问在可数化稀疏数据集中获取错误“无法将字符串转换为浮点”

EN

~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\utils\validation.py in check_array(array, accept_sparse, dtype, order, copy, force_all_finite, ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)
    400                                       force_all_finite)
    401     else:
--> 402         array = np.array(array, dtype=dtype, order=order, copy=copy)
    403 
    404         if ensure_2d:

ValueError: could not convert string to float: 'IP'

 cv = CountVectorizer( max_features = 500,analyzer='word') 
    cv_addr = cv.fit_transform(data.pop('Clean_addr'))
    for i, col in enumerate(cv.get_feature_names()):
        data[col] = pd.SparseSeries(cv_addr[:, i].toarray().ravel(), fill_value=0)

 train = data.drop(['Co_Name','Cust_ID','Phone','Shpr_ID','Resi_Cnt','Buz_Cnt','Nearby_Cnt','parseNumber','removeString','Qty','bins','Adj_Addr','Resi','Co_Name_FLag','Phone_Type'], axis=1)
    Y = data['Resi']

X_train, X_test, y_train, y_test = train_test_split(train, Y, test_size=0.3)
    gbc = GradientBoostingClassifier(max_depth = 7, n_estimators=1500, min_samples_leaf=10)

    print('Training GBC')

    gbc.fit(X_train, y_train)

 Phone_Type Co_Name_FLag    Product
    undefined   Present     IP
    Landline    Present     IP
    undefined   Not_present IP
    Landline    Present        IPD
    Mobile  Not_Present IP
    Landline    Present         IE
    Mobile          Present         IPF
    Landline    Present          IP
    undefined   Present     IP
    Landline    Present         IP