def train_digits():
digits = load_digits()
X_train, X_test, y_train, y_test = train_test_split(pd.DataFrame(
digits.data),
digits.target,
stratify=digits.target,
test_size=0.25,
random_state=123)
# train models with AutoML
automl = AutoML(mode="Perform", results_path="AutoML_digits")
automl.fit(X_train, y_train)
# compute
predictions = automl.predict_all(X_test)
print(predictions.head())
print("Test accuracy:",
accuracy_score(y_test, predictions["label"].astype(int)))
plot_digits(X_test, predictions)
import numpy as np
import pandas as pd
from supervised.automl import AutoML
from sklearn.model_selection import train_test_split
import os
from sklearn.metrics import log_loss
import warnings
# warnings.filterwarnings("error", category=RuntimeWarning) #pd.core.common.SettingWithCopyWarning)
df = pd.read_csv(
"https://raw.githubusercontent.com/pplonski/datasets-for-start/master/adult/data.csv",
skipinitialspace=True,
)
X = df[df.columns[:-1]]
y = df["income"]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
automl = AutoML(results_path="AutoML_7", mode="Compete")
automl.fit(X_train, y_train)
predictions = automl.predict_all(X_test)
print(predictions.head())
print(predictions.tail())
print(X_test.shape, predictions.shape)
print("LogLoss", log_loss(y_test, predictions["prediction_>50K"]))
def run(dataset, config):
log.info(f"\n**** mljar-supervised [v{supervised.__version__}] ****\n")
save_metadata(config, version=supervised.__version__)
# Mapping of benchmark metrics to MLJAR metrics
metrics_mapping = dict(auc='auc', logloss='logloss', rmse='rmse')
eval_metric = metrics_mapping[
config.metric] if config.metric in metrics_mapping else "auto"
# Mapping of benchmark task to MLJAR ML task
problem_mapping = dict(
binary="binary_classification",
multiclass="multiclass_classification",
regression="regression",
)
ml_task = problem_mapping.get(
dataset.problem_type
) # if None the AutoML will guess about the ML task
is_classification = config.type == "classification"
results_path = output_subdir("results", config)
training_params = {
k: v
for k, v in config.framework_params.items() if not k.startswith("_")
}
column_names, _ = zip(*dataset.columns)
column_types = dict(dataset.columns)
label = dataset.target.name
train = pd.DataFrame(dataset.train.data,
columns=column_names).astype(column_types, copy=False)
X_train = train.drop(columns=label)
y_train = train[label]
test = pd.DataFrame(dataset.test.data,
columns=column_names).astype(column_types, copy=False)
X_test = test.drop(columns=label)
y_test = test[label]
automl = AutoML(results_path=results_path,
total_time_limit=config.max_runtime_seconds,
random_state=config.seed,
ml_task=ml_task,
eval_metric=eval_metric,
**training_params)
with utils.Timer() as training:
automl.fit(X_train, y_train)
with utils.Timer() as predict:
preds = automl.predict_all(X_test)
predictions, probabilities = None, None
if is_classification:
predictions = preds["label"].values
cols = [f"prediction_{c}" for c in np.unique(y_train)]
probabilities = preds[cols].values
else:
predictions = preds["prediction"].values
# clean the results
if not config.framework_params.get("_save_artifacts", False):
shutil.rmtree(results_path, ignore_errors=True)
return result(output_file=config.output_predictions_file,
predictions=predictions,
truth=y_test,
probabilities=probabilities,
models_count=len(automl._models),
training_duration=training.duration,
predict_duration=predict.duration)
import numpy as np
import pandas as pd
from supervised.automl import AutoML
from sklearn.metrics import accuracy_score
import os
nrows = 100
ncols = 3
X = np.random.rand(nrows, ncols)
X = pd.DataFrame(X, columns=[f"f{i}" for i in range(ncols)])
#y = np.random.randint(0, 2, nrows)
y = np.random.permutation(["a", "B"] * 50)
automl = AutoML(model_time_limit=10) #, algorithms=["Decision Tree"])
automl.fit(X, y)
print("Train accuracy", accuracy_score(y, automl.predict_all(X)["label"]))
#X = np.random.rand(1000, 10)
#X = pd.DataFrame(X, columns=[f"f{i}" for i in range(10)])
#y = np.random.randint(0, 2, 1000)
#print("Test accuracy", accuracy_score(y, automl.predict(X)["label"]))
y = df["Survived"]
for col in df.columns:
print(col, df[col].dtype)
automl = AutoML(
results_path="AutoML_39",
# algorithms=["Xgboost"],
# model_time_limit=20,
# train_ensemble=True,
mode="Explain"
)
# automl.set_advanced(start_random_models=3)
automl.fit(X, y)
pred = automl.predict_all(X)
print("Train accuracy", accuracy_score(y, pred["label"]))
test = pd.read_csv("tests/data/Titanic/test_with_Survived.csv")
test_cols = [
"Parch",
"Ticket",
"Fare",
"Pclass",
"Name",
"Sex",
"Age",
"SibSp",
"Cabin",
"Embarked",
def run(dataset, config):
log.info(f"\n**** mljar-supervised [v{supervised.__version__}] ****\n")
# Mapping of benchmark metrics to MLJAR metrics
metrics_mapping = dict(auc='auc', logloss='logloss', rmse='rmse')
eval_metric = metrics_mapping[
config.metric] if config.metric in metrics_mapping else "auto"
# Mapping of benchmark task to MLJAR ML task
problem_mapping = dict(
binary="binary_classification",
multiclass="multiclass_classification",
regression="regression",
)
ml_task = problem_mapping.get(
dataset.problem_type
) # if None the AutoML will guess about the ML task
is_classification = config.type == "classification"
results_path = output_subdir("results", config)
training_params = {
k: v
for k, v in config.framework_params.items() if not k.startswith("_")
}
X_train, y_train = dataset.train.X, dataset.train.y.squeeze()
X_test, y_test = dataset.test.X, dataset.test.y.squeeze()
automl = AutoML(results_path=results_path,
total_time_limit=config.max_runtime_seconds,
random_state=config.seed,
ml_task=ml_task,
eval_metric=eval_metric,
**training_params)
with Timer() as training:
automl.fit(X_train, y_train)
with Timer() as predict:
preds = automl.predict_all(X_test)
predictions, probabilities, probabilities_labels = None, None, None
if is_classification:
# preds is a dataframe with columns ["prediction_LABEL", .., "label"]
if y_train.dtype == bool and preds["label"].dtype == int:
# boolean target produces integer predictions for mljar-supervised <= 0.10.6
# https://github.com/mljar/mljar-supervised/issues/442
preds = preds.rename(
{
"prediction_0": "False",
"prediction_1": "True"
}, axis=1)
preds["label"] = preds["label"].astype(bool)
else:
preds.columns = [
c.replace("prediction_", "", 1) for c in preds.columns
]
predictions = preds["label"].values
probabilities_labels = list(preds.columns)[:-1]
probabilities = preds[probabilities_labels].values
else:
predictions = preds["prediction"].values
# clean the results
if not config.framework_params.get("_save_artifacts", False):
shutil.rmtree(results_path, ignore_errors=True)
return result(output_file=config.output_predictions_file,
predictions=predictions,
truth=y_test,
probabilities=probabilities,
probabilities_labels=probabilities_labels,
models_count=len(automl._models),
training_duration=training.duration,
predict_duration=predict.duration)
import warnings
from sklearn import datasets
from sklearn.pipeline import make_pipeline
from sklearn.decomposition import PCA
from supervised import AutoML
from supervised.exceptions import AutoMLException
# warnings.filterwarnings('error')
warnings.filterwarnings(
"error",
category=pd.core.common.SettingWithCopyWarning) # message="*ndarray*")
df = pd.read_csv("tests/data/iris_missing_values_missing_target.csv")
X = df[["feature_1", "feature_2", "feature_3", "feature_4"]]
y = df["class"]
automl = AutoML()
automl.fit(X, y)
predictions = automl.predict_all(X)
print(predictions.head())
print(predictions.tail())
print(X.shape)
print(predictions.shape)