Python 3.x 无法在iris数据集上实现广域和深层网络tensorflow

我对iris数据集做了一些修改，添加了两列，country和forest，因此我可以在数据上添加一些分类功能，并尝试实现tensorflow，如下代码所示：

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import datetime

import tensorflow as tf
import pandas as pd
import numpy as np
import tempfile
tf.logging.set_verbosity(tf.logging.ERROR)

IRIS_TRAINING="iris_training.csv"
IRIS_TEST="iris_test.csv"

start=datetime.datetime.now()
tf.reset_default_graph()
#categorical features
country=tf.contrib.layers.sparse_column_with_keys(column_name='country',keys=[0,1,2,3])
forest=tf.contrib.layers.sparse_column_with_keys(column_name='forest',keys=[0,1,2,3,4,5])
#continous features
sepal_length=tf.contrib.layers.real_valued_column('sepal_length')
sepal_width=tf.contrib.layers.real_valued_column('sepal_width')
petal_length=tf.contrib.layers.real_valued_column('petal_length')
petal_width=tf.contrib.layers.real_valued_column('petal_width')
#wide columns
wide_columns=[forest,country,tf.contrib.layers.crossed_column([forest,country],hash_bucket_size=int(1e4))]
deep_columns=[ tf.contrib.layers.embedding_column(country,dimension=8),tf.contrib.layers.embedding_column(forest,dimension=8),sepal_length,sepal_width,petal_length,petal_width]
COLUMNS=['sepal_length','sepal_width','petal_length','petal_width','label']
LABEL_COLUMN=['label']
CATEGORICAL_COLUMNS=['country','forest']
CONTINUOUS_COLUMNS=['sepal_length','sepal_width','petal_length','petal_width']
#Load datesest
print("loading dataset")
training_set=pd.read_csv(IRIS_TRAINING,names=COLUMNS,skipinitialspace=True,skiprows=1)
np.random.seed(42)
training_set['country']=np.random.choice(range(1,4),training_set.shape[0])
training_set['forest']=np.random.choice(range(0,6),training_set.shape[0])
training_set['label']=training_set['label'].astype(int)
test_set=pd.read_csv(IRIS_TEST,names=COLUMNS,skipinitialspace=True,skiprows=1)
test_set['country']=np.random.choice(range(0,4),test_set.shape[0])
test_set['forest']=np.random.choice(range(0,6),test_set.shape[0])
test_set['label']=training_set['label'].astype(int)
print("finished loading dataset")
print(training_set.head)
print(test_set.head)
print((datetime.datetime.now()-start).seconds)

#generating input for the classifier

def input_fn(df):
   continuous_cols = {k: tf.constant(df[k].values) for k in CONTINUOUS_COLUMNS}
   categorical_cols = {k: tf.SparseTensor( indices=[[i, 0] for i in range(df[k].size)], values=df[k].values, shape=[df[k].size, 1]) for k in CATEGORICAL_COLUMNS}
   feature_cols = dict(continuous_cols.items() | categorical_cols.items())
   label = tf.constant(df[LABEL_COLUMN].values)
   return feature_cols,label




#Config and initiate model
print("Initializing model")
validation_metrics = {
    "accuracy":
        tf.contrib.learn.metric_spec.MetricSpec(
            metric_fn=tf.contrib.metrics.streaming_accuracy,
            prediction_key=tf.contrib.learn.prediction_key.PredictionKey.
            CLASSES),
    "precision":
        tf.contrib.learn.metric_spec.MetricSpec(
            metric_fn=tf.contrib.metrics.streaming_precision,
            prediction_key=tf.contrib.learn.prediction_key.PredictionKey.
            CLASSES),
    "recall":
        tf.contrib.learn.metric_spec.MetricSpec(
            metric_fn=tf.contrib.metrics.streaming_recall,
            prediction_key=tf.contrib.learn.prediction_key.PredictionKey.
            CLASSES)
}

#validation_monitor = tf.contrib.learn.monitors.ValidationMonitor( test_set.data, test_set.target, every_n_steps=50,metrics=validation_metrics)

def train_input_fn():
    return input_fn(training_set)


def eval_input_fn():
    return input_fn(test_set)


model_dir=tempfile.mkdtemp()
m=tf.contrib.learn.DNNLinearCombinedClassifier(linear_feature_columns=wide_columns,dnn_feature_columns=deep_columns,dnn_hidden_units=[100,50],n_classes=3,model_dir=model_dir,config=tf.contrib.learn.RunConfig(save_checkpoints_secs=1))
print("Finished Model Init")
print((datetime.datetime.now()-start).seconds)

#fit the model 
print("Train the model the model")
m.fit(input_fn=train_input_fn,steps=60)
print("Finished finiting the model")
print((datetime.datetime.now()-start).seconds)


#Evaluate Classifier
print("Evaluating model")
results=m.evaluate(input_fn=eval_input_fn,step=1)
for key in sorted(results):
    print("%s : %s"+(key,results[key]))
#accuracy_score=classifier.evaluate(x=test_set.data,y=test_set.target)["accuracy"]

#print('Accuracy score:{0:f}'.format(accuracy_score))
print("Finished Evaluating the model")
print((datetime.datetime.now()-start).seconds)

然而，我得到的张量流并不明显：

Traceback (most recent call last):
  File "iris_wide_deep.py", line 97, in <module>
    m.fit(input_fn=train_input_fn,steps=60)
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/estimators/dnn_linear_combined.py", line 711, in fit
    max_steps=max_steps)
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/util/deprecation.py", line 191, in new_func
    return func(*args, **kwargs)
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 355, in fit
    max_steps=max_steps)
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 699, in _train_model
    train_ops = self._get_train_ops(features, labels)
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 1052, in _get_train_ops
    return self._call_model_fn(features, labels, model_fn_lib.ModeKeys.TRAIN)
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 1019, in _call_model_fn
    params=self.params)
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/learn/python/learn/estimators/dnn_linear_combined.py", line 443, in _dnn_linear_combined_model_fn
    scope=scope)
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/layers/python/layers/feature_column_ops.py", line 247, in input_from_feature_columns
    default_name='input_from_feature_columns')
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/layers/python/layers/feature_column_ops.py", line 159, in _input_from_feature_columns
    transformed_tensor = transformer.transform(column)
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/layers/python/layers/feature_column_ops.py", line 869, in transform
    feature_column.insert_transformed_feature(self._columns_to_tensors)
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/layers/python/layers/feature_column.py", line 916, in insert_transformed_feature
    self.sparse_id_column.insert_transformed_feature(columns_to_tensors)
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/layers/python/layers/feature_column.py", line 592, in insert_transformed_feature
    name="lookup")
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/contrib/lookup/lookup_ops.py", line 622, in string_to_index
    keys = ops.convert_to_tensor(mapping, dtypes.string)
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 669, in convert_to_tensor
    ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/constant_op.py", line 176, in _constant_tensor_conversion_function
    return constant(v, dtype=dtype, name=name)
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/constant_op.py", line 165, in constant
    tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape, verify_shape=verify_shape))
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/tensor_util.py", line 367, in make_tensor_proto
    _AssertCompatible(values, dtype)
  File "/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/tensor_util.py", line 302, in _AssertCompatible
    (dtype.name, repr(mismatch), type(mismatch).__name__))
TypeError: Expected string, got 0 of type 'int' instead.
(tensorflow) 

回溯（最近一次呼叫最后一次）：
文件“iris\u wide\u deep.py”，第97行，在
m、 配合（输入\u fn=传动系\u输入\u fn，步数=60）
文件“/home/elitessaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/contrib/learn/python/learn/learn/estimators/dnn_linear_combined.py”，第711行
最大步数=最大步数）
文件“/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/python/util/deprecation.py”，第191行，在新函数中
返回函数（*args，**kwargs）
文件“/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/contrib/learn/python/learn/learn/estimators/estimator.py”，第355行，以合适的格式
最大步数=最大步数）
文件“/home/elitessaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/contrib/learn/python/learn/learn/estimators/estimator.py”，第699行，列车模型
列车运行=自我。获取列车运行（功能、标签）
文件“/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/contrib/learn/python/learn/learn/estimators/estimator.py”，第1052行，在“获取”列车运行中
返回self.\u调用\u model\u fn（特性、标签、model\u fn\u lib.ModeKeys.TRAIN）
文件“/home/elitessaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/contrib/learn/python/learn/learn/estimators/estimator.py”，第1019行，在调用模型fn中
params=self.params）
文件“/home/elitessaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/contrib/learn/python/learn/learn/estimators/dnn\u linear\u combined.py”，第443行，在“dnn\u linear\u combined\u”模型中
范围=范围）
文件“/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/contrib/layers/python/python/layers/feature_column_ops.py”，第247行，输入_from_feature_columns
默认值\u name='input\u from\u feature\u columns'）
文件“/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/contrib/layers/python/python/layers/feature\u column\u ops.py”，第159行，在“input\u from\u feature\u columns”中
变换张量=变换器。变换（列）
文件“/home/elitessaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/contrib/layers/python/layers/feature_column_ops.py”，第869行，在转换中
特征列。插入转换的特征（自列到张量）
文件“/home/elitessaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/contrib/layers/python/layers/feature_column.py”，第916行，插入_特征
self.sparse\u id\u column.insert\u transformed\u特征（columns\u to\u张量）
文件“/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/contrib/layers/python/layers/feature_column.py”，第592行，插入_特征
name=“查找”）
文件“/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/contrib/lookup/lookup_ops.py”，第622行，字符串索引
keys=ops.convert_to_tensor（映射，dtypes.string）
文件“/home/elitessaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/python/framework/ops.py”，第669行，转换为tensor
ret=conversion\u func（值，dtype=dtype，name=name，as\u ref=as\u ref）
文件“/home/eliethesaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/python/framework/constant\u op.py”，第176行，在“constant\u tensor\u conversion”函数中
返回常量（v，dtype=dtype，name=name）
文件“/home/elitessaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/python/framework/constant_op.py”，第165行，常量
tensor_util.make_tensor_proto（值，dtype=dtype，shape=shape，verify_shape=verify_shape））
文件“/home/elitessaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/python/framework/tensor\u util.py”，第367行，在make\u tensor\u proto中
_资产可兼容（值、数据类型）
文件“/home/elitessaiyan/anaconda3/envs/tensorflow/lib/python3.5/site packages/tensorflow/python/framework/tensor_util.py”，第302行，在资产可兼容文件中
（dtype.name、repr（不匹配）、type（不匹配）。\uu name
TypeError:应为字符串，取而代之的是类型为“int”的0。
（张量流）

在此，我非常感谢您提供一些指导，因为我在给定的示例中尝试尽可能多地复制数据集类型

由此，我发现使用数字作为分类特征（国家）值被推断为这一行上的数字

categorical_cols = {k: tf.SparseTensor( indices=[[i, 0] for i in range(df[k].size)], values=df[k].values, shape=[df[k].size, 1]) for k in CATEGORICAL_COLUMNS}

由于tensorflow将其张量存储在numpy数组中，所以在此之前，它会尝试在存储它们之前推断数据类型

由于我在读取csv文件后没有指定它们的类型，它们被作为对象发送到SparseTensor对象，SparseTensor对象反过来检查数据类型

我希望这有帮助

你的代码乱七八糟。阅读