j] #调换位置,相互赋值
print("第{}次迭代排序结果:{}".format((len(nums)-j-1),nums))
return nums
if __name__=='__main__':
print('经过冒泡法排序最终得到:{}'.format(BubbleSort(list_nums)))
def get_nums():
nums=[]
n=int(input("一共有几个整数?"))
for i in range(n):
x=int(input('请按次随机输入第{}个整数(剩余{}次输入)：'.format(i+1,n-i)))
nums.append(x)
return nums
if __name__=='__main__':
myList=get_nums()
def selectedSort(myList):
#获取list的长度
length = len(myList)
#一共进行多少轮比较
for i in range(0,length-1):
#默认设置最小值得index为当前值
smallest = i
#用当先最小index的值分别与后面的值进行比较,以便获取最小index
for j in range(i+1,length):
#如果找到比当前值小的index,则进行两值交换
if myList[j]<myList[smallest]:
tmp = myList[j]
myList[j] = myList[smallest]
myList[smallest]=tmp
#打印每一轮比较好的列表
print("Round ",i,": ",myList) #根据第一个i循环进行打印,而不是选j循环
print("选择排序法:迭代过程 ")
selectedSort(myList)
def merge_sort(LIST):
start = []
end = []
while len(LIST) > 1:
a = min(LIST)
b = max(LIST)
start.append(a)
end.append(b)
LIST.remove(a)
LIST.remove(b)
if LIST:
start.append(LIST[0])
end.reverse()
return (start + end)
if __name__=='__main__':
nums=[]
n=int(input('一共几位数: '))
for i in range(n):
x=int(input("请依次输入整数:"))
nums.append(x)
print(merge_sort(nums))
# =============================================================================
#10.1.2
# =============================================================================
import pandas as pd
df=pd.DataFrame({'key1':['a','a','b','b','a'],'key2':['one','two','one','two','one'],'data1':np.random.randn(5),'data2':np.random.randn(5)})
df
df.groupby(['key1','key2'])['data1'].mean()
people=pd.DataFrame(np.random.randn(5,5),columns=['a','b','c','d','e'],index=['joe','steve','wes','jim','travis'])
people
mapping={'a':'red','b':'red','c':'blue','d':'blue','e':'red','f':'orange'}
by_column=people.groupby(mapping,axis=1)
by_column.mean()
map_series=pd.Series(mapping)
people.groupby(len).sum()
# =============================================================================
# 分组加权
# =============================================================================
import pandas as pd
df=pd.DataFrame({'目录':['a','a','a','a','b','b','b','b'],'data':np.random.randn(8),'weights':np.random.randn(8)})
df
grouped=df.groupby('目录')
get_weighpoint=lambda x: np.average(x['data'],weights=x['weights'])
grouped.apply(get_weighpoint)
# =============================================================================
# 
# =============================================================================

spx=pd.read_csv('stock_px_2.csv',index_col=0,parse_dates=True)
spx
spx.info()
from datetime import datetime
datestrs=['7/6/2011','8/6/2011']
[datetime.strptime(x,'%m/%d/%Y')for x in datestrs]
dates=pd.date_range('1/1/2018',periods=1000)
dates
long_df=pd.DataFrame(np.random.randn(1000,4),index=dates,columns=['Colorado','Texas','New York','Ohio'])
long_df
pd.date_range('2018-10-1',periods=30,freq='1h')
# =============================================================================
# 
# =============================================================================
close_px_all=pd.read_csv("stock_px_2.csv",parse_dates=True,index_col=0)
close_px=close_px_all[['AAPL','MSFT','XOM']]
close_px=close_px.resample("B").ffill()
close_px.AAPL.plot()
close_px.AAPL.rolling(250).mean().plot()
import pandas as pd
import numpy as np
values=pd.Series(['apple','orange','apple','apple']*2)
values
pd.unique(values)
pd.value_counts(values)
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.linear_model import RANSACRegressor, LinearRegression, TheilSenRegressor
from sklearn.metrics import explained_variance_score, mean_absolute_error, mean_squared_error, median_absolute_error, r2_score
from sklearn.svm import SVR
from sklearn.linear_model import Ridge,Lasso,ElasticNet,BayesianRidge
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.cross_validation import train_test_split
data = pd.read_csv('../cement_data.csv')
# 查看数据记录的长度，共1030行
print(len(data))
# 查看前五行数据
data.head()
import pandas
titanic=pandas.read_csv('train.csv')
titanic.head()
titanic.describe()
titanic['Age']=titanic['Age'].fillna(titanic['Age'].median())
print(titanic['Sex'].unique()) #找Sex特征里的分类字符名，只有两种可能性
titanic.loc[titanic['Sex']=='female','Sex']=1#把分类字符名转换成整数1,0形式，进行标记
titanic.loc[titanic['Sex']=='male','Sex']=0
#对embarked　登船地　进行填充（按最多标记）
print(titanic['Embarked'].unique())
titanic['Embarked']=titanic['Embarked'].fillna('S')
titanic.loc[titanic['Embarked']=='S']=0
titanic.loc[titanic['Embarked']=='C']=1
titanic.loc[titanic['Embarked']=='Q']=2
# =============================================================================
# 引进模型，线性回归
# =============================================================================
from sklearn.linear_model import LinearRegression
from sklearn.cross_validation import KFold
#cross_validation　交叉验证，进行调参，训练数据集分成三份，三份做交叉验证

predictors=['Pclass','Sex','Age','SibSp','Parch','Fare','Embarked'] #需要输入并做预测的特征列
alg=LinearRegression()
kf=KFold(titanic.shape[0],n_folds=3,random_state=1) #shape[0]一共有多少行,random_state=1 随机种子开启，n_fold=3把训练集分为三份

predictions=[]
for train,test in kf:
train_predictors=titanic[predictors].iloc[train,:]
#交叉验证中，除开训练的部分
train_target=titanic['Survived'].iloc[train]#获取目标训练集
alg.fit(train_predictors,train_target) #依据模型，训练

test_predictions=alg.predict(titanic[predictors].iloc[test,:]) #测试集

predictions.append(test_predictions)
import numpy as np
predictions=np.concatenate(predictions,axis=0)
# 整理输出值,按照可能性分类到0,1
predictions[predictions>=0.5]=0
predictions[predictions<0.5]=1
accuracy=sum(predictions[predictions==titanic['Survived']])/len(predictions)
print(accuracy)
# =============================================================================
# 逻辑回归
# =============================================================================
from sklearn import cross_validation
from sklearn.linear_model import LogisticRegression
alg=LogisticRegression(random_state=1)
scores=cross_validation.cross_val_score(alg,titanic[predictors],titanic['Survived'],cv=3)
print(scores.mean())
# =============================================================================
# 随机森林
# =============================================================================
from sklearn import cross_validation
from sklearn.ensemble import RandomForestClassifier
predictors=['Pclass','Sex','Age','SibSp','Parch','Fare','Embarked']
alg=RandomForestClassifier(random_state=1,n_estimators=10,min_samples_split=2,min_samples_leaf=1)
kf=cross_validation.KFold(titanic.shape[0],n_folds=3,random_state=1)
scores=scores=cross_validation.cross_val_score(alg,titanic[predictors],titanic['Survived'],cv=kf)
print(scores.mean())

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
# from random import randrange
# num = int(input('摇几次骰子: '))
# sides=int(input('筛子有几个面: '))
# sum=0
# for i in range(num):
#
sum+= randrange(sides)+1
# print('最终的点数和是 ',sum,'平均点数是:',sum/num)
# from random import shuffle
# from pprint import pprint
# values=list(range(1,11))+'Jack Queen King'.split()
#并入列表中
# card_suits='diamonds clubs hearts spades'.split()
# value_suit=['{} of {}'.format(v,c) for v in values for c in card_suits]
# shuffle(value_suit)
#打乱顺序
# pprint(value_suit[:12])
# while value_suit:
#
input(value_suit.pop())

f=open('a123.txt','a')
f.write('hello aaaaaaaaaaaaadddddddddddddddddd')
f.close()
f=open('a123.txt','r')
for i in range(10):
print(f.readline(),end='')
f = open('a123.txt','a')
f.write('Thisnis nonhaikou')
f.close()
def process(string):
print('处理中...',string)
# with open('a123.txt','r') as f:
#
while True:
#
line=f.readline()
#
if not line:
#
break
#
process(line)
with open('a123.txt','r') as f:
for line in f:
process(line)
with open('a123.txt','r') as f:
for line in f.readlines():
process(line)
def triangles():
row = [1]
while True:
yield(row)
row = [1] + [row[k] + row[k + 1] for k in range(len(row) - 1)] + [1]
n = 0
results = []
for t in triangles():
print(t)
results.append(t)
n = n + 1
if n == 10:
break
if results == [
[1],
[1, 1],
[1, 2, 1],
[1, 3, 3, 1],
[1, 4, 6, 4, 1],
[1, 5, 10, 10, 5, 1],
[1, 6, 15, 20, 15, 6, 1],
[1, 7, 21, 35, 35, 21, 7, 1],
[1, 8, 28, 56, 70, 56, 28, 8, 1],
[1, 9, 36, 84, 126, 126, 84, 36, 9, 1]
]:
print('测试通过!')
else:
print('测试失败!')
' a test module '
__author__ = 'Michael Liao'
import sys
def test():
args = sys.argv
if len(args)==1:
print('Hello, world!')
elif len(args)==2:
print('Hello, %s!' % args[1])
else:
print('Too many arguments!')
if __name__=='__main__':
test()
class Student(object):
pass
bart = Student()
bart.name='jojo'
bart.name
class Student(object):
def __init__(self, name, score):
self.name = name
self.score = score
def get_grade(self):
if self.score >= 90:
return 'A'
elif self.score >= 60:
return 'B'
else:
return 'C'
gg=Student('aaa',100)
gg.get_grade()
for c in "python":
if c=='t':
continue
print(c,end=' ')
s='python'
while s !='':
for c in s:
print(c,end='')
s=s[:-1]
import random
from pprint import pprint
pprint(random.seed(10))
random.random()
from random import random
from time import perf_counter
DARTS=1000*10000
hits=0.0
start=perf_counter()
for i in range(1,DARTS+1):
x,y=random(),random()
dist=pow(x**2+y**2,0.5)
if dist <= 1:
hits=hits+1
pi = 4*(hits/DARTS)
print("圆周率值是:{}".format(pi))
print('运行时间是:{:.20f}s'.format(perf_counter()-start))
import requests
r=requests.get('http://www.shipxy.com/')
r.status_code
r.text
for i in range(1,5):
for j in range(1,5):
for k in range(1,5):
if (i!=j)and(j!=k)and(k!=i):
print(i,j,k)
profit = int(input('输入发放的利润值(万元): '))
if 0 <= profit <10:
print('提成为:',profit*0.1,'万元')
if 10 <= profit < 20:
print('提成为:',(profit-10)*0.075+10*0.1,'万元')
if 20 <= profit < 40:
print('提成为:',(profit-20)*0.05+10*0.075+10*0.1,'万元')
if 40 <= profit < 60:
print('提成为:',(profit-40)*0.03+20*0.05+10*0.075+10*0.1,'万元')
if 60 <= profit < 100:
print('提成为:',(profit-60)*0.015+20*0.03+20*0.05+10*0.075+10*0.1,'万元')
if profit >= 100:
print('提成为:',(profit-100)*0.01+40*0.015+20*0.03+20*0.05+10*0.075+10*0.1,'万元')
profit = int(input('输入企业的利润值(万元): '))
gap = [100,60,40,20,10,0]
ratio =[0.01,0.015,0.03,0.05,0.075,0.1]
bonus=0
for idx in range(0,6):
if profit >= gap[idx]:
bonus += (profit-gap[idx])*ratio[idx]
profit=gap[idx]
print('提成为:',bonus,'万元')
profit = int(input('输入企业的利润值(万元): '))
def get_bonus(profit):
bonus = 0
if 0 <= profit <= 10:
bonus = 0.1*profit
elif (profit > 10) and (profit <= 20):
bonus = (profit-10)*0.075 + get_bonus(10)
elif (profit > 20) and (profit <= 40):
bonus = (profit-20)*0.05 + get_bonus(20)
elif (profit > 40) and (profit <= 60):
bonus = (profit-40)*0.03 + get_bonus(40)
elif (profit > 60) and (profit <= 100):
bonus = (profit-60)*0.015 + get_bonus(60)
elif (profit >100):
bonus = (profit-100)*0.01 + get_bonus(100)
else:
print("利润输入值不能为负")
return bonus
if __name__ == '__main__':
print('提成为:',get_bonus(profit),'万元')
'''
分析：
x + 100 = m^2
x + 100 + 168 = n^2
n^2 - m^2 = 168
(n + m) * (n - m) = 168
n > m >= 0
n - m 最小值为 1
n + m 最大为 168
n 最大值为 168
m 最大值为 167
'''
def _test():
for m in range(0, 168):
for n in range(m + 1, 169):
#print('n=%s,m=%s' % (n, m))
if (n + m) * (n - m) == 168:
print("该数为:" + str(n * n - 168 - 100))
print("该数为:" + str(m * m - 100))
print('n为%s,m为%s' % (n, m))
if __name__ == '__main__':
_test()
def test1():
for n in range(0,168):
for m in range(n,169):
if (m+n)*(m-n) == 168:
print("这个整数是: ",str(n*n-100))
if __name__ =='__main__':
test1()
import pandas as pd
df = pd.read_csv(r'c:UsersclementeDesktopalltrain.csv',index_col='Id')
df.head()
for i in range(0,7):
for j in range(0,7):
for k in range(0,7):
for g in range(0,7):
for h in range(0,7):
while (i!=j) and(i!=g) and(g!=h)and(h!=k)and(k!=i):
if (i+j+k+g+h)==15:
print (i,j,k,g,h)
import random
def gen5num():
alldigit=[0,1,2,3,4,5,6,0]
first=random.randint(0,6)
#randint包含两端,0和6

alldigit.remove(first)
second=random.choice(alldigit)
alldigit.remove(second)
third=random.choice(alldigit)
alldigit.remove(third)
forth=random.choice(alldigit)
alldigit.remove(forth)
fiveth=random.choice(alldigit)
alldigit.remove(fiveth)
if (first+second+third+forth+fiveth)==15:
return first,second,third,forth,fiveth
if __name__=='__main__':
for i in range(100):
print(gen5num())
#!/usr/bin/env python3
#coding=utf-8
from itertools import permutations
t = 0
for i in permutations('0123456',5):
print(''.join(i))
t += 1
print("不重复的数量有:%s"%t)
def sum_1():
"""
aaaddd
"""
for i in '01234567':
p += int(i)
print(sum(p))
sum_1()
np.*load*?
#题目：数组中找出两个元素之和 等于给定的整数
# 思路：
# 1、将数组元素排序；
# 2、array[i]与a[j](j的取值：i+1到len_array-1) 相加；
# 3、如两两相加＜整数继续，如＝整数则输出元素值；
# 4、如＞则直接退出，i+1 开始下一轮相加比较
def addData(array, sumdata):
"""
aaaadddd
"""
temp_array = array
temp_sumdata = sumdata
print ("sumdata: {}".format(temp_sumdata))
sorted(temp_array)
len_temp_array = len(temp_array)
# 计数符合条件的组数
num = 0
for i in range(0, len_temp_array-1):
for j in range(i+1, len_temp_array):
for k in range(j+1,len_temp_array):
if temp_array[i] + temp_array[j] + temp_array[k] < temp_sumdata:
continue
elif temp_array[i] + temp_array[j] + temp_array[k] == temp_sumdata:
num += 1
print("Group {} :".format(num))
print("下标：{}, 元素值： {}".format(i, temp_array[i]))
else:
break
if __name__=="__main__":
test_array = [0,1,2,3,4,5,6,0]
test_sumdata = 4
addData(test_array, test_sumdata)
#题目：数组中找出两个元素之和 等于给定的整数
# 思路：
# 1、将数组元素排序；
# 2、array[i]与a[j](j的取值：i+1到len_array-1) 相加；
# 3、如两两相加＜整数继续，如＝整数则输出元素值；
# 4、如＞则直接退出，i+1 开始下一轮相加比较
import numpy as np
names=np.array(['Bob','Joe','Will','Bob','Will','Joe','Joe'])
data=np.random.randn(7,4)
names
data
names == 'Bob'
data[names=='Bob']
arr[[4,3,0,6]]
import matplotlib.pyplot as plt
points = np.arange(-5,5,0.01)
xs,ys=np.meshgrid(points,points)
z=np.sqrt(xs**2+ys**2)
plt.imshow(z,cmap=plt.cm.gray)
plt.colorbar()
plt.title("图像
$sqrt{x^2+y^2}$")
import pandas as pd
obj=pd.Series(range(3),index=["a","b","c"])
index=obj.index
index[1]='d'
import numpy as np
import pandas as pd
data=pd.DataFrame(np.arange(16).reshape(4,4),index=[1,2,3,4],columns=["one","two","three","forth"])
data<3
df1=pd.DataFrame({"A":[1,2]})
df1
obj=pd.Series(["a","a","b","c"]*4)
obj
obj.describe()
import json
result = json.loads(obj)
result
import pandas as pd
ages=[12,34,23,45,67,30,20,55,98,30,43]
bins=[1,20,30,40,50,100]
cats=pd.cut(ages,bins)
cats
cats.codes
pd.value_counts(cats)
DataF=pd.DataFrame(np.arange(5*4).reshape((5,4)))
DataF
sample_1=np.random.permutation(5*4)
sample_1.reshape(5,4)
df=pd.DataFrame({'key':['b','b','a','c','a','b'],'data1':range(6)})
df
df[["data1"]]
import pandas as pd
left=pd.DataFrame({'key1':['foo','foo','bar'],'key2':['one','two','one'],'lval':[1,2,3]})
right=pd.DataFrame({'key1':['foo','foo','bar','bar'],'key2':['one','one','one','two'],'rval':[4,5,6,7]})
pd.merge(left,right,on=['key1'])
import matplotlib.pyplot as plt
import numpy as np
data=np.arange(10000)
plt.plot(data)
fig=plt.figure()
ax1=fig.add_subplot(2,2,1)
ax2=fig.add_subplot(2,2,2)
ax3=fig.add_subplot(2,2,3)
ax1.hist(np.random.randn(100),bins=20,color='k',alpha=0.5)
ax2.scatter(np.arange(30),np.arange(30)+3*np.random.randn(30))
ax3.plot(np.random.randn(50).cumsum(),drawstyle='steps-post')
fig=plt.figure()
ax=fig.add_subplot(1,1,1)
rect=plt.Rectangle((0.5,0.8),0.4,0.4,color='g',alpha=0.4)
ax.add_patch(rect)
plt.savefig("真的.svg",bbox_inches='tight')
s=pd.Series(np.random.randn(10).cumsum())
s.plot()
s=pd.Series(np.random.randn(10).cumsum(),index=np.arange(0,100,10))
s.plot()
df=pd.DataFrame(np.random.randn(10,4).cumsum(0),columns=['A','B','C','D'],index=np.arange(0,100,10))
df.plot()
fig,axes=plt.subplots(2,1)
data=pd.Series(np.random.rand(16),index=list("abcdefghijklmnop"))
data.plot.bar(ax=axes[0],color='k',alpha=0.7)
data.plot.barh(ax=axes[1],color='g',alpha=0.7)
plt.show()
df=pd.DataFrame(np.random.rand(6,4),index=['one','two','three','four','five','six'],columns=pd.Index(['A','B','C','D'],name='Genus'))
df
df.plot.bar()
df.plot.barh(stacked=True,alpha=0.5)
tips=pd.read_csv('tips.csv')
party_counts = pd.crosstab(tips['day'],tips['size'])
party_counts
party_counts=party_counts.loc[:,2:5]
party_counts
party_counts.sum(1)
party_pcts= party_counts.div(party_counts.sum(1),axis=0)
party_pcts.plot.bar()
import seaborn as sns
tips=pd.read_csv('tips.csv')
tips['tip_pct']=tips['tip']/(tips['total_bill']-tips['tip'])
tips.head()
sns.barplot(x='tip_pct',y='day',data=tips,orient='h')
sns.barplot(x='tip_pct',y='day',hue='time',data=tips,orient='h')
sns.set(style='whitegrid')
tips['tip_pct'].plot.hist(bins=50)
tips['total_bill'].plot.hist(bins=50)
tips['tip_pct'].plot.density()
tips['total_bill'].plot.density()
comp1=np.random.normal(0,1,size=200)
comp2=np.random.normal(10,2,size=200)
values=pd.Series(np.concatenate([comp1,comp2]))
sns.distplot(values,bins=101,color='k')
macro=pd.read_csv('macrodata.csv')
data=macro[['cpi','m1','tbilrate','unemp']]
trans_data=np.log(data).diff().dropna()
trans_data.head()
trans_data[-5:]
sns.regplot("m1","unemp",data=trans_data)
plt.title('Changes in log {} versus log {}'.format('m1','unemp'))
sns.set(style="ticks", color_codes=True)
sns.pairplot(trans_data,diag_kind='kde',kind='reg')
sns.pairplot(trans_data,diag_kind='hist',kind='reg')
sns.factorplot(x='day',y='tip_pct',row='time',hue='smoker',kind='box',data=tips[tips.tip_pct<0.5])
tips.describe()
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
df=pd.DataFrame({'key1':['a','a','b','b','a'],'key2':['one','two','one','two','one'],'data1':np.random.randn(5),'data2':np.random.randn(5)})
df
group_1=df['data1'].groupby(df['key1'])
group_1.describe()
group_2=df['data1'].groupby([df['key1'],df['key2']]).mean()
group_2
states=np.array(['Ohio','California','California','Ohio','Ohio'])
years=np.array([2005,2005,2006,2005,2006])
df['data1'].groupby([states,years]).mean()
dict(list(df.groupby('key1')))
try:
year=input("输入年份:")
month=input("输入月份: ")
day=input("输入日期号: ")
finally:
print("正在计算")
months2days=[0,31,59,90,120,151,181,212,243,273,304,334]
# 闰年
if int(year) % 4 ==0:
for i in range(2,12,1):
months2days[i] +=1
month_index=[]
for j in range(12):
month_index.append(i+1)
dict_md=dict(zip(month_index,months2days))
whichday=dict_md[int(month)]+int(day)
print('结果是: 第{}天'.format(whichday))
def unsortedSearch(list, i, u):
found = False
pos = 0
pos2 = 0
while pos < len(list) and not found:
if int(list[pos]) < int(u) :
if int(list[pos2]) > int(i):
found = True
pos2 = pos2 + 1
pos = pos + 1
return found
unsortedList = ['1', '3', '4', '2', '6', '9', '2', '1', '3', '7']
num1 = '3'
num2 = '5'
isItThere = unsortedSearch(unsortedList, num1, num2)
if isItThere:
print ("There is a number between those values")
else:
print ("There isn't a number between those values")
def get_nums():
nums=[]
n=int(input("一共有几个整数?"))
for i in range(n):
x=int(input('请按次随机输入第{}个整数(剩余{}次输入)：'.format(i+1,n-i)))
nums.append(x)
return nums
if __name__=='__main__':
list_nums=get_nums()
def BubbleSort(nums):
#冒泡法
print('初始整数集合为:{}'.format(nums))
for i in range(len(nums)-1):
for j in range(len(nums)-i-1):
if nums[j]>nums[j+1]:
nums[j],nums[j+1]=nums[j+1],nums[j] #调换位置,相互赋值
print("第{}次迭代排序结果:{}".format((len(nums)-j-1),nums))
return nums
if __name__=='__main__':
print('经过冒泡法排序最终得到:{}'.format(BubbleSort(list_nums)))
def get_nums():
nums=[]
n=int(input("一共有几个整数?"))
for i in range(n):
x=int(input('请按次随机输入第{}个整数(剩余{}次输入)：'.format(i+1,n-i)))
nums.append(x)
return nums
if __name__=='__main__':
myList=get_nums()
def selectedSort(myList):
#获取list的长度
length = len(myList)
#一共进行多少轮比较
for i in range(0,length-1):
#默认设置最小值得index为当前值
smallest = i
#用当先最小index的值分别与后面的值进行比较,以便获取最小index
for j in range(i+1,length):
#如果找到比当前值小的index,则进行两值交换
if myList[j]<myList[smallest]:
tmp = myList[j]
myList[j] = myList[smallest]
myList[smallest]=tmp
#打印每一轮比较好的列表
print("Round ",i,": ",myList) #根据第一个i循环进行打印,而不是选j循环
print("选择排序法:迭代过程 ")
selectedSort(myList)
def merge_sort(LIST):
start = []
end = []
while len(LIST) > 1:
a = min(LIST)
b = max(LIST)
start.append(a)
end.append(b)
LIST.remove(a)
LIST.remove(b)
if LIST:
start.append(LIST[0])
end.reverse()
return (start + end)
if __name__=='__main__':
nums=[]
n=int(input('一共几位数: '))
for i in range(n):
x=int(input("请依次输入整数:"))
nums.append(x)
print(merge_sort(nums))
# =============================================================================
#10.1.2
# =============================================================================
import pandas as pd
df=pd.DataFrame({'key1':['a','a','b','b','a'],'key2':['one','two','one','two','one'],'data1':np.random.randn(5),'data2':np.random.randn(5)})
df
df.groupby(['key1','key2'])['data1'].mean()
people=pd.DataFrame(np.random.randn(5,5),columns=['a','b','c','d','e'],index=['joe','steve','wes','jim','travis'])
people
mapping={'a':'red','b':'red','c':'blue','d':'blue','e':'red','f':'orange'}
by_column=people.groupby(mapping,axis=1)
by_column.mean()
map_series=pd.Series(mapping)
people.groupby(len).sum()
# =============================================================================
# 分组加权
# =============================================================================
import pandas as pd
df=pd.DataFrame({'目录':['a','a','a','a','b','b','b','b'],'data':np.random.randn(8),'weights':np.random.randn(8)})
df
grouped=df.groupby('目录')
get_weighpoint=lambda x: np.average(x['data'],weights=x['weights'])
grouped.apply(get_weighpoint)
# =============================================================================
# 
# =============================================================================

spx=pd.read_csv('stock_px_2.csv',index_col=0,parse_dates=True)
spx
spx.info()
from datetime import datetime
datestrs=['7/6/2011','8/6/2011']
[datetime.strptime(x,'%m/%d/%Y')for x in datestrs]
dates=pd.date_range('1/1/2018',periods=1000)
dates
long_df=pd.DataFrame(np.random.randn(1000,4),index=dates,columns=['Colorado','Texas','New York','Ohio'])
long_df
pd.date_range('2018-10-1',periods=30,freq='1h')
# =============================================================================
# 
# =============================================================================
close_px_all=pd.read_csv("stock_px_2.csv",parse_dates=True,index_col=0)
close_px=close_px_all[['AAPL','MSFT','XOM']]
close_px=close_px.resample("B").ffill()
close_px.AAPL.plot()
close_px.AAPL.rolling(250).mean().plot()
import pandas as pd
import numpy as np
values=pd.Series(['apple','orange','apple','apple']*2)
values
pd.unique(values)
pd.value_counts(values)
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.linear_model import RANSACRegressor, LinearRegression, TheilSenRegressor
from sklearn.metrics import explained_variance_score, mean_absolute_error, mean_squared_error, median_absolute_error, r2_score
from sklearn.svm import SVR
from sklearn.linear_model import Ridge,Lasso,ElasticNet,BayesianRidge
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.cross_validation import train_test_split
data = pd.read_csv('../cement_data.csv')
# 查看数据记录的长度，共1030行
print(len(data))
# 查看前五行数据
data.head()
import pandas
titanic=pandas.read_csv('train.csv')
titanic.head()
titanic.describe()
titanic['Age']=titanic['Age'].fillna(titanic['Age'].median())
print(titanic['Sex'].unique()) #找Sex特征里的分类字符名，只有两种可能性
titanic.loc[titanic['Sex']=='female','Sex']=1#把分类字符名转换成整数1,0形式，进行标记
titanic.loc[titanic['Sex']=='male','Sex']=0
#对embarked　登船地　进行填充（按最多标记）
print(titanic['Embarked'].unique())
titanic['Embarked']=titanic['Embarked'].fillna('S')
titanic.loc[titanic['Embarked']=='S']=0
titanic.loc[titanic['Embarked']=='C']=1
titanic.loc[titanic['Embarked']=='Q']=2
# =============================================================================
# 引进模型，线性回归
# =============================================================================
from sklearn.linear_model import LinearRegression
from sklearn.cross_validation import KFold
#cross_validation　交叉验证，进行调参，训练数据集分成三份，三份做交叉验证

predictors=['Pclass','Sex','Age','SibSp','Parch','Fare','Embarked'] #需要输入并做预测的特征列
alg=LinearRegression()
kf=KFold(titanic.shape[0],n_folds=3,random_state=1) #shape[0]一共有多少行,random_state=1 随机种子开启，n_fold=3把训练集分为三份

predictions=[]
for train,test in kf:
train_predictors=titanic[predictors].iloc[train,:]
#交叉验证中，除开训练的部分
train_target=titanic['Survived'].iloc[train]#获取目标训练集
alg.fit(train_predictors,train_target) #依据模型，训练

test_predictions=alg.predict(titanic[predictors].iloc[test,:]) #测试集

predictions.append(test_predictions)
import numpy as np
predictions=np.concatenate(predictions,axis=0)
# 整理输出值,按照可能性分类到0,1
predictions[predictions>=0.5]=0
predictions[predictions<0.5]=1
accuracy=sum(predictions[predictions==titanic['Survived']])/len(predictions)
print(accuracy)
# =============================================================================
# 逻辑回归
# =============================================================================
from sklearn import cross_validation
from sklearn.linear_model import LogisticRegression
alg=LogisticRegression(random_state=1)
scores=cross_validation.cross_val_score(alg,titanic[predictors],titanic['Survived'],cv=3)
print(scores.mean())
# =============================================================================
# 随机森林
# =============================================================================
from sklearn import cross_validation
from sklearn.ensemble import RandomForestClassifier
predictors=['Pclass','Sex','Age','SibSp','Parch','Fare','Embarked']
alg=RandomForestClassifier(random_state=1,n_estimators=10,min_samples_split=2,min_samples_leaf=1)
kf=cross_validation.KFold(titanic.shape[0],n_folds=3,random_state=1)
scores=scores=cross_validation.cross_val_score(alg,titanic[predictors],titanic['Survived'],cv=kf)
print(scores.mean())