Rud*_*udy 5 python machine-learning pandas scikit-learn tensorflow
我正在尝试创建一个Python 3程序,使用Tensorflow将句子分类.但是,当我尝试运行代码时,我遇到了一系列非常长的错误.以下错误似乎是我的问题的基础:
InvalidArgumentError:断言失败:[标签ID必须<n_classes] [条件x <y不按元素持有:x(线性/头部/ ToFloat:0)=] [[4] [4] 1 ...] [y (linear/head/assert_range/Const:0)=] 2
我正在使用Scikit-Learn的LabelEncoder()方法来创建标签ID,这应该符合这个要求; 他们的文档页面说:" 编码值0和之间的标签n_classes-1. "
我试图运行的代码是:
import tensorflow as tf
import pandas as pd
from sklearn import preprocessing
from sklearn.model_selection import train_test_split
data_df = pd.read_csv('data.csv') #data.csv has 2 columns: "Category", and "Description"
features = data_df.drop('Category', axis=1) #drop Category column
lab_enc = preprocessing.LabelEncoder()
labels = lab_enc.fit_transform(data_df['Category']) #Encode labels with value between 0 and n_classes-1
labels = pd.Series(labels) #pandas_input_func needs the labels in Series format
features_train, features_test, labels_train, labels_test = train_test_split(features, labels, test_size=0.3, random_state=101)
description = tf.feature_column.categorical_column_with_hash_bucket('Description', hash_bucket_size=1000)
feat_cols = [description]
input_func = tf.estimator.inputs.pandas_input_fn(x=features_train, y=labels_train, batch_size=100, num_epochs=None, shuffle=True)
model = tf.estimator.LinearClassifier(feature_columns=feat_cols)
model.train(input_fn=input_func, steps=1000)
Run Code Online (Sandbox Code Playgroud)
关于如何继续,我有点不知所措.我只找到了一个帖子引用一个类似的问题在这里,但该用户的问题似乎是一个不同性质的矿井,如果我理解正确.
任何见解都非常感谢!
试试这个:
# Explicitly specify the number of classes, e.g. 10
model = tf.estimator.LinearClassifier(feature_columns=feat_cols, n_classes=10)
Run Code Online (Sandbox Code Playgroud)
默认值n_classes=2,内部意味着tensorflow使用sigmoid交叉熵损失.设置类的数量将使其成为softmax交叉熵.
| 归档时间: |
|
| 查看次数: |
1831 次 |
| 最近记录: |