def main(): # If the training and test sets aren't stored locally, download them. if not os.path.exists(IRIS_TRAINING): raw = urlopen(IRIS_TRAINING_URL).read() with open(IRIS_TRAINING, "wb") as f: f.write(raw) if not os.path.exists(IRIS_TEST): raw = urlopen(IRIS_TEST_URL).read() with open(IRIS_TEST, "wb") as f: f.write(raw) # Load datasets. training_set = load_csv_with_header(filename=IRIS_TRAINING, target_dtype=np.int, features_dtype=np.float32) test_set = load_csv_with_header(filename=IRIS_TEST, target_dtype=np.int, features_dtype=np.float32) # Specify that all features have real-value data feature_columns = [real_valued_column("", dimension=4)] # Build 3 layer DNN with 10, 20, 10 units respectively. classifier = DNNClassifier(feature_columns=feature_columns, hidden_units=[10, 20, 10], n_classes=3, model_dir="/tmp/iris_model") # Define the training inputs def get_train_inputs(): x = tf.constant(training_set.data) y = tf.constant(training_set.target) return x, y # Fit model. classifier.fit(input_fn=get_train_inputs, steps=2000) # Define the test inputs def get_test_inputs(): x = tf.constant(test_set.data) y = tf.constant(test_set.target) return x, y # Evaluate accuracy. accuracy_score = classifier.evaluate(input_fn=get_test_inputs, steps=1)["accuracy"] print("\nTest Accuracy: {0:f}\n".format(accuracy_score)) # Classify two new flower samples. def new_samples(): return np.array([[6.4, 3.2, 4.5, 1.5], [5.8, 3.1, 5.0, 1.7]], dtype=np.float32) predictions = list(classifier.predict(input_fn=new_samples)) print("New Samples, Class Predictions: {}\n".format(predictions))
def deep_learning_tensor_flow_iris(): import tensorflow as tf import numpy as np print(tf.__version__) from tensorflow.contrib.learn.python.learn.datasets import base # Data files IRIS_TRAINING = "data-science-modules/data-sets/Wine.csv" IRIS_TEST = "data-science-modules/data-sets/Wine.csv" # Load datasets. training_set = base.load_csv_with_header(filename=IRIS_TRAINING, features_dtype=np.float32, target_dtype=np.int) test_set = base.load_csv_with_header(filename=IRIS_TEST, features_dtype=np.float32, target_dtype=np.int) # Specify that all features have real-value data feature_name = "flower_features" feature_columns = [ tf.feature_column.numeric_column(feature_name, shape=[13]) ] classifier = tf.estimator.LinearClassifier( feature_columns=feature_columns, n_classes=3, model_dir="/tmp/iris_model") def input_fn(dataset): def _fn(): features = {feature_name: tf.constant(dataset.data)} label = tf.constant(dataset.target) return features, label return _fn # Fit model. classifier.train(input_fn=input_fn(training_set), steps=1000) print('fit done') # Evaluate accuracy. accuracy_score = classifier.evaluate(input_fn=input_fn(test_set), steps=100)["accuracy"] print('\nAccuracy: {0:f}'.format(accuracy_score)) # Export the model for serving feature_spec = { 'flower_features': tf.FixedLenFeature(shape=[4], dtype=np.float32) } serving_fn = tf.estimator.export.build_parsing_serving_input_receiver_fn( feature_spec) classifier.export_savedmodel(export_dir_base='/tmp/iris_model' + '/export', serving_input_receiver_fn=serving_fn)
def load_data(): trainset = base.load_csv_with_header(TRAIN_FILE, target_dtype=np.float32, features_dtype=np.float32) testset = base.load_csv_with_header(TEST_FILE, target_dtype=np.float32, features_dtype=np.float32) trainset = change_data(trainset) testset = change_data(testset) return (trainset, testset)
from __future__ import print_function import numpy as np import tensorflow as tf from tensorflow.contrib.learn.python.learn.datasets import base tf.logging.set_verbosity(tf.logging.INFO) # Data sets IRIS_TRAINING = "iris_training.csv" IRIS_TEST = "iris_test.csv" # Load datasets. training_set = base.load_csv_with_header(filename=IRIS_TRAINING, features_dtype=np.float64, target_dtype=np.int) test_set = base.load_csv_with_header(filename=IRIS_TEST, features_dtype=np.float64, target_dtype=np.int) # Specify that all features have real-value data feature_columns = [tf.contrib.layers.real_valued_column("flower_features", dimension=4)] # Build 3 layer DNN with 10, 20, 10 units respectively. model_dir="/tmp/iris_model" classifier = tf.contrib.learn.DNNClassifier(feature_columns=feature_columns, hidden_units=[10, 20, 10], n_classes=3, model_dir=model_dir)
import tensorflow as tf from tensorflow.contrib.learn.python.learn.datasets import base import numpy as np # Load datasets. #Data Scource #http://download.tensorflow.org/data/iris_training.csv #http://download.tensorflow.org/data/iris_test.csv training_set = base.load_csv_with_header(filename="iris_training.csv", features_dtype=np.float32, target_dtype=np.int) test_set = base.load_csv_with_header(filename="iris_test.csv", features_dtype=np.float32, target_dtype=np.int) # Model creation # Specifying features (real-value data) feature_name = "flower_features" feature_columns = [tf.feature_column.numeric_column(feature_name, shape=[4])] #Using/Inheriting Linear Classifier from Estimator classifier = tf.estimator.LinearClassifier(feature_columns=feature_columns, n_classes=3, model_dir="/Users/iris_model") #Defining Input function
import tensorflow as tf import numpy as np from tensorflow.contrib.learn.python.learn.datasets import base #from tf.data import base # import tensorflow_datasets as tfds #from tensorflow.data import base IRIS_TRAIN = 'iris_training.csv' IRIS_TEST = 'iris_test.csv' base.load_csv_with_header(filename=IRIS_TRAIN, features_dtype=np.float32, target_dtype=np.int) train_set = base.load_csv_with_header(filename=IRIS_TRAIN, features_dtype=np.float32, target_dtype=np.int) test_set = base.load_csv_with_header(filename=IRIS_TEST, features_dtype=np.float32, target_dtype=np.int)