Related
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn import preprocessing
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import precision_score, recall_score, f1_score,\
accuracy_score, balanced_accuracy_score,classification_report,\
plot_confusion_matrix, confusion_matrix
from sklearn.model_selection import KFold, GridSearchCV
from sklearn.model_selection import train_test_split
import lightgbm as lgb
from tensorflow.keras.layers import Input, Dense, Reshape, Flatten, Dropout, multiply, Concatenate
from tensorflow.keras.layers import BatchNormalization, Activation, Embedding, ZeroPadding2D, LeakyReLU
from tensorflow.keras.models import Sequential, Model
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.initializers import RandomNormal
import tensorflow.keras.backend as K
from sklearn.utils import shuffle
import pickle
from tqdm import tqdm
import numpy as np
from scipy import stats
import pandas as pd
np.random.seed(1635848)
def get_data_XYZ_one_dimensional(n, a=-2, c=1/2, random_state=None, verbose=True):
"""
Generates pseudo-random data distributed according to the distribution defined in section 2.1 of the document
"Math/Confounders and data generation.pdf".
:param n: Number of data points to generate.
:param a: Mean of X.
:param c: Shape parameter for Weibull distribution.
:param random_state: Used to set the seed of numpy.random before generation of random numbers.
:param verbose: If True will display a progress bar. If False it will not display a progress bar.
:return: Pandas DataFrame with three columns (corresponding to X, Y and Z) and n rows (corresponding to the n
generated pseudo-random samples).
"""
np.random.seed(random_state)
output = []
iterator = tqdm(range(n)) if verbose else range(n)
for _ in iterator:
X = stats.norm.rvs(loc=-2, scale=1)
Y = stats.bernoulli.rvs(p=1/(1+np.exp(-X)))
if Y == 0:
Z = stats.expon.rvs(scale=np.exp(-X)) # note: np.exp(-X) could be cached for more computational efficiency but would render the code less useful
elif Y == 1:
Z = stats.weibull_min.rvs(c=c, scale=np.exp(-X))
else:
assert False
output.append((X, Y, Z))
return pd.DataFrame(output, columns=["Personal information", "Treatment", "Time to event"])
data = get_data_XYZ_one_dimensional(n=100, random_state=0)
print(data)
# The Architecture of CGAN
class cGAN():
"""
Class containing 3 methods (and __init__): generator, discriminator and train.
Generator is trained using random noise and label as inputs. Discriminator is trained
using real/fake samples and labels as inputs.
"""
def __init__(self,latent_dim=100, out_shape=3):
self.latent_dim = latent_dim
self.out_shape = out_shape
self.num_classes = 2
# using Adam as our optimizer
optimizer = Adam(0.0002, 0.5)
# building the discriminator
self.discriminator = self.discriminator()
self.discriminator.compile(loss=['binary_crossentropy'],
optimizer=optimizer,
metrics=['accuracy'])
# building the generator
self.generator = self.generator()
noise = Input(shape=(self.latent_dim,))
label = Input(shape=(1,))
gen_samples = self.generator([noise, label])
# we don't train discriminator when training generator
self.discriminator.trainable = False
valid = self.discriminator([gen_samples, label])
# combining both models
self.combined = Model([noise, label], valid)
self.combined.compile(loss=['binary_crossentropy'],
optimizer=optimizer,
metrics=['accuracy'])
def generator(self):
init = RandomNormal(mean=0.0, stddev=0.02)
model = Sequential()
model.add(Dense(128, input_dim=self.latent_dim))
model.add(Dropout(0.2))
model.add(LeakyReLU(alpha=0.2))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(256))
model.add(Dropout(0.2))
model.add(LeakyReLU(alpha=0.2))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(512))
model.add(Dropout(0.2))
model.add(LeakyReLU(alpha=0.2))
model.add(BatchNormalization(momentum=0.8))
model.add(Dense(self.out_shape, activation='tanh'))
noise = Input(shape=(self.latent_dim,))
label = Input(shape=(1,), dtype='int32')
label_embedding = Flatten()(Embedding(self.num_classes, self.latent_dim)(label))
model_input = multiply([noise, label_embedding])
gen_sample = model(model_input)
model.summary()
return Model([noise, label], gen_sample, name="Generator")
def discriminator(self):
init = RandomNormal(mean=0.0, stddev=0.02)
model = Sequential()
model.add(Dense(512, input_dim=self.out_shape, kernel_initializer=init))
model.add(LeakyReLU(alpha=0.2))
model.add(Dense(256, kernel_initializer=init))
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.4))
model.add(Dense(128, kernel_initializer=init))
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.4))
model.add(Dense(1, activation='sigmoid'))
gen_sample = Input(shape=(self.out_shape,))
label = Input(shape=(1,), dtype='int32')
label_embedding = Flatten()(Embedding(self.num_classes, self.out_shape)(label))
model_input = multiply([gen_sample, label_embedding])
validity = model(model_input)
model.summary()
return Model(inputs=[gen_sample, label], outputs=validity, name="Discriminator")
def train(self, X_train, y_train, pos_index, neg_index, epochs, sampling=False, batch_size=32, sample_interval=100, plot=True):
# though not recommended, defining losses as global helps as in analysing our cgan out of the class
global G_losses
global D_losses
G_losses = []
D_losses = []
# Adversarial ground truths
valid = np.ones((batch_size, 1))
fake = np.zeros((batch_size, 1))
for epoch in range(epochs):
# if sampling==True --> train discriminator with 8 sample from positive class and rest with negative class
if sampling:
idx1 = np.random.choice(pos_index, 3)
idx0 = np.random.choice(neg_index, batch_size-3)
idx = np.concatenate((idx1, idx0))
# if sampling!=True --> train discriminator using random instances in batches of 32
else:
idx = np.random.choice(len(y_train), batch_size)
samples, labels = X_train[idx], y_train[idx]
samples, labels = shuffle(samples, labels)
# Sample noise as generator input
noise = np.random.normal(0, 1, (batch_size, self.latent_dim))
gen_samples = self.generator.predict([noise, labels])
# label smoothing
if epoch < epochs//1.5:
valid_smooth = (valid+0.1)-(np.random.random(valid.shape)*0.1)
fake_smooth = (fake-0.1)+(np.random.random(fake.shape)*0.1)
else:
valid_smooth = valid
fake_smooth = fake
# Train the discriminator
self.discriminator.trainable = True
d_loss_real = self.discriminator.train_on_batch([samples, labels], valid_smooth)
d_loss_fake = self.discriminator.train_on_batch([gen_samples, labels], fake_smooth)
d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)
# Train Generator
self.discriminator.trainable = False
sampled_labels = np.random.randint(0, 2, batch_size).reshape(-1, 1)
# Train the generator
g_loss = self.combined.train_on_batch([noise, sampled_labels], valid)
if (epoch+1)%sample_interval==0:
print('[%d/%d]\tLoss_D: %.4f\tLoss_G: %.4f'
% (epoch, epochs, d_loss[0], g_loss[0]))
G_losses.append(g_loss[0])
D_losses.append(d_loss[0])
if plot:
if epoch+1==epochs:
plt.figure(figsize=(10,5))
plt.title("Generator and Discriminator Loss")
plt.plot(G_losses,label="G")
plt.plot(D_losses,label="D")
plt.xlabel("iterations")
plt.ylabel("Loss")
plt.legend()
plt.show()
data.Treatment.value_counts()
scaler = StandardScaler()
X = scaler.fit_transform(data.drop('Treatment', 1))
y = data['Treatment'].values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
lgb_1 = lgb.LGBMClassifier()
lgb_1.fit(X_train, y_train)
y_pred = lgb_1.predict(X_test)
# evaluation
print(classification_report(y_test, y_pred))
plot_confusion_matrix(lgb_1, X_test, y_test)
plt.show()
le = preprocessing.LabelEncoder()
for i in ['Personal information', 'Treatment', 'Time to event']:
data[i] = le.fit_transform(data[i].astype(str))
y_train = y_train.reshape(-1,1)
pos_index = np.where(y_train==1)[0]
neg_index = np.where(y_train==0)[0]
cgan.train(X_train, y_train, pos_index, neg_index, epochs=500)
Here, the training gives an error ValueError: Input 0 of layer "Discriminator" is incompatible with the layer: expected shape=(None, 3), found shape=(100, 2). Well I understand I have to fix the shape by changing the input but where and how to do it.
Also there are 3 columns in data so how to go about making this work?
I think the fix out_shape=2 and not 3 because the generated output has 2 and you stated the number of classes to be 2 as well. Unless there is something else I am missing.
def __init__(self, latent_dim=100, out_shape=2):
I have Covid-19 X-ray dataset from Kaggle. I split and resize image in to the following dimension.
X_train (675, 256, 256, 3), X_test (225, 256, 256, 3) and X_val (225, 256, 256, 3). My code to train a densenet121 is the following
import numpy as np
import os
import random
from sklearn.utils import class_weight
from keras.layers import Dense, GlobalAveragePooling2D, Dropout, Input, Activation, BatchNormalization
from keras.applications import DenseNet121
from keras.models import Model
from keras import applications as A
from tensorflow.keras.models import load_model
from keras.callbacks import EarlyStopping, ReduceLROnPlateau, ModelCheckpoint
from keras.optimizers import SGD
seed_value = 1234
os.environ['PYTHONHASHSEED']=str(seed_value)
random.seed(seed_value)
np.random.seed(seed_value)
X_train = A.densenet.preprocess_input(X_train)
X_test = A.densenet.preprocess_input(X_test)
X_val = A.densenet.preprocess_input(X_val)
def get_model(hparams):
input_tensor = Input(shape=(256, 256, 3))
pretrain = DenseNet121(weights='imagenet', input_tensor=input_tensor, include_top=False)
idx = 52
x = pretrain.output
x = GlobalAveragePooling2D()(x)
x = Dense(64, use_bias=False)(x)
x = Dropout(0.25)(x)
x = BatchNormalization(axis=-1)(x)
x = Activation("relu")(x)
predictions = Dense(hparams["nclass"], activation="softmax")(x)
model = Model(inputs=pretrain.input, outputs=predictions)
for layer in model.layers:
if "BatchNormalization" in layer.__class__.__name__:
layer.trainable = True
else:
layer.trainable = False
for i in range(len(model.layers)):
if i > idx:
model.layers[i].trainable = True
model.compile(optimizer=SGD(lr=hparams["lr"]), loss="categorical_crossentropy", metrics=["accuracy"])
return model
weights = class_weight.compute_class_weight("balanced", classes=np.unique(y_train_labels), y=y_train_labels)
class_weights = dict(zip(np.unique(y_train_labels), weights))
es = EarlyStopping(monitor="val_loss",
mode="min",
patience=20,
verbose=1,
restore_best_weights=True)
mc = ModelCheckpoint(filepath="../models/mymodel.h5",
monitor="val_loss",
mode="min",
verbose=1,
save_best_only=True)
reduce_lr = ReduceLROnPlateau(monitor="val_loss",
factor=0.9,
patience=5,
min_lr=0.000001,
verbose=1)
history = model.fit(x=X_train,
y=y_train,
class_weight=class_weights,
validation_data=(X_val, y_val),
epochs=500,
batch_size=8,
callbacks=[es, mc, reduce_lr])
Prediction of shows probability of 3 classes (e.g. [0.1, 0.6, 0.3]) but when I load model later using this command.
classifier = load_model("mymodel.h5", compile=False)
probs = classifier.predict(X_test)
It seems that the prediction results is no longer probability but a class label (also incorrectly if we refer to the previous prediction [0.1, 0.6, 0.3] ... I got [0, 0, 1] as the output of the load model. I'm using keras version 2.3.1 and tensorflow 2.1.0. May I know what went wrong and how to fix it?
I went over
a basic example of tf2.0
containing very simple code
from __future__ import absolute_import, division, print_function, unicode_literals
import os
import tensorflow as tf
import cProfile
# Fetch and format the mnist data
(mnist_images, mnist_labels), _ = tf.keras.datasets.mnist.load_data()
dataset = tf.data.Dataset.from_tensor_slices(
(tf.cast(mnist_images[...,tf.newaxis]/255, tf.float32),
tf.cast(mnist_labels,tf.int64)))
dataset = dataset.shuffle(1000).batch(32)
# Build the model
mnist_model = tf.keras.Sequential([
tf.keras.layers.Conv2D(16,[3,3], activation='relu',
input_shape=(None, None, 1)),
tf.keras.layers.Conv2D(16,[3,3], activation='relu'),
tf.keras.layers.GlobalAveragePooling2D(),
tf.keras.layers.Dense(10)
])
for images,labels in dataset.take(1):
print("Logits: ", mnist_model(images[0:1]).numpy())
optimizer = tf.keras.optimizers.Adam()
loss_object = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
loss_history = []
def train_step(model, images, labels):
with tf.GradientTape() as tape:
logits = model(images, training=True)
# Add asserts to check the shape of the output.
tf.debugging.assert_equal(logits.shape, (32, 10))
loss_value = loss_object(labels, logits)
loss_history.append(loss_value.numpy().mean())
grads = tape.gradient(loss_value, model.trainable_variables)
optimizer.apply_gradients(zip(grads, model.trainable_variables))
def train(epochs):
for epoch in range(epochs):
for (batch, (images, labels)) in enumerate(dataset):
train_step(mnist_model, images, labels)
print ('Epoch {} finished'.format(epoch))
I trained it and save trainable_variables before and after by the following
t0=mnist_model.trainable_variables
train(epochs = 3)
t1=mnist_model.trainable_variables
diff = tf.reduce_mean(tf.abs(t0[0] - t1[0]))
# whethere indexing [0] or [1] etc. gets the same outcome of diff
print(diff.numpy())
They are the same!!!
So am I checking somethere incorrect? If that is the case, how can I observe those updated variables correctly?
You aren't creating new arrays of variables, just 2 pointers on the same object
Try to do so
t0 = np.array(mnist_model.trainable_variables)
Tensorflow's feature_columns API is quite useful for non-numerical feature processing. However, the current API doc is more about using feature_columns with tensorflow Estimator. Is there a possible way to use feature_columns for categorical features representation and then build a model based on tf.keras?
The only reference I found is the following tutorial. It shows how to feed feature columns to a Keras Sequential model: Link
The code snippet is as follows:
from tensorflow.python.feature_column import feature_column_v2 as fc
feature_columns = [fc.embedding_column(ccv, dimension=3), ...]
feature_layer = fc.FeatureLayer(feature_columns)
model = tf.keras.Sequential([
feature_layer,
tf.keras.layers.Dense(128, activation=tf.nn.relu),
tf.keras.layers.Dense(64, activation=tf.nn.relu),
tf.keras.layers.Dense(1, activation=tf.nn.sigmoid)
])
...
model.fit(dataset, steps_per_epoch=8) # dataset is created from tensorflow Dataset API
The question is how to use a customed model with keras functional model API. I tried the following, but it did not work (tensorflow version 1.12)
feature_layer = fc.FeatureLayer(feature_columns)
dense_features = feature_layer(features) # features is a dict of ndarrays in dataset
layer1 = tf.keras.layers.Dense(128, activation=tf.nn.relu)(dense_features)
layer2 = tf.keras.layers.Dense(64, activation=tf.nn.relu)(layer1)
output = tf.keras.layers.Dense(1, activation=tf.nn.sigmoid)(layer2)
model = Model(inputs=dense_features, outputs=output)
The error log:
ValueError: Input tensors to a Model must come from `tf.layers.Input`. Received: Tensor("feature_layer/concat:0", shape=(4, 3), dtype=float32) (missing previous layer metadata).
I don't kown how to transform feature columns to keras model's input.
The behavior you desire could be achieved and it's able to combine tf.feature_column and keras functional API. And, actually, is not mentioned in TF docs.
This works at least in TF 2.0.0-beta1, but may being changed or even simplified in further releases.
Please check out issue in TensorFlow github repository Unable to use FeatureColumn with Keras Functional API #27416. There you will find useful comments about tf.feature_column and Keras Functional API.
Because you ask about general approach I would just copy the snippet with example from the link above. update: the code below should work
from __future__ import absolute_import, division, print_function
import numpy as np
import pandas as pd
#!pip install tensorflow==2.0.0-alpha0
import tensorflow as tf
from tensorflow import feature_column
from tensorflow import keras
from tensorflow.keras import layers
from sklearn.model_selection import train_test_split
csv_file = tf.keras.utils.get_file('heart.csv', 'https://storage.googleapis.com/download.tensorflow.org/data/heart.csv')
dataframe = pd.read_csv(csv_file, nrows = 10000)
dataframe.head()
train, test = train_test_split(dataframe, test_size=0.2)
train, val = train_test_split(train, test_size=0.2)
print(len(train), 'train examples')
print(len(val), 'validation examples')
print(len(test), 'test examples')
# Define method to create tf.data dataset from Pandas Dataframe
# This worked with tf 2.0 but does not work with tf 2.2
def df_to_dataset_tf_2_0(dataframe, label_column, shuffle=True, batch_size=32):
dataframe = dataframe.copy()
#labels = dataframe.pop(label_column)
labels = dataframe[label_column]
ds = tf.data.Dataset.from_tensor_slices((dict(dataframe), labels))
if shuffle:
ds = ds.shuffle(buffer_size=len(dataframe))
ds = ds.batch(batch_size)
return ds
def df_to_dataset(dataframe, label_column, shuffle=True, batch_size=32):
dataframe = dataframe.copy()
labels = dataframe.pop(label_column)
#labels = dataframe[label_column]
ds = tf.data.Dataset.from_tensor_slices((dataframe.to_dict(orient='list'), labels))
if shuffle:
ds = ds.shuffle(buffer_size=len(dataframe))
ds = ds.batch(batch_size)
return ds
batch_size = 5 # A small batch sized is used for demonstration purposes
train_ds = df_to_dataset(train, label_column = 'target', batch_size=batch_size)
val_ds = df_to_dataset(val,label_column = 'target', shuffle=False, batch_size=batch_size)
test_ds = df_to_dataset(test, label_column = 'target', shuffle=False, batch_size=batch_size)
age = feature_column.numeric_column("age")
feature_columns = []
feature_layer_inputs = {}
# numeric cols
for header in ['age', 'trestbps', 'chol', 'thalach', 'oldpeak', 'slope', 'ca']:
feature_columns.append(feature_column.numeric_column(header))
feature_layer_inputs[header] = tf.keras.Input(shape=(1,), name=header)
# bucketized cols
age_buckets = feature_column.bucketized_column(age, boundaries=[18, 25, 30, 35])
feature_columns.append(age_buckets)
# indicator cols
thal = feature_column.categorical_column_with_vocabulary_list(
'thal', ['fixed', 'normal', 'reversible'])
thal_one_hot = feature_column.indicator_column(thal)
feature_columns.append(thal_one_hot)
feature_layer_inputs['thal'] = tf.keras.Input(shape=(1,), name='thal', dtype=tf.string)
# embedding cols
thal_embedding = feature_column.embedding_column(thal, dimension=8)
feature_columns.append(thal_embedding)
# crossed cols
crossed_feature = feature_column.crossed_column([age_buckets, thal], hash_bucket_size=1000)
crossed_feature = feature_column.indicator_column(crossed_feature)
feature_columns.append(crossed_feature)
feature_layer = tf.keras.layers.DenseFeatures(feature_columns)
feature_layer_outputs = feature_layer(feature_layer_inputs)
x = layers.Dense(128, activation='relu')(feature_layer_outputs)
x = layers.Dense(64, activation='relu')(x)
baggage_pred = layers.Dense(1, activation='sigmoid')(x)
model = keras.Model(inputs=[v for v in feature_layer_inputs.values()], outputs=baggage_pred)
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
model.fit(train_ds)
If you use tensorflow dataset API, that code could do well.
featurlayer = keras.layers.DenseFeatures(feature_columns=feature_columns)
train_dataset = train_dataset.map(lambda x, y: (featurlayer(x), y))
test_dataset = test_dataset.map(lambda x, y: (featurlayer(x), y))
model.fit(train_dataset, epochs=, steps_per_epoch=, # all_data/batch_num =
validation_data=test_dataset,
validation_steps=)
tf.feature_column.input_layer
user this function, and this api doc has a sample .
you can transform featur_columns into Tensor, and then use it into Mode()
I have been recently reading this document in TensorFlow 2.0 alpha version. It has examples using Keras together with the feature column API. Not sure if TF 2.0 is what you are going to use
Here is the simplest code that can reproduce the problem:
import numpy as np
import random
import tensorflow as tf
tf.set_random_seed(12345)
np.random.seed(12345)
random.seed(12345)
unusable1 = tf.constant(1e-3, tf.float32)
unusable2 = tf.constant(1e-3, tf.float32)
unusable3 = tf.constant(1e-3, tf.float32)
X = tf.placeholder(tf.float32, shape=[2, 3])
cell = tf.contrib.rnn.BasicRNNCell(5)
changed_data = tf.reduce_sum(cell(X, state = tf.zeros((2, 5)))[0])
with tf.Session() as sess:
tf.global_variables_initializer().run()
output = sess.run(changed_data, feed_dict={X: np.ones((2, 3))})
print(output) # = -1.46618
The result of the above code is -1.46618 on my machine.
However, if I comment out three unusable constant tensor declarations, the result becomes 1.76918!
import numpy as np
import random
import tensorflow as tf
tf.set_random_seed(12345)
np.random.seed(12345)
random.seed(12345)
# unusable1 = tf.constant(1e-3, tf.float32)
# unusable2 = tf.constant(1e-3, tf.float32)
# unusable3 = tf.constant(1e-3, tf.float32)
X = tf.placeholder(tf.float32, shape=[2, 3])
cell = tf.contrib.rnn.BasicRNNCell(5)
changed_data = tf.reduce_sum(cell(X, state = tf.zeros((2, 5)))[0])
with tf.Session() as sess:
tf.global_variables_initializer().run()
output = sess.run(changed_data, feed_dict={X: np.ones((2, 3))})
print(output) # = 1.76918
Actually, you can add/delete/modify constant tensor declarations as much as you like, the result varies quite different!
What's the problem?
The initializers for variables are getting different op-level seeds because seeding is based on (1) the graph-level seed, and (2) the op id if an op-level seed is not explicitly set (a deterministic function of the previously created ops in the current graph). This prevents every variable from getting exactly the same initialization when a graph-level seed has been set. See get_seed for the implementation.