Module 3 - Machine Learning Deep Dive


Back to Package

Machines learn in different ways and there are several different strategies or methods to apply for a use case in the form of supervised, unsupervised, semi-supervised, and reinforcement learning. Training a machine using basic rules or letting the machine discover patterns independently or using a mix of the two will cover many different problems that can be addressed in an organization.  This module will be a mixture of deep-dive into machine learning types, limitations, and hands-on development of machine learning solutions.

Learning Outcomes
  • Select the appropriate machine learning task for a real-world application
  • Use a dataset to fit a new model  
  • Build a machine learning model based on the business application
  • Use cross-validation for a supervised learning model
  • Assess the model performance in terms by error metrics for each ML task.

Key:

Complete
Failed
Available
Locked
Session 1(Slides & Replay): Dive into Supervised Learning with H2O-3 - Classification & Regression Case Studies
Click on View to access the replay and the slides
Click on View to access the replay and the slides Slides and Replay of our first ML Foundations Course session Module 3.
Classification Case Study Hands-On Assignment in H2O-3 (Part 1)
Select the "Read" button to begin.
Select the "Read" button to begin. This is Part 1 of a 2-part exercise wherein you are required to complete a case study pertaining to classification machine learning problems using the open-source machine learning platform, H2O-3.
Regression Case Study Hands-On Assignment in H2O-3 (Part 2)
Select the "Read" button to begin.
Select the "Read" button to begin. This is Part 2 of a 2-part exercise wherein you are required to complete a case study pertaining to regression machine learning problems using the open-source machine learning platform, H2O-3.
Quiz 1: Supervised Learning with H2O-3
10 Questions  |  3 attempts  |  8/10 points to pass
10 Questions  |  3 attempts  |  8/10 points to pass
Session 2(Slides & Replay): Automated Machine Learning with H2O Driverless AI
Click on View to access the replay and the slides
Click on View to access the replay and the slides Slides and Replay of our second ML Foundations Course session Module 3.
Quiz 2: Automatic Machine Learning with H2O Driverless AI
10 Questions  |  3 attempts  |  8/10 points to pass
10 Questions  |  3 attempts  |  8/10 points to pass
Session 3(Slides & Replay): AutoML with H2O-3
Click on View to access the replay and the slides
Click on View to access the replay and the slides Slides and Replay of our third ML Foundations Course session Module 3.
AutoML Case Study Hands-On Assignment in H2O-3
Select the "Read" button to begin.
Select the "Read" button to begin. This is the hands-on exercise wherein you are required to complete a case study pertaining to supervised machine learning problems using the H2O-3 AutoML.
Quiz 3: AutoML with H2O-3
10 Questions  |  3 attempts  |  8/10 points to pass
10 Questions  |  3 attempts  |  8/10 points to pass
Session 4(Slides and Replay): Dive into Unsupervised Learning with H2O-3 - Clustering
Click on View to access the replay and the slides
Click on View to access the replay and the slides Slides and Replay of our fourth ML Foundations Course session Module 3.
Unsupervised Learning Case Study Hands-On Assignment in H2O-3
Select the "Read" button to begin.
Select the "Read" button to begin. This is the hands-on exercise wherein you are required to complete a case study pertaining to Anomaly Detection with Isolation Forests using H2O-3.
Quiz 4: Dive into Unsupervised Learning with H2O-3 - Clustering
10 Questions  |  3 attempts  |  8/10 points to pass
10 Questions  |  3 attempts  |  8/10 points to pass
You must be logged in to post to the discussion
  • Rs

    Can DAI build Unsupervised Learning models via data recipe URL  and use this labeled data into supervised learning ? 

    Reply
  • RS

    Problem solved with the awasome Terrence !!!

    https://1drv.ms/u/s!AoB9AwPNjo...

    Reply
  • RS

    Please note that:

    1. Unsupervised Learning Case Study Hands-On Assignment in H2O-3

    Contains various errors:

    a. data load is not possible with the instruction

    #Import the dataset df = h2o.import_file("creditcard.csv")

    while can be loaded with

    import h2o
    h2o.init()
    df = "https://www.kaggle.com/mlg-ulb/creditcardfraud"
    df = h2o.import_file(path=df)


    b.

    threshold = quantile_frame[0, "predictQuantiles"]
    predictions["predicted_class"] = predictions["predict"] > threshold
    predictions["class"] = df["Class"]
    predictions

    get the following error:

    --------------------------------------------------------------------------- H2OResponseError Traceback (most recent call last) /opt/conda/envs/h2o/lib/python3.6/site-packages/IPython/core/formatters.py in __call__(self, obj) 700 type_pprinters=self.type_printers, 701 deferred_pprinters=self.deferred_printers) --> 702 printer.pretty(obj) 703 printer.flush() 704 return stream.getvalue() /opt/conda/envs/h2o/lib/python3.6/site-packages/IPython/lib/pretty.py in pretty(self, obj) 392 if cls is not object \ 393 and callable(cls.__dict__.get('__repr__')): --> 394 return _repr_pprint(obj, self, cycle) 395 396 return _default_pprint(obj, self, cycle) /opt/conda/envs/h2o/lib/python3.6/site-packages/IPython/lib/pretty.py in _repr_pprint(obj, p, cycle) 698 """A pprint that just redirects to the normal repr function.""" 699 # Find newlines and replace them with p.break_() --> 700 output = repr(obj) 701 lines = output.splitlines() 702 with p.group(): /opt/conda/envs/h2o/lib/python3.6/site-packages/h2o/frame.py in __repr__(self) 546 stk = traceback.extract_stack() 547 if not ("IPython" in stk[-2][0] and "info" == stk[-2][2]): --> 548 self.show() 549 return "" 550 /opt/conda/envs/h2o/lib/python3.6/site-packages/h2o/frame.py in show(self, use_pandas, rows, cols) 580 print("This H2OFrame is empty.") 581 return --> 582 if not self._ex._cache.is_valid(): self._frame()._ex._cache.fill() 583 if H2ODisplay._in_zep(): 584 print("%html " + self._ex._cache._tabulate("html", False, rows=rows)) /opt/conda/envs/h2o/lib/python3.6/site-packages/h2o/frame.py in _frame(self, rows, rows_offset, cols, cols_offset, fill_cache) 698 699 def _frame(self, rows=10, rows_offset=0, cols=-1, cols_offset=0, fill_cache=False): --> 700 self._ex._eager_frame() 701 if fill_cache: 702 self._ex._cache.fill(rows=rows, rows_offset=rows_offset, cols=cols, cols_offset=cols_offset) /opt/conda/envs/h2o/lib/python3.6/site-packages/h2o/expr.py in _eager_frame(self) 89 if not self._cache.is_empty(): return 90 if self._cache._id is not None: return # Data already computed under ID, but not cached locally ---> 91 self._eval_driver('frame') 92 93 def _eager_scalar(self): # returns a scalar (or a list of scalars) /opt/conda/envs/h2o/lib/python3.6/site-packages/h2o/expr.py in _eval_driver(self, top) 113 """ 114 exec_str = self._get_ast_str(top) --> 115 res = ExprNode.rapids(exec_str) 116 if 'scalar' in res: 117 if isinstance(res['scalar'], list): /opt/conda/envs/h2o/lib/python3.6/site-packages/h2o/expr.py in rapids(expr) 257 :returns: The JSON response (as a python dictionary) of the Rapids execution 258 """ --> 259 return h2o.api("POST /99/Rapids", data={"ast": expr, "session_id": h2o.connection().session_id}) 260 261 /opt/conda/envs/h2o/lib/python3.6/site-packages/h2o/h2o.py in api(endpoint, data, json, filename, save_to) 107 # type checks are performed in H2OConnection class 108 _check_connection() --> 109 return h2oconn.request(endpoint, data=data, json=json, filename=filename, save_to=save_to) 110 111 /opt/conda/envs/h2o/lib/python3.6/site-packages/h2o/backend/connection.py in request(self, endpoint, data, json, filename, save_to) 476 save_to = save_to(resp) 477 self._log_end_transaction(start_time, resp) --> 478 return self._process_response(resp, save_to) 479 480 except (requests.exceptions.ConnectionError, requests.exceptions.HTTPError) as e: /opt/conda/envs/h2o/lib/python3.6/site-packages/h2o/backend/connection.py in _process_response(response, save_to) 822 # Client errors (400 = "Bad Request", 404 = "Not Found", 412 = "Precondition Failed") 823 if status_code in {400, 404, 412} and isinstance(data, (H2OErrorV3, H2OModelBuilderErrorV3)): --> 824 raise H2OResponseError(data) 825 826 # Server errors (notably 500 = "Server Error") H2OResponseError: Server error java.lang.IllegalArgumentException: Error: Column Class not found Request: POST /99/Rapids data: {'ast': "(tmp= py_4_sid_9777 (append transformation_88a4_IsolationForest_model_python_1601839425358_1_on_creditcardfraud.hex (> (cols_py transformation_88a4_IsolationForest_model_python_1601839425358_1_on_creditcardfraud.hex 'predict') 0.9706984667802384) 'predicted_class' (cols_py creditcardfraud.hex 'Class') 'class'))", 'session_id': '_sid_9777'}
    Reply
  • RS

    There is apparently no way to finish this one:

    AutoML Case Study Hands-On Assignment in H2O-3

    in 2 hours... Even clicking one cell / flow after the other without interruption due to the algo. training time...

    Reply
  • RS

    Quiz 1: Supervised Learning with H2O

    It is possible to have 3 attempts here too ?

    Reply
  • FV

    Hi Rino, the number of attempts have been updated for this quiz too. 

    Reply
  • RS

    Thanks a lot...

  • FV

    Hi Everyone, 

    Quiz 2 and 3 have been posted. Also, from now on you will get 3 attempts per quiz. 

    Reply
  • RS

    I think now the session is gone... let's hope for tomorrow !

    Reply
  • TR

    I tried Chrome and Firefox 1f626.png

    Reply
  • RS

    Same on Edge Browser...

    Reply
  • TR

    Same here:  

    Zoom API Error: User does not exist: terrence_rideau@yahoo.com.

    Sorry, you do not have permission to access /webinar/187782 with Request method: GET

    Reply
  • MM

    Hi, same here...

    Reply
  • RS

    Cannot join: error

    Zoom API Error: User does not exist: r.simeone@mclink.it.

    Sorry, you do not have permission to access /webinar/187782 with Request method: GET

    Reply
  • SM

    Hands on Session on H2O-3 is incomplete please see to it.

    Reply
  • FV

    All,

    The Quiz and hands-on assignments for Session 1 have been posted. Also, the labs in Aquarium are now available for you to complete the hands-on assignments. 

    Reply
  • AG

    Hi Team,

    Session is Live Now.

    Thank You.

    Reply
  • AG

    Hi Team,

    Today session timings.

    As In Zoom its showing 10:30 PM IST.

    Please confirm the lecture timings.

    Reply
  • TR

    I am trying to install H2O in Anaconda in Windows using the following command "conda install -c h2oai h2o"

    I got this following error:

    Collecting package metadata (current_repodata.json): failed

    CondaHTTPError: HTTP 000 CONNECTION FAILED for url
    Elapsed: -

    An HTTP error occurred when trying to retrieve this URL.
    HTTP errors are often intermittent, and a simple retry will get you on your way.
    'https://conda.anaconda.org/h2oai/win-64'

    Anyone having or have seen this issue before?

    Reply
  • FV

    Hi Terrence, did you create an anaconda environment and ran the following line?

    conda config --append channels conda-forge

    Also, make sure to have a JDK version (previous versions to version 15) installed before you try to install H2O-3

    Reply