ilblackdragon

import random
import pandas
import numpy as np
from sklearn import metrics, cross_validation

import tensorflow as tf
from tensorflow.contrib import layers
from tensorflow.contrib import learn

random.seed(42)

ilblackdragon

def dnn_tanh(features, target):
    target = tf.one_hot(target, 2, 1.0, 0.0)
    logits = layers.stack(features, layers.fully_connected, [10, 20, 10],
        activation_fn=tf.tanh)
    prediction, loss = learn.models.logistic_regression(logits, target)
    train_op = layers.optimize_loss(loss,
        tf.contrib.framework.get_global_step(), optimizer='SGD', learning_rate=0.05)
    return tf.argmax(prediction, dimension=1), loss, train_op

random.seed(42)

ilblackdragon

>>> classifier = learn.DNNClassifier(hidden_units=[10, 20, 10],
...    n_classes=2,
...    feature_columns=learn.infer_real_valued_columns_from_input(X_train),
...    optimizer=tf.train.GradientDescentOptimizer(learning_rate=0.05))
>>> classifier.fit(X_train, y_train, batch_size=128, steps=500)
>>> score = accuracy_score(classifier.predict(X_test), y_test)
>>> print("Accuracy: %f" % score)
Accuracy: 0.67597765363

ilblackdragon

import random
from sklearn import datasets, cross_validation, metrics
import tensorflow as tf
from tensorflow.contrib import layers
from tensorflow.contrib import learn

random.seed(42)

# Load dataset and split it into train / test subsets.