106 lines
3.2 KiB
Python
106 lines
3.2 KiB
Python
from sklearn.linear_model import LinearRegression
|
|
from sklearn.model_selection import train_test_split
|
|
from tensorflow.keras import Input, Model
|
|
from tensorflow.keras.models import Sequential, save_model
|
|
from tensorflow.keras.layers import Dense
|
|
from tensorflow.keras import losses
|
|
from sklearn.metrics import mean_squared_error
|
|
from utils import save_sklearn_model, save_keras_model
|
|
import os
|
|
import random
|
|
import numpy as np
|
|
import tensorflow as tf
|
|
from keras import backend as K
|
|
|
|
#
|
|
# FIX THE RANDOM GENERATOR SEEDS
|
|
#
|
|
seed_value = 0
|
|
# 1. Set `PYTHONHASHSEED` environment variable at a fixed value
|
|
os.environ['PYTHONHASHSEED'] = str(seed_value)
|
|
# 2. Set `python` built-in pseudo-random generator at a fixed value
|
|
random.seed(seed_value)
|
|
# 3. Set `numpy` pseudo-random generator at a fixed value
|
|
np.random.seed(seed_value)
|
|
# 4. Set the `tensorflow` pseudo-random generator at a fixed value
|
|
tf.random.set_seed(seed_value)
|
|
# 5. Configure a new global `tensorflow` session
|
|
session_conf = tf.compat.v1.ConfigProto(intra_op_parallelism_threads=1,
|
|
inter_op_parallelism_threads=1)
|
|
sess = tf.compat.v1.Session(graph=tf.compat.v1.get_default_graph(),
|
|
config=session_conf)
|
|
tf.compat.v1.keras.backend.set_session(sess)
|
|
|
|
d = os.path.dirname(__file__)
|
|
|
|
data = np.load("../data/data.npz")
|
|
xs = data["x"] # 2000x2
|
|
y = data["y"] # 2000x1
|
|
points = np.shape(xs)[0]
|
|
|
|
# We manually include in the feature vectors a '1' column corresponding to theta_0,
|
|
# so disable
|
|
lr = LinearRegression(fit_intercept=False)
|
|
|
|
# Build x feature vector with columns for theta_3 and theta_4
|
|
X = np.zeros([points, 5])
|
|
X[:, 0] = 1
|
|
X[:, 1:3] = xs
|
|
X[:, 3] = xs[:, 0] * xs[:, 1]
|
|
X[:, 4] = np.sin(xs[:, 0])
|
|
|
|
# Shuffle our data for division in training, and test set
|
|
|
|
train_ratio = 0.1
|
|
validation_ratio = 0.1
|
|
|
|
X_t, X_test, y_t, y_test = train_test_split(X, y, test_size=train_ratio)
|
|
X_train, X_val, y_train, y_val = train_test_split(X_t, y_t, test_size=validation_ratio)
|
|
np.savez('test', x=X_test, y=y_test, allow_pickle=True)
|
|
|
|
# Fit with train data
|
|
reg = lr.fit(X_t, y_t)
|
|
|
|
print("# Linear regression:")
|
|
|
|
# Print the resulting parameters
|
|
print("f(x) = %g + %g * x_1 + %g * x_2 + %g * x_1 * x_2 + %g * sin(x_1)" % tuple(reg.coef_))
|
|
|
|
save_sklearn_model(reg, "../deliverable/linear_regression.pickle")
|
|
|
|
# Non-linear regression:
|
|
print("\n# Feed-forward NN:")
|
|
|
|
A = X_val
|
|
|
|
X_train = X_train[:, 1:3]
|
|
X_val = X_val[:, 1:3]
|
|
|
|
mean = np.mean(X_train, axis=0)
|
|
std = np.std(X_train, axis=0)
|
|
|
|
X_train -= mean
|
|
X_train /= std
|
|
|
|
X_val -= mean
|
|
X_val /= std
|
|
|
|
network = Sequential()
|
|
network.add(Dense(22, activation='tanh'))
|
|
network.add(Dense(15, activation='sigmoid'))
|
|
network.add(Dense(1, activation='linear'))
|
|
network.compile(optimizer='adam', loss='mse')
|
|
|
|
epochs = 5000
|
|
callback = tf.keras.callbacks.EarlyStopping(monitor='loss', patience=120)
|
|
network.fit(X_train, y_train, epochs=epochs, verbose=1,
|
|
validation_data=(X_val, y_val), callbacks=[callback])
|
|
|
|
network.save("../deliverable/nonlinear_model")
|
|
save_sklearn_model({"mean": mean, "std": std}, "../deliverable/nonlinear_model_normalizers.pickle")
|
|
|
|
# Print the final validation set MSE, which was used to tailor the NN architecture after
|
|
# several manual trials
|
|
msq = mean_squared_error(network.predict(X_val), y_val)
|
|
print(msq)
|