lars/FYS-STK4155
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
Morten Hjorth-Jensen
2021-09-23 09:04:35 +02:00
parent 7e96edbcf0
commit ca96a8b4dd
9 changed files with 110 additions and 78 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/pub/week38/html/._week38-bs014.html
+7 -6
View File
@@ -518,12 +518,13 @@ The intercept is the value of our output/target variable
when all our features are zero and our function crosses the \( y \)-axis (for a one-dimensional case).
<p>
Printing the MSE, we see first that both methods give the same
MSE. However, changing the value of the intercept gives a larger or
smaller MSE, meaning that the MSE is penalized by the value of the
intercept! Setting the intercept to true in the <b>Scikit-Learn</b>
function or simply scaling our results, leads to a fit which is
independent of the specific value of the intercept.
Printing the MSE, we see first that both methods give the same MSE, as
they should. However, when we move to for example Ridge regression,
the way we treat the intercept may give a larger or smaller MSE,
meaning that the MSE can be penalized by the value of the
intercept. Not including the intercept in the fit, means that the
regularization term does not include \( \beta_0 \). For different values
of \( \lambda \), this may lead to differeing MSE values.
<p>
<p>
doc/pub/week38/html/._week38-bs015.html
+6 -2
View File
@@ -421,7 +421,7 @@ MathJax.Hub.Config({
<h2 id="code-examples" class="anchor">Code Examples </h2>
<p>
Armed with this wisdom, we attempt first simply set the intercept eqault to <b>False</b> in our implementation of Ridge regression for yet another vanilla data set.
Armed with this wisdom, we attempt first simply set the intercept equal to <b>False</b> in our implementation of Ridge regression for yet another vanilla data set.
<p>
@@ -463,7 +463,6 @@ lambdas <span style="color: #666666">=</span> np<span style="color: #666666">.</
<span style="color: #008000; font-weight: bold">for</span> i <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(nlambdas):
lmb <span style="color: #666666">=</span> lambdas[i]
OwnRidgeBeta <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>pinv(X_train<span style="color: #666666">.</span>T <span style="color: #666666">@</span> X_train<span style="color: #666666">+</span>lmb<span style="color: #666666">*</span>I) <span style="color: #666666">@</span> X_train<span style="color: #666666">.</span>T <span style="color: #666666">@</span> y_train
<span style="color: #408080; font-style: italic"># include lasso using Scikit-Learn</span>
<span style="color: #408080; font-style: italic"># Note: we include the intercept column and no scaling</span>
RegRidge <span style="color: #666666">=</span> linear_model<span style="color: #666666">.</span>Ridge(lmb,fit_intercept<span style="color: #666666">=</span><span style="color: #008000; font-weight: bold">False</span>)
RegRidge<span style="color: #666666">.</span>fit(X_train,y_train)
@@ -478,6 +477,11 @@ lambdas <span style="color: #666666">=</span> np<span style="color: #666666">.</
<span style="color: #008000">print</span>(OwnRidgeBeta)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;Beta values for Scikit-Learn Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(RegRidge<span style="color: #666666">.</span>coef_)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;MSE values for own Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(MSEOwnRidgePredict[i])
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;MSE values for Scikit-Learn Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(MSERidgePredict[i])
<span style="color: #408080; font-style: italic"># Now plot the results</span>
plt<span style="color: #666666">.</span>figure()
plt<span style="color: #666666">.</span>plot(np<span style="color: #666666">.</span>log10(lambdas), MSEOwnRidgePredict, <span style="color: #BA2121">&#39;r&#39;</span>, label <span style="color: #666666">=</span> <span style="color: #BA2121">&#39;MSE own Ridge Test&#39;</span>)
doc/pub/week38/html/._week38-bs016.html
+5 -5
View File
@@ -478,16 +478,11 @@ lambdas <span style="color: #666666">=</span> np<span style="color: #666666">.</
intercept_ <span style="color: #666666">=</span> y_scaler <span style="color: #666666">-</span> X_train_mean<span style="color: #AA22FF">@OwnRidgeBeta</span> <span style="color: #408080; font-style: italic">#The intercept can be shifted so the model can predict on uncentered data</span>
<span style="color: #408080; font-style: italic">#Add intercept to prediction</span>
ypredictOwnRidge <span style="color: #666666">=</span> X_test <span style="color: #666666">@</span> OwnRidgeBeta <span style="color: #666666">+</span> intercept_
<span style="color: #408080; font-style: italic">#EQUIVALENT PREDICTION:</span>
<span style="color: #408080; font-style: italic">#Add intercept to prediction</span>
ypredictOwnRidge <span style="color: #666666">=</span> X_test_scaled <span style="color: #666666">@</span> OwnRidgeBeta <span style="color: #666666">+</span> y_scaler
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;Values for own Ridge prediction&quot;</span>)
<span style="color: #008000">print</span>(ypredictOwnRidge)
RegRidge <span style="color: #666666">=</span> linear_model<span style="color: #666666">.</span>Ridge(lmb)
RegRidge<span style="color: #666666">.</span>fit(X_train,y_train)
ypredictRidge <span style="color: #666666">=</span> RegRidge<span style="color: #666666">.</span>predict(X_test)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;Values for SL Ridge prediction&quot;</span>)
<span style="color: #008000">print</span>(ypredictRidge)
MSEOwnRidgePredict[i] <span style="color: #666666">=</span> MSE(y_test,ypredictOwnRidge)
MSERidgePredict[i] <span style="color: #666666">=</span> MSE(y_test,ypredictRidge)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;Beta values for own Ridge implementation&quot;</span>)
@@ -498,6 +493,11 @@ lambdas <span style="color: #666666">=</span> np<span style="color: #666666">.</
<span style="color: #008000">print</span>(intercept_)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&#39;Intercept from Scikit-Learn Ridge implementation&#39;</span>)
<span style="color: #008000">print</span>(RegRidge<span style="color: #666666">.</span>intercept_)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;MSE values for own Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(MSEOwnRidgePredict[i])
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;MSE values for Scikit-Learn Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(MSERidgePredict[i])
<span style="color: #408080; font-style: italic"># Now plot the results</span>
plt<span style="color: #666666">.</span>figure()
doc/pub/week38/html/week38-reveal.html
+18 -13
View File
@@ -771,12 +771,13 @@ The intercept is the value of our output/target variable
when all our features are zero and our function crosses the \( y \)-axis (for a one-dimensional case).
<p>
Printing the MSE, we see first that both methods give the same
MSE. However, changing the value of the intercept gives a larger or
smaller MSE, meaning that the MSE is penalized by the value of the
intercept! Setting the intercept to true in the <b>Scikit-Learn</b>
function or simply scaling our results, leads to a fit which is
independent of the specific value of the intercept.
Printing the MSE, we see first that both methods give the same MSE, as
they should. However, when we move to for example Ridge regression,
the way we treat the intercept may give a larger or smaller MSE,
meaning that the MSE can be penalized by the value of the
intercept. Not including the intercept in the fit, means that the
regularization term does not include \( \beta_0 \). For different values
of \( \lambda \), this may lead to differeing MSE values.
</section>
@@ -784,7 +785,7 @@ independent of the specific value of the intercept.
<h2 id="code-examples">Code Examples </h2>
<p>
Armed with this wisdom, we attempt first simply set the intercept eqault to <b>False</b> in our implementation of Ridge regression for yet another vanilla data set.
Armed with this wisdom, we attempt first simply set the intercept equal to <b>False</b> in our implementation of Ridge regression for yet another vanilla data set.
<p>
@@ -826,7 +827,6 @@ lambdas = np.logspace(-<span style="color: #B452CD">4</span>, <span style="color
<span style="color: #8B008B; font-weight: bold">for</span> i <span style="color: #8B008B">in</span> <span style="color: #658b00">range</span>(nlambdas):
lmb = lambdas[i]
OwnRidgeBeta = np.linalg.pinv(X_train.T @ X_train+lmb*I) @ X_train.T @ y_train
<span style="color: #228B22"># include lasso using Scikit-Learn</span>
<span style="color: #228B22"># Note: we include the intercept column and no scaling</span>
RegRidge = linear_model.Ridge(lmb,fit_intercept=<span style="color: #8B008B; font-weight: bold">False</span>)
RegRidge.fit(X_train,y_train)
@@ -841,6 +841,11 @@ lambdas = np.logspace(-<span style="color: #B452CD">4</span>, <span style="color
<span style="color: #658b00">print</span>(OwnRidgeBeta)
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&quot;Beta values for Scikit-Learn Ridge implementation&quot;</span>)
<span style="color: #658b00">print</span>(RegRidge.coef_)
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&quot;MSE values for own Ridge implementation&quot;</span>)
<span style="color: #658b00">print</span>(MSEOwnRidgePredict[i])
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&quot;MSE values for Scikit-Learn Ridge implementation&quot;</span>)
<span style="color: #658b00">print</span>(MSERidgePredict[i])
<span style="color: #228B22"># Now plot the results</span>
plt.figure()
plt.plot(np.log10(lambdas), MSEOwnRidgePredict, <span style="color: #CD5555">&#39;r&#39;</span>, label = <span style="color: #CD5555">&#39;MSE own Ridge Test&#39;</span>)
@@ -919,16 +924,11 @@ lambdas = np.logspace(-<span style="color: #B452CD">4</span>, <span style="color
intercept_ = y_scaler - X_train_mean<span style="color: #707a7c">@OwnRidgeBeta</span> <span style="color: #228B22">#The intercept can be shifted so the model can predict on uncentered data</span>
<span style="color: #228B22">#Add intercept to prediction</span>
ypredictOwnRidge = X_test @ OwnRidgeBeta + intercept_
<span style="color: #228B22">#EQUIVALENT PREDICTION:</span>
<span style="color: #228B22">#Add intercept to prediction</span>
ypredictOwnRidge = X_test_scaled @ OwnRidgeBeta + y_scaler
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&quot;Values for own Ridge prediction&quot;</span>)
<span style="color: #658b00">print</span>(ypredictOwnRidge)
RegRidge = linear_model.Ridge(lmb)
RegRidge.fit(X_train,y_train)
ypredictRidge = RegRidge.predict(X_test)
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&quot;Values for SL Ridge prediction&quot;</span>)
<span style="color: #658b00">print</span>(ypredictRidge)
MSEOwnRidgePredict[i] = MSE(y_test,ypredictOwnRidge)
MSERidgePredict[i] = MSE(y_test,ypredictRidge)
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&quot;Beta values for own Ridge implementation&quot;</span>)
@@ -939,6 +939,11 @@ lambdas = np.logspace(-<span style="color: #B452CD">4</span>, <span style="color
<span style="color: #658b00">print</span>(intercept_)
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&#39;Intercept from Scikit-Learn Ridge implementation&#39;</span>)
<span style="color: #658b00">print</span>(RegRidge.intercept_)
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&quot;MSE values for own Ridge implementation&quot;</span>)
<span style="color: #658b00">print</span>(MSEOwnRidgePredict[i])
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&quot;MSE values for Scikit-Learn Ridge implementation&quot;</span>)
<span style="color: #658b00">print</span>(MSERidgePredict[i])
<span style="color: #228B22"># Now plot the results</span>
plt.figure()
doc/pub/week38/html/week38-solarized.html
+18 -13
View File
@@ -905,12 +905,13 @@ The intercept is the value of our output/target variable
when all our features are zero and our function crosses the \( y \)-axis (for a one-dimensional case).
<p>
Printing the MSE, we see first that both methods give the same
MSE. However, changing the value of the intercept gives a larger or
smaller MSE, meaning that the MSE is penalized by the value of the
intercept! Setting the intercept to true in the <b>Scikit-Learn</b>
function or simply scaling our results, leads to a fit which is
independent of the specific value of the intercept.
Printing the MSE, we see first that both methods give the same MSE, as
they should. However, when we move to for example Ridge regression,
the way we treat the intercept may give a larger or smaller MSE,
meaning that the MSE can be penalized by the value of the
intercept. Not including the intercept in the fit, means that the
regularization term does not include \( \beta_0 \). For different values
of \( \lambda \), this may lead to differeing MSE values.
<p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
@@ -918,7 +919,7 @@ independent of the specific value of the intercept.
<h2 id="code-examples">Code Examples </h2>
<p>
Armed with this wisdom, we attempt first simply set the intercept eqault to <b>False</b> in our implementation of Ridge regression for yet another vanilla data set.
Armed with this wisdom, we attempt first simply set the intercept equal to <b>False</b> in our implementation of Ridge regression for yet another vanilla data set.
<p>
@@ -960,7 +961,6 @@ lambdas = np.logspace(-<span style="color: #B452CD">4</span>, <span style="color
<span style="color: #8B008B; font-weight: bold">for</span> i <span style="color: #8B008B">in</span> <span style="color: #658b00">range</span>(nlambdas):
lmb = lambdas[i]
OwnRidgeBeta = np.linalg.pinv(X_train.T @ X_train+lmb*I) @ X_train.T @ y_train
<span style="color: #228B22"># include lasso using Scikit-Learn</span>
<span style="color: #228B22"># Note: we include the intercept column and no scaling</span>
RegRidge = linear_model.Ridge(lmb,fit_intercept=<span style="color: #8B008B; font-weight: bold">False</span>)
RegRidge.fit(X_train,y_train)
@@ -975,6 +975,11 @@ lambdas = np.logspace(-<span style="color: #B452CD">4</span>, <span style="color
<span style="color: #658b00">print</span>(OwnRidgeBeta)
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&quot;Beta values for Scikit-Learn Ridge implementation&quot;</span>)
<span style="color: #658b00">print</span>(RegRidge.coef_)
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&quot;MSE values for own Ridge implementation&quot;</span>)
<span style="color: #658b00">print</span>(MSEOwnRidgePredict[i])
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&quot;MSE values for Scikit-Learn Ridge implementation&quot;</span>)
<span style="color: #658b00">print</span>(MSERidgePredict[i])
<span style="color: #228B22"># Now plot the results</span>
plt.figure()
plt.plot(np.log10(lambdas), MSEOwnRidgePredict, <span style="color: #CD5555">&#39;r&#39;</span>, label = <span style="color: #CD5555">&#39;MSE own Ridge Test&#39;</span>)
@@ -1053,16 +1058,11 @@ lambdas = np.logspace(-<span style="color: #B452CD">4</span>, <span style="color
intercept_ = y_scaler - X_train_mean<span style="color: #707a7c">@OwnRidgeBeta</span> <span style="color: #228B22">#The intercept can be shifted so the model can predict on uncentered data</span>
<span style="color: #228B22">#Add intercept to prediction</span>
ypredictOwnRidge = X_test @ OwnRidgeBeta + intercept_
<span style="color: #228B22">#EQUIVALENT PREDICTION:</span>
<span style="color: #228B22">#Add intercept to prediction</span>
ypredictOwnRidge = X_test_scaled @ OwnRidgeBeta + y_scaler
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&quot;Values for own Ridge prediction&quot;</span>)
<span style="color: #658b00">print</span>(ypredictOwnRidge)
RegRidge = linear_model.Ridge(lmb)
RegRidge.fit(X_train,y_train)
ypredictRidge = RegRidge.predict(X_test)
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&quot;Values for SL Ridge prediction&quot;</span>)
<span style="color: #658b00">print</span>(ypredictRidge)
MSEOwnRidgePredict[i] = MSE(y_test,ypredictOwnRidge)
MSERidgePredict[i] = MSE(y_test,ypredictRidge)
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&quot;Beta values for own Ridge implementation&quot;</span>)
@@ -1073,6 +1073,11 @@ lambdas = np.logspace(-<span style="color: #B452CD">4</span>, <span style="color
<span style="color: #658b00">print</span>(intercept_)
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&#39;Intercept from Scikit-Learn Ridge implementation&#39;</span>)
<span style="color: #658b00">print</span>(RegRidge.intercept_)
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&quot;MSE values for own Ridge implementation&quot;</span>)
<span style="color: #658b00">print</span>(MSEOwnRidgePredict[i])
<span style="color: #658b00">print</span>(<span style="color: #CD5555">&quot;MSE values for Scikit-Learn Ridge implementation&quot;</span>)
<span style="color: #658b00">print</span>(MSERidgePredict[i])
<span style="color: #228B22"># Now plot the results</span>
plt.figure()
doc/pub/week38/html/week38.html
+18 -13
View File
@@ -910,12 +910,13 @@ The intercept is the value of our output/target variable
when all our features are zero and our function crosses the \( y \)-axis (for a one-dimensional case).
<p>
Printing the MSE, we see first that both methods give the same
MSE. However, changing the value of the intercept gives a larger or
smaller MSE, meaning that the MSE is penalized by the value of the
intercept! Setting the intercept to true in the <b>Scikit-Learn</b>
function or simply scaling our results, leads to a fit which is
independent of the specific value of the intercept.
Printing the MSE, we see first that both methods give the same MSE, as
they should. However, when we move to for example Ridge regression,
the way we treat the intercept may give a larger or smaller MSE,
meaning that the MSE can be penalized by the value of the
intercept. Not including the intercept in the fit, means that the
regularization term does not include \( \beta_0 \). For different values
of \( \lambda \), this may lead to differeing MSE values.
<p>
<!-- !split --><br><br><br><br><br><br><br><br><br><br>
@@ -923,7 +924,7 @@ independent of the specific value of the intercept.
<h2 id="code-examples">Code Examples </h2>
<p>
Armed with this wisdom, we attempt first simply set the intercept eqault to <b>False</b> in our implementation of Ridge regression for yet another vanilla data set.
Armed with this wisdom, we attempt first simply set the intercept equal to <b>False</b> in our implementation of Ridge regression for yet another vanilla data set.
<p>
@@ -965,7 +966,6 @@ lambdas <span style="color: #666666">=</span> np<span style="color: #666666">.</
<span style="color: #008000; font-weight: bold">for</span> i <span style="color: #AA22FF; font-weight: bold">in</span> <span style="color: #008000">range</span>(nlambdas):
lmb <span style="color: #666666">=</span> lambdas[i]
OwnRidgeBeta <span style="color: #666666">=</span> np<span style="color: #666666">.</span>linalg<span style="color: #666666">.</span>pinv(X_train<span style="color: #666666">.</span>T <span style="color: #666666">@</span> X_train<span style="color: #666666">+</span>lmb<span style="color: #666666">*</span>I) <span style="color: #666666">@</span> X_train<span style="color: #666666">.</span>T <span style="color: #666666">@</span> y_train
<span style="color: #408080; font-style: italic"># include lasso using Scikit-Learn</span>
<span style="color: #408080; font-style: italic"># Note: we include the intercept column and no scaling</span>
RegRidge <span style="color: #666666">=</span> linear_model<span style="color: #666666">.</span>Ridge(lmb,fit_intercept<span style="color: #666666">=</span><span style="color: #008000; font-weight: bold">False</span>)
RegRidge<span style="color: #666666">.</span>fit(X_train,y_train)
@@ -980,6 +980,11 @@ lambdas <span style="color: #666666">=</span> np<span style="color: #666666">.</
<span style="color: #008000">print</span>(OwnRidgeBeta)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;Beta values for Scikit-Learn Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(RegRidge<span style="color: #666666">.</span>coef_)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;MSE values for own Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(MSEOwnRidgePredict[i])
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;MSE values for Scikit-Learn Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(MSERidgePredict[i])
<span style="color: #408080; font-style: italic"># Now plot the results</span>
plt<span style="color: #666666">.</span>figure()
plt<span style="color: #666666">.</span>plot(np<span style="color: #666666">.</span>log10(lambdas), MSEOwnRidgePredict, <span style="color: #BA2121">&#39;r&#39;</span>, label <span style="color: #666666">=</span> <span style="color: #BA2121">&#39;MSE own Ridge Test&#39;</span>)
@@ -1058,16 +1063,11 @@ lambdas <span style="color: #666666">=</span> np<span style="color: #666666">.</
intercept_ <span style="color: #666666">=</span> y_scaler <span style="color: #666666">-</span> X_train_mean<span style="color: #AA22FF">@OwnRidgeBeta</span> <span style="color: #408080; font-style: italic">#The intercept can be shifted so the model can predict on uncentered data</span>
<span style="color: #408080; font-style: italic">#Add intercept to prediction</span>
ypredictOwnRidge <span style="color: #666666">=</span> X_test <span style="color: #666666">@</span> OwnRidgeBeta <span style="color: #666666">+</span> intercept_
<span style="color: #408080; font-style: italic">#EQUIVALENT PREDICTION:</span>
<span style="color: #408080; font-style: italic">#Add intercept to prediction</span>
ypredictOwnRidge <span style="color: #666666">=</span> X_test_scaled <span style="color: #666666">@</span> OwnRidgeBeta <span style="color: #666666">+</span> y_scaler
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;Values for own Ridge prediction&quot;</span>)
<span style="color: #008000">print</span>(ypredictOwnRidge)
RegRidge <span style="color: #666666">=</span> linear_model<span style="color: #666666">.</span>Ridge(lmb)
RegRidge<span style="color: #666666">.</span>fit(X_train,y_train)
ypredictRidge <span style="color: #666666">=</span> RegRidge<span style="color: #666666">.</span>predict(X_test)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;Values for SL Ridge prediction&quot;</span>)
<span style="color: #008000">print</span>(ypredictRidge)
MSEOwnRidgePredict[i] <span style="color: #666666">=</span> MSE(y_test,ypredictOwnRidge)
MSERidgePredict[i] <span style="color: #666666">=</span> MSE(y_test,ypredictRidge)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;Beta values for own Ridge implementation&quot;</span>)
@@ -1078,6 +1078,11 @@ lambdas <span style="color: #666666">=</span> np<span style="color: #666666">.</
<span style="color: #008000">print</span>(intercept_)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&#39;Intercept from Scikit-Learn Ridge implementation&#39;</span>)
<span style="color: #008000">print</span>(RegRidge<span style="color: #666666">.</span>intercept_)
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;MSE values for own Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(MSEOwnRidgePredict[i])
<span style="color: #008000">print</span>(<span style="color: #BA2121">&quot;MSE values for Scikit-Learn Ridge implementation&quot;</span>)
<span style="color: #008000">print</span>(MSERidgePredict[i])
<span style="color: #408080; font-style: italic"># Now plot the results</span>
plt<span style="color: #666666">.</span>figure()
doc/pub/week38/ipynb/ipynb-week38-src.tar.gz
BIN
View File
Binary file not shown.
doc/pub/week38/ipynb/week38.ipynb
+19 -13
View File
@@ -837,17 +837,19 @@
"The intercept is the value of our output/target variable\n",
"when all our features are zero and our function crosses the $y$-axis (for a one-dimensional case). \n",
"\n",
"Printing the MSE, we see first that both methods give the same\n",
"MSE. However, changing the value of the intercept gives a larger or\n",
"smaller MSE, meaning that the MSE is penalized by the value of the\n",
"intercept! Setting the intercept to true in the **Scikit-Learn**\n",
"function or simply scaling our results, leads to a fit which is\n",
"independent of the specific value of the intercept.\n",
"Printing the MSE, we see first that both methods give the same MSE, as\n",
"they should. However, when we move to for example Ridge regression,\n",
"the way we treat the intercept may give a larger or smaller MSE,\n",
"meaning that the MSE can be penalized by the value of the\n",
"intercept. Not including the intercept in the fit, means that the\n",
"regularization term does not include $\\beta_0$. For different values\n",
"of $\\lambda$, this may lead to differeing MSE values.\n",
"\n",
"\n",
"\n",
"## Code Examples\n",
"\n",
"Armed with this wisdom, we attempt first simply set the intercept eqault to **False** in our implementation of Ridge regression for yet another vanilla data set."
"Armed with this wisdom, we attempt first simply set the intercept equal to **False** in our implementation of Ridge regression for yet another vanilla data set."
]
},
{
@@ -896,7 +898,6 @@
"for i in range(nlambdas):\n",
" lmb = lambdas[i]\n",
" OwnRidgeBeta = np.linalg.pinv(X_train.T @ X_train+lmb*I) @ X_train.T @ y_train\n",
" # include lasso using Scikit-Learn\n",
" # Note: we include the intercept column and no scaling\n",
" RegRidge = linear_model.Ridge(lmb,fit_intercept=False)\n",
" RegRidge.fit(X_train,y_train)\n",
@@ -911,6 +912,11 @@
" print(OwnRidgeBeta)\n",
" print(\"Beta values for Scikit-Learn Ridge implementation\")\n",
" print(RegRidge.coef_)\n",
" print(\"MSE values for own Ridge implementation\")\n",
" print(MSEOwnRidgePredict[i])\n",
" print(\"MSE values for Scikit-Learn Ridge implementation\")\n",
" print(MSERidgePredict[i])\n",
"\n",
"# Now plot the results\n",
"plt.figure()\n",
"plt.plot(np.log10(lambdas), MSEOwnRidgePredict, 'r', label = 'MSE own Ridge Test')\n",
@@ -998,16 +1004,11 @@
" intercept_ = y_scaler - X_train_mean@OwnRidgeBeta #The intercept can be shifted so the model can predict on uncentered data\n",
" #Add intercept to prediction\n",
" ypredictOwnRidge = X_test @ OwnRidgeBeta + intercept_ \n",
" #EQUIVALENT PREDICTION:\n",
" #Add intercept to prediction\n",
" ypredictOwnRidge = X_test_scaled @ OwnRidgeBeta + y_scaler \n",
" print(\"Values for own Ridge prediction\")\n",
" print(ypredictOwnRidge)\n",
" RegRidge = linear_model.Ridge(lmb)\n",
" RegRidge.fit(X_train,y_train)\n",
" ypredictRidge = RegRidge.predict(X_test)\n",
" print(\"Values for SL Ridge prediction\")\n",
" print(ypredictRidge)\n",
" MSEOwnRidgePredict[i] = MSE(y_test,ypredictOwnRidge)\n",
" MSERidgePredict[i] = MSE(y_test,ypredictRidge)\n",
" print(\"Beta values for own Ridge implementation\")\n",
@@ -1018,6 +1019,11 @@
" print(intercept_)\n",
" print('Intercept from Scikit-Learn Ridge implementation')\n",
" print(RegRidge.intercept_)\n",
" print(\"MSE values for own Ridge implementation\")\n",
" print(MSEOwnRidgePredict[i])\n",
" print(\"MSE values for Scikit-Learn Ridge implementation\")\n",
" print(MSERidgePredict[i])\n",
"\n",
"\n",
"# Now plot the results\n",
"plt.figure()\n",
doc/src/week38/week38.do.txt
+19 -13
View File
@@ -550,18 +550,20 @@ plt.show()
The intercept is the value of our output/target variable
when all our features are zero and our function crosses the $y$-axis (for a one-dimensional case).
Printing the MSE, we see first that both methods give the same
MSE. However, changing the value of the intercept gives a larger or
smaller MSE, meaning that the MSE is penalized by the value of the
intercept! Setting the intercept to true in the _Scikit-Learn_
function or simply scaling our results, leads to a fit which is
independent of the specific value of the intercept.
Printing the MSE, we see first that both methods give the same MSE, as
they should. However, when we move to for example Ridge regression,
the way we treat the intercept may give a larger or smaller MSE,
meaning that the MSE can be penalized by the value of the
intercept. Not including the intercept in the fit, means that the
regularization term does not include $\beta_0$. For different values
of $\lambda$, this may lead to differeing MSE values.
!split
===== Code Examples =====
Armed with this wisdom, we attempt first simply set the intercept eqault to _False_ in our implementation of Ridge regression for yet another vanilla data set.
Armed with this wisdom, we attempt first simply set the intercept equal to _False_ in our implementation of Ridge regression for yet another vanilla data set.
!bc pycod
import numpy as np
@@ -601,7 +603,6 @@ lambdas = np.logspace(-4, 4, nlambdas)
for i in range(nlambdas):
lmb = lambdas[i]
OwnRidgeBeta = np.linalg.pinv(X_train.T @ X_train+lmb*I) @ X_train.T @ y_train
# include lasso using Scikit-Learn
# Note: we include the intercept column and no scaling
RegRidge = linear_model.Ridge(lmb,fit_intercept=False)
RegRidge.fit(X_train,y_train)
@@ -616,6 +617,11 @@ for i in range(nlambdas):
print(OwnRidgeBeta)
print("Beta values for Scikit-Learn Ridge implementation")
print(RegRidge.coef_)
print("MSE values for own Ridge implementation")
print(MSEOwnRidgePredict[i])
print("MSE values for Scikit-Learn Ridge implementation")
print(MSERidgePredict[i])
# Now plot the results
plt.figure()
plt.plot(np.log10(lambdas), MSEOwnRidgePredict, 'r', label = 'MSE own Ridge Test')
@@ -691,16 +697,11 @@ for i in range(nlambdas):
intercept_ = y_scaler - X_train_mean@OwnRidgeBeta #The intercept can be shifted so the model can predict on uncentered data
#Add intercept to prediction
ypredictOwnRidge = X_test @ OwnRidgeBeta + intercept_
#EQUIVALENT PREDICTION:
#Add intercept to prediction
ypredictOwnRidge = X_test_scaled @ OwnRidgeBeta + y_scaler
print("Values for own Ridge prediction")
print(ypredictOwnRidge)
RegRidge = linear_model.Ridge(lmb)
RegRidge.fit(X_train,y_train)
ypredictRidge = RegRidge.predict(X_test)
print("Values for SL Ridge prediction")
print(ypredictRidge)
MSEOwnRidgePredict[i] = MSE(y_test,ypredictOwnRidge)
MSERidgePredict[i] = MSE(y_test,ypredictRidge)
print("Beta values for own Ridge implementation")
@@ -711,6 +712,11 @@ for i in range(nlambdas):
print(intercept_)
print('Intercept from Scikit-Learn Ridge implementation')
print(RegRidge.intercept_)
print("MSE values for own Ridge implementation")
print(MSEOwnRidgePredict[i])
print("MSE values for Scikit-Learn Ridge implementation")
print(MSERidgePredict[i])
# Now plot the results
plt.figure()