深度神经网络 广告相似人群扩展

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']
# CSV_COLUMN_NAMES = 'label,age,gender,education,consumptionAbility,LBS,house'.split(',')
CSV_COLUMN_NAMES = 'label,age,gender,education,consumptionAbility,house'.split(',')
# SPECIES = ['Setosa', 'Versicolor', 'Virginica']
# label,age,gender,education,consumptionAbility,LBS,house
# label,age,gender,education,consumptionAbility,LBS,house
SPECIES = [0, 1]
#SPECIES = [1, 0]


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
    # return 'iris_training.csv', 'iris_test.csv'
    return 'myu_oriv_tB.csv', 'myu_oriv_rB.csv'


# def load_data(label_name='Species'):
def load_data(label_name='label'):
    train_path, test_path = maybe_download()

    """Parses the csv file in TRAIN_URL and TEST_URL."""

    # Create a local copy of the training set.
    # train_path = tf.keras.utils.get_file(fname=TRAIN_URL.split('/')[-1],
    #                                      origin=TRAIN_URL)
    # train_path now holds the pathname: ~/.keras/datasets/iris_training.csv

    # Parse the local CSV file.
    train = pd.read_csv(filepath_or_buffer=train_path,
                        names=CSV_COLUMN_NAMES,  # list of column names
                        header=0  # ignore the first row of the CSV file.
                        )
    # train now holds a pandas DataFrame, which is data structure
    # analogous to a table.

    # 1. Assign the DataFrame's labels (the right-most column) to train_label.
    # 2. Delete (pop) the labels from the DataFrame.
    # 3. Assign the remainder of the DataFrame to train_features

    #   label_name = y_name
    train_features, train_label = train, train.pop(label_name)

    # Apply the preceding logic to the test set.
    # test_path = tf.keras.utils.get_file(TEST_URL.split('/')[-1], TEST_URL)
    test = pd.read_csv(test_path, names=CSV_COLUMN_NAMES, header=0)
    test_features, test_label = test, test.pop(label_name)

    # Return four DataFrames.
    return (train_features, train_label), (test_features, test_label)


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)
    dataset = dataset.shuffle(3).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 a 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], [0.0], [0.0], [0.0]]
CSV_TYPES = [[0], [0], [0], [0], [0], [0], [0]]
CSV_TYPES = [[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')
    label = features.pop('label')

    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)
    dataset = dataset.shuffle(2).repeat().batch(batch_size)

    # Return the dataset.
    return dataset

　　

#  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 qq_iris_data_mystudy

parser = argparse.ArgumentParser()
parser.add_argument('--batch_size', default=2, type=int, help='batch size')
parser.add_argument('--train_steps', default=2, type=int,
                    help='number of training steps')

res_f = 'res.txt'
with open(res_f, 'w', encoding='utf-8') as fw:
    fw.write('')


def main(argv):
    args = parser.parse_args(argv[1:])

    # Fetch the data
    (train_x, train_y), (test_x, test_y) = qq_iris_data_mystudy.load_data()

    my_feature_columns, predict_x = [], {}
    for key in train_x.keys():
        my_feature_columns.append(tf.feature_column.numeric_column(key=key))
        #predict_x[key] = [float(i) for i in test_x[key].values]
        predict_x[key] = [int(i) for i in test_x[key].values]
    expected = [0 for i in predict_x[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=2)

    # Train the Model.
    classifier.train(
        input_fn=lambda: qq_iris_data_mystudy.train_input_fn(train_x, train_y,
                                                             args.batch_size),
        steps=args.train_steps)

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

    print('
Test set accuracy: {accuracy:0.3f}
'.format(**eval_result))

    predictions = classifier.predict(
        input_fn=lambda: qq_iris_data_mystudy.eval_input_fn(predict_x,
                                                            labels=None,
                                                            batch_size=args.batch_size))

    template = ('
myProgress{}/{}ORI{}||RESULT{}|| Prediction is "{}" ({:.1f}%), expected "{}"')

    c, c_all_ = 0, len(expected)
    for pred_dict, expec in zip(predictions, expected):
        class_id = pred_dict['class_ids'][0]
        probability = pred_dict['probabilities'][class_id]
        ori = ','.join([str(predict_x[k][c]) for k in predict_x])
        print(template.format(c, c_all_, ori, str(pred_dict), qq_iris_data_mystudy.SPECIES[class_id],
                              100 * probability, expec))
        c += 1


        fw_s = '{}---{}
'.format(ori,pred_dict['probabilities'][1])
        with open(res_f, 'a', encoding='utf-8') as fw:
            fw.write(fw_s)


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