def test_imputer_init():
with pytest.raises(ValueError) as e:
imputer = Imputer(data_featurizers='item_name', label_encoders=['brand'], data_encoders='')
with pytest.raises(ValueError) as e:
imputer = Imputer(data_featurizers=[BowFeaturizer('item_name')],
label_encoders="brand",
data_encoders='')
with pytest.raises(ValueError) as e:
imputer = Imputer(data_featurizers=[BowFeaturizer('item_name')],
label_encoders=[CategoricalEncoder("brand")],
data_encoders='')
with pytest.raises(ValueError) as e:
imputer = Imputer(data_featurizers=[BowFeaturizer('item_name')],
label_encoders=[CategoricalEncoder("brand")],
data_encoders=[BowEncoder('not_in_featurizers')])
with pytest.raises(ValueError) as e:
imputer = Imputer(data_featurizers=[BowFeaturizer('item_name')],
label_encoders=[CategoricalEncoder("brand")],
data_encoders=[BowEncoder('brand')])
label_encoders = [CategoricalEncoder('brand', max_tokens=10)]
data_featurizers = [LSTMFeaturizer('item_name'), EmbeddingFeaturizer('manufacturer')]
data_encoders = [
SequentialEncoder(
'item_name'
),
CategoricalEncoder(
'manufacturer'
)
]
imputer = Imputer(
data_featurizers=data_featurizers,
label_encoders=label_encoders,
data_encoders=data_encoders
)
assert imputer.output_path == "brand"
assert imputer.module_path == 'brand/model'
assert imputer.metrics_path == 'brand/fit-test-metrics.json'
assert imputer.output_path == "brand"
assert imputer.module_path == 'brand/model'
assert imputer.metrics_path == 'brand/fit-test-metrics.json'
imputer = Imputer(
data_featurizers=data_featurizers,
label_encoders=[CategoricalEncoder('B Rand', max_tokens=10)],
data_encoders=data_encoders
)
assert imputer.output_path == "b_rand"
shutil.rmtree("b_rand")
def test_imputer_real_data_all_featurizers(test_dir, data_frame):
"""
Tests Imputer with sequential, bag-of-words and categorical variables as inputs
this could be run as part of integration test suite.
"""
feature_col = "string_feature"
categorical_col = "categorical_feature"
label_col = "label"
n_samples = 5000
num_labels = 3
seq_len = 20
vocab_size = int(2**10)
latent_dim = 30
embed_dim = 30
# generate some random data
random_data = data_frame(feature_col=feature_col,
label_col=label_col,
vocab_size=vocab_size,
num_labels=num_labels,
num_words=seq_len,
n_samples=n_samples)
# we use a the label prefixes as a dummy categorical input variable
random_data[categorical_col] = random_data[label_col].apply(
lambda x: x[:2])
df_train, df_test, df_val = random_split(random_data, [.8, .1, .1])
data_encoder_cols = [
BowEncoder(feature_col, feature_col + "_bow", max_tokens=vocab_size),
SequentialEncoder(feature_col,
feature_col + "_lstm",
max_tokens=vocab_size,
seq_len=seq_len),
CategoricalEncoder(categorical_col, max_tokens=num_labels)
]
label_encoder_cols = [CategoricalEncoder(label_col, max_tokens=num_labels)]
data_cols = [
BowFeaturizer(feature_col + "_bow", vocab_size=vocab_size),
LSTMFeaturizer(field_name=feature_col + "_lstm",
seq_len=seq_len,
latent_dim=latent_dim,
num_hidden=30,
embed_dim=embed_dim,
num_layers=2,
vocab_size=num_labels),
EmbeddingFeaturizer(field_name=categorical_col,
embed_dim=embed_dim,
vocab_size=num_labels)
]
output_path = os.path.join(test_dir, "tmp",
"imputer_experiment_synthetic_data")
num_epochs = 10
batch_size = 32
learning_rate = 1e-2
imputer = Imputer(data_featurizers=data_cols,
label_encoders=label_encoder_cols,
data_encoders=data_encoder_cols,
output_path=output_path).fit(train_df=df_train,
test_df=df_val,
learning_rate=learning_rate,
num_epochs=num_epochs,
batch_size=batch_size,
calibrate=False)
len_df_before_predict = len(df_test)
pred = imputer.transform(df_test)
assert len(pred[label_col]) == len_df_before_predict
assert sum(df_test[label_col].values == pred[label_col]) == len(df_test)
_ = imputer.predict_proba_top_k(df_test, top_k=2)
_, metrics = imputer.transform_and_compute_metrics(df_test)
assert metrics[label_col]['avg_f1'] > 0.9
deserialized = Imputer.load(imputer.output_path)
_, metrics_deserialized = deserialized.transform_and_compute_metrics(
df_test)
assert metrics_deserialized[label_col]['avg_f1'] > 0.9
# training on a small data set to get a imputer with low precision
not_so_precise_imputer = Imputer(data_featurizers=data_cols,
label_encoders=label_encoder_cols,
data_encoders=data_encoder_cols,
output_path=output_path).fit(
train_df=df_train[:50],
test_df=df_test,
learning_rate=learning_rate,
num_epochs=num_epochs,
batch_size=batch_size,
calibrate=False)
df_test = df_test.reset_index()
predictions_df = not_so_precise_imputer.predict(
df_test, precision_threshold=.5, imputation_suffix="_imputed")
assert predictions_df.columns.contains(label_col + "_imputed")
assert predictions_df.columns.contains(label_col + "_imputed_proba")
def test_imputer_duplicate_encoder_output_columns(test_dir, data_frame):
"""
Tests Imputer with sequential, bag-of-words and categorical variables as inputs
this could be run as part of integration test suite.
"""
feature_col = "string_feature"
categorical_col = "categorical_feature"
label_col = "label"
n_samples = 1000
num_labels = 10
seq_len = 100
vocab_size = int(2**10)
latent_dim = 30
embed_dim = 30
# generate some random data
random_data = data_frame(feature_col=feature_col,
label_col=label_col,
vocab_size=vocab_size,
num_labels=num_labels,
num_words=seq_len,
n_samples=n_samples)
# we use a the label prefixes as a dummy categorical input variable
random_data[categorical_col] = random_data[label_col].apply(
lambda x: x[:2])
df_train, df_test, df_val = random_split(random_data, [.8, .1, .1])
data_encoder_cols = [
BowEncoder(feature_col, feature_col, max_tokens=vocab_size),
SequentialEncoder(feature_col,
feature_col,
max_tokens=vocab_size,
seq_len=seq_len),
CategoricalEncoder(categorical_col, max_tokens=num_labels)
]
label_encoder_cols = [CategoricalEncoder(label_col, max_tokens=num_labels)]
data_cols = [
BowFeaturizer(feature_col, vocab_size=vocab_size),
LSTMFeaturizer(field_name=feature_col,
seq_len=seq_len,
latent_dim=latent_dim,
num_hidden=30,
embed_dim=embed_dim,
num_layers=2,
vocab_size=num_labels),
EmbeddingFeaturizer(field_name=categorical_col,
embed_dim=embed_dim,
vocab_size=num_labels)
]
output_path = os.path.join(test_dir, "tmp",
"imputer_experiment_synthetic_data")
num_epochs = 20
batch_size = 16
learning_rate = 1e-3
with pytest.raises(ValueError) as e:
imputer = Imputer(data_featurizers=data_cols,
label_encoders=label_encoder_cols,
data_encoders=data_encoder_cols,
output_path=output_path)
imputer.fit(train_df=df_train,
test_df=df_val,
learning_rate=learning_rate,
num_epochs=num_epochs,
batch_size=batch_size)
def test_automatic_calibration(data_frame):
"""
Fit model with all featurisers and assert
that calibration improves the expected calibration error.
"""
feature_col = "string_feature"
categorical_col = "categorical_feature"
label_col = "label"
n_samples = 2000
num_labels = 3
seq_len = 20
vocab_size = int(2**10)
latent_dim = 30
embed_dim = 30
# generate some random data
random_data = data_frame(feature_col=feature_col,
label_col=label_col,
vocab_size=vocab_size,
num_labels=num_labels,
num_words=seq_len,
n_samples=n_samples)
# we use a the label prefixes as a dummy categorical input variable
random_data[categorical_col] = random_data[label_col].apply(
lambda x: x[:2])
df_train, df_test, df_val = random_split(random_data, [.8, .1, .1])
data_encoder_cols = [
BowEncoder(feature_col, feature_col + "_bow", max_tokens=vocab_size),
SequentialEncoder(feature_col,
feature_col + "_lstm",
max_tokens=vocab_size,
seq_len=seq_len),
CategoricalEncoder(categorical_col, max_tokens=num_labels)
]
label_encoder_cols = [CategoricalEncoder(label_col, max_tokens=num_labels)]
data_cols = [
BowFeaturizer(feature_col + "_bow", vocab_size=vocab_size),
LSTMFeaturizer(field_name=feature_col + "_lstm",
seq_len=seq_len,
latent_dim=latent_dim,
num_hidden=30,
embed_dim=embed_dim,
num_layers=2,
vocab_size=num_labels),
EmbeddingFeaturizer(field_name=categorical_col,
embed_dim=embed_dim,
vocab_size=num_labels)
]
num_epochs = 20
batch_size = 32
learning_rate = 1e-2
imputer = Imputer(data_featurizers=data_cols,
label_encoders=label_encoder_cols,
data_encoders=data_encoder_cols).fit(
train_df=df_train,
test_df=df_val,
learning_rate=learning_rate,
num_epochs=num_epochs,
batch_size=batch_size)
assert imputer.calibration_info['ece_pre'] > imputer.calibration_info[
'ece_post']