[머신러닝] 분류 : 자동차 시장 세분화 분류 예측

Q. [마케팅] 자동차 시장 세분화

• 자동차 회사는 새로운 전략을 수립하기 위해 4개의 시장으로 세분화했습니다.
• 기존 고객 분류 자료를 바탕으로 신규 고객이 어떤 분류에 속할지 예측해 주세요!

• 예측할 값(y): "Segmentation" (1,2,3,4)
• 평가: Macro f1-score
• data: train.csv, test.csv
• 제출 형식:

  ID,Segmentation
  458989,1
  458994,2
  459000,3
  459003,4

 

답안 제출 참고

• 아래 코드 예측변수와 수험번호를 개인별로 변경하여 활용
• pd.DataFrame({'ID': test.ID, 'Segmentation': pred}).to_csv('003000000.csv', index=False)

노트북 구분

• basic: 수치형 데이터만 활용 -> 학습 및 test데이터 예측
• intermediate: 범주형 데이터도 활용 -> 학습 및 test데이터 예측
• advanced: 학습 및 교차 검증(모델 평가) -> 하이퍼파라미터 튜닝 -> test데이터 예측

학습을 위한 채점

• 최종 파일을 "수험번호.csv"가 아닌 "submission.csv" 작성 후 오른쪽 메뉴 아래 "submit" 버튼 클릭 -> 리더보드에 점수 및 등수 확인 가능함
• pd.DataFrame({'ID': test.ID, 'Segmentation': pred}).to_csv('submission.csv', index=False)

 

---

 

데이터 불러오기

자동차 시장 세분화 분류를 위해 big-data-analytics-certification csv 파일을 불러옵니다.

# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)

# Input data files are available in the read-only "../input/" directory
# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory

import os
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))

# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" 
# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session

import pandas as pd
import numpy as np

X = pd.read_csv('/kaggle/input/big-data-analytics-certification-kr-2022/train.csv')
X_Submission = pd.read_csv('/kaggle/input/big-data-analytics-certification-kr-2022/test.csv')

 

EDA

X = X.drop(columns = ['TravelInsurance'])

#print(X.shape, X_submission.shape)
#    (1490, 9) (497, 9)

#print(X.info(), X_submission.info())
# 결측치X

object = ['Employment Type' ,'GraduateOrNot','FrequentFlyer','EverTravelledAbroad']
# print(X[object].nunique())
# print(X_submission[object].nunique())

# print(X['Employment Type'].unique())
# print(X_submission['Employment Type'].unique())

dfX = pd.concat([X, X_submission])

print(dfX.info(), dfX.shape)

>>> (1987, 9)

전처리

dfX = pd.get_dummies(dfX)
#dfX.shape
#(1987, 14)
#dfX.info()
# 결측치 채우기
dfX['AnnualIncome'] = dfX['AnnualIncome'].fillna(dfX['AnnualIncome'].median())

dfX['AnnualIncome'].isna().sum()

>>> 0

size = X.shape[0]
#print(size)
#1490

X1 = dfX.iloc[:size,:]
X_submission1 = dfX.iloc[size :,:]

print(X1.shape, X_submission1.shape)

>>> (1490, 14) (497, 14)

모델 학습 및 예측

from sklearn.model_selection import train_test_split

from sklearn.ensemble import RandomForestClassifier 
from sklearn.tree import DecisionTreeClassifier

from sklearn.metrics import roc_auc_score

xtrain, xtest, ytrain, ytest = train_test_split(X1, Y, test_size = 0.25,
                                               stratify = Y, random_state = 7438)
                                               
print([x.shape for x in [xtrain, xtest, ytrain, ytest]])

>>> (1117, 14), (373, 14), (1117,), (373,)

 

model1 = RandomForestClassifier(max_depth = 7,random_state = 7438).fit(xtrain, ytrain)
a = model1.score(xtrain, ytrain)
b = model1.score(xtest, ytest)
ypred = model1.predict_proba(xtest)[:,1]
c = roc_auc_score(ytest,ypred)


print(f' {x} {a:.4f} {b:.4f} {abs(a-b):.4f} {c:.4f}')

>>> 3 0.7825 0.7989 0.0165 0.8305
>>> 4 0.7923 0.8097 0.0174 0.8371
>>> 5 0.8111 0.8231 0.0120 0.8469
>>> 6 0.8451 0.8338 0.0113 0.8489
>>> 7 0.8559 0.8525 0.0033 0.8563
>>> 8 0.8675 0.8445 0.0230 0.8499

 

X_submission1.id

 

 

 

model = RandomForestClassifier(max_depth = 7,random_state = 7438).fit(xtrain, ytrain)
ypred = model1.predict_proba(X_submission1)[:,1]

submission = pd.DataFrame({'id' : X_submission1.id, 'TravelInsurance' : ypred})
submission.to_csv('result.csv', index=False)

ddff = pd.read_csv('result.csv')
ddff

 

 

 

 

 

 

케글출처 : https://www.kaggle.com/competitions/big-data-analytics-certification-kr-2022