0

我正在尝试使用烧瓶部署 XGBClassifier 模型。将值提供给网页上的相关字段后，它给了我以下错误：-

DataFrame.dtypes for data must be int, float, bool or categorical.  When
categorical type is supplied, DMatrix parameter
`enable_categorical` must be set to `True`.JobType, EdType, maritalstatus, 
occupation, relationship, gender

我使用了一个热编码器来编码 7 个分类变量，其余 3 个是数字的。以下是我的代码： -

train_x, test_x, train_y, test_y = train_test_split(data1, y, test_size = 0.2, 
random_state=69)

# IMPUTING NAN VALUES
train_x['JobType'].fillna(train_x['JobType'].value_counts().index[0], inplace = True) 
train_x['occupation'].fillna(train_x['occupation'].value_counts().index[0], inplace = True)

test_x['JobType'].fillna(train_x['JobType'].value_counts().index[0], inplace = True)
test_x['occupation'].fillna(train_x['occupation'].value_counts().index[0], inplace = True)

# SEPARATING CATEGORICAL VARIABLES
train_x_cat = train_x.select_dtypes(include = 'object')
train_x_num = train_x.select_dtypes(include = 'number')

test_x_cat = test_x.select_dtypes(include = 'object')
test_x_num = test_x.select_dtypes(include = 'number')

#ONE HOT ENCODING THE CATEGORICAL VARIABLES AND THEN CONCAT THEM TO NUMERICAL VARIABLES
ohe = OneHotEncoder(handle_unknown='ignore', sparse = False)
train_x_encoded = pd.DataFrame(ohe.fit_transform(train_x_cat))
train_x_encoded.columns = ohe.get_feature_names(train_x_cat.columns)

train_x_encoded = train_x_encoded.reset_index(drop = True)
train_x_num = train_x_num.reset_index(drop = True)
train_x1 = pd.concat([train_x_num, train_x_encoded], axis = 1)


test_x_encoded = pd.DataFrame(ohe.transform(test_x_cat))
test_x_encoded.columns = ohe.get_feature_names(test_x_cat.columns)

test_x_encoded = test_x_encoded.reset_index(drop = True)
test_x_num = test_x_num.reset_index(drop = True)
test_x1 = pd.concat([test_x_num, test_x_encoded], axis = 1)

#XGBC MODEL
model = XGBClassifier(random_state = 69)

#Hyperparameter tuning
def objective(trial):
    learning_rate = trial.suggest_float('learning_rate', 0.001, 0.01)
    n_estimators = trial.suggest_int('n_estimators', 10, 500)
    sub_sample = trial.suggest_float('sub_sample', 0.0, 1.0)
    max_depth = trial.suggest_int('max_depth', 1, 20)

    params = {'max_depth' : max_depth,
           'n_estimators' : n_estimators,
           'sub_sample' : sub_sample,
           'learning_rate' : learning_rate}

    model.set_params(**params)

    return np.mean(-1 * cross_val_score(model, train_x1, train_y,
                                    cv = 5, n_jobs = -1, scoring = 'neg_mean_squared_error'))

xgbc_study = optuna.create_study(direction = 'minimize')
xgbc_study.optimize(objective, n_trials = 10)

xgbc_study.best_params
optuna_rfc_mse = xgbc_study.best_value

model.set_params(**xgbc_study.best_params)
model.fit(train_x1, train_y)

这是我的 Flask (app.py) 代码：-

@app.route('/', methods = ['GET', 'POST'])
def main():
    if request.method == 'GET':
       return render_template('index.html')

    if request.method == "POST":
       Age = request.form['age']
       Jobtypes = request.form['JobType']
       EducationType = request.form['EdType']
       MaritalStatus = request.form['maritalstatus']
       Occupation = request.form['occupation']
       Relationship = request.form['relationship']
       Gender = request.form['gender']
       CapitalGain = request.form['capitalgain']
       CapitalLoss = request.form['capitalloss']
       HoursPerWeek = request.form['hrsperweek']
    
       data = [[Age, Jobtypes, EducationType, MaritalStatus, Occupation, Relationship, 
             Gender, CapitalGain, CapitalLoss, HoursPerWeek]]
    
       input_variables = pd.DataFrame(data, columns = ['age', 'JobType', 'EdType', 
                                                       'maritalstatus', 'occupation', 
                                                       'relationship', 'gender', 
                                                       'capitalgain', 'capitalloss', 
                                                       'hrsperweek'], 
                                                       dtype = 'float', index = ['input'])
    
       predictions = model.predict(input_variables)[0]
       print(predictions)
    
       return render_template('index.html', original_input = {'age':Age, 'JobType':Jobtypes, 
                                                              'EdType':EducationType,
                                                           'maritalstatus':MaritalStatus, 
                                                           'occupation':Occupation, 
                                                           'relationship':Relationship, 
                                                           'gender':Gender, 
                                                           'capitalgain':CapitalGain,
                                                           'capitalloss':CapitalLoss, 
                                                           'hrsperweek':HoursPerWeek},
                                                            result = predictions)

错误表明数据类型应该是 int、categorical、float 或 boolean。但是我已经对变量进行了编码，然后拟合了模型。那么为什么会出错呢？

提前致谢！

4

0 回答 0