microsoftdocs/ml-basics

Exercise notebooks for Machine Learning modules on Microsoft Learn

Machine Learning Basics

This repository contains the exercise files for the Create machine learning models learning path on Microsoft Learn.

Contributing

We are not currently accepting external contributions for this repo. If you encounter any problems, please report an issue.

ml-basics's Issues

Feature request: html repr of pipeline

Thanks for the course. You may have this later i'm only up to 02.

You may want to add the html repr functionally to visualize the scikit-learn pipeplines

https://scikit-learn.org/stable/modules/compose.html#visualizing-composite-estimators

https://scikit-learn.org/stable/auto_examples/compose/plot_column_transformer_mixed_types.html#html-representation-of-pipeline

Small bug in displaying groupby with pandas data frame

So in 01 - Data Exploration.ipynb notebook we have
print(df_students.groupby(df_students.Pass)['StudyHours', 'Grade'].mean()) , but this gives an error below.
ValueError: Cannot subset columns with a tuple with more than one element. Use a list instead.

Solution:

Change it to print(df_students.groupby(df_students.Pass)[['StudyHours', 'Grade']].mean()) to fix and resolve it.

Note:
A very small but important fix.

cannot import name 'export_text' in sklearn.tree

I am getting an error in this code snippet:

from sklearn.tree import DecisionTreeRegressor
from sklearn.tree import export_text

# Train the model
model = DecisionTreeRegressor().fit(X_train, y_train)
print (model, "\n")

# Visualize the model tree
tree = export_text(model)
print(tree)

Error:

---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
<ipython-input-17-58c166972779> in <module>
      1 from sklearn.tree import DecisionTreeRegressor
----> 2 from sklearn.tree import export_text
      3 
      4 # Train the model
      5 model = DecisionTreeRegressor().fit(X_train, y_train)

ImportError: cannot import name 'export_text'

Small bug in Notebook

Found a small bug in '05a - Deep Neural Networks (TensorFlow)'.
First notebook cell:

# The dataset is too small to be useful for deep learning
# So we'll oversample it to triple its size
for i in range(1,3):
    penguins = penguins.append(penguins)

This is not correct, as this will not triple its size.

Possible Fix:

# The dataset is too small to be useful for deep learning
# So we'll oversample it to triple its size
penguins_3x = pd.DataFrame()
for i in range(3):
    penguins_3x = penguins_3x.append(penguins)
penguins = penguins_3x

Feature request: a requirements file

https://github.com/MicrosoftDocs/ml-basics/blob/master/local-setup.md states which packages to use. It would be helpful to provide a requirements file in either a .txt for .yaml form to simplify package installation.

Outlier removal in Flight solutions

Hello team,

I need a small explanation regarding this code section in the Flight solutions in the Challenges folder.

• First, we are calculating the quantile of ArrDelay then removing it. And, then calculating the quantile of DepDelay and removing it. Wouldnt it affects the calculation? Is this the correct way? Try changing the sequences like the below image. It changes the stats.

• Shouldn't be like this?
  

Thank you !

Small incorrect Penguin species name in Notebook Classification.ipynb

Hi Team,
Isn't issue, but just that I love penguin and I found incorrect species name :
penguin_classes = ['Amelie', 'Gentoo', 'Chinstrap']
Is Adelie and not Amelie :)

Regards,
Faiçal

Chintan

The torch deep learning model should not use softmax last layer + CrossEntropyLoss

Torch CrossEntropyLoss expects logits instead of normalized probabilities.

Error in Data Exploration.ipynb notebook

When I try to run the cells 32: print(df_students.groupby(df_students.Pass).Name.count()) and cell 33: print(df_students.groupby(df_students.Pass)['StudyHours', 'Grade'].mean())
I get this error: ValueError: Grouper for '<class 'pandas.core.frame.DataFrame'>' not 1-dimensional

I am using the Python 3.6 - AzureML Kernel.

Thank you

typo - cell 10 - 05b - Convolutional Neural Networks (Tensorflow).ipynb

There's a typo on cell 10 at 05b - Convolutional Neural Networks (Tensorflow).ipynb:

Note: We're only using 5 epochs to minimze the training [...]

Should be:

Note: We're only using 5 epochs to minimize the training [...]

Test data leakage in step 05a (PyTorch and Tensorflow)

The two notebooks 05a - Deep Neural Networks (PyTorch).ipynb and 05a - Deep Neural Networks (TensorFlow).ipynb contain the following piece of code:

	 # The dataset is too small to be useful for deep learning
	 # So we'll oversample it to increase its size
	 for i in range(1,3):
		 penguins = penguins.append(penguins)

This creates a new dataframe that contains four copies of each row of the original dataframe. Since this happens before the training/test split, the probability of a row of the original dataframe to be present in both training and test set is approximately 0.75. In other words, one can expect 3/4 of the original rows to be present in both sets.

This constitutes a leakage of information from the test set into the training set, which renders the test set incapable of assessing the generalization capability of the trained model. In the case of the penguin toy dataset, this does not matter much: The three species appear to be well-separated in feature space, so that overfitting is not an immediate concern. Still, mixing training and test data is bad practice and should not be taught to ML beginners.

I therefore suggest the removal of the piece of code shown above. Since the model is no longer exposed to multiple copies of each row in one epoch of training, the number of epochs has to be increased to achieve the same test set accuracy. Training for 100 instead of 50 epochs worked well in my tests.

Typo code cell #57 notebook "01 - Data Exploration"

"Grade vs Salary" comment should be "Grade vs StudyHours"

CNN w/ TensorFlow: Link to challenge not valid

The link to the challenge is not valid anymore and goes to '404 - page not found'.

Unable to run the labs

Hi,

I have followed the steps as mentioned. However, when I try opening any of the ipynb files, I see a message saying reconnecting to kernel and that never happens. I am unable to continue. Could you please help? Am I missing anything?

05c - OOM

Running

base_model = keras.applications.resnet.ResNet50(weights='imagenet', include_top=False, input_shape=(224,224,3))

Gives
InternalError: CUDA runtime implicit initialization on GPU:0 failed. Status: out of memory

Full Traceback and enviornment below

TensorFlow version: 2.3.1
Keras version: 2.4.0

Note i'm running locally and I do have a GPU so not sure if that is the cause

---------------------------------------------------------------------------
InternalError                             Traceback (most recent call last)
<ipython-input-4-50b0035545e7> in <module>
----> 1 base_model = keras.applications.resnet.ResNet50(weights='imagenet', include_top=False, input_shape=(224,224,3))
      2 print(base_model.summary())

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/keras/applications/resnet.py in ResNet50(include_top, weights, input_tensor, input_shape, pooling, classes, **kwargs)
    473 
    474   return ResNet(stack_fn, False, True, 'resnet50', include_top, weights,
--> 475                 input_tensor, input_shape, pooling, classes, **kwargs)
    476 
    477 

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/keras/applications/resnet.py in ResNet(stack_fn, preact, use_bias, model_name, include_top, weights, input_tensor, input_shape, pooling, classes, classifier_activation, **kwargs)
    169   x = layers.ZeroPadding2D(
    170       padding=((3, 3), (3, 3)), name='conv1_pad')(img_input)
--> 171   x = layers.Conv2D(64, 7, strides=2, use_bias=use_bias, name='conv1_conv')(x)
    172 
    173   if not preact:

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
    924     if _in_functional_construction_mode(self, inputs, args, kwargs, input_list):
    925       return self._functional_construction_call(inputs, args, kwargs,
--> 926                                                 input_list)
    927 
    928     # Maintains info about the `Layer.call` stack.

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in _functional_construction_call(self, inputs, args, kwargs, input_list)
   1096         # Build layer if applicable (if the `build` method has been
   1097         # overridden).
-> 1098         self._maybe_build(inputs)
   1099         cast_inputs = self._maybe_cast_inputs(inputs, input_list)
   1100 

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in _maybe_build(self, inputs)
   2641         # operations.
   2642         with tf_utils.maybe_init_scope(self):
-> 2643           self.build(input_shapes)  # pylint:disable=not-callable
   2644       # We must set also ensure that the layer is marked as built, and the build
   2645       # shape is stored since user defined build functions may not be calling

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/keras/layers/convolutional.py in build(self, input_shape)
    202         constraint=self.kernel_constraint,
    203         trainable=True,
--> 204         dtype=self.dtype)
    205     if self.use_bias:
    206       self.bias = self.add_weight(

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in add_weight(self, name, shape, dtype, initializer, regularizer, trainable, constraint, partitioner, use_resource, synchronization, aggregation, **kwargs)
    612         synchronization=synchronization,
    613         aggregation=aggregation,
--> 614         caching_device=caching_device)
    615     if regularizer is not None:
    616       # TODO(fchollet): in the future, this should be handled at the

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/training/tracking/base.py in _add_variable_with_custom_getter(self, name, shape, dtype, initializer, getter, overwrite, **kwargs_for_getter)
    748         dtype=dtype,
    749         initializer=initializer,
--> 750         **kwargs_for_getter)
    751 
    752     # If we set an initializer and the variable processed it, tracking will not

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer_utils.py in make_variable(name, shape, dtype, initializer, trainable, caching_device, validate_shape, constraint, use_resource, collections, synchronization, aggregation, partitioner)
    143       synchronization=synchronization,
    144       aggregation=aggregation,
--> 145       shape=variable_shape if variable_shape else None)
    146 
    147 

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/ops/variables.py in __call__(cls, *args, **kwargs)
    258   def __call__(cls, *args, **kwargs):
    259     if cls is VariableV1:
--> 260       return cls._variable_v1_call(*args, **kwargs)
    261     elif cls is Variable:
    262       return cls._variable_v2_call(*args, **kwargs)

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/ops/variables.py in _variable_v1_call(cls, initial_value, trainable, collections, validate_shape, caching_device, name, variable_def, dtype, expected_shape, import_scope, constraint, use_resource, synchronization, aggregation, shape)
    219         synchronization=synchronization,
    220         aggregation=aggregation,
--> 221         shape=shape)
    222 
    223   def _variable_v2_call(cls,

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/ops/variables.py in <lambda>(**kwargs)
    197                         shape=None):
    198     """Call on Variable class. Useful to force the signature."""
--> 199     previous_getter = lambda **kwargs: default_variable_creator(None, **kwargs)
    200     for _, getter in ops.get_default_graph()._variable_creator_stack:  # pylint: disable=protected-access
    201       previous_getter = _make_getter(getter, previous_getter)

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/ops/variable_scope.py in default_variable_creator(next_creator, **kwargs)
   2595         synchronization=synchronization,
   2596         aggregation=aggregation,
-> 2597         shape=shape)
   2598   else:
   2599     return variables.RefVariable(

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/ops/variables.py in __call__(cls, *args, **kwargs)
    262       return cls._variable_v2_call(*args, **kwargs)
    263     else:
--> 264       return super(VariableMetaclass, cls).__call__(*args, **kwargs)
    265 
    266 

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/ops/resource_variable_ops.py in __init__(self, initial_value, trainable, collections, validate_shape, caching_device, name, dtype, variable_def, import_scope, constraint, distribute_strategy, synchronization, aggregation, shape)
   1516           aggregation=aggregation,
   1517           shape=shape,
-> 1518           distribute_strategy=distribute_strategy)
   1519 
   1520   def _init_from_args(self,

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/ops/resource_variable_ops.py in _init_from_args(self, initial_value, trainable, collections, caching_device, name, dtype, constraint, synchronization, aggregation, distribute_strategy, shape)
   1649           with ops.name_scope("Initializer"), device_context_manager(None):
   1650             initial_value = ops.convert_to_tensor(
-> 1651                 initial_value() if init_from_fn else initial_value,
   1652                 name="initial_value", dtype=dtype)
   1653           if shape is not None:

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/keras/initializers/initializers_v2.py in __call__(self, shape, dtype)
    395        (via `tf.keras.backend.set_floatx(float_dtype)`)
    396     """
--> 397     return super(VarianceScaling, self).__call__(shape, dtype=_get_dtype(dtype))
    398 
    399 

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/ops/init_ops_v2.py in __call__(self, shape, dtype)
    559     else:
    560       limit = math.sqrt(3.0 * scale)
--> 561       return self._random_generator.random_uniform(shape, -limit, limit, dtype)
    562 
    563   def get_config(self):

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/ops/init_ops_v2.py in random_uniform(self, shape, minval, maxval, dtype)
   1042       op = random_ops.random_uniform
   1043     return op(
-> 1044         shape=shape, minval=minval, maxval=maxval, dtype=dtype, seed=self.seed)
   1045 
   1046   def truncated_normal(self, shape, mean, stddev, dtype):

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/util/dispatch.py in wrapper(*args, **kwargs)
    199     """Call target, and fall back on dispatchers if there is a TypeError."""
    200     try:
--> 201       return target(*args, **kwargs)
    202     except (TypeError, ValueError):
    203       # Note: convert_to_eager_tensor currently raises a ValueError, not a

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/ops/random_ops.py in random_uniform(shape, minval, maxval, dtype, seed, name)
    286     maxval = 1
    287   with ops.name_scope(name, "random_uniform", [shape, minval, maxval]) as name:
--> 288     shape = tensor_util.shape_tensor(shape)
    289     # In case of [0,1) floating results, minval and maxval is unused. We do an
    290     # `is` comparison here since this is cheaper than isinstance or  __eq__.

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/framework/tensor_util.py in shape_tensor(shape)
   1027       # not convertible to Tensors because of mixed content.
   1028       shape = tuple(map(tensor_shape.dimension_value, shape))
-> 1029   return ops.convert_to_tensor(shape, dtype=dtype, name="shape")
   1030 
   1031 

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/framework/ops.py in convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, dtype_hint, ctx, accepted_result_types)
   1497 
   1498     if ret is None:
-> 1499       ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
   1500 
   1501     if ret is NotImplemented:

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/framework/constant_op.py in _constant_tensor_conversion_function(v, dtype, name, as_ref)
    336                                          as_ref=False):
    337   _ = as_ref
--> 338   return constant(v, dtype=dtype, name=name)
    339 
    340 

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/framework/constant_op.py in constant(value, dtype, shape, name)
    262   """
    263   return _constant_impl(value, dtype, shape, name, verify_shape=False,
--> 264                         allow_broadcast=True)
    265 
    266 

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/framework/constant_op.py in _constant_impl(value, dtype, shape, name, verify_shape, allow_broadcast)
    273       with trace.Trace("tf.constant"):
    274         return _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
--> 275     return _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
    276 
    277   g = ops.get_default_graph()

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/framework/constant_op.py in _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
    298 def _constant_eager_impl(ctx, value, dtype, shape, verify_shape):
    299   """Implementation of eager constant."""
--> 300   t = convert_to_eager_tensor(value, ctx, dtype)
    301   if shape is None:
    302     return t

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/framework/constant_op.py in convert_to_eager_tensor(value, ctx, dtype)
     95     except AttributeError:
     96       dtype = dtypes.as_dtype(dtype).as_datatype_enum
---> 97   ctx.ensure_initialized()
     98   return ops.EagerTensor(value, ctx.device_name, dtype)
     99 

~/local/bin/anaconda3/envs/ml-basics/lib/python3.7/site-packages/tensorflow/python/eager/context.py in ensure_initialized(self)
    537         if self._use_tfrt is not None:
    538           pywrap_tfe.TFE_ContextOptionsSetTfrt(opts, self._use_tfrt)
--> 539         context_handle = pywrap_tfe.TFE_NewContext(opts)
    540       finally:
    541         pywrap_tfe.TFE_DeleteContextOptions(opts)

InternalError: CUDA runtime implicit initialization on GPU:0 failed. Status: out of memory

(ml-basics) ray@ray-MS-7B43:~$ conda list
# packages in environment at /home/ray/local/bin/anaconda3/envs/ml-basics:
#
# Name                    Version                   Build  Channel
_libgcc_mutex             0.1                        main  
absl-py                   0.10.0                   pypi_0    pypi
argon2-cffi               20.1.0                   pypi_0    pypi
astunparse                1.6.3                    pypi_0    pypi
async-generator           1.10                     pypi_0    pypi
attrs                     20.2.0                   pypi_0    pypi
backcall                  0.2.0                    pypi_0    pypi
bleach                    3.2.1                    pypi_0    pypi
ca-certificates           2020.7.22                     0  
cachetools                4.1.1                    pypi_0    pypi
certifi                   2020.6.20                py37_0  
cffi                      1.14.3                   pypi_0    pypi
chardet                   3.0.4                    pypi_0    pypi
cycler                    0.10.0                   pypi_0    pypi
decorator                 4.4.2                    pypi_0    pypi
defusedxml                0.6.0                    pypi_0    pypi
entrypoints               0.3                      pypi_0    pypi
future                    0.18.2                   pypi_0    pypi
gast                      0.3.3                    pypi_0    pypi
google-auth               1.22.1                   pypi_0    pypi
google-auth-oauthlib      0.4.1                    pypi_0    pypi
google-pasta              0.2.0                    pypi_0    pypi
grpcio                    1.32.0                   pypi_0    pypi
h5py                      2.10.0                   pypi_0    pypi
idna                      2.10                     pypi_0    pypi
imageio                   2.9.0                    pypi_0    pypi
importlib-metadata        2.0.0                    pypi_0    pypi
ipykernel                 5.3.4                    pypi_0    pypi
ipython                   7.18.1                   pypi_0    pypi
ipython-genutils          0.2.0                    pypi_0    pypi
ipywidgets                7.5.1                    pypi_0    pypi
jedi                      0.17.2                   pypi_0    pypi
jinja2                    2.11.2                   pypi_0    pypi
joblib                    0.17.0                   pypi_0    pypi
jsonschema                3.2.0                    pypi_0    pypi
jupyter                   1.0.0                    pypi_0    pypi
jupyter-client            6.1.7                    pypi_0    pypi
jupyter-console           6.2.0                    pypi_0    pypi
jupyter-core              4.6.3                    pypi_0    pypi
jupyterlab-pygments       0.1.2                    pypi_0    pypi
keras-preprocessing       1.1.2                    pypi_0    pypi
kiwisolver                1.2.0                    pypi_0    pypi
ld_impl_linux-64          2.33.1               h53a641e_7  
libedit                   3.1.20191231         h14c3975_1  
libffi                    3.3                  he6710b0_2  
libgcc-ng                 9.1.0                hdf63c60_0  
libstdcxx-ng              9.1.0                hdf63c60_0  
markdown                  3.3.1                    pypi_0    pypi
markupsafe                1.1.1                    pypi_0    pypi
matplotlib                3.3.2                    pypi_0    pypi
mistune                   0.8.4                    pypi_0    pypi
nbclient                  0.5.0                    pypi_0    pypi
nbconvert                 6.0.7                    pypi_0    pypi
nbformat                  5.0.7                    pypi_0    pypi
ncurses                   6.2                  he6710b0_1  
nest-asyncio              1.4.1                    pypi_0    pypi
networkx                  2.5                      pypi_0    pypi
notebook                  6.1.4                    pypi_0    pypi
oauthlib                  3.1.0                    pypi_0    pypi
openssl                   1.1.1h               h7b6447c_0  
opt-einsum                3.3.0                    pypi_0    pypi
packaging                 20.4                     pypi_0    pypi
pandas                    1.1.3                    pypi_0    pypi
pandocfilters             1.4.2                    pypi_0    pypi
parso                     0.7.1                    pypi_0    pypi
pexpect                   4.8.0                    pypi_0    pypi
pickleshare               0.7.5                    pypi_0    pypi
pillow                    7.2.0                    pypi_0    pypi
pip                       20.2.3                   py37_0  
prometheus-client         0.8.0                    pypi_0    pypi
prompt-toolkit            3.0.8                    pypi_0    pypi
protobuf                  3.13.0                   pypi_0    pypi
ptyprocess                0.6.0                    pypi_0    pypi
pyasn1                    0.4.8                    pypi_0    pypi
pyasn1-modules            0.2.8                    pypi_0    pypi
pycparser                 2.20                     pypi_0    pypi
pygments                  2.7.1                    pypi_0    pypi
pyparsing                 2.4.7                    pypi_0    pypi
pyrsistent                0.17.3                   pypi_0    pypi
python                    3.7.9                h7579374_0  
python-dateutil           2.8.1                    pypi_0    pypi
pytz                      2020.1                   pypi_0    pypi
pywavelets                1.1.1                    pypi_0    pypi
pyzmq                     19.0.2                   pypi_0    pypi
qtconsole                 4.7.7                    pypi_0    pypi
qtpy                      1.9.0                    pypi_0    pypi
readline                  8.0                  h7b6447c_0  
requests                  2.24.0                   pypi_0    pypi
requests-oauthlib         1.3.0                    pypi_0    pypi
rsa                       4.6                      pypi_0    pypi
scikit-image              0.17.2                   pypi_0    pypi
scikit-learn              0.23.2                   pypi_0    pypi
scipy                     1.5.2                    pypi_0    pypi
send2trash                1.5.0                    pypi_0    pypi
setuptools                50.3.0           py37hb0f4dca_1  
sqlite                    3.33.0               h62c20be_0  
tensorboard               2.3.0                    pypi_0    pypi
tensorboard-plugin-wit    1.7.0                    pypi_0    pypi
tensorflow                2.3.1                    pypi_0    pypi
tensorflow-estimator      2.3.0                    pypi_0    pypi
termcolor                 1.1.0                    pypi_0    pypi
terminado                 0.9.1                    pypi_0    pypi
testpath                  0.4.4                    pypi_0    pypi
threadpoolctl             2.1.0                    pypi_0    pypi
tifffile                  2020.10.1                pypi_0    pypi
tk                        8.6.10               hbc83047_0  
torch                     1.6.0+cpu                pypi_0    pypi
torchvision               0.7.0+cpu                pypi_0    pypi
tornado                   6.0.4                    pypi_0    pypi
traitlets                 5.0.4                    pypi_0    pypi
urllib3                   1.25.10                  pypi_0    pypi
wcwidth                   0.2.5                    pypi_0    pypi
webencodings              0.5.1                    pypi_0    pypi
werkzeug                  1.0.1                    pypi_0    pypi
wheel                     0.35.1                     py_0  
widgetsnbextension        3.5.1                    pypi_0    pypi
wrapt                     1.12.1                   pypi_0    pypi
xz                        5.2.5                h7b6447c_0  
zipp                      3.3.0                    pypi_0    pypi
zlib                      1.2.11               h7b6447c_3  

02 - why normalize=False in LinearRegression

In https://github.com/MicrosoftDocs/ml-basics/blob/master/02%20-%20Regression.ipynb

you have model = LinearRegression(normalize=False).fit(X_train, y_train). I'm curious what the normalize=False does. Would you mind explaining in the notebook?

Swapped axes on heatmap in classification notebook

The axes on the heatmap in the classification notebook are incorrect. Predicted species should be on the horizontal axis and actual species should be on the vertical axis. The scikit-learn documentation for the confusion matrix states that it returns "Confusion matrix whose i-th row and j-th column entry indicates the number of samples with true label being i-th class and prediced label being j-th class."

Need more explaination and reasoning for the code samples, not useless comments

I'm a beginner, trying to teach myself machine learning. It is frustrating to the read comments that are just useless english translation the code, which the code already showing. Look at the sample below from the "05b-Convolutional Neural Network (PyTorch).ipynb" file, where I added comments indicating the more meaningful comments would actually provide some meaningful values to help with the learning.

# Create a neural net class
class Net(nn.Module):
    # Constructor
    def __init__(self, num_classes=3):
        super(Net, self).__init__()
        
        # Our images are RGB, so input channels = 3. We'll apply 12 filters in the first convolutional layer
#explain why 12 filters
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=3, stride=1, padding=1)
        
        # We'll apply max pooling with a kernel size of 2
#explain why using max pooling of kernel size of 2
        self.pool = nn.MaxPool2d(kernel_size=2)
        
        # A second convolutional layer takes 12 input channels, and generates 12 outputs
        self.conv2 = nn.Conv2d(in_channels=12, out_channels=12, kernel_size=3, stride=1, padding=1)
        
        # A third convolutional layer takes 12 inputs and generates 24 outputs
#explain why gernerates 24 outputs
        self.conv3 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=3, stride=1, padding=1)
        
        # A drop layer deletes 20% of the features to help prevent overfitting
#explain how this help prevent overfitting
        self.drop = nn.Dropout2d(p=0.2)

typo: 05c pytorch

https://github.com/MicrosoftDocs/ml-basics/blob/master/05c%20-%20Transfer%20Learning%20(PyTorch).ipynb

Now print the full model, which will include the feature extraction layers of the base model and our preediction layer

to

Now print the full model,

which will include the feature extraction layers of the base model and our prediction layer

typo: 05a pytorch

https://github.com/MicrosoftDocs/ml-basics/blob/master/05a%20-%20Deep%20Neural%20Networks%20(PyTorch).ipynb

Take a look at the first 25 training features and corresponding labels

Should be

Take a look at the first 25 training samples and corresponding labels

issue - 05b - Convolutional Neural Networks (Tensorflow).ipynb

Issue at step - explore the data

---

NameError Traceback (most recent call last)
in
7
8 # Get the class names
----> 9 classes = os.listdir(data_folder)
10 classes.sort()
11 print(len(classes), 'classes:')

NameError: name 'os' is not defined

Matplotlib positioning error in 05a - Deep Neural Networks (TensorFlow)

Should be moved up a few blocks

Microsoft

There is an error with Keras.__version__ in the Tensorflow Notebook

As of the console output, Keras has no attribute called "version".

Keras has been integrated into Tensorflow and when imported from tensorflow they have the same version.

At least according to StackOverflow:

https://stackoverflow.com/questions/73934025/attributeerror-module-keras-has-no-attribute-version

The resolutions of this issue would consist of deleting one line of code in https://github.com/MicrosoftDocs/ml-basics/blob/master/05a%20-%20Deep%20Neural%20Networks%20(TensorFlow).ipynb right after importing TF.

import tensorflow
from tensorflow import keras
from tensorflow.keras import models
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras import utils
from tensorflow.keras import optimizers

# Set random seed for reproducability
tensorflow.random.set_seed(0)

print("Libraries imported.")
print('Keras version:',keras.__version__) #This line has to go
print('TensorFlow version:',tensorflow.__version__)