这是我的完整代码和回溯。这是我的机器学习模型的起始代码。将会有很多补充。
import pandas as pd
import tensorflow as tf
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn import metrics
from IPython import display
from tensorflow.python.data import Dataset
tf.logging.set_verbosity(tf.logging.ERROR)
pd.options.display.max_rows = 5
pd.options.display.float_format = '{:.1f}'.format
housing_data = pd.read_csv("train.csv")
housing_data = housing_data.reindex(
np.random.permutation(housing_data.index))
housing_data = pd.get_dummies(
housing_data).dropna()
预处理特征。这里还有更多工作要做。
def preprocess_features(housing_data):
selected_features = housing_data
selected_features = selected_features.drop(columns = "SalePrice")
processed_features = selected_features.copy()
return processed_features
def preprocess_target(housing_data):
output_target = pd.DataFrame()
output_target["SalePrice"] = (housing_data.SalePrice / 1000.0)
return output_target
training_examples = preprocess_features(housing_data.head(900))
training_targets = preprocess_target(housing_data.head(900))
validation_examples = preprocess_features(housing_data.tail(221))
validation_targets = preprocess_target(housing_data.tail(221))
def construct_feature_columns(input_features):
'''
Returns the set of feature columns for tf.estimator classifiers and regressors
'''
return set([tf.feature_column.numeric_column(my_feature) for my_feature in input_features])
def my_input_fn(features, targets, batch_size = 1, shuffle = True, num_epochs = None):
#convert the pandas dataframe into a numpy array
features = {key:np.array(value) for key,value in dict(features).items()}
#create the dataset
ds = Dataset.from_tensor_slices((features,targets))
ds = ds.batch(batch_size).repeat(num_epochs)
#shuffle the data
if shuffle:
ds = ds.shuffle(1000)
#return the features and targets tuple for next iteration
features,labels=
ds.make_one_shot_iterator().get_next()
return features,labels
线性分类器
def train_linear_classifier_model(
learning_rate,
regularization_strength,
steps,
batch_size,
training_examples,
training_targets,
validation_examples,
validation_targets
):
periods = 10
steps_per_period = steps / periods
my_optimizer = tf.train.FtrlOptimizer(learning_rate=learning_rate, l1_regularization_strength=regularization_strength)
my_optimizer = tf.contrib.estimator.clip_gradients_by_norm(my_optimizer, 5.0)
linear_classifier = tf.estimator.LinearClassifier(
feature_columns=construct_feature_columns(training_examples),
optimizer=my_optimizer
)
training_input_fn = lambda: my_input_fn(training_examples,
training_targets["SalePrice"],
batch_size=batch_size)
predict_training_input_fn = lambda: my_input_fn(training_examples,
training_targets["SalePrice"],
num_epochs=1,
shuffle=False)
predict_validation_input_fn = lambda: my_input_fn(validation_examples,
validation_targets["SalePrice"],
num_epochs=1,
shuffle=False)
print("Training model...")
print("LogLoss (on validation data):")
training_log_losses = []
validation_log_losses = []
for period in range (0, periods):
linear_classifier.train(
input_fn=training_input_fn,
steps=steps_per_period
)
# Take a break and compute predictions.
training_probabilities = linear_classifier.predict(input_fn=predict_training_input_fn)
training_probabilities = np.array([item['probabilities'] for item in training_probabilities])
validation_probabilities = linear_classifier.predict(input_fn=predict_validation_input_fn)
validation_probabilities = np.array([item['probabilities'] for item in validation_probabilities])
# Compute training and validation loss.
training_log_loss = metrics.log_loss(training_targets, training_probabilities)
validation_log_loss = metrics.log_loss(validation_targets, validation_probabilities)
# Occasionally print the current loss.
print(" period %02d : %0.2f" % (period, validation_log_loss))
# Add the loss metrics from this period to our list.
training_log_losses.append(training_log_loss)
validation_log_losses.append(validation_log_loss)
print("Model training finished.")
# Output a graph of loss metrics over periods.
plt.ylabel("LogLoss")
plt.xlabel("Periods")
plt.title("LogLoss vs. Periods")
plt.tight_layout()
plt.plot(training_log_losses, label="training")
plt.plot(validation_log_losses, label="validation")
plt.legend()
return linear_classifier
linear_classifier = train_linear_classifier_model(
learning_rate=0.1,
regularization_strength=0.1,
steps=300,
batch_size=100,
training_examples=training_examples,
training_targets=training_targets,
validation_examples=validation_examples,
validation_targets = validation_targets)
这是我的回溯
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-75-f9d203769761> in <module>()
7 training_targets=training_targets,
8 validation_examples=validation_examples,
----> 9 validation_targets = validation_targets)
<ipython-input-74-e1dbd56d9615> in train_linear_classifier_model(learning_rate, regularization_strength, steps, batch_size, training_examples, training_targets, validation_examples, validation_targets)
40 linear_classifier.train(
41 input_fn=training_input_fn,
---> 42 steps=steps_per_period
43 )
44 # Take a break and compute predictions.
c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\estimator\estimator.py in train(self, input_fn, hooks, steps, max_steps, saving_listeners)
350
351 saving_listeners = _check_listeners_type(saving_listeners)
--> 352 loss = self._train_model(input_fn, hooks, saving_listeners)
353 logging.info('Loss for final step: %s.', loss)
354 return self
c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\estimator\estimator.py in _train_model(self, input_fn, hooks, saving_listeners)
810 worker_hooks.extend(input_hooks)
811 estimator_spec = self._call_model_fn(
--> 812 features, labels, model_fn_lib.ModeKeys.TRAIN, self.config)
813
814 if self._warm_start_settings:
c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\estimator\estimator.py in _call_model_fn(self, features, labels, mode, config)
791
792 logging.info('Calling model_fn.')
--> 793 model_fn_results = self._model_fn(features=features, **kwargs)
794 logging.info('Done calling model_fn.')
795
c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\estimator\canned\linear.py in _model_fn(features, labels, mode, config)
314 optimizer=optimizer,
315 partitioner=partitioner,
--> 316 config=config)
317
318 super(LinearClassifier, self).__init__(
c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\estimator\canned\linear.py in _linear_model_fn(features, labels, mode, head, feature_columns, optimizer, partitioner, config)
155 logit_fn = _linear_logit_fn_builder(
156 units=head.logits_dimension, feature_columns=feature_columns)
--> 157 logits = logit_fn(features=features)
158
159 def _train_op_fn(loss):
c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\estimator\canned\linear.py in linear_logit_fn(features)
96 feature_columns=feature_columns,
97 units=units,
---> 98 cols_to_vars=cols_to_vars)
99 bias = cols_to_vars.pop('bias')
100 if units > 1:
c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\feature_column\feature_column.py in linear_model(features, feature_columns, units, sparse_combiner, weight_collections, trainable, cols_to_vars)
422 for column in sorted(feature_columns, key=lambda x: x.name):
423 with variable_scope.variable_scope(
--> 424 None, default_name=column._var_scope_name): # pylint: disable=protected-access
425 ordered_columns.append(column)
426 weighted_sum = _create_weighted_sum(
c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\ops\variable_scope.py in __enter__(self)
1901
1902 try:
-> 1903 return self._enter_scope_uncached()
1904 except:
1905 if self._graph_context_manager is not None:
c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\ops\variable_scope.py in _enter_scope_uncached(self)
2001 self._default_name)
2002 try:
-> 2003 current_name_scope_name = current_name_scope.__enter__()
2004 except:
2005 current_name_scope.__exit__(*sys.exc_info())
c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\framework\ops.py in __enter__(self)
5619 try:
5620 self._name_scope = g.name_scope(self._name)
-> 5621 return self._name_scope.__enter__()
5622 except:
5623 self._g_manager.__exit__(*sys.exc_info())
c:\users\user\appdata\local\programs\python\python35\lib\contextlib.py in __enter__(self)
57 def __enter__(self):
58 try:
---> 59 return next(self.gen)
60 except StopIteration:
61 raise RuntimeError("generator didn't yield") from None
c:\users\user\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\framework\ops.py in name_scope(self, name)
3942 # (viz. '-', '\', '/', and '_').
3943 if not _VALID_SCOPE_NAME_REGEX.match(name):
-> 3944 raise ValueError("'%s' is not a valid scope name" % name)
3945 else:
3946 # Scopes created in the root must match the more restrictive
ValueError: 'Exterior1st_Wd Sdng' is not a valid scope name
我无法理解术语“Exterior1st_Wd Sdng”的含义，因为我没有任何这样命名的变量。 提前致谢!
最佳答案
我试图弄清楚 Tensorflow 中允许使用哪些范围名称，而此页面是第一个结果，因此我将借此机会在这里为具有相同查询的其他人发布答案。
在撰写本文时，允许的范围名称似乎受到 this 的限制。 Tensorflow 源代码中的行:
_VALID_SCOPE_NAME_REGEX = re.compile("^[A-Za-z0-9_.\\-/>]*$")
换句话说，作用域名称可以包含字母(大小写)、数字和 _、.、\、-、/、>。 (值得注意的是，它们不能包含空格。)
希望有人觉得这有帮助。
关于python-3.x - 当我尝试创建 Kaggle 竞赛模型时获取 "Tensorflow %s is not valid scope name error"，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/51876460/