def _gen_xgb_model(model_type: str, xgb_params: dict):
"""generate an xgboost model
Multiple model types that can be estimated using
the XGBoost Scikit-Learn API.
Input can either be a predefined json model configuration or one
of the five xgboost model types: "classifier", "regressor", "ranker",
"rf_classifier", or "rf_regressor".
In either case one can pass in a params dict to modify defaults values.
Based on `mlutils.models.gen_sklearn_model`, see the function
`sklearn_classifier` in this repository.
:param model_type: one of "classifier", "regressor",
"ranker", "rf_classifier", or
"rf_regressor"
:param xgb_params: class init parameters
"""
mtypes = {
"classifier": "xgboost.XGBClassifier",
"regressor": "xgboost.XGBRegressor",
"ranker": "xgboost.XGBRanker",
"rf_classifier": "xgboost.XGBRFClassifier",
"rf_regressor": "xgboost.XGBRFRegressor",
}
if model_type.endswith("json"):
model_config = model_type
elif model_type in mtypes.keys():
model_config = mtypes[model_type]
else:
raise Exception("unrecognized model type, see help documentation")
return gen_sklearn_model(model_config, xgb_params)
def train_model(
context: MLClientCtx,
model_pkg_class: str,
dataset: DataItem,
label_column: str = "labels",
encode_cols: List[str] = [],
sample: int = -1,
test_size: float = 0.30,
train_val_split: float = 0.70,
test_set_key: str = "test_set",
model_evaluator = None,
models_dest: str = "",
plots_dest: str = "plots",
file_ext: str = "parquet",
model_pkg_file: str = "",
random_state: int = 1,
) -> None:
"""train a classifier
An optional cutom model evaluator can be supplied that should have the signature:
`my_custom_evaluator(context, xvalid, yvalid, model)` and return a dictionary of
scalar "results", a "plots" keys with a list of PlotArtifacts, and
and "tables" key containing a returned list of TableArtifacts.
:param context: the function context
:param model_pkg_class: the model to train, e.g, "sklearn.neural_networks.MLPClassifier",
or json model config
:param dataset: ("data") name of raw data file
:param label_column: ground-truth (y) labels
:param encode_cols: dictionary of names and prefixes for columns that are
to hot be encoded.
:param sample: Selects the first n rows, or select a sample
starting from the first. If negative <-1, select
a random sample
:param test_size: (0.05) test set size
:param train_val_split: (0.75) Once the test set has been removed the
training set gets this proportion.
:param test_set_key: key of held out data in artifact store
:param model_evaluator: (None) a custom model evaluator can be specified
:param models_dest: ("") models subfolder on artifact path
:param plots_dest: plot subfolder on artifact path
:param file_ext: ("parquet") format for test_set_key hold out data
:param random_state: (1) sklearn rng seed
"""
models_dest = models_dest or "model"
raw, labels, header = get_sample(dataset, sample, label_column)
if encode_cols:
raw = pd.get_dummies(raw,
columns=list(encode_cols.keys()),
prefix=list(encode_cols.values()),
drop_first=True)
(xtrain, ytrain), (xvalid, yvalid), (xtest, ytest) = get_splits(raw, labels, 3, test_size, 1-train_val_split, random_state)
context.log_dataset(test_set_key,
df=pd.concat([xtest, ytest.to_frame()], axis=1),
format=file_ext, index=False,
labels={"data-type": "held-out"},
artifact_path=context.artifact_subpath('data'))
model_config = gen_sklearn_model(model_pkg_class,
context.parameters.items())
model_config["FIT"].update({"X": xtrain,
"y": ytrain.values})
ClassifierClass = create_class(model_config["META"]["class"])
model = ClassifierClass(**model_config["CLASS"])
model.fit(**model_config["FIT"])
artifact_path = context.artifact_subpath(models_dest)
plots_path = context.artifact_subpath(models_dest, plots_dest)
if model_evaluator:
eval_metrics = model_evaluator(context, xvalid, yvalid, model,
plots_artifact_path=plots_path)
else:
eval_metrics = eval_model_v2(context, xvalid, yvalid, model,
plots_artifact_path=plots_path)
context.set_label('class', model_pkg_class)
context.log_model("model", body=dumps(model),
artifact_path=artifact_path,
extra_data=eval_metrics,
model_file="model.pkl",
metrics=context.results,
labels={"class": model_pkg_class})
def train_model(context: MLClientCtx,
dataset: DataItem,
model_pkg_class: str,
label_column: str = "label",
train_validation_size: float = 0.75,
sample: float = 1.0,
models_dest: str = "models",
test_set_key: str = "test_set",
plots_dest: str = "plots",
dask_key: str = "dask_key",
dask_persist: bool = False,
scheduler_key: str = '',
file_ext: str = "parquet",
random_state: int = 42) -> None:
"""
Train a sklearn classifier with Dask
:param context: Function context.
:param dataset: Raw data file.
:param model_pkg_class: Model to train, e.g, "sklearn.ensemble.RandomForestClassifier",
or json model config.
:param label_column: (label) Ground-truth y labels.
:param train_validation_size: (0.75) Train validation set proportion out of the full dataset.
:param sample: (1.0) Select sample from dataset (n-rows/% of total), randomzie rows as default.
:param models_dest: (models) Models subfolder on artifact path.
:param test_set_key: (test_set) Mlrun db key of held out data in artifact store.
:param plots_dest: (plots) Plot subfolder on artifact path.
:param dask_key: (dask key) Key of dataframe in dask client "datasets" attribute.
:param dask_persist: (False) Should the data be persisted (through the `client.persist`)
:param scheduler_key: (scheduler) Dask scheduler configuration, json also logged as an artifact.
:param file_ext: (parquet) format for test_set_key hold out data
:param random_state: (42) sklearn seed
"""
if scheduler_key:
client = Client(scheduler_key)
else:
client = Client()
context.logger.info("Read Data")
df = dataset.as_df(df_module=dd)
context.logger.info("Prep Data")
numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']
df = df.select_dtypes(include=numerics)
if df.isna().any().any().compute() == True:
raise Exception('NAs valus found')
df_header = df.columns
df = df.sample(frac=sample).reset_index(drop=True)
encoder = LabelEncoder()
encoder = encoder.fit(df[label_column])
X = df.drop(label_column, axis=1).to_dask_array(lengths=True)
y = encoder.transform(df[label_column])
classes = df[label_column].drop_duplicates() # no unique values in dask
classes = [str(i) for i in classes]
context.logger.info("Split and Train")
X_train, X_test, y_train, y_test = model_selection.train_test_split(
X, y, train_size=train_validation_size, random_state=random_state)
scaler = StandardScaler()
scaler = scaler.fit(X_train)
X_train_transformed = scaler.transform(X_train)
X_test_transformed = scaler.transform(X_test)
model_config = gen_sklearn_model(model_pkg_class,
context.parameters.items())
model_config["FIT"].update({"X": X_train_transformed, "y": y_train})
ClassifierClass = create_class(model_config["META"]["class"])
model = ClassifierClass(**model_config["CLASS"])
with joblib.parallel_backend("dask"):
model = model.fit(**model_config["FIT"])
artifact_path = context.artifact_subpath(models_dest)
plots_path = context.artifact_subpath(models_dest, plots_dest)
context.logger.info("Evaluate")
extra_data_dict = {}
for report in (ROCAUC, ClassificationReport, ConfusionMatrix):
report_name = str(report.__name__)
plt.cla()
plt.clf()
plt.close()
viz = report(model, classes=classes, per_class=True, is_fitted=True)
viz.fit(X_train_transformed,
y_train) # Fit the training data to the visualizer
viz.score(X_test_transformed,
y_test.compute()) # Evaluate the model on the test data
plot = context.log_artifact(PlotArtifact(report_name,
body=viz.fig,
title=report_name),
db_key=False)
extra_data_dict[str(report)] = plot
if report_name == 'ROCAUC':
context.log_results({
"micro": viz.roc_auc.get("micro"),
"macro": viz.roc_auc.get("macro")
})
elif report_name == 'ClassificationReport':
for score_name in viz.scores_:
for score_class in viz.scores_[score_name]:
context.log_results({
score_name + "-" + score_class:
viz.scores_[score_name].get(score_class)
})
viz = FeatureImportances(model,
classes=classes,
per_class=True,
is_fitted=True,
labels=df_header.delete(
df_header.get_loc(label_column)))
viz.fit(X_train_transformed, y_train)
viz.score(X_test_transformed, y_test)
plot = context.log_artifact(PlotArtifact("FeatureImportances",
body=viz.fig,
title="FeatureImportances"),
db_key=False)
extra_data_dict[str("FeatureImportances")] = plot
plt.cla()
plt.clf()
plt.close()
context.logger.info("Log artifacts")
artifact_path = context.artifact_subpath(models_dest)
plots_path = context.artifact_subpath(models_dest, plots_dest)
context.set_label('class', model_pkg_class)
context.log_model("model",
body=dumps(model),
artifact_path=artifact_path,
model_file="model.pkl",
extra_data=extra_data_dict,
metrics=context.results,
labels={"class": model_pkg_class})
context.log_artifact("standard_scaler",
body=dumps(scaler),
artifact_path=artifact_path,
model_file="scaler.gz",
label="standard_scaler")
context.log_artifact("label_encoder",
body=dumps(encoder),
artifact_path=artifact_path,
model_file="encoder.gz",
label="label_encoder")
df_to_save = delayed(np.column_stack)((X_test, y_test)).compute()
context.log_dataset(
test_set_key,
df=pd.DataFrame(df_to_save,
columns=df_header), # improve log dataset ability
format=file_ext,
index=False,
labels={"data-type": "held-out"},
artifact_path=context.artifact_subpath('data'))
context.logger.info("Done!")