基于python的旅游系统_基于python的去哪儿网旅游数据分析

末蓝、 2022-10-28 10:28 452阅读 0赞

20011 基于python的去哪儿网旅游数据分析

运行视频、代码等：

链接：https://pan.baidu.com/s/1tw4Qvtcuwt7ys36M7HvLSg

提取码：1589

复制这段内容后打开百度网盘手机App，操作更方便哦

技术

Python + Pandas + Numpy + Pyecharts

功能详情

数据抽取

数据清洗

数据分析

数据展示

主要展示了不同时间不同城市的景区的销售情况。

系统相关截图

景点门票销售额排行

![4ea16c7bcabb461968e8e03ae0e49446.png][]

![668d395217ee98c08a43160aeed46fcf.png][]

![bf1afc54268fbe1563eae966160d7001.png][]

import random

with open('hw.txt', 'w') as f:

f.write('height\\tweight\\n')

for i in range(100):

height = random.randint(1600, 1900) / 10

weight = (height - 100) \* 0.9 + random.randint(-50, 50) / 10

f.write('%.1f\\t%.1f\\n' % (height, weight))

linear\_regression.py:

author = 'DivinerShi'

import numpy as np

import matplotlib.pyplot as plt

def compute\_error(b,m,data):

totalError = 0

\#Two ways to implement this

\#first way

\# for i in range(0,len(data)):

\# x = data\[i,0\]

\# y = data\[i,1\]

\# totalError += (y-(m\*x+b))\*\*2

\# print('(%f\*%f+%f)=%f,y=%f,loss=%f,totalError=%f' % (m,x,b,(m\*x+b),y,(y-(m\*x+b))\*\*2,totalError))

\#second way

x = data\[:,0\]

y = data\[:,1\]

totalError = (y-m\*x-b)\*\*2

totalError = np.sum(totalError,axis=0)

return totalError/float(len(data))

def optimizer(data,starting\_b,starting\_m,learning\_rate,num\_iter):

b = starting\_b

m = starting\_m

\#gradient descent

for i in range(num\_iter):

\#update b and m with the new more accurate b and m by performing

\# thie gradient step

b,m =compute\_gradient(b,m,data,learning\_rate)

if i%100==0:

print('iter \{0\}:error=\{1\}'.format(i,compute\_error(b,m,data)))

return \[b,m\]

def compute\_gradient(b\_current,m\_current,data ,learning\_rate):

b\_gradient = 0

m\_gradient = 0

N = float(len(data))

\#Two ways to implement this

\#first way

\# for i in range(0,len(data)):

\# x = data\[i,0\]

\# y = data\[i,1\]

\# \#computing partial derivations of our error function

\# \#b\_gradient = -(2/N)\*sum((y-(m\*x+b))^2)

\# \#m\_gradient = -(2/N)\*sum(x\*(y-(m\*x+b))^2)

\# b\_gradient += -(2/N)\*(y-((m\_current\*x)+b\_current))

\# m\_gradient += -(2/N) \* x \* (y-((m\_current\*x)+b\_current))

\# \# print('m\_current=%f,b\_current=%f,N=%f,x=%f,y=%f,y-((m\_current\*x)+b\_current)=%f, b\_gradient=%f, m\_gradient=%f' % (m\_current, b\_current, N, x, y, y-((m\_current\*x)+b\_current), b\_gradient, m\_gradient))

\#Vectorization implementation

x = data\[:,0\]

y = data\[:,1\]

b\_gradient = -(2/N)\*(y-m\_current\*x-b\_current)

b\_gradient = np.sum(b\_gradient,axis=0)

m\_gradient = -(2/N)\*x\*(y-m\_current\*x-b\_current)

m\_gradient = np.sum(m\_gradient,axis=0)

\#update our b and m values using out partial derivations

new\_b = b\_current - (learning\_rate \* b\_gradient)

new\_m = m\_current - (learning\_rate \* m\_gradient)

return \[new\_b,new\_m\]

def Linear\_regression():

\# get train data

\# data =np.loadtxt('data.csv',delimiter=',')

data =np.loadtxt('hw.txt',delimiter='\\t',skiprows=True)

\#define hyperparamters

\#learning\_rate is used for update gradient

\#defint the number that will iteration

\# define y =mx+b

learning\_rate = 0.000001

initial\_b =0.0

initial\_m = 0.0

num\_iter = 10000

\#train model

\#print b m error

print('initial variables:\\n initial\_b = \{0\}\\n intial\_m = \{1\}\\n error of begin = \{2\} \\n'\\

.format(initial\_b,initial\_m,compute\_error(initial\_b,initial\_m,data)))

\#optimizing b and m

\[b ,m\] = optimizer(data,initial\_b,initial\_m,learning\_rate,num\_iter)

\#print final b m error

print('final formula parmaters:\\n b = \{1\}\\n m=\{2\}\\n error of end = \{3\} \\n'.format(num\_iter,b,m,compute\_error(b,m,data)))

\#plottting

x = data\[:,0\]

y = data\[:,1\]

y\_predict = m\*x+b

plt.scatter(x, y, color = 'blue')

plt.plot(x,y\_predict,'k-', color = 'red', linewidth = 4)

\# plt.show()

from sklearn import linear\_model

regr = linear\_model.LinearRegression()

regr.fit(x.reshape(-1,1), y)

print(regr.coef\_, regr.intercept\_)

plt.scatter(x, y, color = 'blue')

plt.plot(x, regr.predict(x.reshape(-1,1)), color = 'orange', linewidth = 4)

plt.show()

def lr\_by\_sklearn():

from sklearn import linear\_model

data =np.loadtxt('hw.txt',delimiter='\\t',skiprows=True)

x = data\[:,0\]

y = data\[:,1\]

regr = linear\_model.LinearRegression()

regr.fit(x.reshape(-1,1), y)

print(regr.coef\_, regr.intercept\_)

\# import pandas as pd

\# data = pd.read\_csv('hw.txt', sep='\\t')

\# regr.fit(data\['height'\].values.reshape(-1,1), data\['weight'\])

\# plt.scatter(data\['height'\], data\['weight'\], color = 'blue')

\# plt.plot(data\['height'\], regr.predict(data\['height'\].values.reshape(-1,1)), color = 'orange', linewidth = 4)

\# plt.show()

plt.scatter(x, y, color = 'blue')

plt.plot(x, regr.predict(x.reshape(-1,1)), color = 'orange', linewidth = 4)

plt.show()

if name =='main':

Linear\_regression()

lr\_by\_sklearn()

import numpy as np

df2 = df.groupby('addr').agg(\[np.mean, np.var\])

df2\['x'\] = 1

from math import pi, exp, sqrt

def f(x, mean, var):

return exp(-(x-mean)\*\*2/(2var))/sqrt(2pi\*var)

df2\['p\_x\_min'\]=df2\[\['min','x'\]\].apply(lambda x: f(x\['x'\], x\['min'\]\['mean'\], x\['min'\]\['var'\]), axis=1)

df2\['p\_x\_max'\]=df2\[\['max','x'\]\].apply(lambda x: f(x\['x'\], x\['max'\]\['mean'\], x\['max'\]\['var'\]), axis=1)

(df2\['p\_x\_min'\]pcpa\['java'\]).argmax()

方法二：

from numpy import genfromtxt

x = genfromtxt('51.txt', delimiter='\\t', skip\_header=True, usecols=(2,3))

x.shape

y = genfromtxt('51.txt', delimiter='\\t', skip\_header=True, usecols=(1), dtype=str)

y.shape

import numpy as np

np.unique(y)

from sklearn.naive\_bayes import GaussianNB

clf = GaussianNB()

拟合数据

clf.fit(x, y)

print(clf.predict(\[\[0.8, 1.2\]\]))

print(clf.predict\_proba(\[\[0.8, 1.2\]\]))

print(clf.predict\_log\_proba(\[\[0.8, 1.2\]\]))

import urllib.request

import re

import sqlite3

def get\_content(page, key):

url = 'https://search.51job.com/list/010000%2C020000%2C030200%2C040000,000000,0000,00,9,99,' + key + ',2,' + str(page) + '.html'

a = urllib.request.urlopen(url)

html = a.read().decode('gbk')

lst = re.findall(r'(北京|上海|广州|深圳).\*?\\s+(\\d+.?\\d?)-(\\d+.?\\d?)(万|千)/(年|月)', html)

return lst

conn = sqlite3.connect('51.db')

c = conn.cursor()

c.execute('''CREATE TABLE IF NOT EXISTS jobs

(key text, addr text, min float, max float)''')

c.execute('''delete from jobs''')

conn.commit()

with open('51.txt', 'w') as f:

f.write('%s\\t%s\\t%s\\t%s\\n' % ('key','addr','min','max'))

for key in ('python', 'java'):

for each in range(1, 11):

for items in get\_content(each, key):

min = float(items\[1\])

max = float(items\[2\])

if items\[3\] == "千":

min /= 10

max /= 10

if items\[4\] == "年":

min /= 12

max /= 12

f.write('%s\\t%s\\t%s\\t%s\\n' % (key, items\[0\], round(min, 2), round(max, 2)))

c.execute("INSERT INTO jobs VALUES (?,?,?,?)", (key, items\[0\], round(min, 2), round(max, 2)))

conn.commit()

conn.close()

if name == 'main':

lst = get\_content(1, 'python')

print(lst)

[4ea16c7bcabb461968e8e03ae0e49446.png]: /images/20221024/46b969e235b749fe8c71cfe310745e64.png
[668d395217ee98c08a43160aeed46fcf.png]: /images/20221024/07b611e8758e452cb5d461d5415c0d3f.png
[bf1afc54268fbe1563eae966160d7001.png]: /images/20221024/f531997876394152bfe3ead94776e8b5.png