用estimator构建一个简单的神经网络

estimator最主要的就两个部分
input_fn
model_fn

模型可以自定义
输入需要转成字典

import os
import pandas as pd
import tensorflow as tf


FUTURES = ['SepalLength', 'SepalWidth', 'PetalLength', 'PetalWidth', 'Species']
SPECIES = ['Setosa', 'Versicolor', 'Virginica']


##加载数据
dir_path = "data"
train_path = os.path.join(dir_path, 'iris_training.csv')
test_path = os.path.join(dir_path, 'iris_test.csv')

train = pd.read_csv(train_path, names=FUTURES, header=0)
train_x, train_y = train, train.pop('Species')

test = pd.read_csv(test_path, names=FUTURES, header=0)
test_x, test_y = test, test.pop('Species')

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

##构建我们自定义的模型

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):
    # 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:train_input_fn(train_x, train_y, 20),
        steps=10)

    # Evaluate the model.
    eval_result = classifier.evaluate(
        input_fn=lambda:eval_input_fn(test_x, test_y, 20))

    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:eval_input_fn(predict_x,
                                      labels=None,
                                      batch_size=10))

    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(SPECIES[class_id],
                              100 * probability, expec))


if __name__ == '__main__':
    tf.logging.set_verbosity(tf.logging.INFO)
    tf.app.run(main)