logging.info(f"TRAIN_ID {proj_id}")
logging.info(f"TRAIN_PATH {train_path}")
#
# Read dataset
#
#fields = """doc_id,hotel_name,hotel_url,street,city,state,country,zip,class,price,
#num_reviews,CLEANLINESS,ROOM,SERVICE,LOCATION,VALUE,COMFORT,overall_ratingsource""".replace("\n",'').split(",")
read_table_opts = dict(sep="\t", names=fields, index_col=False)
df = pd.read_table(train_path, **read_table_opts)
#split train/test
X_train, X_test, y_train, y_test = train_test_split(df.iloc[:, 2:],
df.iloc[:, 1],
test_size=0.2)
#
# Train the model
#
model.fit(X_train, y_train)
#model_score = model.score(X_test, y_test)
model_score = log_loss(y_test, model.predict_proba(X_test)[:, 1])
logging.info(f"model score: {model_score:.3f}")
# save the model
dump(model, "{}.joblib".format(proj_id))
data_loader = DataLoader()
x_train, y_train, x_test, y_test, classes = data_loader.load_data()
x_train2 = (x_train / 255) - 0.5
x_test2 = (x_test / 255) - 0.5
y_train2 = keras.utils.to_categorical(y_train, NUM_CLASSES)
y_test2 = keras.utils.to_categorical(y_test, NUM_CLASSES)
model = model()
model.load_weights("weights/weights.h5")
# make test predictions
y_pred_test = model.predict_proba(x_test)
y_pred_test_classes = np.argmax(y_pred_test, axis=1)
y_pred_test_max_probas = np.max(y_pred_test, axis=1)
plt.figure(figsize=(7, 6))
plt.title('Confusion matrix', fontsize=16)
plt.imshow(confusion_matrix(y_test, y_pred_test_classes))
plt.xticks(np.arange(10), classes, rotation=45, fontsize=12)
plt.yticks(np.arange(10), classes, fontsize=12)
plt.colorbar()
plt.show()
print("Test accuracy:", accuracy_score(y_test, y_pred_test_classes))
cols = 8
from model import model
# Calculate predictions
predictions = model.predict_proba({
# "rain": "heavy",
"train": "delayed"
})
# Print predictions for each node
for node, prediction in zip(model.states, predictions):
if isinstance(prediction, str):
print("{}: {}".format(node.name, prediction))
else:
print("{}".format(node.name))
for value, probability in prediction.parameters[0].items():
print(" {}: {}".format(value, probability))
from model import model
# Insert evidence that train is delayed (Observed evidence)
predictions = model.predict_proba({"train": "delayed"})
# calculate the probability for each event
for node, prediction in zip(model.states, predictions):
if isinstance(prediction, str):
print(f"{node.name}: {prediction}")
else:
print(f"{node.name}")
for value, probability in prediction.parameters[0].items():
print(f"\t{value}: ", end='')
print("{:.4f}".format(probability))
