def test_plt_exact_prediction_reproducibility():
X_train, Y_train = load_dataset(TEST_DATASET, "train", root=TEST_DATA_PATH)
X_test, Y_test = load_dataset(TEST_DATASET, "test", root=TEST_DATA_PATH)
print("\n")
for mc in model_configs:
print("model config: ", mc)
plt = PLT(MODEL_PATH, **mc)
plt.fit(X_train, Y_train)
Y_pred = plt.predict(X_test, top_k=1)
p_at_1 = precision_at_k(Y_test, Y_pred, k=1)
for rc in representation_configs:
print(" prediction config: ", rc)
for _ in range(repeat):
plt = PLT(MODEL_PATH, **mc, **rc)
Y_pred = plt.predict(X_test, top_k=1)
assert p_at_1 == precision_at_k(Y_test, Y_pred, k=1)
shutil.rmtree(MODEL_PATH, ignore_errors=True)
def test_seed_reproducibility():
X_train, Y_train = load_dataset(TEST_DATASET, "train", root=TEST_DATA_PATH)
X_test, Y_test = load_dataset(TEST_DATASET, "test", root=TEST_DATA_PATH)
for i in range(repeat):
plt_1 = PLT(MODEL_PATH + "-1", optimizer="adagrad", epochs=1, loss="log", seed=i)
plt_1.fit(X_train, Y_train)
Y_pred_1 = plt_1.predict(X_test, top_k=1)
p_at_1_1 = precision_at_k(Y_test, Y_pred_1, k=1)
tree_structure_1 = plt_1.get_tree_structure()
plt_2 = PLT(MODEL_PATH + "-2", optimizer="adagrad", epochs=1, loss="log", seed=i)
plt_2.fit(X_train, Y_train)
Y_pred_2 = plt_2.predict(X_test, top_k=1)
p_at_1_2 = precision_at_k(Y_test, Y_pred_2, k=1)
tree_structure_2 = plt_2.get_tree_structure()
assert len(set(tree_structure_1) - set(tree_structure_2)) == 0
assert p_at_1_1 == p_at_1_2
shutil.rmtree(MODEL_PATH + "-1", ignore_errors=True)
shutil.rmtree(MODEL_PATH + "-2", ignore_errors=True)
# from XML Repository (http://manikvarma.org/downloads/XC/XMLRepository.html).
X_train, Y_train = load_dataset("eurlex-4k", "train")
X_test, Y_test = load_dataset("eurlex-4k", "test")
# Create Probabilistic Labels Tree model,
# directory "eurlex-model" will be created and used during model training.
# napkinXC stores already trained parts of the model to save RAM.
# Model directory is only a required argument for model constructors.
plt = PLT("eurlex-model")
# Fit the model on the training dataset.
# The model weights and additional data will be stored in "eurlex-model" directory.
# Features matrix X must be SciPy csr_matrix, NumPy array, or list of tuples of (idx, value),
# while labels matrix Y should be list of lists or tuples containing positive labels.
plt.fit(X_train, Y_train)
# After the training model is not loaded to RAM.
# You can preload the model to RAM to perform prediction.
plt.load()
# Predict only five top labels for each data point in the test dataset.
# This will also load the model if it is not loaded.
Y_pred = plt.predict(X_test, top_k=5)
# Evaluate the prediction with precision at 5 measure.
print("Precision at k:", precision_at_k(Y_test, Y_pred, k=5))
# Unload the model from RAM
# You can also just delete the object if you do not need it
plt.unload()
# napkinXC stores already trained parts of the model to save RAM.
# Model directory is only a required argument for model constructors.
plt = PLT("eurlex-model")
# Fit the model on the training (observed) dataset.
# The model weights and additional data will be stored in "eurlex-model" directory.
# Features matrix X must be SciPy csr_matrix, NumPy array, or list of tuples of (idx, value),
# while labels matrix Y should be list of lists or tuples containing positive labels.
plt.fit(X_train, Y_train)
# After the training model is not loaded to RAM.
# You can preload the model to RAM to perform prediction.
plt.load()
# Predict five top labels for each data point in the test dataset using standard uniform-cost search
Y_pred = plt.predict(X_test, top_k=5)
# Calculate inverse propensity values (aka propensity scores) and predict with label weights
inv_ps = inverse_propensity(Y_train, A=0.55, B=1.5)
ps_Y_pred = plt.predict(X_test, labels_weights=inv_ps, top_k=5)
# Evaluate the both predictions with propensity-scored and vanilla precision at 5 measure.
print("Standard prediction:")
print(" Precision at k:", precision_at_k(Y_test, Y_pred, k=5))
print(" Propensity-scored precision at k:",
psprecision_at_k(Y_test, Y_pred, inv_ps, k=5))
print("Prediction weighted by inverse propensity:")
print(" Precision at k:", precision_at_k(Y_test, ps_Y_pred, k=5))
print(" Propensity-scored precision at k:",
psprecision_at_k(Y_test, ps_Y_pred, inv_ps, k=5))
X_train, Y_train = load_dataset("eurlex-4k", "train")
X_test, Y_test = load_dataset("eurlex-4k", "test")
# Using sklearn, lets split training dataset into dataset for training and tuning thresholds for macro F-measure.
X_train, X_valid, Y_train, Y_valid = train_test_split(X_train,
Y_train,
test_size=0.2,
random_state=0)
# Create Probabilistic Labels Tree model and fit it on the training dataset.
# The model weights and additional data will be stored in "eurlex-model" directory.
plt = PLT("eurlex-model")
plt.fit(X_train, Y_train)
# First lets check macro F1 measure performance with const. threshold = 0.5
Y_pred_single_th = plt.predict(X_test, threshold=0.5)
print("Micro F1 measure with const. threshold = 0.5:",
f1_measure(Y_test, Y_pred_single_th, average='micro', zero_division=0))
print("Macro F1 measure with const. threshold = 0.5:",
f1_measure(Y_test, Y_pred_single_th, average='macro', zero_division=0))
# Now lets use Online F measure optimization procedure to find better thresholds.
# OFO can be used to find optimal threshold/thresholds for micro F1 measure and macro F1 measure.
micro_ths = plt.ofo(X_valid, Y_valid, type="micro", a=1, b=2, epochs=5)
macro_ths = plt.ofo(X_valid, Y_valid, type="macro", a=1, b=2, epochs=10)
# Lets predict with the new thresholds and compare the results
Y_pred_micro_ths = plt.predict(X_test, threshold=micro_ths)
Y_pred_macro_ths = plt.predict(X_test, threshold=macro_ths)
print("Micro F1 measure with thresholds from OFO procedure:",
# The beginning is the same as in the basic.py example.
# Use load_dataset function to load one of the benchmark datasets
# from XML Repository (http://manikvarma.org/downloads/XC/XMLRepository.html).
X_train, Y_train = load_dataset("eurlex-4k", "train")
X_test, Y_test = load_dataset("eurlex-4k", "test")
# Create PLT model with "eurlex-model" directory,
# it will be created and used during model training for storing weights.
# napkinXC stores already trained parts of the models to save RAM.
plt = PLT("eurlex-model")
# Fit the model on the training dataset.
# The model weights and additional data will be stored in "eurlex-model" directory.
plt.fit(X_train, Y_train)
# Predict.
Y_pred = plt.predict(X_test, top_k=1)
print("Precision at 1:", precision_at_k(Y_test, Y_pred, k=1))
# Delete plt object.
del plt
# To load the model, create a new PLT object with the same directory as the previous one.
new_plt = PLT("eurlex-model")
# Predict using a new model object.
Y_pred = new_plt.predict(X_test, top_k=1)
print("Precision at 1 after loading:", precision_at_k(Y_test, Y_pred, k=1))