$ jupyter lab

$ conda install -c conda-forge jupyterlab
$ jupyter lab

#url（ここにURLを入れてください）
url = ''

from bs4 import BeautifulSoup
import urllib3
import re
import requests
import time
import pandas as pd
from pandas import Series, DataFrame

#URL（ここにURLを入れてください）
url = ''

result = requests.get(url)
c = result.content

soup = BeautifulSoup(c)

summary = soup.find("div",{'id':'js-bukkenList'})
body = soup.find("body")
pages = body.find_all("div",{'class':'pagination pagination_set-nav'})
pages_text = str(pages)
pages_split = pages_text.split('</a></li>\n</ol>')
pages_split0 = pages_split[0]
pages_split1 = pages_split0[-3:]
pages_split2 = pages_split1.replace('>','')
pages_split3 = int(pages_split2)

urls = []

urls.append(url)

for i in range(pages_split3-1):
    pg = str(i+2)
    url_page = url + '&page=' + pg
    urls.append(url_page)

names = [] 
addresses = [] 
locations0 = [] 
locations1 = [] 
locations2 = [] 
ages = [] 
heights = [] 
floors = []
rent = [] 
admin = []
others = [] 
floor_plans = [] 
areas = []
detail_urls = [] 

for url in urls:
    result = requests.get(url)
    c = result.content
    soup = BeautifulSoup(c)
    summary = soup.find("div",{'id':'js-bukkenList'})
    apartments = summary.find_all("div",{'class':'cassetteitem'})

    for apartment in apartments:

        room_number = len(apartment.find_all('tbody'))

        name = apartment.find('div', class_='cassetteitem_content-title').text
        address = apartment.find('li', class_='cassetteitem_detail-col1').text

        for i in range(room_number):
            names.append(name)
            addresses.append(address)

        sublocation = apartment.find('li', class_='cassetteitem_detail-col2')
        cols = sublocation.find_all('div')
        for i in range(len(cols)):
            text = cols[i].find(text=True)
            for j in range(room_number):
                if i == 0:
                    locations0.append(text)
                elif i == 1:
                    locations1.append(text)
                elif i == 2:
                    locations2.append(text)

        age_and_height = apartment.find('li', class_='cassetteitem_detail-col3')
        age = age_and_height('div')[0].text
        height = age_and_height('div')[1].text

        for i in range(room_number):
            ages.append(age)
            heights.append(height)

        table = apartment.find('table')
        rows = []
        rows.append(table.find_all('tr'))

        data = []
        for row in rows:
            for tr in row:
                cols = tr.find_all('td')
                if len(cols) != 0:
                    _floor = cols[2].text
                    _floor = re.sub('[\r\n\t]', '', _floor)

                    _rent_cell = cols[3].find('ul').find_all('li')
                    _rent = _rent_cell[0].find('span').text
                    _admin = _rent_cell[1].find('span').text

                    _deposit_cell = cols[4].find('ul').find_all('li')
                    _deposit = _deposit_cell[0].find('span').text
                    _reikin = _deposit_cell[1].find('span').text
                    _others = _deposit + '/' + _reikin

                    _floor_cell = cols[5].find('ul').find_all('li')
                    _floor_plan = _floor_cell[0].find('span').text
                    _area = _floor_cell[1].find('span').text

                    _detail_url = cols[8].find('a')['href']
                    _detail_url = 'https://suumo.jp' + _detail_url

                    text = [_floor, _rent, _admin, _others, _floor_plan, _area, _detail_url]
                    data.append(text)

        for row in data:
            floors.append(row[0])
            rent.append(row[1])
            admin.append(row[2])
            others.append(row[3])
            floor_plans.append(row[4])
            areas.append(row[5])
            detail_urls.append(row[6])


        time.sleep(3)

names = Series(names)
addresses = Series(addresses)
locations0 = Series(locations0)
locations1 = Series(locations1)
locations2 = Series(locations2)
ages = Series(ages)
heights = Series(heights)
floors = Series(floors)
rent = Series(rent)
admin = Series(admin)
others = Series(others)
floor_plans = Series(floor_plans)
areas = Series(areas)
detail_urls = Series(detail_urls)

suumo_df = pd.concat([names, addresses, locations0, locations1, locations2, ages, heights, floors, rent, admin, others, floor_plans, areas, detail_urls], axis=1)

suumo_df.columns=['マンション名','住所','立地1','立地2','立地3','築年数','建物の高さ','階層','賃料料','管理費', '敷/礼/保証/敷引,償却','間取り','専有面積', '詳細URL']

suumo_df.to_csv('suumo.csv', sep = '\t', encoding='utf-16', header=True, index=False)

import pandas as pd
import numpy as np
from sklearn.preprocessing import OrdinalEncoder
from sklearn import preprocessing
import pandas_profiling as pdp 

df = pd.read_csv('suumo.csv', sep='\t', encoding='utf-16')

splitted1 = df['立地1'].str.split(' 歩', expand=True)
splitted1.columns = ['立地11', '立地12']
splitted2 = df['立地2'].str.split(' 歩', expand=True)
splitted2.columns = ['立地21', '立地22']
splitted3 = df['立地3'].str.split(' 歩', expand=True)
splitted3.columns = ['立地31', '立地32']

splitted4 = df['敷/礼/保証/敷引,償却'].str.split('/', expand=True)
splitted4.columns = ['敷金', '礼金']

df = pd.concat([df, splitted1, splitted2, splitted3, splitted4], axis=1)

df.drop(['立地1','立地2','立地3','敷/礼/保証/敷引,償却'], axis=1, inplace=True)

df = df.dropna(subset=['賃料料'])

df['賃料料'] = df['賃料料'].str.replace(u'万円', u'')
df['敷金'] = df['敷金'].str.replace(u'万円', u'')
df['礼金'] = df['礼金'].str.replace(u'万円', u'')
df['管理費'] = df['管理費'].str.replace(u'円', u'')
df['築年数'] = df['築年数'].str.replace(u'新築', u'0') 
df['築年数'] = df['築年数'].str.replace(u'99年以上', u'0') #
df['築年数'] = df['築年数'].str.replace(u'築', u'')
df['築年数'] = df['築年数'].str.replace(u'年', u'')
df['専有面積'] = df['専有面積'].str.replace(u'm', u'')
df['立地12'] = df['立地12'].str.replace(u'分', u'')
df['立地22'] = df['立地22'].str.replace(u'分', u'')
df['立地32'] = df['立地32'].str.replace(u'分', u'')

df['管理費'] = df['管理費'].replace('-',0)
df['敷金'] = df['敷金'].replace('-',0)
df['礼金'] = df['礼金'].replace('-',0)

splitted5 = df['立地11'].str.split('/', expand=True)
splitted5.columns = ['路線1', '駅1']
splitted5['徒歩1'] = df['立地12']
splitted6 = df['立地21'].str.split('/', expand=True)
splitted6.columns = ['路線2', '駅2']
splitted6['徒歩2'] = df['立地22']
splitted7 = df['立地31'].str.split('/', expand=True)
splitted7.columns = ['路線3', '駅3']
splitted7['徒歩3'] = df['立地32']

df = pd.concat([df, splitted5, splitted6, splitted7], axis=1)

df.drop(['立地11','立地12','立地21','立地22','立地31','立地32'], axis=1, inplace=True)

df['賃料料'] = pd.to_numeric(df['賃料料'])
df['管理費'] = pd.to_numeric(df['管理費'])
df['敷金'] = pd.to_numeric(df['敷金'])
df['礼金'] = pd.to_numeric(df['礼金'])
df['築年数'] = pd.to_numeric(df['築年数'])
df['専有面積'] = pd.to_numeric(df['専有面積'])

df['賃料料'] = df['賃料料'] * 10000
df['敷金'] = df['敷金'] * 10000
df['礼金'] = df['礼金'] * 10000

df['徒歩1'] = pd.to_numeric(df['徒歩1'])
df['徒歩2'] = pd.to_numeric(df['徒歩2'])
df['徒歩3'] = pd.to_numeric(df['徒歩3'])

splitted8 = df['階層'].str.split('-', expand=True)
splitted8.columns = ['階1', '階2']
splitted8['階1'].str.encode('cp932')
splitted8['階1'] = splitted8['階1'].str.replace(u'階', u'')
splitted8['階1'] = splitted8['階1'].str.replace(u'B', u'-')
splitted8['階1'] = splitted8['階1'].str.replace(u'M', u'')
splitted8['階1'] = pd.to_numeric(splitted8['階1'])
df = pd.concat([df, splitted8], axis=1)

df['建物の高さ'] = df['建物の高さ'].str.replace(u'地下1地上', u'')
df['建物の高さ'] = df['建物の高さ'].str.replace(u'地下2地上', u'')
df['建物の高さ'] = df['建物の高さ'].str.replace(u'地下3地上', u'')
df['建物の高さ'] = df['建物の高さ'].str.replace(u'地下4地上', u'')
df['建物の高さ'] = df['建物の高さ'].str.replace(u'地下5地上', u'')
df['建物の高さ'] = df['建物の高さ'].str.replace(u'地下6地上', u'')
df['建物の高さ'] = df['建物の高さ'].str.replace(u'地下7地上', u'')
df['建物の高さ'] = df['建物の高さ'].str.replace(u'地下8地上', u'')
df['建物の高さ'] = df['建物の高さ'].str.replace(u'地下9地上', u'')
df['建物の高さ'] = df['建物の高さ'].str.replace(u'平屋', u'1')
df['建物の高さ'] = df['建物の高さ'].str.replace(u'階建', u'')
df['建物の高さ'] = pd.to_numeric(df['建物の高さ'])

df = df.reset_index(drop=True)
df['間取りDK'] = 0
df['間取りK'] = 0
df['間取りL'] = 0
df['間取りS'] = 0
df['間取り'] = df['間取り'].str.replace(u'ワンルーム', u'1') 

for x in range(len(df)):
    if 'DK' in df['間取り'][x]:
        df.loc[x,'間取りDK'] = 1
df['間取り'] = df['間取り'].str.replace(u'DK',u'')

for x in range(len(df)):
    if 'K' in df['間取り'][x]:
        df.loc[x,'間取りK'] = 1        
df['間取り'] = df['間取り'].str.replace(u'K',u'')

for x in range(len(df)):
    if 'L' in df['間取り'][x]:
        df.loc[x,'間取りL'] = 1        
df['間取り'] = df['間取り'].str.replace(u'L',u'')

for x in range(len(df)):
    if 'S' in df['間取り'][x]:
        df.loc[x,'間取りS'] = 1        
df['間取り'] = df['間取り'].str.replace(u'S',u'')

df['間取り'] = pd.to_numeric(df['間取り'])

splitted9 = df['住所'].str.split('区', expand=True)
splitted9.columns = ['区', '市町村']
splitted9['区'] = splitted9['区'] + '区'
splitted9['区'] = splitted9['区'].str.replace('東京都','')
df = pd.concat([df, splitted9], axis=1)

df_for_search = df.copy()

df[['路線1','路線2','路線3', '駅1', '駅2','駅3','市町村']] = df[['路線1','路線2','路線3', '駅1', '駅2','駅3','市町村']].fillna("NAN")

oe = preprocessing.OrdinalEncoder()
df[['路線1','路線2','路線3', '駅1', '駅2','駅3','市町村']] = oe.fit_transform(df[['路線1','路線2','路線3', '駅1', '駅2','駅3','市町村']].values) 

df['賃料料+管理費'] = df['賃料料'] + df['管理費']

#上限価格を設定
df = df[df['賃料料+管理費'] < 300000]

df = df[["マンション名",'賃料料+管理費', '築年数', '建物の高さ', '階1',
       '専有面積','路線1','路線2','路線3', '駅1', '駅2','駅3','徒歩1', '徒歩2','徒歩3','間取り', '間取りDK', '間取りK', '間取りL', '間取りS',
       '市町村']]

df.columns = ['name','real_rent','age', 'hight', 'level','area', 'route_1','route_2','route_3','station_1','station_2','station_3','distance_1','distance_2','distance_3','room_number','DK','K','L','S','adress']


pdp.ProfileReport(df)

df = df[df['賃料料+管理費'] < 300000]

df["per_area"] = df["area"]/df["room_number"]
df["height_level"] = df["height"]*df["level"]
df["area_height_level"] = df["area"]*df["height_level"]
df["distance_staion_1"] = df["station_1"]*df["distance_1"]

conda install -c conda-forge lightgbm

import matplotlib.pyplot as plt
import japanize_matplotlib
import lightgbm as lgb
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import mean_squared_error
from sklearn.metrics import r2_score

y = df["real_rent"]
X = df.drop(['real_rent',"name"], axis=1) 

X_train, X_test, y_train, y_test = train_test_split(X, y,test_size=0.33, random_state=0)

lgb_train = lgb.Dataset(X_train, y_train)
lgb_eval = lgb.Dataset(X_test, y_test, reference=lgb_train)

lgbm_params = {
        'objective': 'regression',
        'metric': 'rmse',
        'num_leaves':80
}

model = lgb.train(lgbm_params, lgb_train, valid_sets=lgb_eval, verbose_eval=-1)

y_pred = model.predict(X_test, num_iteration=model.best_iteration)

print(r2_score(y_test, y_pred)  )
lgb.plot_importance(model, figsize=(12, 6))
plt.show()

pred = list(model.predict(X, num_iteration=model.best_iteration))
pred = pd.Series(pred, name="予測値")
diff = pd.Series(df["賃料料+管理費"]-pred,name="予測値との差")
df_search = pd.concat([df_for_search,diff,pred], axis=1)
df_search = df_search.sort_values("予測値との差")
df_search = df_search[["マンション名",'賃料料+管理費', '予測値',  '予測値との差', '詳細URL']]
df_search.to_csv('otoku.csv', sep = '\t',encoding='utf-16')