빅데이터 분석기사 샘플문제 문제풀이

 

[Dataset] 작업형 제1유형.zip

0.00MB

[Dataset] 작업형 제2유형.zip

0.13MB

유형별 예시문제.pdf

0.13MB

시험환경 접속

https://dataq.goorm.io/exam/116674/%EC%B2%B4%ED%97%98%ED%95%98%EA%B8%B0/quiz/1

구름EDU - 모두를 위한 맞춤형 IT교육

 

 

단답형 

데이터베이스

 

 

작업형 1

sklearn을 활용하여 문제해결

import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler


# 데이터 프레임 불러오기
df = pd.read_csv('mtcars.csv')

# '열'만 따로 떼놓기 
df_qsec = df['qsec']

# reshape를 통한 2차원 배열 만들기 (pd.Series를 numpy로 변환)
x = df_qsec.values.reshape(-1, 1)
x

# MinMaxScaler 사용
scaler = MinMaxScaler()
print(type(x))

# fit_tranform을 사용해 데이터 변환하기
y = scaler.fit_transform(x)
print((y>0.5).sum())

 

직접 코드를 작성하여 문제해결

import pandas as pd
import numpy as np

df = pd.read_csv('mtcars.csv')
x = df['qsec']

print(x)

x_max = x.max()
x_min = x.min()

y = (x - x_min) / (x_max - x_min)

print(y[y>0.5].count())

 

 

작업형 2

# 사용자 코딩

import pandas as pd
import numpy as np
import sklearn

from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import roc_auc_score
from xgboost import XGBClassifier 

# Get DF

X_train_path = 'data/X_train.csv'
X_test_path = 'data/X_test.csv'
y_train_path = 'data/y_train.csv'
y_test_path = '123456.csv'

X_train = pd.read_csv(X_train_path)
X_train_id = X_train.iloc[:, 0]
X = X_train.iloc[:, 1:]

X_test = pd.read_csv(X_test_path)
X_test_id = X_test.iloc[:, 0]
X_test = X_test.iloc[:, 1:]

y_train = pd.read_csv(y_train_path)
y = y_train.iloc[:, 1]


# info 
# X_train.info()
# X_train.isnull().sum()


# DF preprocessing
# LabelEncdoder
X.loc[:, ['주구매상품', '주구매지점']] = X.loc[:, ['주구매상품', '주구매지점']].apply(LabelEncoder().fit_transform)
X_test.loc[:, ['주구매상품', '주구매지점']] = X_test.loc[:, ['주구매상품', '주구매지점']].apply(LabelEncoder().fit_transform)

# NaN to zero
X.loc[:, ['환불금액']] = X.loc[:, ['환불금액']].fillna(0)
X_test.loc[:, ['환불금액']] = X_test.loc[:, ['환불금액']].fillna(0)

# model_selection
from sklearn.model_selection import train_test_split
X1, X2, y1, y2 = train_test_split(X, y, test_size=0.3, random_state=999, stratify = y)


# Model
# RFC
rfc = RandomForestClassifier()
rfc.fit(X1, y1)

pred = rfc.predict_proba(X2)[:, 1]

# Score
from sklearn.metrics import roc_auc_score
print(roc_auc_score(y2, pred))
result_pred = rfc.predict_proba(X_test)[:,1]
result_pred = pd.DataFrame(result_pred)
result = pd.concat([X_test_id, result_pred], axis=1)
result.columns = ['cust_id', 'gender']
# print(result)
result.to_csv(y_test_path, index=False)

df = pd.read_csv(y_test_path)
print(df)

 

# XGBC
xgbc = XGBClassifier(learning_rate = 0.02, max_depth=20)
xgbc.fit(X_train, y_train)
print('XGBC ACC.:', xgbc.score(X_train, y_train))

predict = xgbc.predict_proba(X_test)
predict = pd.DataFrame(predict)
answer = pd.concat([X_test_id, predict], axis=1)
answer.to_csv(y_test_path, index=False)

 

 

---

 

#빅데이터분석기사후기 #빅데이터분석기사실기 #빅데이터분석기사필기pdf #빅데이터분석기사합격률 #빅데이터분석기사쓸모 #빅데이터분석기사2022일정 #빅데이터분석기사전망 #빅데이터분석기사실기 #빅데이터분석기사실기파이썬 #빅데이터분석기사실기파이썬 #빅데이터분석기사실기문제 #빅데이터분석기사실기합격률 #빅데이터분석기사실기준비 #빅데이터분석기사필기기출문제 #빅데이터분석기사필기복원 #빅분기기출 #빅분기정리 #빅분기난이도 #빅분기필기복원