def my_model():
train_path = "data/iris_training.csv"
test_path = "data/iris_test.csv"
batch_size = 100
train_steps = 1000
_, (test_x, test_y) = load_data()
# All the inputs are numeric
# 定义特征列
feature_columns = [
tf.feature_column.numeric_column(key) for key in CSV_COLUMN_NAMES[:-1]
]
# 构建estimator
classifier = tf.estimator.LinearClassifier(feature_columns=feature_columns,
n_classes=3,
model_dir="models/iris_Linear")
# 训练
classifier.train(input_fn=lambda: csv_input_fn(train_path, batch_size),
steps=train_steps)
# 评估，返回eval_result是一个字典，有4个key：accuracy，average_loss，global_step，loss
eval_result = classifier.evaluate(input_fn=lambda: eval_input_fn(
features=test_x, labels=test_y, batch_size=batch_size))
print('Test set accuracy: {:0.3f}'.format(eval_result["accuracy"]))
def main(argv):
args = parser.parse_args(argv[1:])
# 加载数据， pandas类型
(train_x, train_y), (test_x, test_y) = iris_data.load_data()
# feature columns描述如何使用输入数据
my_feature_columns = []
for key in train_x.keys():
my_feature_columns.append(tf.feature_column.numeric_column(key=key))
# 建立模型，并保存模型
my_checkpoint_config = tf.estimator.RunConfig(
save_checkpoints_secs=20 * 60, # 每20分钟保存一次
keep_checkpoint_max=10) # 保存10个最近的检查点
cls = tf.estimator.DNNClassifier(hidden_units=[10, 10],
feature_columns=my_feature_columns,
n_classes=3,
model_dir='model/',
config=my_checkpoint_config)
# 训练模型
# cls.train(input_fn=lambda:iris_data.train_input_fn(train_x, train_y, args.batch_size),
# steps=args.train_steps)
cls.train(input_fn=lambda: iris_data.csv_input_fn('iris_training.csv', args
.batch_size),
steps=args.train_steps)
# 评价模型
eval_res = cls.evaluate(input_fn=lambda: iris_data.eval_input_fn(
test_x, test_y, args.batch_size))
print("\n Test Set accuracy: {:0.3f}\n".format(eval_res['accuracy']))
# 预测
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 = cls.predict(input_fn=lambda: iris_data.eval_input_fn(
predict_x, labels=None, batch_size=args.batch_size))
template = ('\n Prediction is "{}" ({:.1f}%), expected "{}"')
for pred_dict, expec in zip(predictions, expected):
class_id = pred_dict['class_ids'][0]
prob = pred_dict['probabilities'][class_id]
print(template.format(iris_data.SPECIES[class_id], 100 * prob, expec))
import iris_data
import pandas as pd
import tensorflow as tf
train_path, test_path = iris_data.maybe_download()
print(train_path)
# All the inputs are numeric
feature_columns = [
tf.feature_column.numeric_column(name)
for name in iris_data.CSV_COLUMN_NAMES[1:]
]
# Build the estimator
est = tf.estimator.LinearClassifier(feature_columns, n_classes=2)
# Train the estimator
batch_size = 100
est.train(steps=1000,
input_fn=lambda: iris_data.csv_input_fn(train_path, batch_size))
def parse_csv2():
train_path, test_path = iris_data.maybe_download()
iris_data.csv_input_fn(train_path, 1000)