def test_explain_prediction(self):
mdb = Predictor(name='test_explain_prediction')
n_points = 100
input_dataframe = pd.DataFrame(
{
'numeric_x': list(range(n_points)),
'categorical_x': [int(x % 2 == 0) for x in range(n_points)],
},
index=list(range(n_points)))
input_dataframe[
'numeric_y'] = input_dataframe.numeric_x + 2 * input_dataframe.categorical_x
mdb.learn(from_data=input_dataframe,
to_predict='numeric_y',
stop_training_in_x_seconds=1,
use_gpu=False,
advanced_args={'force_predict': True})
# Test predicting using a data frame
result = mdb.predict(when_data=pd.DataFrame([{
"numeric_x": 10,
'categorical_x': 1
}]))
explanation_new = result[0].explanation['numeric_y']
assert isinstance(explanation_new['predicted_value'], int)
assert isinstance(explanation_new['confidence_interval'], list)
assert isinstance(explanation_new['confidence_interval'][0], float)
assert isinstance(explanation_new['important_missing_information'],
list)
assert isinstance(explanation_new['prediction_quality'], str)
assert len(str(result[0])) > 20
def test_category_tags_output(self):
vocab = random.sample(SMALL_VOCAB, 10)
vocab = {i: word for i, word in enumerate(vocab)}
# x1 contains the index of first tag present
# x2 contains the index of second tag present
# if a tag is missing then x1/x2 contain -1 instead
# Thus the dataset should be perfectly predicted
n_points = 5000
x1 = [
random.randint(0,
len(vocab) - 1) if random.random() > 0.1 else -1
for i in range(n_points)
]
x2 = [
random.randint(0,
len(vocab) - 1) if random.random() > 0.1 else -1
for i in range(n_points)
]
tags = []
for x1_index, x2_index in zip(x1, x2):
row_tags = set([vocab.get(x1_index), vocab.get(x2_index)])
row_tags = [x for x in row_tags if x is not None]
tags.append(','.join(row_tags))
df = pd.DataFrame({'x1': x1, 'x2': x2, 'tags': tags})
df_train = df.iloc[:round(n_points * 0.9)]
df_test = df.iloc[round(n_points * 0.9):]
predictor = Predictor('test')
predictor.learn(from_data=df_train,
to_predict='tags',
advanced_args=dict(deduplicate_data=False),
stop_training_in_x_seconds=60,
use_gpu=False)
model_data = F.get_model_data('test')
assert model_data['data_analysis_v2']['tags']['typing'][
'data_type'] == DATA_TYPES.CATEGORICAL
assert model_data['data_analysis_v2']['tags']['typing'][
'data_subtype'] == DATA_SUBTYPES.TAGS
predictions = predictor.predict(when_data=df_test)
test_tags = df_test.tags.apply(lambda x: x.split(','))
predicted_tags = []
for i in range(len(predictions)):
predicted_tags.append(predictions[i]['tags'])
test_tags_encoded = predictor.transaction.model_backend.predictor._mixer.encoders[
'tags'].encode(test_tags)
pred_labels_encoded = predictor.transaction.model_backend.predictor._mixer.encoders[
'tags'].encode(predicted_tags)
score = f1_score(test_tags_encoded,
pred_labels_encoded,
average='weighted')
assert score >= 0.3
def test_timeseries(self, tmp_path):
ts_hours = 12
data_len = 120
train_file_name = os.path.join(str(tmp_path), 'train_data.csv')
test_file_name = os.path.join(str(tmp_path), 'test_data.csv')
features = generate_value_cols(['date', 'int'], data_len,
ts_hours * 3600)
labels = [generate_timeseries_labels(features)]
feature_headers = list(map(lambda col: col[0], features))
label_headers = list(map(lambda col: col[0], labels))
# Create the training dataset and save it to a file
columns_train = list(
map(lambda col: col[1:int(len(col) * 3 / 4)], features))
columns_train.extend(
list(map(lambda col: col[1:int(len(col) * 3 / 4)], labels)))
columns_to_file(columns_train,
train_file_name,
headers=[*feature_headers, *label_headers])
# Create the testing dataset and save it to a file
columns_test = list(
map(lambda col: col[int(len(col) * 3 / 4):], features))
columns_to_file(columns_test, test_file_name, headers=feature_headers)
mdb = Predictor(name='test_timeseries')
mdb.learn(from_data=train_file_name,
to_predict=label_headers,
timeseries_settings={
'order_by': [feature_headers[0]],
'window': 3
},
stop_training_in_x_seconds=10,
use_gpu=False,
advanced_args={'force_predict': True})
results = mdb.predict(when_data=test_file_name, use_gpu=False)
for row in results:
expect_columns = [
label_headers[0], label_headers[0] + '_confidence'
]
for col in expect_columns:
assert col in row
models = F.get_models()
model_data = F.get_model_data(models[0]['name'])
assert model_data
def test_category_tags_input(self):
vocab = random.sample(SMALL_VOCAB, 10)
# tags contains up to 2 randomly selected tags
# y contains the sum of indices of tags
# the dataset should be nearly perfectly predicted
n_points = 5000
tags = []
y = []
for i in range(n_points):
row_tags = []
row_y = 0
for k in range(2):
if random.random() > 0.2:
selected_index = random.randint(0, len(vocab) - 1)
if vocab[selected_index] not in row_tags:
row_tags.append(vocab[selected_index])
row_y += selected_index
tags.append(','.join(row_tags))
y.append(row_y)
df = pd.DataFrame({'tags': tags, 'y': y})
df_train = df.iloc[:round(n_points * 0.9)]
df_test = df.iloc[round(n_points * 0.9):]
predictor = Predictor(name='test')
predictor.learn(from_data=df_train,
to_predict='y',
advanced_args=dict(deduplicate_data=False),
stop_training_in_x_seconds=40,
use_gpu=False)
model_data = F.get_model_data('test')
assert model_data['data_analysis_v2']['tags']['typing'][
'data_type'] == DATA_TYPES.CATEGORICAL
assert model_data['data_analysis_v2']['tags']['typing'][
'data_subtype'] == DATA_SUBTYPES.TAGS
predictions = predictor.predict(when_data=df_test)
test_y = df_test.y.apply(str)
predicted_y = []
for i in range(len(predictions)):
predicted_y.append(predictions[i]['y'])
score = accuracy_score(test_y, predicted_y)
assert score >= 0.2
def test_multilabel_prediction(self, tmp_path):
train_file_name = os.path.join(str(tmp_path), 'train_data.csv')
test_file_name = os.path.join(str(tmp_path), 'test_data.csv')
data_len = 60
features = generate_value_cols(['int', 'float', 'int', 'float'], data_len)
labels = []
labels.append(generate_log_labels(features))
labels.append(generate_timeseries_labels(features))
feature_headers = list(map(lambda col: col[0], features))
label_headers = list(map(lambda col: col[0], labels))
# Create the training dataset and save it to a file
columns_train = list(
map(lambda col: col[1:int(len(col) * 3 / 4)], features))
columns_train.extend(
list(map(lambda col: col[1:int(len(col) * 3 / 4)], labels)))
columns_to_file(columns_train, train_file_name,
headers=[*feature_headers, *label_headers])
# Create the testing dataset and save it to a file
columns_test = list(
map(lambda col: col[int(len(col) * 3 / 4):], features))
columns_to_file(columns_test, test_file_name,
headers=feature_headers)
mdb = Predictor(name='test_multilabel_prediction')
mdb.learn(
from_data=train_file_name,
to_predict=label_headers,
stop_training_in_x_seconds=1,
use_gpu=False,
advanced_args={'force_predict': True}
)
results = mdb.predict(when_data=test_file_name)
models = F.get_models()
model_data = F.get_model_data(models[0]['name'])
assert model_data
for i in range(len(results)):
row = results[i]
for label in label_headers:
expect_columns = [label, label + '_confidence']
for col in expect_columns:
assert col in row
def test_house_pricing(self, use_gpu):
"""
Tests whole pipeline from downloading the dataset to making predictions and explanations.
"""
# Create & Learn
name = 'home_rentals_price'
mdb = Predictor(name=name)
mdb.learn(
to_predict='rental_price',
from_data=
"https://s3.eu-west-2.amazonaws.com/mindsdb-example-data/home_rentals.csv",
backend='lightwood',
stop_training_in_x_seconds=80,
use_gpu=use_gpu)
def assert_prediction_interface(predictions):
for prediction in predictions:
assert hasattr(prediction, 'explanation')
test_results = mdb.test(
when_data=
"https://s3.eu-west-2.amazonaws.com/mindsdb-example-data/home_rentals.csv",
accuracy_score_functions=r2_score,
predict_args={'use_gpu': use_gpu})
assert test_results['rental_price_accuracy'] >= 0.8
predictions = mdb.predict(
when_data=
"https://s3.eu-west-2.amazonaws.com/mindsdb-example-data/home_rentals.csv",
use_gpu=use_gpu)
assert_prediction_interface(predictions)
predictions = mdb.predict(when_data={'sqft': 300}, use_gpu=use_gpu)
assert_prediction_interface(predictions)
amd = F.get_model_data(name)
assert isinstance(json.dumps(amd), str)
for k in [
'status', 'name', 'version', 'data_source', 'current_phase',
'updated_at', 'created_at', 'train_end_at'
]:
assert isinstance(amd[k], str)
assert isinstance(amd['predict'], (list, str))
assert isinstance(amd['is_active'], bool)
for k in ['validation_set_accuracy', 'accuracy']:
assert isinstance(amd[k], float)
for k in amd['data_preparation']:
assert isinstance(amd['data_preparation'][k], (int, float))
for k in amd['data_analysis']:
assert (len(amd['data_analysis'][k]) > 0)
assert isinstance(amd['data_analysis'][k][0], dict)
model_analysis = amd['model_analysis']
assert (len(model_analysis) > 0)
assert isinstance(model_analysis[0], dict)
input_importance = model_analysis[0]["overall_input_importance"]
assert (len(input_importance) > 0)
assert isinstance(input_importance, dict)
for k in ['train', 'test', 'valid']:
assert isinstance(model_analysis[0][k + '_data_accuracy'], dict)
assert len(model_analysis[0][k + '_data_accuracy']) == 1
assert model_analysis[0][k +
'_data_accuracy']['rental_price'] > 0.4
for column, importance in zip(input_importance["x"],
input_importance["y"]):
assert isinstance(column, str)
assert (len(column) > 0)
assert isinstance(importance, (float, int))
assert (importance >= 0 and importance <= 10)
# Test confidence estimation after save -> load
p = None
F.export_predictor(name)
F.import_model(f"{name}.zip", f"{name}-new")
p = Predictor(name=f'{name}-new')
predictions = p.predict(when_data={'sqft': 1000},
use_gpu=use_gpu,
run_confidence_variation_analysis=True)
assert_prediction_interface(predictions)
def test_custom_backend(self):
predictor = Predictor(name='custom_model_test_predictor')
class CustomDTModel():
def __init__(self):
self.clf = LinearRegression()
le = preprocessing.LabelEncoder()
def set_transaction(self, transaction):
self.transaction = transaction
self.output_columns = self.transaction.lmd['predict_columns']
self.input_columns = [
x for x in self.transaction.lmd['columns']
if x not in self.output_columns
]
self.train_df = self.transaction.input_data.train_df
self.test_dt = train_df = self.transaction.input_data.test_df
def train(self):
self.le_arr = {}
for col in [*self.output_columns, *self.input_columns]:
self.le_arr[col] = preprocessing.LabelEncoder()
self.le_arr[col].fit(
pd.concat([
self.transaction.input_data.train_df,
self.transaction.input_data.test_df,
self.transaction.input_data.validation_df
])[col])
X = []
for col in self.input_columns:
X.append(self.le_arr[col].transform(
self.transaction.input_data.train_df[col]))
X = np.swapaxes(X, 1, 0)
# Only works with one output column
Y = self.le_arr[self.output_columns[0]].transform(
self.transaction.input_data.train_df[
self.output_columns[0]])
self.clf.fit(X, Y)
def predict(self, mode='predict', ignore_columns=[]):
if mode == 'predict':
df = self.transaction.input_data.data_frame
if mode == 'validate':
df = self.transaction.input_data.validation_df
elif mode == 'test':
df = self.transaction.input_data.test_df
X = []
for col in self.input_columns:
X.append(self.le_arr[col].transform(df[col]))
X = np.swapaxes(X, 1, 0)
predictions = self.clf.predict(X)
formated_predictions = {self.output_columns[0]: predictions}
return formated_predictions
dt_model = CustomDTModel()
predictor.learn(
to_predict='rental_price',
from_data=
"https://s3.eu-west-2.amazonaws.com/mindsdb-example-data/home_rentals.csv",
backend=dt_model,
use_gpu=False)
predictions = predictor.predict(
when_data=
"https://s3.eu-west-2.amazonaws.com/mindsdb-example-data/home_rentals.csv",
backend=dt_model)
assert predictions