我对TensorFlow /机器学习相当新，因此有一些困难。我有一个csv格式here的数据集，想要用像here这样的pandas读取它。它工作在一个不同的数据集，但我修改和扩展，但我想我在这里缺少一些重要的东西。基本上我所要做的就是预测给定数据集的“整体”评级。这是我的代码和我得到的追溯：
import pandas as pd
import tensorflow as tf
import tempfile
COLUMNS = ["reviewerID", "asin", "reviewerName", "helpful_0", "helpful_1", "reviewText",
"overall", "summary", "unixReviewTime"]
CATEGORICAL_COLUMNS = ["reviewerID", "reviewerName", "reviewText", "summary"]
CONTINUOUS_COLUMNS = ["helpful_0", "helpful_1", "unixReviewTime"]
df_train = pd.read_csv('Digital_Music_5.csv', names=COLUMNS, skipinitialspace=True,
low_memory=False, skiprows=1)
df_test = pd.read_csv('Digital_Music_5_test.csv', names=COLUMNS,
skipinitialspace=True, skiprows=1)
LABEL_COLUMN = "label"
df_train[LABEL_COLUMN] = df_train["overall"]
df_test[LABEL_COLUMN] = df_train["overall"]
print(df_train)
def input_fn(df):
# Creates a dictionary mapping from each continuous feature column name (k)
# to the values of that column stored in a constant Tensor.
continuous_cols = {k: tf.constant(df[k].values)
for k in CONTINUOUS_COLUMNS}
# Creates a dictionary mapping from each categorical feature column name
# (k) to the values of that column stored in a tf.SparseTensor.
categorical_cols = {k: tf.SparseTensor(
indices=[[i, 0] for i in range(df[k].size)],
values=df[k].values,
dense_shape=[df[k].size, 1],) for k in CATEGORICAL_COLUMNS}
# Merges the two dictionaries into one.
feature_cols = dict(continuous_cols)
feature_cols.update(categorical_cols)
# Converts the label column into a constant Tensor.
label = tf.constant(df[LABEL_COLUMN].values)
# Returns the feature columns and the label.
return feature_cols, label
def train_input_fn():
return input_fn(df_train)
def eval_input_fn():
return input_fn(df_test)
reviewText = tf.contrib.layers.sparse_column_with_hash_bucket("reviewText", hash_bucket_size=100000)
reviewerID = tf.contrib.layers.sparse_column_with_hash_bucket("reviewerID", hash_bucket_size=100000)
reviewerName = tf.contrib.layers.sparse_column_with_hash_bucket("reviewerName", hash_bucket_size=100000)
summary = tf.contrib.layers.sparse_column_with_hash_bucket("summary", hash_bucket_size=100000)
asin = tf.contrib.layers.real_valued_column("asin")
helpful_0 = tf.contrib.layers.real_valued_column("helpful_0")
helpful_1 = tf.contrib.layers.real_valued_column("helpful_1")
unixReviewTime = tf.contrib.layers.real_valued_column("unixReviewTime")
# reviewText_x_summary = tf.contrib.layers.crossed_column([reviewText, summary], hash_bucket_size=100000)
# reviewerID_x_reviewerName = tf.contrib.layers.crossed_column([reviewerID, reviewerName], hash_bucket_size=100000)
# reviewText_x_reviewerID_x_reviewerName = tf.contrib.layers.crossed_column([reviewText, reviewerID, reviewerName], hash_bucket_size=100000)
model_dir = tempfile.mkdtemp()
m = tf.contrib.learn.LinearClassifier(feature_columns=[reviewText, reviewerName, summary,
asin, helpful_0, helpful_1, unixReviewTime], optimizer=tf.train.FtrlOptimizer(
learning_rate=0.1,
l1_regularization_strength=1.0,
l2_regularization_strength=1.0),
model_dir=model_dir)
m.fit(input_fn=train_input_fn, steps=200)
# results = m.evaluate(input_fn=eval_input_fn, steps=1)
# for key in sorted(results):
# print("{}: {}".format(key, results[key]))
回溯：
Traceback (most recent call last):
File "amazon_reviews.py", line 78, in <module>
m.fit(input_fn=train_input_fn, steps=200)
File "/home/cfritz/virtualenvs/tensorflow/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 280, in new_func
return func(*args, **kwargs)
File "/home/cfritz/virtualenvs/tensorflow/lib/python3.6/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 426, in fit
loss = self._train_model(input_fn=input_fn, hooks=hooks)
File "/home/cfritz/virtualenvs/tensorflow/lib/python3.6/site-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 932, in _train_model
features, labels = input_fn()
File "amazon_reviews.py", line 47, in train_input_fn
return input_fn(df_train)
File "amazon_reviews.py", line 36, in input_fn
dense_shape=[df[k].size, 1],) for k in CATEGORICAL_COLUMNS}
File "amazon_reviews.py", line 36, in <dictcomp>
dense_shape=[df[k].size, 1],) for k in CATEGORICAL_COLUMNS}
File "/home/cfritz/virtualenvs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/sparse_tensor.py", line 125, in __init__
values, name="values", as_ref=True)
File "/home/cfritz/virtualenvs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 702, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/home/cfritz/virtualenvs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py", line 110, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
File "/home/cfritz/virtualenvs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py", line 99, in constant
tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape, verify_shape=verify_shape))
File "/home/cfritz/virtualenvs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py", line 451, in make_tensor_proto
append_fn(tensor_proto, proto_values)
File "/home/cfritz/virtualenvs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py", line 109, in SlowAppendObjectArrayToTensorProto
tensor_proto.string_val.extend([compat.as_bytes(x) for x in proto_values])
File "/home/cfritz/virtualenvs/tensorflow/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py", line 109, in <listcomp>
tensor_proto.string_val.extend([compat.as_bytes(x) for x in proto_values])
File "/home/cfritz/virtualenvs/tensorflow/lib/python3.6/site-packages/tensorflow/python/util/compat.py", line 65, in as_bytes
(bytes_or_text,))
TypeError: Expected binary or unicode string, got nan
答案 0 :(得分：5)
您的输入DataFrame包含由pd.read_csv()映射到NaN的空审阅者名称和审阅文本，但TensorFlow需要字符串而不是NaN。
使用以下命令检查空单元格：
df_train[df_train.isnull().any(axis=1)]
您可以使用
将这些NaN转换为空字符串df_train.fillna('', inplace=True)
或让pd.read_csv()直接使用na_values=[]创建空字符串而不是NAN：
df_train = pd.read_csv('Digital_Music_5.csv', names=COLUMNS,
skipinitialspace=True, low_memory=False,
skiprows=1, na_values=[])