通过一个开源的实例理解机器学习中的分类
premade_estimator.py如下：
# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""An Example of a DNNClassifier for the Iris dataset."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import tensorflow as tf
import iris_data
parser = argparse.ArgumentParser()
parser.add_argument('--batch_size', default=100, type=int, help='batch size')
parser.add_argument('--train_steps', default=1000, type=int,
help='number of training steps')
def main(argv):
args = parser.parse_args(argv[1:])
# Fetch the data
(train_x, train_y), (test_x, test_y) = iris_data.load_data()
# Feature columns describe how to use the input.
my_feature_columns = []
for key in train_x.keys():
my_feature_columns.append(tf.feature_column.numeric_column(key=key))
# Build 2 hidden layer DNN with 10, 10 units respectively.
classifier = tf.estimator.DNNClassifier(
feature_columns=my_feature_columns,
# Two hidden layers of 10 nodes each.
hidden_units=[10, 10],
# The model must choose between 3 classes.
n_classes=3)
# Train the Model.
classifier.train(
input_fn=lambda:iris_data.train_input_fn(train_x, train_y,
args.batch_size),
steps=args.train_steps)
# Evaluate the model.
eval_result = classifier.evaluate(
input_fn=lambda:iris_data.eval_input_fn(test_x, test_y,
args.batch_size))
print('\nTest set accuracy: {accuracy:0.3f}\n'.format(**eval_result))
# Generate predictions from the model
expected = ['Setosa', 'Versicolor', 'Virginica']
predict_x = {
'SepalLength': [5.1, 5.9, 6.9],
'SepalWidth': [3.3, 3.0, 3.1],
'PetalLength': [1.7, 4.2, 5.4],
'PetalWidth': [0.5, 1.5, 2.1],
}
predictions = classifier.predict(
input_fn=lambda:iris_data.eval_input_fn(predict_x,
labels=None,
batch_size=args.batch_size))
template = ('\nPrediction is "{}" ({:.1f}%), expected "{}"')
for pred_dict, expec in zip(predictions, expected):
class_id = pred_dict['class_ids'][0]
probability = pred_dict['probabilities'][class_id]
print(template.format(iris_data.SPECIES[class_id],
100 * probability, expec))
if __name__ == '__main__':
tf.logging.set_verbosity(tf.logging.INFO)
tf.app.run(main)
iris_data.py如下：
import pandas as pd
import tensorflow as tf
TRAIN_URL = "http://download.tensorflow.org/data/iris_training.csv"
TEST_URL = "http://download.tensorflow.org/data/iris_test.csv"
CSV_COLUMN_NAMES = ['SepalLength', 'SepalWidth',
'PetalLength', 'PetalWidth', 'Species']
SPECIES = ['Setosa', 'Versicolor', 'Virginica']
def maybe_download():
train_path = tf.keras.utils.get_file(TRAIN_URL.split('/')[-1], TRAIN_URL)
test_path = tf.keras.utils.get_file(TEST_URL.split('/')[-1], TEST_URL)
return train_path, test_path
def load_data(y_name='Species'):
"""Returns the iris dataset as (train_x, train_y), (test_x, test_y)."""
train_path, test_path = maybe_download()
train = pd.read_csv(train_path, names=CSV_COLUMN_NAMES, header=0)
train_x, train_y = train, train.pop(y_name)
test = pd.read_csv(test_path, names=CSV_COLUMN_NAMES, header=0)
test_x, test_y = test, test.pop(y_name)
return (train_x, train_y), (test_x, test_y)
def train_input_fn(features, labels, batch_size):
"""An input function for training"""
# Convert the inputs to a Dataset.
dataset = tf.data.Dataset.from_tensor_slices((dict(features), labels))
# Shuffle, repeat, and batch the examples.
dataset = dataset.shuffle(1000).repeat().batch(batch_size)
# Return the dataset.
return dataset
def eval_input_fn(features, labels, batch_size):
"""An input function for evaluation or prediction"""
features=dict(features)
if labels is None:
# No labels, use only features.
inputs = features
else:
inputs = (features, labels)
# Convert the inputs to a Dataset.
dataset = tf.data.Dataset.from_tensor_slices(inputs)
# Batch the examples
assert batch_size is not None, "batch_size must not be None"
dataset = dataset.batch(batch_size)
# Return the dataset.
return dataset
# The remainder of this file contains a simple example of a csv parser,
# implemented using the `Dataset` class.
# `tf.parse_csv` sets the types of the outputs to match the examples given in
# the `record_defaults` argument.
CSV_TYPES = [[0.0], [0.0], [0.0], [0.0], [0]]
def _parse_line(line):
# Decode the line into its fields
fields = tf.decode_csv(line, record_defaults=CSV_TYPES)
# Pack the result into a dictionary
features = dict(zip(CSV_COLUMN_NAMES, fields))
# Separate the label from the features
label = features.pop('Species')
return features, label
def csv_input_fn(csv_path, batch_size):
# Create a dataset containing the text lines.
dataset = tf.data.TextLineDataset(csv_path).skip(1)
# Parse each line.
dataset = dataset.map(_parse_line)
# Shuffle, repeat, and batch the examples.
dataset = dataset.shuffle(1000).repeat().batch(batch_size)
# Return the dataset.
return dataset
estimator_test.py如下：
# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""A simple smoke test that runs these examples for 1 training iteraton."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import tensorflow as tf
import pandas as pd
from six.moves import StringIO
import iris_data
import custom_estimator
import premade_estimator
FOUR_LINES = "\n".join([
"1,52.40, 2823,152,2",
"164, 99.80,176.60,66.20,1",
"176,2824, 136,3.19,0",
"2,177.30,66.30, 53.10,1",])
def four_lines_data():
text = StringIO(FOUR_LINES)
df = pd.read_csv(text, names=iris_data.CSV_COLUMN_NAMES)
xy = (df, df.pop("Species"))
return xy, xy
class RegressionTest(tf.test.TestCase):
"""Test the regression examples in this directory."""
@tf.test.mock.patch.dict(premade_estimator.__dict__,
{"load_data": four_lines_data})
def test_premade_estimator(self):
premade_estimator.main([None, "--train_steps=1"])
@tf.test.mock.patch.dict(custom_estimator.__dict__,
{"load_data": four_lines_data})
def test_custom_estimator(self):
custom_estimator.main([None, "--train_steps=1"])
if __name__ == "__main__":
tf.test.main()
custom_estimator.py如下：
# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""An Example of a custom Estimator for the Iris dataset."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import tensorflow as tf
import iris_data
parser = argparse.ArgumentParser()
parser.add_argument('--batch_size', default=100, type=int, help='batch size')
parser.add_argument('--train_steps', default=1000, type=int,
help='number of training steps')
def my_model(features, labels, mode, params):
"""DNN with three hidden layers and learning_rate=0.1."""
# Create three fully connected layers.
net = tf.feature_column.input_layer(features, params['feature_columns'])
for units in params['hidden_units']:
net = tf.layers.dense(net, units=units, activation=tf.nn.relu)
# Compute logits (1 per class).
logits = tf.layers.dense(net, params['n_classes'], activation=None)
# Compute predictions.
predicted_classes = tf.argmax(logits, 1)
if mode == tf.estimator.ModeKeys.PREDICT:
predictions = {
'class_ids': predicted_classes[:, tf.newaxis],
'probabilities': tf.nn.softmax(logits),
'logits': logits,
}
return tf.estimator.EstimatorSpec(mode, predictions=predictions)
# Compute loss.
loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)
# Compute evaluation metrics.
accuracy = tf.metrics.accuracy(labels=labels,
predictions=predicted_classes,
name='acc_op')
metrics = {'accuracy': accuracy}
tf.summary.scalar('accuracy', accuracy[1])
if mode == tf.estimator.ModeKeys.EVAL:
return tf.estimator.EstimatorSpec(
mode, loss=loss, eval_metric_ops=metrics)
# Create training op.
assert mode == tf.estimator.ModeKeys.TRAIN
optimizer = tf.train.AdagradOptimizer(learning_rate=0.1)
train_op = optimizer.minimize(loss, global_step=tf.train.get_global_step())
return tf.estimator.EstimatorSpec(mode, loss=loss, train_op=train_op)
def main(argv):
args = parser.parse_args(argv[1:])
# Fetch the data
(train_x, train_y), (test_x, test_y) = iris_data.load_data()
# Feature columns describe how to use the input.
my_feature_columns = []
for key in train_x.keys():
my_feature_columns.append(tf.feature_column.numeric_column(key=key))
# Build 2 hidden layer DNN with 10, 10 units respectively.
classifier = tf.estimator.Estimator(
model_fn=my_model,
params={
'feature_columns': my_feature_columns,
# Two hidden layers of 10 nodes each.
'hidden_units': [10, 10],
# The model must choose between 3 classes.
'n_classes': 3,
})
# Train the Model.
classifier.train(
input_fn=lambda:iris_data.train_input_fn(train_x, train_y, args.batch_size),
steps=args.train_steps)
# Evaluate the model.
eval_result = classifier.evaluate(
input_fn=lambda:iris_data.eval_input_fn(test_x, test_y, args.batch_size))
print('\nTest set accuracy: {accuracy:0.3f}\n'.format(**eval_result))
# Generate predictions from the model
expected = ['Setosa', 'Versicolor', 'Virginica']
predict_x = {
'SepalLength': [5.1, 5.9, 6.9],
'SepalWidth': [3.3, 3.0, 3.1],
'PetalLength': [1.7, 4.2, 5.4],
'PetalWidth': [0.5, 1.5, 2.1],
}
predictions = classifier.predict(
input_fn=lambda:iris_data.eval_input_fn(predict_x,
labels=None,
batch_size=args.batch_size))
for pred_dict, expec in zip(predictions, expected):
template = ('\nPrediction is "{}" ({:.1f}%), expected "{}"')
class_id = pred_dict['class_ids'][0]
probability = pred_dict['probabilities'][class_id]
print(template.format(iris_data.SPECIES[class_id],
100 * probability, expec))
if __name__ == '__main__':
tf.logging.set_verbosity(tf.logging.INFO)
tf.app.run(main)
运行premade_estimator.py结果如下：
D:\programming\machine_learning\models-master\samples\core\get_started>python premade_estimator.py
C:\Users\Anaconda3\lib\site-packages\h5py\__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
Downloading data from http://download.tensorflow.org/data/iris_training.csv
8192/2194 [================================================================================================================] - 0s 0s/step
Downloading data from http://download.tensorflow.org/data/iris_test.csv
8192/573 [============================================================================================================================================================================================================================================================================================================================================================================================================================================] - 0s 0s/step
INFO:tensorflow:Using default config.
WARNING:tensorflow:Using temporary folder as model directory: C:\Users\AppData\Local\Temp\tmp5qeyrvn6
INFO:tensorflow:Using config: {'_model_dir': 'C:\\Users\\AppData\\Local\\Temp\\tmp5qeyrvn6', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true
graph_options {
rewrite_options {
meta_optimizer_iterations: ONE
}
}
, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_service': None, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x000001D479D11A90>, '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}
WARNING:tensorflow:From C:\Users\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
INFO:tensorflow:Calling model_fn.
WARNING:tensorflow:From C:\Users\Anaconda3\lib\site-packages\tensorflow\python\feature_column\feature_column_v2.py:2703: to_float (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast instead.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Create CheckpointSaverHook.
INFO:tensorflow:Graph was finalized.
2019-04-14 20:54:40.320943: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Saving checkpoints for 0 into C:\Users\AppData\Local\Temp\tmp5qeyrvn6\model.ckpt.
INFO:tensorflow:loss = 241.21529, step = 1
INFO:tensorflow:global_step/sec: 464.203
INFO:tensorflow:loss = 19.586277, step = 101 (0.216 sec)
INFO:tensorflow:global_step/sec: 706.107
INFO:tensorflow:loss = 10.944989, step = 201 (0.142 sec)
INFO:tensorflow:global_step/sec: 618.935
INFO:tensorflow:loss = 7.979789, step = 301 (0.163 sec)
INFO:tensorflow:global_step/sec: 626.513
INFO:tensorflow:loss = 7.2976875, step = 401 (0.159 sec)
INFO:tensorflow:global_step/sec: 698.682
INFO:tensorflow:loss = 9.718931, step = 501 (0.144 sec)
INFO:tensorflow:global_step/sec: 640.209
INFO:tensorflow:loss = 4.3173347, step = 601 (0.155 sec)
INFO:tensorflow:global_step/sec: 713.584
INFO:tensorflow:loss = 7.0657053, step = 701 (0.140 sec)
INFO:tensorflow:global_step/sec: 742.719
INFO:tensorflow:loss = 5.1807976, step = 801 (0.137 sec)
INFO:tensorflow:global_step/sec: 737.24
INFO:tensorflow:loss = 5.4548182, step = 901 (0.134 sec)
INFO:tensorflow:Saving checkpoints for 1000 into C:\Users\AppData\Local\Temp\tmp5qeyrvn6\model.ckpt.
INFO:tensorflow:Loss for final step: 2.9431791.
INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Starting evaluation at 2019-04-14T12:54:44Z
INFO:tensorflow:Graph was finalized.
WARNING:tensorflow:From C:\Users\Anaconda3\lib\site-packages\tensorflow\python\training\saver.py:1266: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
INFO:tensorflow:Restoring parameters from C:\Users\AppData\Local\Temp\tmp5qeyrvn6\model.ckpt-1000
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
INFO:tensorflow:Finished evaluation at 2019-04-14-12:54:45
INFO:tensorflow:Saving dict for global step 1000: accuracy = 0.93333334, average_loss = 0.064269036, global_step = 1000, loss = 1.9280711
INFO:tensorflow:Saving 'checkpoint_path' summary for global step 1000: C:\Users\AppData\Local\Temp\tmp5qeyrvn6\model.ckpt-1000
Test set accuracy: 0.933
INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Done calling model_fn.
INFO:tensorflow:Graph was finalized.
INFO:tensorflow:Restoring parameters from C:\Users\AppData\Local\Temp\tmp5qeyrvn6\model.ckpt-1000
INFO:tensorflow:Running local_init_op.
INFO:tensorflow:Done running local_init_op.
Prediction is "Setosa" (99.6%), expected "Setosa"
Prediction is "Versicolor" (99.5%), expected "Versicolor"
Prediction is "Virginica" (99.0%), expected "Virginica"
20190414
网友评论