Restore Folder Structure in Research > Machine Learning

Folder change modifies the links and hurt SEO scores.

04 Research Environment/08 Machine Learning/03 Popular Libraries/00.json → 04 Research Environment/08 Machine Learning/00.json

@@ -14,6 +14,8 @@
     "07" : "",
     "08" : "",
     "09" : "",
-    "10" : ""
+    "10" : "",
+    "11" : "",
+    "12" : ""
   }
 }

04 Research Environment/08 Machine Learning/03 Popular Libraries/01 Aesera/04 Prepare Data.html → 04 Research Environment/08 Machine Learning/03 Aesera/04 Prepare Data.html

@@ -1,4 +1,4 @@
-<p>You need some <a href="/docs/v2/research-environment/machine-learning/popular-libraries/aesera#03-Get-Historical-Data">historical data</a> to prepare the data for the model. If you have historical data, manipulate it to train and test the model. In this example, use the following features and labels:</p>
+<p>You need some <a href="/docs/v2/research-environment/machine-learning/aesera#03-Get-Historical-Data">historical data</a> to prepare the data for the model. If you have historical data, manipulate it to train and test the model. In this example, use the following features and labels:</p>
 
 <table class="qc-table table">
     <thead>

04 Research Environment/08 Machine Learning/03 Popular Libraries/01 Aesera/05 Train Models.html → 04 Research Environment/08 Machine Learning/03 Aesera/05 Train Models.html

@@ -1,4 +1,4 @@
-<p>You need to <a href="/docs/v2/research-environment/machine-learning/popular-libraries/aesera#04-Prepare-Data">prepare the historical data</a> for training before you train the model. If you have prepared the data, build and train the model. In this example, build a Logistic Regression model with log loss cross entropy and square error as cost function. Follow these steps to create the model:</p>
+<p>You need to <a href="/docs/v2/research-environment/machine-learning/aesera#04-Prepare-Data">prepare the historical data</a> for training before you train the model. If you have prepared the data, build and train the model. In this example, build a Logistic Regression model with log loss cross entropy and square error as cost function. Follow these steps to create the model:</p>
 
 <ol>
     <li>Generate a dataset.</li>

04 Research Environment/08 Machine Learning/03 Popular Libraries/01 Aesera/06 Test Models.html → 04 Research Environment/08 Machine Learning/03 Aesera/06 Test Models.html

@@ -1,4 +1,4 @@
-<p>You need to <a href='/docs/v2/research-environment/machine-learning/popular-libraries/aesera#05-Train-Models'>build and train the model</a> before you test its performance. If you have trained the model, test it on the out-of-sample data. Follow these steps to test the model:</p>
+<p>You need to <a href='/docs/v2/research-environment/machine-learning/aesera#05-Train-Models'>build and train the model</a> before you test its performance. If you have trained the model, test it on the out-of-sample data. Follow these steps to test the model:</p>
 
 <ol>
     <li>Call the <code>predict</code> method with the features of the testing period.</li>

04 Research Environment/08 Machine Learning/03 Popular Libraries/02 GPlearn/04 Prepare Data.html → 04 Research Environment/08 Machine Learning/04 GPlearn/04 Prepare Data.html

@@ -1,4 +1,4 @@
-<p>You need some <a href="/docs/v2/research-environment/machine-learning/popular-libraries/gplearn#03-Get-Historical-Data">historical data</a> to prepare the data for the model. If you have historical data, manipulate it to train and test the model. In this example, use the following features and labels:</p>
+<p>You need some <a href="/docs/v2/research-environment/machine-learning/gplearn#03-Get-Historical-Data">historical data</a> to prepare the data for the model. If you have historical data, manipulate it to train and test the model. In this example, use the following features and labels:</p>
 
 <table class="qc-table table" id="live-trading-custer-sizes-table">
     <thead>

04 Research Environment/08 Machine Learning/03 Popular Libraries/02 GPlearn/05 Train Models.html → 04 Research Environment/08 Machine Learning/04 GPlearn/05 Train Models.html

@@ -1,4 +1,4 @@
-<p>You need to <a href="/docs/v2/research-environment/machine-learning/popular-libraries/gplearn#04-Prepare-Data">prepare the historical data</a> for training before you train the model. If you have prepared the data, build and train the model. In this example, create a Symbolic Transformer to generate new non-linear features and then build a Symbolic Regressor model. Follow these steps to create the model:</p>
+<p>You need to <a href="/docs/v2/research-environment/machine-learning/gplearn#04-Prepare-Data">prepare the historical data</a> for training before you train the model. If you have prepared the data, build and train the model. In this example, create a Symbolic Transformer to generate new non-linear features and then build a Symbolic Regressor model. Follow these steps to create the model:</p>
 
 <ol>
     <li>Declare a set of functions to use for feature engineering.</li>

04 Research Environment/08 Machine Learning/03 Popular Libraries/02 GPlearn/06 Test Models.html → 04 Research Environment/08 Machine Learning/04 GPlearn/06 Test Models.html

@@ -1,4 +1,4 @@
-<p>You need to <a href="/docs/v2/research-environment/machine-learning/popular-libraries/gplearn#05-Train-Models">build and train the model</a> before you test its performance. If you have trained the model, test it on the out-of-sample data. Follow these steps to test the model:</p>
+<p>You need to <a href="/docs/v2/research-environment/machine-learning/gplearn#05-Train-Models">build and train the model</a> before you test its performance. If you have trained the model, test it on the out-of-sample data. Follow these steps to test the model:</p>
 
 <ol>
     <li>Feature engineer the testing set data.</li>

04 Research Environment/08 Machine Learning/03 Popular Libraries/03 Hmmlearn/04 Prepare Data.html → 04 Research Environment/08 Machine Learning/05 Hmmlearn/04 Prepare Data.html

@@ -1,4 +1,4 @@
-<p>You need some <a href='/docs/v2/research-environment/machine-learning/popular-libraries/hmmlearn#03-Get-Historical-Data'>historical data</a> to prepare the data for the model. If you have historical data, manipulate it to train and test the model. Follow these steps to prepare the data:</p>
+<p>You need some <a href='/docs/v2/research-environment/machine-learning/hmmlearn#03-Get-Historical-Data'>historical data</a> to prepare the data for the model. If you have historical data, manipulate it to train and test the model. Follow these steps to prepare the data:</p>
 
 <ol>
     <li>Select the close column of the historical data DataFrame.</li>

04 Research Environment/08 Machine Learning/03 Popular Libraries/03 Hmmlearn/05 Train Models.html → 04 Research Environment/08 Machine Learning/05 Hmmlearn/05 Train Models.html

@@ -1,4 +1,4 @@
-<p>You need to <a href='/docs/v2/research-environment/machine-learning/popular-libraries/hmmlearn#04-Prepare-Data'>prepare the historical data</a> for training before you train the model. If you have prepared the data, build and train the model. In this example, assume the market has only 2 regimes and the market returns follow a Gaussian distribution. Therefore, create a 2-component Hidden Markov Model with Gaussian emissions, which is equivalent to a Gaussian mixture model with 2 means. Follow these steps to create the model:</p>
+<p>You need to <a href='/docs/v2/research-environment/machine-learning/hmmlearn#04-Prepare-Data'>prepare the historical data</a> for training before you train the model. If you have prepared the data, build and train the model. In this example, assume the market has only 2 regimes and the market returns follow a Gaussian distribution. Therefore, create a 2-component Hidden Markov Model with Gaussian emissions, which is equivalent to a Gaussian mixture model with 2 means. Follow these steps to create the model:</p>
 
 <ol>
     <li>Call the <code>GaussianHMM</code> constructor with the number of components, a covariance type, and the number of iterations.</li>

04 Research Environment/08 Machine Learning/03 Popular Libraries/03 Hmmlearn/06 Test Models.html → 04 Research Environment/08 Machine Learning/05 Hmmlearn/06 Test Models.html

@@ -1,4 +1,4 @@
-<p>You need to <a href="/docs/v2/research-environment/machine-learning/popular-libraries/hmmlearn#05-Train-Models">build and train the model</a> before you test its performance. If you have trained the model, test it on the out-of-sample data. Follow these steps to test the model:</p>
+<p>You need to <a href="/docs/v2/research-environment/machine-learning/hmmlearn#05-Train-Models">build and train the model</a> before you test its performance. If you have trained the model, test it on the out-of-sample data. Follow these steps to test the model:</p>
 
 <ol>
     <li>Call the predict method with the testing dataset.</li>

04 Research Environment/08 Machine Learning/03 Popular Libraries/04 Keras/04 Prepare Data.html → 04 Research Environment/08 Machine Learning/06 Keras/04 Prepare Data.html

@@ -1,4 +1,4 @@
-<p>You need some <a href="/docs/v2/research-environment/machine-learning/popular-libraries/keras#03-Get-Historical-Data">historical data</a> to prepare the data for the model. If you have historical data, manipulate it to train and test the model. In this example, use the following features and labels:</p>
+<p>You need some <a href="/docs/v2/research-environment/machine-learning/keras#03-Get-Historical-Data">historical data</a> to prepare the data for the model. If you have historical data, manipulate it to train and test the model. In this example, use the following features and labels:</p>
 
 <table class="qc-table table">
     <thead>

04 Research Environment/08 Machine Learning/03 Popular Libraries/04 Keras/06 Test Models.html → 04 Research Environment/08 Machine Learning/06 Keras/06 Test Models.html

@@ -1,4 +1,4 @@
-<p>You need to  <a href="/docs/v2/research-environment/machine-learning/popular-libraries/keras#05-Train-Models">build and train the model</a> before you test its performance. If you have trained the model, test it on the out-of-sample data. Follow these steps to test the model:</p>
+<p>You need to  <a href="/docs/v2/research-environment/machine-learning/keras#05-Train-Models">build and train the model</a> before you test its performance. If you have trained the model, test it on the out-of-sample data. Follow these steps to test the model:</p>
 
 <ol>
     <li>Call the <code>predict</code> method with the features of the testing period.</li>

04 Research Environment/08 Machine Learning/03 Popular Libraries/05 PyTorch/05 Train Models.html → 04 Research Environment/08 Machine Learning/07 PyTorch/05 Train Models.html

@@ -1,4 +1,4 @@
-<p>You need to <a href="/docs/v2/research-environment/machine-learning/popular-libraries/pytorch#04-Prepare-Data">prepare the historical data</a> for training before you train the model. If you have prepared the data, build and train the model. In this example, create a deep neural network with 2 hidden layers. Follow these steps to create the model:</p>
+<p>You need to <a href="/docs/v2/research-environment/machine-learning/pytorch#04-Prepare-Data">prepare the historical data</a> for training before you train the model. If you have prepared the data, build and train the model. In this example, create a deep neural network with 2 hidden layers. Follow these steps to create the model:</p>
 
 <ol>
     <li>Define a subclass of <code>nn.Module</code> to be the model.<br></li>

04 Research Environment/08 Machine Learning/03 Popular Libraries/05 PyTorch/06 Test Models.html → 04 Research Environment/08 Machine Learning/07 PyTorch/06 Test Models.html

@@ -1,4 +1,4 @@
-<p>You need to  <a href="/docs/v2/research-environment/machine-learning/popular-libraries/pytorch#05-Train-Models">build and train the model</a> before you test its performance. If you have trained the model, test it on the out-of-sample data. Follow these steps to test the model:</p>
+<p>You need to  <a href="/docs/v2/research-environment/machine-learning/pytorch#05-Train-Models">build and train the model</a> before you test its performance. If you have trained the model, test it on the out-of-sample data. Follow these steps to test the model:</p>
 
 <ol>
     <li>Predict with the testing data.</li>

04 Research Environment/08 Machine Learning/03 Popular Libraries/06 Scikit-Learn/04 Prepare Data.html → 04 Research Environment/08 Machine Learning/08 Scikit-Learn/04 Prepare Data.html

@@ -1,4 +1,4 @@
-<p>You need some <a href="/docs/v2/research-environment/machine-learning/popular-libraries/scikit-learn#03-Get-Historical-Data">historical data</a> to prepare the data for the model. If you have historical data, manipulate it to train and test the model. In this example, use the following features and labels:</p>
+<p>You need some <a href="/docs/v2/research-environment/machine-learning/scikit-learn#03-Get-Historical-Data">historical data</a> to prepare the data for the model. If you have historical data, manipulate it to train and test the model. In this example, use the following features and labels:</p>
 
 <table class="qc-table table">
     <thead>

04 Research Environment/08 Machine Learning/03 Popular Libraries/06 Scikit-Learn/05 Train Models.html → 04 Research Environment/08 Machine Learning/08 Scikit-Learn/05 Train Models.html

@@ -1,4 +1,4 @@
-<p>You need to <a href="/docs/v2/research-environment/machine-learning/popular-libraries/scikit-learn#04-Prepare-Data">prepare the historical data</a> for training before you train the model. If you have prepared the data, build and train the model. In this example, build a Support Vector Regressor model and optimize its hyperparameters with grid search cross-validation. Follow these steps to create the model:</p>
+<p>You need to <a href="/docs/v2/research-environment/machine-learning/scikit-learn#04-Prepare-Data">prepare the historical data</a> for training before you train the model. If you have prepared the data, build and train the model. In this example, build a Support Vector Regressor model and optimize its hyperparameters with grid search cross-validation. Follow these steps to create the model:</p>
 
 <ol>
     <li>Set the choices of hyperparameters used for grid search testing.</li>

04 Research Environment/08 Machine Learning/03 Popular Libraries/06 Scikit-Learn/06 Test Models.html → 04 Research Environment/08 Machine Learning/08 Scikit-Learn/06 Test Models.html

@@ -1,4 +1,4 @@
-<p>You need to <a href='/docs/v2/research-environment/machine-learning/popular-libraries/scikit-learn#05-Train-Models'>build and train the model</a> before you test its performance. If you have trained the model, test it on the out-of-sample data. Follow these steps to test the model:</p>
+<p>You need to <a href='/docs/v2/research-environment/machine-learning/scikit-learn#05-Train-Models'>build and train the model</a> before you test its performance. If you have trained the model, test it on the out-of-sample data. Follow these steps to test the model:</p>
 
 <ol>
     <li>Call the <code>predict</code> method with the features of the testing period.</li>

04 Research Environment/08 Machine Learning/03 Popular Libraries/07 Stable Baselines/04 Prepare Data.html → 04 Research Environment/08 Machine Learning/09 Stable Baselines/04 Prepare Data.html

@@ -1,5 +1,5 @@
 <p>
-    You need some <a href="/docs/v2/research-environment/machine-learning/popular-libraries/stable-baselines#03-Get-Historical-Data">historical data</a> to prepare the data for the model. 
+    You need some <a href="/docs/v2/research-environment/machine-learning/stable-baselines#03-Get-Historical-Data">historical data</a> to prepare the data for the model. 
     If you have historical data, manipulate it to train and test the model.
     In this example, extract the close price series as the outcome and obtain the partial-differenced time-series of OHLCV values as the observation.
 </p>

04 Research Environment/08 Machine Learning/03 Popular Libraries/07 Stable Baselines/05 Train Models.html → 04 Research Environment/08 Machine Learning/09 Stable Baselines/05 Train Models.html

@@ -1,4 +1,4 @@
-<p>You need to <a href="/docs/v2/research-environment/machine-learning/popular-libraries/stable-baselines#04-Prepare-Data">prepare the historical data</a> for training before you train the model. If you have prepared the data, build and train the environment and the model. In this example, create a <code>gym</code> environment to initialize the training environment, agent and reward. Then, create a RL model by DQN algorithm. Follow these steps to create the environment and the model:</p>
+<p>You need to <a href="/docs/v2/research-environment/machine-learning/stable-baselines#04-Prepare-Data">prepare the historical data</a> for training before you train the model. If you have prepared the data, build and train the environment and the model. In this example, create a <code>gym</code> environment to initialize the training environment, agent and reward. Then, create a RL model by DQN algorithm. Follow these steps to create the environment and the model:</p>
 
 <ol>
     <li>Split the data for training and testing to evaluate our model.</li>

04 Research Environment/08 Machine Learning/03 Popular Libraries/07 Stable Baselines/06 Test Models.html → 04 Research Environment/08 Machine Learning/09 Stable Baselines/06 Test Models.html

@@ -1,4 +1,4 @@
-<p>You need to <a href="/docs/v2/research-environment/machine-learning/popular-libraries/stable-baselines#05-Train-Models">build and train the model</a> before you test its performance. If you have trained the model, test it on the out-of-sample data. Follow these steps to test the model:</p>
+<p>You need to <a href="/docs/v2/research-environment/machine-learning/stable-baselines#05-Train-Models">build and train the model</a> before you test its performance. If you have trained the model, test it on the out-of-sample data. Follow these steps to test the model:</p>
 
 <ol>
     <li>Initialize a return series to calculate performance and a list to store the equity value at each timestep.</li>

04 Research Environment/08 Machine Learning/03 Popular Libraries/08 TensorFlow/04 Prepare Data.html → 04 Research Environment/08 Machine Learning/10 TensorFlow/04 Prepare Data.html

@@ -1,4 +1,4 @@
-<p>You need some <a href="/docs/v2/research-environment/machine-learning/popular-libraries/tensorflow#03-Get-Historical-Data">historical data</a> to prepare the data for the model. If you have historical data, manipulate it to train and test the model. In this example, use the following features and labels:</p>
+<p>You need some <a href="/docs/v2/research-environment/machine-learning/tensorflow#03-Get-Historical-Data">historical data</a> to prepare the data for the model. If you have historical data, manipulate it to train and test the model. In this example, use the following features and labels:</p>
 
 <table class="qc-table table" id="live-trading-custer-sizes-table">
     <thead>

04 Research Environment/08 Machine Learning/03 Popular Libraries/08 TensorFlow/05 Train Models.html → 04 Research Environment/08 Machine Learning/10 TensorFlow/05 Train Models.html

@@ -1,4 +1,4 @@
-<p>You need to <a href="/docs/v2/research-environment/machine-learning/popular-libraries/tensorflow#04-Prepare-Data">prepare the historical data</a> for training before you train the model. If you have prepared the data, build and train the model. In this example, build a neural network model that predicts the future price of the SPY.</p>
+<p>You need to <a href="/docs/v2/research-environment/machine-learning/tensorflow#04-Prepare-Data">prepare the historical data</a> for training before you train the model. If you have prepared the data, build and train the model. In this example, build a neural network model that predicts the future price of the SPY.</p>
 
 <h4>Build the Model</h4>
 <p>Follow these steps to build the model:</p>

04 Research Environment/08 Machine Learning/03 Popular Libraries/09 Tslearn/04 Prepare Data.html → 04 Research Environment/08 Machine Learning/11 Tslearn/04 Prepare Data.html

@@ -1,4 +1,4 @@
-<p>You need some <a href="/docs/v2/research-environment/machine-learning/popular-libraries/tslearn#03-Get-Historical-Data">historical data</a> to prepare the data for the model. If you have historical data, manipulate it to train and test the model. In this example, standardize the log close price time-series of the securities. Follow these steps to prepare the data:</p>
+<p>You need some <a href="/docs/v2/research-environment/machine-learning/tslearn#03-Get-Historical-Data">historical data</a> to prepare the data for the model. If you have historical data, manipulate it to train and test the model. In this example, standardize the log close price time-series of the securities. Follow these steps to prepare the data:</p>
 
 <ol>
     <li>Unstack the historical DataFrame and select the close column.</li>

Resources/machine-learning/prepare-data.html

@@ -1,4 +1,4 @@
-<p>You need some <a href="/docs/v2/research-environment/machine-learning/popular-libraries/pytorch#03-Get-Historical-Data">historical data</a> to prepare the data for the model. If you have historical data, manipulate it to train and test the model. In this example, use the following features and labels:</p>
+<p>You need some <a href="/docs/v2/research-environment/machine-learning/pytorch#03-Get-Historical-Data">historical data</a> to prepare the data for the model. If you have historical data, manipulate it to train and test the model. In this example, use the following features and labels:</p>
 
 <table class="qc-table table">
     <thead>