ここまでの経過：
<![CDATA[$ source [venv のパス]/venv/bin/activate
(venv) $ python
>>> import tensorflow as tf
>>> tf.enable_eager_execution()
>>> train_file_path = "[ / からのパス]/.keras/datasets/train.csv"
>>> test_file_path = "[ / からのパス]/.keras/datasets/eval.csv"
>>> LABEL_COLUMN = 'survived'
>>> def get_dataset(file_path, **kwargs):
... dataset = tf.data.experimental.make_csv_dataset(
... file_path,
... batch_size=5,
... label_name=LABEL_COLUMN,
... na_value="?",
... num_epochs=1,
... ignore_errors=True,
... **kwargs)
... return dataset
...
>>>
>>> raw_train_data = get_dataset(train_file_path)
>>> raw_test_data = get_dataset(test_file_path)
>>> import numpy as np
>>> np.set_printoptions(precision=3, suppress=True)
>>> def show_batch(dataset):
... for batch, label in dataset.take(1):
... for key, value in batch.items():
... print("{:20s}: {}".format(key,value.numpy()))
...
>>>
------------------------------------------------------------------
>>> class PackNumericFeatures(object):
... def __init__(self, names):
... self.names = names
...
... def __call__(self, features, labels):
... numeric_features = [features.pop(name) for name in self.names]
... numeric_features = [tf.cast(feat, tf.float32) for feat in numeric_features]
... numeric_features = tf.stack(numeric_features, axis=-1)
... features['numeric'] = numeric_features
... return features, labels
...
>>>
>>> NUMERIC_FEATURES = ['age','n_siblings_spouses','parch', 'fare']
>>> packed_train_data = raw_train_data.map(PackNumericFeatures(NUMERIC_FEATURES))
>>> packed_test_data = raw_test_data.map(PackNumericFeatures(NUMERIC_FEATURES))
>>> import pandas as pd
>>> desc = pd.read_csv(train_file_path)[NUMERIC_FEATURES].describe()
>>> MEAN = np.array(desc.T['mean'])
>>> STD = np.array(desc.T['std'])
>>> def normalize_numeric_data(data, mean, std):
... return (data-mean)/std
...
>>>
>>> import functools
>>> normalizer = functools.partial(normalize_numeric_data, mean=MEAN, std=STD)
>>> numeric_column = tf.feature_column.numeric_column(
... 'numeric', normalizer_fn=normalizer, shape=[len(NUMERIC_FEATURES)])
...
>>>
>>> numeric_columns = [numeric_column]
>>> CATEGORIES = {
... 'sex': ['male', 'female'],
... 'class' : ['First', 'Second', 'Third'],
... 'deck' : ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J'],
... 'embark_town' : ['Cherbourg', 'Southhampton', 'Queenstown'],
... 'alone' : ['y', 'n']
... }
...
>>>
>>> categorical_columns = []
>>> for feature, vocab in CATEGORIES.items():
... cat_col = tf.feature_column.categorical_column_with_vocabulary_list(
... key=feature, vocabulary_list=vocab)
... categorical_columns.append(tf.feature_column.indicator_column(cat_col))
...
>>>
>>> preprocessing_layer
... = tf.keras.layers.DenseFeatures(categorical_columns+numeric_columns)]]>
preprocessing_layer から始まる model の構成：
- preprocessing_layer
- tf.keras.layers.Dense(128, activation='relu')
- tf.keras.layers.Dense(128, activation='relu')
- tf.keras.layers.Dense(1)
このモデルの構築：
<![CDATA[>>> model = tf.keras.Sequential([
... preprocessing_layer,
... tf.keras.layers.Dense(128, activation='relu'),
... tf.keras.layers.Dense(128, activation='relu'),
... tf.keras.layers.Dense(1),
... ])
>>> model.compile(
... loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
... optimizer='adam',
... metrics=['accuracy'])
>>> ]]>
|