modular maf implementation, Python=3.7.10 scripts

scripts/data_loader.py

+import numpy as np 
+import pandas as pd
+from pathlib import Path
+import xlrd 
+
+class load_data:
+    def __init__(self, filename, directory):
+        self.filename = filename
+        self.directory = directory
+        
+    def create_directory(self, directory):
+        Path(directory).mkdir(parents=True, exist_ok=True)
+        
+    def read_data(self, directory, filename):
+        data_dir = self.directory + self.filename 
+        wb = xlrd.open_workbook(data_dir, encoding_override='iso-8859-1')
+        return pd.read_excel(wb)
\ No newline at end of file

scripts/data_preprocesser.py

+import numpy as np
+import pandas as pd 
+import matplotlib.pyplot as plt
+
+class preprocess_data:
+    def __init__(self, scaler, fillna_vals, dropna_vals, drop_vals):
+        self.scaler = scaler 
+        self.fillna_vals = fillna_vals
+        self.dropna_vals = dropna_vals 
+        self.drop_vals = drop_vals
+        
+    def dropna_features(self, data):
+        data = data.dropna(subset = self.dropna_vals)
+        return data 
+    
+    def impute(self, data):
+        for feature in self.fillna_vals: 
+            data[feature] = data[feature].fillna(value = np.mean(data[feature]))
+        return data 
+    
+    def drop_features(self, data):
+        data.drop(self.drop_vals, axis=1, inplace=True)
+        data.reset_index(drop=True, inplace=True)
+        return data
+    
+    def encode_categorical(self, data):
+        data = pd.get_dummies(data)
+        return data 
+    
+    def scale(self, data):
+        columns = data.columns
+        data = self.scaler.fit_transform(data)
+        data = pd.DataFrame(data,columns=columns) 
+        return data
+

scripts/maf.py

+import numpy as np 
+import tensorflow as tf
+import tensorflow_probability as tfp
+tf.compat.v1.disable_eager_execution() 
+import os 
+
+import matplotlib.pyplot as plt 
+plt.style.use('seaborn')
+
+tfd = tfp.distributions
+tfb = tfp.bijectors
+
+class MAF:
+    def __init__(self, dtype, tf_version, batch_size, params, hidden_units, base_dist, dims):
+        self.tf_version = tf_version
+        self.dtype = dtype
+        self.base_dist = base_dist
+        self.dims = dims
+        self.params = params 
+        self.hidden_units = hidden_units 
+        self.batch_size = batch_size
+        
+    def get_tf_version(self):
+        return self.tf_version
+    
+    def get_session(self):
+        return tf.compat.v1.Session()
+        
+    def get_dims(self, data):
+        return data.shape[1]
+    
+    def create_tensor(self, data):
+        dataset = tf.data.Dataset.from_tensor_slices(data.astype(self.dtype))
+        dataset = dataset.repeat()
+        dataset = dataset.shuffle(buffer_size=data.shape[0])
+        dataset = dataset.prefetch(2*self.batch_size)
+        dataset = dataset.batch(self.batch_size)
+        data_iterator = tf.compat.v1.data.make_one_shot_iterator(dataset)
+        samples = data_iterator.get_next()
+        return samples
+    
+    def get_shift_scale_func(self, data):
+        func = tfb.AutoregressiveNetwork(params=self.params, hidden_units=self.hidden_units)
+        return func 
+    
+    def make_maf(self, data):
+        distribution = self.base_dist
+        sample_shape = self.get_dims(data)
+        shift_scale_function = self.get_shift_scale_func(data)
+        bijector = tfb.MaskedAutoregressiveFlow(shift_scale_function)
+        maf = tfd.TransformedDistribution(tfd.Sample(distribution, sample_shape), bijector)
+        return maf
+ 
\ No newline at end of file

scripts/maf_execute.py

+import os 
+os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' 
+import numpy as np
+from sklearn.preprocessing import StandardScaler
+
+import tensorflow as tf
+tf.compat.v1.disable_eager_execution() 
+import tensorflow_probability as tfp
+
+import matplotlib.pyplot as plt
+
+from data_loader import load_data
+from data_preprocesser import preprocess_data
+from maf import MAF 
+
+def train(session, loss, optimizer, steps=int(1e5)):
+    
+    """ optimize for all dimensions """
+    
+    recorded_steps = []
+    recorded_losses = []
+    for i in range(steps):
+        _, loss_per_iteration = session.run([optimizer, loss])
+        if i % 100 == 0:
+            recorded_steps.append(i)
+            recorded_losses.append(loss_per_iteration)
+        if i % int(1e4) == 0:
+            print('Iteration {iteration}: {loss}'.format(iteration=i,loss=loss_per_iteration))
+    return recorded_losses
+
+
+def plot_results(recorded_losses):
+    
+    """ plot loss """
+    print('Displaying results...')
+    fig = plt.figure(figsize=(10,5))
+    x = np.arange(len(recorded_losses))
+    y = recorded_losses
+    m, b = np.polyfit(x, y, 1) 
+    plt.scatter(x, y, s=10, alpha=0.3)
+    plt.plot(x, m*x+b, c="r")
+    plt.title('Loss per 100 iteration')
+    plt.xlabel('Iteration')
+    plt.ylabel('Loss')
+    plt.tight_layout()
+    plt.show()
+
+def main():
+    
+    """ load data """
+
+    filename = 'prostate.xls'
+    directory = '/Users/kaanguney.keklikci/Data/'
+
+    loader = load_data(filename, directory)
+    loader.create_directory(directory)
+    data = loader.read_data(directory, filename)
+    print('Data successfully loaded...\n')
+    
+    """ preprocess data """
+
+    fillna_vals = ['sz', 'sg', 'wt']
+    dropna_vals = ['ekg', 'age']
+    drop_vals = ['patno', 'sdate']
+
+    preprocesser = preprocess_data(StandardScaler(), fillna_vals, dropna_vals, drop_vals)
+    data = preprocesser.dropna_features(data)
+    data = preprocesser.impute(data)
+    data = preprocesser.drop_features(data)
+    data = preprocesser.encode_categorical(data)
+    data = preprocesser.scale(data)
+    print('Data successfully preprocessed...\n')
+    
+    """ set MAF parameters """
+
+    batch_size = 32
+    dtype = np.float32
+    tf_version = tf.__version__
+    params = 2
+    hidden_units = [512,512]
+    base_dist = tfp.distributions.Normal(loc=0., scale=1.)
+    dims = data.shape[1]
+    learning_rate = 1e-4
+    
+    """ initialize samples """
+
+    maf = MAF(dtype, tf_version, batch_size, params, hidden_units, base_dist, dims)
+
+    dims = maf.get_dims(data)
+    samples = maf.create_tensor(data)
+    print(f'TensorFlow version: {maf.tf_version}')
+    print(f'Number of dimensions: {maf.dims}')
+    print(f'Learning rate: {learning_rate}\n')
+    
+    """ initialize MAF """
+
+    maf = maf.make_maf(data)
+    print('Successfully created model...\n')
+    
+    """ initialize loss and optimizer """
+
+    loss = -tf.reduce_mean(maf.log_prob(samples))
+    optimizer = tf.compat.v1.train.AdamOptimizer(learning_rate).minimize(loss)
+
+    session = tf.compat.v1.Session()
+    tf.compat.v1.set_random_seed(42)
+    session.run(tf.compat.v1.global_variables_initializer())
+    print('Optimizer and loss successfully defined...\n')
+    
+    """ start training """
+    recorded_losses = train(session, loss, optimizer)
+    print('Training finished...\n')
+    
+    """ display results """
+    plot_results(recorded_losses)
+    
+    
+if __name__ == "__main__":
+    main()
+
+
+
+