오류가 뜹니다

• #1.문제정의

• #평가:ROC-AUC

• #target:'성별'

• 1

  #최종파일:"result.csv"(컬럼 1개 pred, 1확률값)

•  

•  

  #2.라이브러리 및 데이터 불러오기

•  

  import pandas as pd

• train = pd.read_csv("data/customer_train.csv")

• test = pd.read_csv("data/customer_test.csv")

•  

•  

  #3.탐색적 데이터분석(EDA). shape head info isnull.sum. value_counts. describe target

• pd.set_option('display.max_columns', None)

•  

  print(train.shape, test.shape)

•  

  print(train.head(2))

  print(test.head(2))

•  

  print(train.info())

•  

  print(test.info())

•  

  print(train.isnull().sum())

•  

  print(test.isnull().sum())

•  

  print(train['성별'].value_counts())

•  

•  

  #결측치채우기

•  

  train = train.fillna(0)

•  

  test = test.fillna(0)

•  

  print(train.isnull().sum())

•  

  print(test.isnull().sum())

•  

•  

  # 4.데이터전처리 - object데이터를 인코딩

•  

  df = pd.concat([train,test])

•  

  df = pd.get_dummies(df)

•  

  train = df[:len(train)].copy()

•  

  test = df[len(train):].copy()

•  

  print(train.shape, test.shape)

•  

•  

  #5. 검증 데이터 분할

•  

  from sklearn.model_selection import train_test_split

•  

  X_tr, X_val, y_tr, y_val = train_test_split(train.drop('성별', axis=1), train['성별'], test_size=0.2, random_state=10)

•  

  print(X_tr.shape, X_val.shape, y_tr.shape, y_val.shape)

•  

•  

  #6. 머신러닝 학습 및 평가

•  

  from sklearn.ensemble import RandomForestClassifier

•  

  from sklearn.metrics import roc_auc_score

•  

  model = RandomForestClassifier(random_state=0)

•  

  model.fit(X_tr, y_tr)

•  

  pred = model.predict_proba(X_val)

•  

  score = roc_auc_score(y_val, pred[:,1])

•  

  print(score)

•  

•  

  # 7. 예측 및 평가 파일 생성

•  

  pred = model.predict_proba(test)

•  

  submit = pd.DataFrame({'pred':pred[:,1]})

•  

  submit.to_csv("result.csv")

  print(pd.read_csv("result.csv"))

•  

•  

•  

•  

• 이렇게 했는데요. pred = model.predict_proba(test)만 작성하면 오류가 나는 이유가 뭘까요??

• Makefile:6: recipe for target 'py3_run' failed

  make: *** [py3_run] Error 1

  Traceback (most recent call last):

  File "/goorm/Main.out", line 64, in <module>

  pred = model.predict_proba(test)

  File "/usr/local/lib/python3.9/dist-packages/sklearn/ensemble/_forest.py", line 674, in predict_proba

  X = self._validate_X_predict(X)

  File "/usr/local/lib/python3.9/dist-packages/sklearn/ensemble/_forest.py", line 422, in validateX_predict

  return self.estimators_[0]._validate_X_predict(X, check_input=True)

  File "/usr/local/lib/python3.9/dist-packages/sklearn/tree/_classes.py", line 407, in validateX_predict

  X = self._validate_data(X, dtype=DTYPE, accept_sparse="csr",

  File "/usr/local/lib/python3.9/dist-packages/sklearn/base.py", line 421, in validatedata

  X = check_array(X, **check_params)

  File "/usr/local/lib/python3.9/dist-packages/sklearn/utils/validation.py", line 63, in inner_f

  return f(*args, **kwargs)

  File "/usr/local/lib/python3.9/dist-packages/sklearn/utils/validation.py", line 720, in check_array

  assertall_finite(array,

  File "/usr/local/lib/python3.9/dist-packages/sklearn/utils/validation.py", line 103, in assertall_finite

  raise ValueError(

  ValueError: Input contains NaN, infinity or a value too large for dtype('float32').