update samples from Release-141 as a part of 1.0.57 SDK release

how-to-use-azureml/work-with-data/datasets/datasets-tutorial/train-dataset/train.py

@@ -0,0 +1,43 @@
+import azureml.dataprep as dprep
+import azureml.core
+import pandas as pd
+import logging
+import os
+import datetime
+import shutil
+
+from azureml.core import Workspace, Datastore, Dataset, Experiment, Run
+from sklearn.model_selection import train_test_split
+from azureml.core.compute import ComputeTarget, AmlCompute
+from azureml.core.compute_target import ComputeTargetException
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.externals import joblib
+
+run = Run.get_context()
+workspace = run.experiment.workspace
+
+dataset_name = 'titanic dataset'
+
+dataset = Dataset.get_by_name(workspace=workspace, name=dataset_name)
+df = dataset.to_pandas_dataframe()
+
+x_col = ['Pclass', 'Sex', 'SibSp', 'Parch']
+y_col = ['Survived']
+x_df = df.loc[:, x_col]
+y_df = df.loc[:, y_col]
+
+x_train, x_test, y_train, y_test = train_test_split(x_df, y_df, test_size=0.2, random_state=223)
+
+data = {"train": {"X": x_train, "y": y_train},
+
+        "test": {"X": x_test, "y": y_test}}
+
+clf = DecisionTreeClassifier().fit(data["train"]["X"], data["train"]["y"])
+model_file_name = 'decision_tree.pkl'
+
+print('Accuracy of Decision Tree classifier on training set: {:.2f}'.format(clf.score(x_train, y_train)))
+print('Accuracy of Decision Tree classifier on test set: {:.2f}'.format(clf.score(x_test, y_test)))
+
+os.makedirs('./outputs', exist_ok=True)
+with open(model_file_name, "wb") as file:
+    joblib.dump(value=clf, filename='outputs/' + model_file_name)