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?
