Question

我想在泰坦尼克号数据集中做出预测。我想尝试catboost，因此我遵循了以下指南：https://www.analyticsvidhya.com/blog/2017/08/catboost-automated-categorical-data/ 但是当我尝试复制时不起作用

我试图按照指南进行操作，我认为catboost将负责所有数据转换，因为您可以在指南中看到他正在使用dtypes object，float，int

import pandas as pd
import numpy as np
from catboost import CatBoostRegressor
from sklearn.tree import DecisionTreeRegressor

train = pd.read_csv('train.csv')
test = pd.read_csv('test.csv')


train = train.replace(np.nan, '', regex=True)
train.fillna(-999, inplace=True)
test.fillna(-999,inplace=True)

categorical_features_indices = np.where(X.dtypes != np.float)[0]

train = train.replace(np.nan, '', regex=True)

y= train.Survived

train_features=['Pclass', 'Name', 'Sex', 'Age', 'SibSp',

       'Parch', 'Ticket', 'Fare', 'Cabin', 'Embarked']

X= train[train_features]


from sklearn.model_selection import train_test_split

X_train, X_validation, y_train, y_validation = train_test_split(X, y, train_size=0.7, random_state=1234)

#importing library and building model

from catboost import CatBoostRegressor

model=CatBoostRegressor(iterations=50, depth=3, learning_rate=0.1, loss_function='RMSE')

model.fit(X_train, y_train,cat_features=categorical_features_indices,eval_set=(X_validation, y_validation),plot=True)

---------------------------------------------------------------------------
CatBoostError                             Traceback (most recent call last)
_catboost.pyx in _catboost.get_cat_factor_bytes_representation()

_catboost.pyx in _catboost.get_id_object_bytes_string_representation()

CatBoostError: bad object for id: 40.5

During handling of the above exception, another exception occurred:

CatBoostError                             Traceback (most recent call last)
<ipython-input-103-94f3a250223b> in <module>
      2 from catboost import CatBoostRegressor
      3 model=CatBoostRegressor(iterations=50, depth=3, learning_rate=0.1, loss_function='RMSE')
----> 4 model.fit(X_train, y_train,cat_features=categorical_features_indices,eval_set=(X_validation, y_validation),plot=True)

~\Anaconda3\lib\site-packages\catboost\core.py in fit(self, X, y, cat_features, sample_weight, baseline, use_best_model, eval_set, verbose, logging_level, plot, column_description, verbose_eval, metric_period, silent, early_stopping_rounds, save_snapshot, snapshot_file, snapshot_interval, init_model)
   3359                          use_best_model, eval_set, verbose, logging_level, plot, column_description,
   3360                          verbose_eval, metric_period, silent, early_stopping_rounds,
-> 3361                          save_snapshot, snapshot_file, snapshot_interval, init_model)
   3362 
   3363     def predict(self, data, ntree_start=0, ntree_end=0, thread_count=-1, verbose=None):

~\Anaconda3\lib\site-packages\catboost\core.py in _fit(self, X, y, cat_features, pairs, sample_weight, group_id, group_weight, subgroup_id, pairs_weight, baseline, use_best_model, eval_set, verbose, logging_level, plot, column_description, verbose_eval, metric_period, silent, early_stopping_rounds, save_snapshot, snapshot_file, snapshot_interval, init_model)
   1235         _check_train_params(params)
   1236 
-> 1237         train_pool = _build_train_pool(X, y, cat_features, pairs, sample_weight, group_id, group_weight, subgroup_id, pairs_weight, baseline, column_description)
   1238         if train_pool.is_empty_:
   1239             raise CatBoostError("X is empty.")

~\Anaconda3\lib\site-packages\catboost\core.py in _build_train_pool(X, y, cat_features, pairs, sample_weight, group_id, group_weight, subgroup_id, pairs_weight, baseline, column_description)
    693             raise CatBoostError("y has not initialized in fit(): X is not catboost.Pool object, y must be not None in fit().")
    694         train_pool = Pool(X, y, cat_features=cat_features, pairs=pairs, weight=sample_weight, group_id=group_id,
--> 695                           group_weight=group_weight, subgroup_id=subgroup_id, pairs_weight=pairs_weight, baseline=baseline)
    696     return train_pool
    697 

~\Anaconda3\lib\site-packages\catboost\core.py in __init__(self, data, label, cat_features, column_description, pairs, delimiter, has_header, weight, group_id, group_weight, subgroup_id, pairs_weight, baseline, feature_names, thread_count)
    322                         )
    323 
--> 324                 self._init(data, label, cat_features, pairs, weight, group_id, group_weight, subgroup_id, pairs_weight, baseline, feature_names)
    325         super(Pool, self).__init__()
    326 

~\Anaconda3\lib\site-packages\catboost\core.py in _init(self, data, label, cat_features, pairs, weight, group_id, group_weight, subgroup_id, pairs_weight, baseline, feature_names)
    674             baseline = np.reshape(baseline, (samples_count, -1))
    675             self._check_baseline_shape(baseline, samples_count)
--> 676         self._init_pool(data, label, cat_features, pairs, weight, group_id, group_weight, subgroup_id, pairs_weight, baseline, feature_names)
    677 
    678 

_catboost.pyx in _catboost._PoolBase._init_pool()

_catboost.pyx in _catboost._PoolBase._init_pool()

_catboost.pyx in _catboost._PoolBase._init_features_order_layout_pool()

_catboost.pyx in _catboost._set_features_order_data_pd_data_frame()

_catboost.pyx in _catboost.get_cat_factor_bytes_representation()

CatBoostError: Invalid type for cat_feature[7,4]=40.5 : cat_features must be integer or string, real number values and NaN values should be converted to string.

Answer 1

我尝试从您提供的链接中运行代码，它可以正常工作。也许与您的Python版本有关。

GitHub上有一个问题，也有类似的问题，据说python版本有不同的结果。也许尝试更改您的Python版本。

我的规格：

Windows 10 Home单一语言
Python 3.6.5 | Anaconda，Inc. | （默认值，2018年3月29日，13：32：41）在win32上的[MSC v.1900 64位（AMD64）]

Catboost分类特征数据类型转换

1 个答案: