Fixed broken links for website and Fix image sizes (#23)

* Fixed broken links for website and Fix image sizes

* Minor fix on links

* Added test Reference list for linear regression

* Added references section to all files

Author: hokie45

docs/source/content/overview/crossvalidation.rst

@@ -23,7 +23,7 @@ and is useful if you have a large amount of data or need to implement
 validation quickly and easily.
 
 .. figure:: _img/holdout.png
-   :scale: 50 %
+   :scale: 75 %
    :alt: holdout method
 
 
@@ -35,8 +35,7 @@ data may give your model an unwanted bias towards the training data.
 This lack of training or bias can lead to
 `Underfitting/Overfitting`_ of our model.
 
-.. _Underfitting/Overfitting: overfitting.rst
-
+.. _Underfitting/Overfitting: https://machine-learning-course.readthedocs.io/en/latest/content/overview/overfitting.html
 
 K-Fold Cross Validation
 -----------------------
@@ -49,7 +48,7 @@ combination of data, and the results are averaged to find a total error
 estimation.
 
 .. figure:: _img/kfold.png
-   :scale: 50 %
+   :scale: 75 %
    :alt: kfold method
 
 A "fold" here is a unique section of test data. For instance, if you
@@ -82,7 +81,7 @@ Where "T" is a test point, and "-" is a training point. Below is another
 visualization of LPOCV:
 
 .. figure:: _img/LPOCV.png
-   :scale: 50 %
+   :scale: 75 %
    :alt: kfold method
 
    Ref: http://www.ebc.cat/2017/01/31/cross-validation-strategies/
@@ -102,7 +101,7 @@ Validation, where the number of folds is equal to the number of data
 points.
 
 .. figure:: _img/LOOCV.png
-   :scale: 50 %
+   :scale: 75 %
    :alt: kfold method
 
    Ref: http://www.ebc.cat/2017/01/31/cross-validation-strategies/
@@ -222,6 +221,18 @@ train-test data split is created with the `split()` method:
 Note that you can change the P value at the top of the script to see
 how different values operate.
 
-.. _holdout.py: /code/overview/cross-validation/holdout.py
-.. _k-fold.py: /code/overview/cross-validation/k-fold.py
-.. _leave-p-out.py: /code/overview/cross-validation/leave-p-out.py
+.. _holdout.py: /https://github.com/machinelearningmindset/machine-learning-course/tree/mastercode/overview/cross-validation/holdout.py
+.. _k-fold.py: /https://github.com/machinelearningmindset/machine-learning-course/tree/mastercode/overview/cross-validation/k-fold.py
+.. _leave-p-out.py: /https://github.com/machinelearningmindset/machine-learning-course/tree/mastercode/overview/cross-validation/leave-p-out.py
+
+
+************
+References
+************
+
+1. https://towardsdatascience.com/cross-validation-in-machine-learning-72924a69872f
+2. https://machinelearningmastery.com/k-fold-cross-validation/
+3. https://www.quora.com/What-is-cross-validation-in-machine-learning 
+#. http://www.ebc.cat/2017/01/31/cross-validation-strategies/ 
+
+

docs/source/content/overview/linear-regression.rst

@@ -228,3 +228,18 @@ but still show up in a lot of data sets so this is a good technique to know.
 Learning about linear regression is a good first step towards learning more 
 complicated analysis techniques. We will build on a lot of the concepts 
 covered here in later modules.
+
+
+************
+References
+************
+
+1. https://towardsdatascience.com/introduction-to-machine-learning-algorithms-linear-regression-14c4e325882a
+2. https://machinelearningmastery.com/linear-regression-for-machine-learning/
+3. https://ml-cheatsheet.readthedocs.io/en/latest/linear_regression.html
+#. https://machinelearningmastery.com/implement-simple-linear-regression-scratch-python/
+#. https://medium.com/analytics-vidhya/linear-regression-in-python-from-scratch-24db98184276
+#. https://scikit-learn.org/stable/auto_examples/linear_model/plot_ols.html
+#. https://scikit-learn.org/stable/modules/generated/sklearn.compose.TransformedTargetRegressor.html
+
+

docs/source/content/overview/overfitting.rst

@@ -29,7 +29,7 @@ In practice, this error isn't always at edge cases and can pop up anywhere.
 The noise in training can cause error as seen in the graph below.
 
 .. figure:: _img/Overfit_small.png
-   :scale: 10 %
+   :scale: 100 %
    :alt: Overfit
 (Created using https://www.desmos.com/calculator/dffnj2jbow)
 
@@ -54,7 +54,7 @@ In machine learning, this could be a result of underfitting, the model has not
 had enough exposure to training data to adapt to it, and is currently in a simple state.
 
 .. figure:: _img/Underfit.PNG
-   :scale: 50 %
+   :scale: 100 %
    :alt: Underfit
 (Created using Wolfram Alpha)
 
@@ -97,7 +97,7 @@ how to avoid overfitting in machine learning models.
 Ideally, a good fit looks something like this:
 
 .. figure:: _img/GoodFit.PNG
-   :scale: 50 %
+   :scale: 100 %
    :alt: Underfit
 (Created using Wolfram Alpha)
 
@@ -106,3 +106,13 @@ When using machine learning in any capacity, issues such as overfitting
 frequently come up, and having a grasp of the concept is very important.
 The modules in this section are among the most important in the whole repository,
 since regardless of the implementation, machine learning always includes these fundamentals.
+
+
+************
+References
+************
+
+1. https://machinelearningmastery.com/overfitting-and-underfitting-with-machine-learning-algorithms/
+2. https://medium.com/greyatom/what-is-underfitting-and-overfitting-in-machine-learning-and-how-to-deal-with-it-6803a989c76
+3. https://towardsdatascience.com/overfitting-vs-underfitting-a-conceptual-explanation-d94ee20ca7f9
+

docs/source/content/overview/regularization.rst

@@ -184,3 +184,16 @@ problem in modeling so it's good to know how to mediate it. We have also
 explored some methods of regularization that we can use in different
 situations. With this, we have learned enough about the core concepts of
 machine learning to move onto our next major topic, supervised learning.
+
+
+************
+References
+************
+
+1. https://towardsdatascience.com/regularization-in-machine-learning-76441ddcf99a
+2. https://www.analyticsvidhya.com/blog/2018/04/fundamentals-deep-learning-regularization-techniques 
+3. https://www.quora.com/What-is-regularization-in-machine-learning
+#. https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Ridge.html 
+#. https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Lasso.html
+
+

docs/source/content/supervised/bayes.rst

@@ -208,3 +208,14 @@ come in handy for real-time predictions. We make a lot of assumptions to use
 Naive Bayes so results should be taken with a grain of salt. But if you don’t
 have much data and need fast results, Naive Bayes is a good choice for
 classification problems.
+
+
+************
+References
+************
+
+1. https://machinelearningmastery.com/naive-bayes-classifier-scratch-python/
+2. https://www.analyticsvidhya.com/blog/2017/09/naive-bayes-explained/ 
+3. https://towardsdatascience.com/naive-bayes-in-machine-learning-f49cc8f831b4
+#. https://medium.com/machine-learning-101/chapter-1-supervised-learning-and-naive-bayes-classification-part-1-theory-8b9e361897d5
+

docs/source/content/supervised/decisiontrees.rst

@@ -316,3 +316,17 @@ whether Mike will go shopping:
 
     # Use our tree to predict the outcome of the random values
     prediction_results = tree.predict(encoder.transform(prediction_data))
+
+
+************
+References
+************
+
+1. https://towardsdatascience.com/decision-trees-in-machine-learning-641b9c4e8052
+2. https://heartbeat.fritz.ai/introduction-to-decision-tree-learning-cd604f85e23 
+3. https://machinelearningmastery.com/implement-decision-tree-algorithm-scratch-python/ 
+#. https://sebastianraschka.com/faq/docs/decision-tree-binary.html
+#. https://www.cs.cmu.edu/~bhiksha/courses/10-601/decisiontrees/
+
+
+

docs/source/content/supervised/knn.rst

@@ -20,7 +20,7 @@ k = 1 then the class the object would be in is the class of the closest
 neighbor. Let's look at an example.
 
 .. figure:: _img/knn.png
-   :scale: 50 %
+   :scale: 100 %
    :alt: KNN
 
    Ref: https://coxdocs.org
@@ -60,7 +60,7 @@ to one of them and then we know that distance is roughly close to the other poin
 Here is an example of how the K-D tree looks like.
 
 .. figure:: _img/KNN_KDTree.jpg
-   :scale: 50 %
+   :scale: 100 %
    :alt: KNN K-d tree
 
    Ref: https://slideplayer.com/slide/3273367/
@@ -120,7 +120,7 @@ The program will take the data and plot them on a graph, then use the KNN algori
 The output should look like this:
 
 .. figure:: _img/knn_output_k9.png
-   :scale: 50%
+   :scale: 100%
    :alt: KNN k = 9 output
 
 The green points are classified as benign.
@@ -154,7 +154,7 @@ Try changing the value of n_neighbors to 1 in the code below.
 If you changed the value of n_neighbors to 1 this will classify by the point that is closest to the point. The output should look like this:
 
 .. figure:: _img/knn_output_k1.png
-   :scale: 50%
+   :scale: 100%
    :alt: KNN k = 1 output
 
 Comparing this output to k = 9 you can see a large difference on how it classifies the data. So if you want to ignore outliers you
@@ -165,6 +165,15 @@ Eventually the algorithm will classify all the data into 1 class, and there will
 
 .. _knn.py: https://github.com/machinelearningmindset/machine-learning-course/blob/master/code/supervised/KNN/knn.py
 
-.. _Support Vector Machines: linear_SVM.html
+.. _Support Vector Machines: https://machine-learning-course.readthedocs.io/en/latest/content/supervised/linear_SVM.html
 
 
+************
+References
+************
+
+1. https://medium.com/machine-learning-101/k-nearest-neighbors-classifier-1c1ff404d265
+2. https://www.analyticsvidhya.com/blog/2018/03/introduction-k-neighbours-algorithm-clustering/  
+3. https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsClassifier.html 
+#. https://turi.com/learn/userguide/supervised-learning/knn_classifier.html 
+

docs/source/content/supervised/linear_SVM.rst

@@ -30,7 +30,7 @@ amount of lines that can divide two classes. As you can see in the graph below,
 the circles, so which one do we choose?
 
 .. figure:: _img/Possible_hyperplane.png
-   :scale: 50%
+   :scale: 100%
    :alt: Possible_Hyperplane
 
    Ref: https://towardsdatascience.com/support-vector-machine-introduction-to-machine-learning-algorithms-934a444fca47 
@@ -40,7 +40,7 @@ the line/hyperplane with the **maximum margin**. Maximizing the margin will give
 This is shown in the figure below.  
 
 .. figure:: _img/optimal_hyperplane.png
-   :scale: 50%
+   :scale: 100%
    :alt: Optimal_Hyperplane
 
    Ref: https://towardsdatascience.com/support-vector-machine-introduction-to-machine-learning-algorithms-934a444fca47 
@@ -62,7 +62,7 @@ Support Vector Machines will ignore these outliers. This is shown in the figure
 
 
 .. figure:: _img/SVM_Outliers.png
-   :scale: 50%
+   :scale: 100%
    :alt: Outliers
 
    Ref:  https://www.analyticsvidhya.com/blog/2017/09/understaing-support-vector-machine-example-code/
@@ -78,7 +78,7 @@ There will be data classes that can't be separated with a simple line or hyperpl
 separable data**. Here is an example of that kind of data. 
 
 .. figure:: _img/SVM_Kernal.png
-   :scale: 50%
+   :scale: 100%
    :alt: Kernel
 
    Ref:  https://www.analyticsvidhya.com/blog/2017/09/understaing-support-vector-machine-example-code/
@@ -92,7 +92,7 @@ classified with a circle that separates the data.
 Here is an example of the kernel trick.
 
 .. figure:: _img/SVM_Kernel2.png
-   :scale: 50%
+   :scale: 100%
    :alt: Kernel X Y graph
 
    Ref:  https://www.analyticsvidhya.com/blog/2017/09/understaing-support-vector-machine-example-code/
@@ -145,7 +145,7 @@ The program will take the data and plot them on a graph, then use the SVM to cre
 It also circles the support vectors that determine the hyperplane. The output should look like this:
 
 .. figure:: _img/linear_svm_output.png
-   :scale: 50%
+   :scale: 100%
    :alt: Linear SVM output
 
 The green points are classified as benign.
@@ -173,3 +173,15 @@ the data. You can change it here in the code:
 
 .. _linear_svm.py: https://github.com/machinelearningmindset/machine-learning-course/blob/master/code/supervised/Linear_SVM/linear_svm.py
 
+
+************
+References
+************
+
+1. https://www.analyticsvidhya.com/blog/2017/09/understaing-support-vector-machine-example-code/
+2. https://stackabuse.com/implementing-svm-and-kernel-svm-with-pythons-scikit-learn/
+3. https://towardsdatascience.com/support-vector-machine-introduction-to-machine-learning-algorithms-934a444fca47
+#. https://towardsdatascience.com/https-medium-com-pupalerushikesh-svm-f4b42800e989
+#. https://towardsdatascience.com/support-vector-machines-svm-c9ef22815589
+
+

docs/source/content/supervised/logistic_regression.rst

@@ -25,7 +25,7 @@ Here is the standard logistic function, note that the output is always between
 0 and 1, but never reaches either of those values.
 
 .. figure:: _img/WikiLogistic.svg.png
-   :scale: 20%
+   :scale: 100%
    :alt: Logistic
 Ref: https://en.wikipedia.org/wiki/Logistic_regression
 
@@ -142,3 +142,20 @@ The basic idea is to supply the training data as pairs of input and
 classification, and the model will be built automatically.
 As always, keep in mind the basics mentioned in the overview section of this
 repository, as there is no fool-proof method for machine learning.
+
+
+************
+References
+************
+
+1. https://towardsdatascience.com/logistic-regression-b0af09cdb8ad
+2. https://medium.com/datadriveninvestor/machine-learning-model-logistic-regression-5fa4ffde5773
+3. https://github.com/bfortuner/ml-cheatsheet/blob/master/docs/logistic_regression.rst
+#. https://machinelearningmastery.com/logistic-regression-tutorial-for-machine-learning/
+#. https://towardsdatascience.com/logistic-regression-a-simplified-approach-using-python-c4bc81a87c31
+#. https://hackernoon.com/introduction-to-machine-learning-algorithms-logistic-regression-cbdd82d81a36
+#. https://en.wikipedia.org/wiki/Logistic_regression
+#. https://en.wikipedia.org/wiki/Multinomial_logistic_regression
+#. https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html 
+#. https://towardsdatascience.com/5-reasons-logistic-regression-should-be-the-first-thing-you-learn-when-become-a-data-scientist-fcaae46605c4
+

docs/source/content/unsupervised/clustering.rst

@@ -128,7 +128,7 @@ K-Means is a good choice.
 
 The relevant code is available in the clustering_kmeans.py_ file.
 
-.. _clustering_kmeans.py: /code/unsupervised/Clustering/clustering_kmeans.py
+.. _clustering_kmeans.py: https://github.com/machinelearningmindset/machine-learning-course/code/unsupervised/Clustering/clustering_kmeans.py
 
 In the code, we create the simple data set to use for analysis. Setting up the
 clustering is very simple and requires one line of code:
@@ -187,7 +187,7 @@ the number of expected clusters.
 
 The relevant code is available in the clustering_hierarchical.py_ file.
 
-.. _clustering_hierarchical.py: /code/unsupervised/Clustering/clustering_hierarchical.py
+.. _clustering_hierarchical.py: https://github.com/machinelearningmindset/machine-learning-course/code/unsupervised/Clustering/clustering_hierarchical.py
 
 In the code, we create the simple data set to use for analysis. Setting up the
 clustering is very simple and requires one line of code:
@@ -221,3 +221,15 @@ the toy manufacturer example that could be used for targeted advertising. This
 is a very useful result for businesses and it only took us a few lines of
 code. By developing a good understanding of clustering, you are setting
 yourself up for success in the machine learning world.
+
+
+************
+References
+************
+
+1. https://www.analyticsvidhya.com/blog/2016/11/an-introduction-to-clustering-and-different-methods-of-clustering/
+2. https://medium.com/datadriveninvestor/an-introduction-to-clustering-61f6930e3e0b
+3. https://medium.com/predict/three-popular-clustering-methods-and-when-to-use-each-4227c80ba2b6
+#. https://towardsdatascience.com/the-5-clustering-algorithms-data-scientists-need-to-know-a36d136ef68 
+#. https://scikit-learn.org/stable/modules/generated/sklearn.cluster.KMeans.html
+