MAI/LabWork01/LoadDB.py

190 lines
8.5 KiB
Python
Raw Normal View History

2023-10-12 17:46:05 +04:00
import os
2023-10-26 16:05:43 +04:00
import secrets
from flask import Flask, redirect, url_for, request, render_template, session
2023-10-12 17:46:05 +04:00
from matplotlib import pyplot as plt
2023-09-28 20:48:51 +04:00
from LabWork01.AnalysCustomers import analysCustomersDataFrame
from LabWork01.AnalysSales import analysSalesDataFrame
from LabWork01.AnalysSalesCustomers import analysSalesCustomersDataFrame
from LabWork01.DataFrameAnalys import analysItemsDataFrame
from LabWork01.FuncLoad import createDataFrame
from LabWork01.LabWork3.AddData import addData
2023-10-12 12:26:41 +04:00
from LabWork01.LabWork3.CreateGraphics import createGraphics
2023-10-12 17:46:05 +04:00
from LabWork01.LabWork3.CustomGraphics import createCusGraphics
2023-10-12 12:26:41 +04:00
from LabWork01.LabWork3.DeletePng import deleteAllPng
from LabWork01.LabWork4.SiteSearch import SiteSearch
app = Flask(__name__)
2023-10-26 16:05:43 +04:00
# Для работы session
secret = secrets.token_urlsafe(32)
app.secret_key = secret
#сразу загружаем весь док, чтобы потом просто прыгать по нему
listShops = createDataFrame()
#список типов данных по столбцам
listTypes = listShops.dtypes.to_list()
#формируем записи о кол-ве пустых ячеек в каждом столбце
countNull = listShops.isnull().sum()
# для фильтра Блума
search_engine = SiteSearch()
search_engine.add("https://www.kaggle.com/datasets/ankanhore545/100-highest-valued-unicorns", ["Company", "Valuation", "Country", "State", "City", "Industries", "Founded Year", "Name of Founders", "Total Funding", "Number of Employees"])
search_engine.add("https://www.kaggle.com/datasets/ilyaryabov/tesla-insider-trading", ["Insider Trading", "Relationship", "Date", "Transaction", "Cost", "Shares", "Value", "Shares Total", "SEC Form 4"])
search_engine.add("https://www.kaggle.com/datasets/sameepvani/nasa-nearest-earth-objects", ["NASA", "est_diameter_min", "est_diameter_max", "relative_velocity", "miss_distance", "orbiting_body", "sentry_object", "absolute_magnitude", "hazardous"])
2023-10-26 16:05:43 +04:00
search_engine.add("https://www.kaggle.com/datasets/surajjha101/stores-area-and-sales-data", ["Store", "Area", "Available", "Daily", "Customer", "Sales"])
search_engine.add("https://www.kaggle.com/datasets/uciml/pima-indians-diabetes-database", ["Health", "Diabetes", "India"])
search_engine.add("https://www.kaggle.com/datasets/mirichoi0218/insurance", ["age", "sex", "bmi"])
search_engine.add("https://www.kaggle.com/datasets/muhammedtausif/world-population-by-countries", ["Country", "Population", "Continent", "Capital", "Yearly Change", "Land Area", "Fertility","Density"])
search_engine.add("https://www.kaggle.com/datasets/deepcontractor/car-price-prediction-challenge", ["car", "price", "manufacturer"])
search_engine.add("https://www.kaggle.com/datasets/surajjha101/forbes-billionaires-data-preprocessed", ["Name", "Networth", "Source"])
search_engine.add("https://www.kaggle.com/datasets/fedesoriano/stroke-prediction-dataset", [ "heart_disease" , "bmi", "stroke" ])
@app.route("/")
def home():
2023-10-12 17:46:05 +04:00
return render_template('main_page.html', context=[], main_img=[], image_names=[], tableAnalys=[], titles=[''], listTypes=listTypes, countNull=countNull, firstRow=1, secondRow=4, firstColumn=1, secondColumn=4)
@app.route("/showDiapason", methods=['GET','POST'])
def numtext():
data = request.args
#получаем срез и таблицы по введёным параметрам
newListShops = listShops.iloc[int(data['firstRow'])-1:int(data['secondRow']), int(data['firstColumn']):int(data['secondColumn'])+1]
_range = range(int(data['firstColumn']), int(data['secondColumn'])+1)
#список списков для шаблона
totalList = []
print(countNull[1])
#формирование 4-х списков для шаблонизатора
if 1 in _range:
listStoreArea = newListShops['Store_Area'].to_list()
totalList.append(listStoreArea)
if 2 in _range:
listItemsAvailable = newListShops['Items_Available'].to_list()
totalList.append(listItemsAvailable)
if 3 in _range:
listDailyCustomerCount = newListShops['Daily_Customer_Count'].to_list()
totalList.append(listDailyCustomerCount)
if 4 in _range:
listStoreSales = newListShops['Store_Sales'].to_list()
totalList.append(listStoreSales)
if int(data['firstRow']) and int(data['secondRow']) and int(data['firstColumn']) and int(data['secondColumn']):
2023-10-12 17:46:05 +04:00
return render_template('main_page.html', context=totalList, main_img=[], image_names=[], listTypes=listTypes, countNull=countNull,
firstColumn=int(data['firstColumn']), secondColumn=int(data['secondColumn']),
firstRow=int(data['firstRow']), secondRow=int(data['secondRow']))
2023-09-28 15:14:37 +04:00
return home()
#функция для проведения анализа данных
@app.route("/analysis", methods=['GET', 'POST'])
def analysis():
2023-09-28 20:48:51 +04:00
firstAnalys = analysItemsDataFrame(listShops)
secondAnalys = analysCustomersDataFrame(listShops)
thirdAnalys = analysSalesDataFrame(listShops)
fourthAnalys = analysSalesCustomersDataFrame(listShops)
2023-09-28 15:14:37 +04:00
2023-10-12 17:46:05 +04:00
# удаляем все текущие диаграммы
deleteAllPng()
# начинаем создавать диаграммы
createGraphics(firstAnalys, 'firstAn')
createGraphics(secondAnalys, 'secondAn')
createGraphics(thirdAnalys, 'thirdAn')
createGraphics(fourthAnalys, 'fourthAn')
# дополняем новыми значениями
additionListShops = addData(createDataFrame())
# получаем новые данные
newfirstAnalys = analysItemsDataFrame(additionListShops)
secondAnalys = analysCustomersDataFrame(additionListShops)
thirdAnalys = analysSalesDataFrame(additionListShops)
fourthAnalys = analysSalesCustomersDataFrame(additionListShops)
# создаём новые диаграммы
createGraphics(newfirstAnalys, 'addFirstAn')
createGraphics(secondAnalys, 'addSecondAn')
createGraphics(thirdAnalys, 'addThirdAn')
createGraphics(fourthAnalys, 'addFourthAn')
createCusGraphics(firstAnalys[0], newfirstAnalys[0])
image_names_start = ['firstAn0.jpg', 'firstAn1.jpg', 'firstAn2.jpg',
'secondAn0.jpg', 'secondAn1.jpg', 'secondAn2.jpg',
'thirdAn0.jpg', 'thirdAn1.jpg', 'thirdAn2.jpg',
'fourthAn0.jpg', 'fourthAn1.jpg', 'fourthAn2.jpg']
image_names_addition = ['addFirstAn0.jpg', 'addFirstAn1.jpg', 'addFirstAn2.jpg',
'addSecondAn0.jpg', 'addSecondAn1.jpg', 'addSecondAn2.jpg',
'addThirdAn0.jpg', 'addThirdAn1.jpg', 'addThirdAn2.jpg',
'addFourthAn0.jpg', 'addFourthAn1.jpg', 'addFourthAn2.jpg']
main_img = ['CustomJPG0.jpg']
result = listShops[['Store_Sales']]
# Строим boxplot с использованием Seaborn
plt.title('Valuation Boxplot by Store Sales')
plt.xlabel('Store Sales')
plt.boxplot(result['Store_Sales'])
script_dir = os.path.dirname(__file__)
results_dir = os.path.join(script_dir, 'static/')
plt.savefig(results_dir + 'NewCustomJPG' + str(0) + '.jpg')
newCustomJpg = ['NewCustomJPG0.jpg']
2023-09-28 15:14:37 +04:00
2023-10-12 17:46:05 +04:00
return render_template('main_page.html', context=[], image_names_start=image_names_start,
image_names_addition=image_names_addition,
tableAnalysOne=[],
tableAnalysTwo=[],
tableAnalysThree=[],
tableAnalysFour=[],
main_img=newCustomJpg,
2023-09-28 20:48:51 +04:00
titles=[''],
listTypes=listTypes, countNull=countNull, firstRow=1,
secondRow=4, firstColumn=1, secondColumn=4)
@app.route('/findURL', methods=['GET'])
def get_page_findURL():
2023-10-26 16:05:43 +04:00
return render_template('findURL.html', find=False, notFind=False)
@app.route('/findURL', methods=['POST'])
def findURL():
word = request.form["word"]
if (search_engine.contains(word)):
2023-10-26 16:05:43 +04:00
session["new_word"] = word
return render_template('findURL.html', find=True, notFind=False)
return render_template('findURL.html', find=False, notFind=True)
@app.route('/showFindLinks', methods=['POST'])
def get_page_showFindURL():
word = session.get("new_word", None)
links = search_engine.find_url(word)
word_links = []
for item in links:
word_links.append({item, word})
return render_template('showLinks.html', links=links)
if __name__=="__main__":
app.run(debug=True)
2023-09-14 14:30:19 +04:00