diff --git a/LabWork01/LabWork6/ConvertorDataFrame.py b/LabWork01/LabWork6/ConvertorDataFrame.py index 5e48e05..ce0a029 100644 --- a/LabWork01/LabWork6/ConvertorDataFrame.py +++ b/LabWork01/LabWork6/ConvertorDataFrame.py @@ -4,17 +4,19 @@ def covertorDataFrame(): df = pd.read_csv("../../res/Stores.csv") - countMainRows = 25 + # кол-во строчек для считывания + countMainRows = 35 - newDf = df.head(countMainRows) + # получаем указанное кол-во строчек + mainDF = df.head(countMainRows) - newDf['TextStoreArea'] = df['Store_Area'].apply( + mainDF['TextStoreArea'] = mainDF['Store_Area'].apply( lambda x: 'Small_Area' if x <= 1100 else ('Average_Area' if 1100 < x <= 1700 else 'Big_Area')) - newDf['TextStoreSales'] = df['Store_Sales'].apply( + mainDF['TextStoreSales'] = mainDF['Store_Sales'].apply( lambda x: 'Small_Sales' if x <= 50000 else ('Average_Sales' if 50000 < x <= 80000 else 'Big_Sales')) - newDf['TextDailyCustomerCount'] = df['Daily_Customer_Count'].apply( + mainDF['TextDailyCustomerCount'] = mainDF['Daily_Customer_Count'].apply( lambda x: 'Small_Customer' if x <= 400 else ('Average_Customer' if 400 < x <= 900 else 'Big_Customer')) # using dictionary to convert specific columns @@ -25,11 +27,18 @@ def covertorDataFrame(): 'Store_Sales': str } - newDf = newDf.astype(convert_dict) + mainDF = mainDF.astype(convert_dict) - print(newDf[['TextStoreSales', 'TextStoreSales', 'TextStoreArea']]) + # генеральная выборка + newDfGeneral = mainDF.iloc[0:25] - return newDf[['TextDailyCustomerCount', 'TextStoreArea', 'TextStoreSales']] + # выборка для проверки + newDfSupport = mainDF.iloc[25:35] + + print(newDfSupport[['TextStoreSales', 'TextStoreSales', 'TextStoreArea']]) + + return [newDfGeneral[['TextDailyCustomerCount', 'TextStoreArea', 'TextStoreSales']], + newDfSupport[['TextDailyCustomerCount', 'TextStoreArea', 'TextStoreSales']]] # [['Store_Area', 'Store_Sales', 'Daily_Customer_Count', 'TextStoreArea']] diff --git a/LabWork01/LabWork6/Tree.py b/LabWork01/LabWork6/Tree.py index 8632e60..0504c71 100644 --- a/LabWork01/LabWork6/Tree.py +++ b/LabWork01/LabWork6/Tree.py @@ -2,7 +2,6 @@ import math import pandas as pd from functools import reduce -from LabWork01.FuncLoad import createDataFrame from LabWork01.LabWork6.ConvertorDataFrame import covertorDataFrame # Дата сет @@ -19,7 +18,7 @@ from LabWork01.LabWork6.ConvertorDataFrame import covertorDataFrame # df0 = pd.DataFrame(data) # df0.columns = ["цвет", "форма", "результат"] -df0 = covertorDataFrame() +df0 = covertorDataFrame()[0] # Лямбда-выражение для распределения значений, аргумент - pandas.Series, # возвращаемое значение - массив с количеством каждого из значений