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

added PCA warm up

Browse Source
This commit is contained in:
mhjensen
2019-10-17 14:51:33 +02:00
parent 9ba4369c85
commit 1b8bf9954f
9 changed files with 195 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/pub/DimRed/html/._DimRed-bs007.html
+23 -9
View File
@@ -143,6 +143,9 @@ MathJax.Hub.Config({
<h2 id="___sec6" class="anchor">Why should we think of reducing the dimensionality </h2>
<p>
In addition to the plot of the features, we study now also the covariance (or rather the correlation matrix).
We use also <b>Pandas</b> to compute the correlation matrix.
<p>
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
@@ -152,16 +155,19 @@ MathJax.Hub.Config({
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.datasets</span> <span style="color: #008000; font-weight: bold">import</span> load_breast_cancer
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> LogisticRegression
cancer <span style="color: #666666">=</span> load_breast_cancer()
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">pandas</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">pd</span>
<span style="color: #408080; font-style: italic"># Making a data frame</span>
cancerpd <span style="color: #666666">=</span> pd<span style="color: #666666">.</span>DataFrame(cancer<span style="color: #666666">.</span>data, columns<span style="color: #666666">=</span>cancer<span style="color: #666666">.</span>feature_names)
fig, axes <span style="color: #666666">=</span> plt<span style="color: #666666">.</span>subplots(<span style="color: #666666">15</span>,<span style="color: #666666">2</span>,figsize<span style="color: #666666">=</span>(<span style="color: #666666">10</span>,<span style="color: #666666">20</span>))
male <span style="color: #666666">=</span> cancer<span style="color: #666666">.</span>data[cancer<span style="color: #666666">.</span>target <span style="color: #666666">==</span> <span style="color: #666666">0</span>]
bene <span style="color: #666666">=</span> cancer<span style="color: #666666">.</span>data[cancer<span style="color: #666666">.</span>target <span style="color: #666666">==</span> <span style="color: #666666">1</span>]
malignant <span style="color: #666666">=</span> cancer<span style="color: #666666">.</span>data[cancer<span style="color: #666666">.</span>target <span style="color: #666666">==</span> <span style="color: #666666">0</span>]
benign <span style="color: #666666">=</span> cancer<span style="color: #666666">.</span>data[cancer<span style="color: #666666">.</span>target <span style="color: #666666">==</span> <span style="color: #666666">1</span>]
ax <span style="color: #666666">=</span> axes<span style="color: #666666">.</span>ravel()
<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>(<span style="color: #666666">30</span>):
_, bins <span style="color: #666666">=</span> np<span style="color: #666666">.</span>histogram(cancer<span style="color: #666666">.</span>data[:,i], bins <span style="color: #666666">=50</span>)
ax[i]<span style="color: #666666">.</span>hist(male[:,i], bins <span style="color: #666666">=</span> bins, alpha <span style="color: #666666">=</span> <span style="color: #666666">0.5</span>)
ax[i]<span style="color: #666666">.</span>hist(bene[:,i], bins <span style="color: #666666">=</span> bins, alpha <span style="color: #666666">=</span> <span style="color: #666666">0.5</span>)
ax[i]<span style="color: #666666">.</span>hist(malignant[:,i], bins <span style="color: #666666">=</span> bins, alpha <span style="color: #666666">=</span> <span style="color: #666666">0.5</span>)
ax[i]<span style="color: #666666">.</span>hist(benign[:,i], bins <span style="color: #666666">=</span> bins, alpha <span style="color: #666666">=</span> <span style="color: #666666">0.5</span>)
ax[i]<span style="color: #666666">.</span>set_title(cancer<span style="color: #666666">.</span>feature_names[i])
ax[i]<span style="color: #666666">.</span>set_yticks(())
ax[<span style="color: #666666">0</span>]<span style="color: #666666">.</span>set_xlabel(<span style="color: #BA2121">&quot;Feature magnitude&quot;</span>)
@@ -170,19 +176,27 @@ ax[<span style="color: #666666">0</span>]<span style="color: #666666">.</span>le
fig<span style="color: #666666">.</span>tight_layout()
plt<span style="color: #666666">.</span>show()
<span style="color: #408080; font-style: italic"># Set up training data</span>
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">seaborn</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">sns</span>
correlation_matrix <span style="color: #666666">=</span> cancerpd<span style="color: #666666">.</span>corr()<span style="color: #666666">.</span>round(<span style="color: #666666">1</span>)
<span style="color: #408080; font-style: italic"># use the heatmap function from seaborn to plot the correlation matrix</span>
<span style="color: #408080; font-style: italic"># annot = True to print the values inside the square</span>
sns<span style="color: #666666">.</span>heatmap(data<span style="color: #666666">=</span>correlation_matrix, annot<span style="color: #666666">=</span><span style="color: #008000">True</span>)
plt<span style="color: #666666">.</span>show()
<span style="color: #408080; font-style: italic">#split into train and test and then scale thereafter</span>
X_train, X_test, y_train, y_test <span style="color: #666666">=</span> train_test_split(cancer<span style="color: #666666">.</span>data,cancer<span style="color: #666666">.</span>target,random_state<span style="color: #666666">=0</span>)
<span style="color: #408080; font-style: italic"># Perform Logistic Regression </span>
<span style="color: #008000; font-weight: bold">print</span>(X_train<span style="color: #666666">.</span>shape)
<span style="color: #008000; font-weight: bold">print</span>(X_test<span style="color: #666666">.</span>shape)
logreg <span style="color: #666666">=</span> LogisticRegression()
logreg<span style="color: #666666">.</span>fit(X_train, y_train)
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&quot;Test set accuracy: {:.2f}&quot;</span><span style="color: #666666">.</span>format(logreg<span style="color: #666666">.</span>score(X_test,y_test)))
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&quot;Test set accuracy from Logistic Regression: {:.2f}&quot;</span><span style="color: #666666">.</span>format(logreg<span style="color: #666666">.</span>score(X_test,y_test)))
<span style="color: #408080; font-style: italic"># Scale data</span>
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.preprocessing</span> <span style="color: #008000; font-weight: bold">import</span> StandardScaler
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.preprocessing</span> <span style="color: #008000; font-weight: bold">import</span> MinMaxScaler, StandardScaler
scaler <span style="color: #666666">=</span> StandardScaler()
scaler<span style="color: #666666">.</span>fit(X_train)
X_train_scaled <span style="color: #666666">=</span> scaler<span style="color: #666666">.</span>transform(X_train)
X_test_scaled <span style="color: #666666">=</span> scaler<span style="color: #666666">.</span>transform(X_test)
logreg<span style="color: #666666">.</span>fit(X_train_scaled, y_train)
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&quot;Test set accuracy scaled data: {:.2f}&quot;</span><span style="color: #666666">.</span>format(logreg<span style="color: #666666">.</span>score(X_test_scaled,y_test)))
</pre></div>
doc/pub/DimRed/html/DimRed-reveal.html
+23 -9
View File
@@ -420,6 +420,9 @@ logreg.fit(X_train_scaled, y_train)
<section>
<h2 id="___sec6">Why should we think of reducing the dimensionality </h2>
<p>
In addition to the plot of the features, we study now also the covariance (or rather the correlation matrix).
We use also <b>Pandas</b> to compute the correlation matrix.
<p>
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
@@ -429,16 +432,19 @@ logreg.fit(X_train_scaled, y_train)
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.datasets</span> <span style="color: #8B008B; font-weight: bold">import</span> load_breast_cancer
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.linear_model</span> <span style="color: #8B008B; font-weight: bold">import</span> LogisticRegression
cancer = load_breast_cancer()
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">pandas</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">pd</span>
<span style="color: #228B22"># Making a data frame</span>
cancerpd = pd.DataFrame(cancer.data, columns=cancer.feature_names)
fig, axes = plt.subplots(<span style="color: #B452CD">15</span>,<span style="color: #B452CD">2</span>,figsize=(<span style="color: #B452CD">10</span>,<span style="color: #B452CD">20</span>))
male = cancer.data[cancer.target == <span style="color: #B452CD">0</span>]
bene = cancer.data[cancer.target == <span style="color: #B452CD">1</span>]
malignant = cancer.data[cancer.target == <span style="color: #B452CD">0</span>]
benign = cancer.data[cancer.target == <span style="color: #B452CD">1</span>]
ax = axes.ravel()
<span style="color: #8B008B; font-weight: bold">for</span> i <span style="color: #8B008B">in</span> <span style="color: #658b00">range</span>(<span style="color: #B452CD">30</span>):
_, bins = np.histogram(cancer.data[:,i], bins =<span style="color: #B452CD">50</span>)
ax[i].hist(male[:,i], bins = bins, alpha = <span style="color: #B452CD">0.5</span>)
ax[i].hist(bene[:,i], bins = bins, alpha = <span style="color: #B452CD">0.5</span>)
ax[i].hist(malignant[:,i], bins = bins, alpha = <span style="color: #B452CD">0.5</span>)
ax[i].hist(benign[:,i], bins = bins, alpha = <span style="color: #B452CD">0.5</span>)
ax[i].set_title(cancer.feature_names[i])
ax[i].set_yticks(())
ax[<span style="color: #B452CD">0</span>].set_xlabel(<span style="color: #CD5555">&quot;Feature magnitude&quot;</span>)
@@ -447,19 +453,27 @@ ax[<span style="color: #B452CD">0</span>].legend([<span style="color: #CD5555">&
fig.tight_layout()
plt.show()
<span style="color: #228B22"># Set up training data</span>
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">seaborn</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">sns</span>
correlation_matrix = cancerpd.corr().round(<span style="color: #B452CD">1</span>)
<span style="color: #228B22"># use the heatmap function from seaborn to plot the correlation matrix</span>
<span style="color: #228B22"># annot = True to print the values inside the square</span>
sns.heatmap(data=correlation_matrix, annot=<span style="color: #658b00">True</span>)
plt.show()
<span style="color: #228B22">#split into train and test and then scale thereafter</span>
X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,random_state=<span style="color: #B452CD">0</span>)
<span style="color: #228B22"># Perform Logistic Regression </span>
<span style="color: #8B008B; font-weight: bold">print</span>(X_train.shape)
<span style="color: #8B008B; font-weight: bold">print</span>(X_test.shape)
logreg = LogisticRegression()
logreg.fit(X_train, y_train)
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">&quot;Test set accuracy: {:.2f}&quot;</span>.format(logreg.score(X_test,y_test)))
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">&quot;Test set accuracy from Logistic Regression: {:.2f}&quot;</span>.format(logreg.score(X_test,y_test)))
<span style="color: #228B22"># Scale data</span>
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.preprocessing</span> <span style="color: #8B008B; font-weight: bold">import</span> StandardScaler
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.preprocessing</span> <span style="color: #8B008B; font-weight: bold">import</span> MinMaxScaler, StandardScaler
scaler = StandardScaler()
scaler.fit(X_train)
X_train_scaled = scaler.transform(X_train)
X_test_scaled = scaler.transform(X_test)
logreg.fit(X_train_scaled, y_train)
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">&quot;Test set accuracy scaled data: {:.2f}&quot;</span>.format(logreg.score(X_test_scaled,y_test)))
</pre></div>
doc/pub/DimRed/html/DimRed-solarized.html
+23 -9
View File
@@ -403,6 +403,9 @@ logreg.fit(X_train_scaled, y_train)
<h2 id="___sec6">Why should we think of reducing the dimensionality </h2>
<p>
In addition to the plot of the features, we study now also the covariance (or rather the correlation matrix).
We use also <b>Pandas</b> to compute the correlation matrix.
<p>
<!-- code=python (!bc pycod) typeset with pygments style "perldoc" -->
@@ -412,16 +415,19 @@ logreg.fit(X_train_scaled, y_train)
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.datasets</span> <span style="color: #8B008B; font-weight: bold">import</span> load_breast_cancer
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.linear_model</span> <span style="color: #8B008B; font-weight: bold">import</span> LogisticRegression
cancer = load_breast_cancer()
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">pandas</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">pd</span>
<span style="color: #228B22"># Making a data frame</span>
cancerpd = pd.DataFrame(cancer.data, columns=cancer.feature_names)
fig, axes = plt.subplots(<span style="color: #B452CD">15</span>,<span style="color: #B452CD">2</span>,figsize=(<span style="color: #B452CD">10</span>,<span style="color: #B452CD">20</span>))
male = cancer.data[cancer.target == <span style="color: #B452CD">0</span>]
bene = cancer.data[cancer.target == <span style="color: #B452CD">1</span>]
malignant = cancer.data[cancer.target == <span style="color: #B452CD">0</span>]
benign = cancer.data[cancer.target == <span style="color: #B452CD">1</span>]
ax = axes.ravel()
<span style="color: #8B008B; font-weight: bold">for</span> i <span style="color: #8B008B">in</span> <span style="color: #658b00">range</span>(<span style="color: #B452CD">30</span>):
_, bins = np.histogram(cancer.data[:,i], bins =<span style="color: #B452CD">50</span>)
ax[i].hist(male[:,i], bins = bins, alpha = <span style="color: #B452CD">0.5</span>)
ax[i].hist(bene[:,i], bins = bins, alpha = <span style="color: #B452CD">0.5</span>)
ax[i].hist(malignant[:,i], bins = bins, alpha = <span style="color: #B452CD">0.5</span>)
ax[i].hist(benign[:,i], bins = bins, alpha = <span style="color: #B452CD">0.5</span>)
ax[i].set_title(cancer.feature_names[i])
ax[i].set_yticks(())
ax[<span style="color: #B452CD">0</span>].set_xlabel(<span style="color: #CD5555">&quot;Feature magnitude&quot;</span>)
@@ -430,19 +436,27 @@ ax[<span style="color: #B452CD">0</span>].legend([<span style="color: #CD5555">&
fig.tight_layout()
plt.show()
<span style="color: #228B22"># Set up training data</span>
<span style="color: #8B008B; font-weight: bold">import</span> <span style="color: #008b45; text-decoration: underline">seaborn</span> <span style="color: #8B008B; font-weight: bold">as</span> <span style="color: #008b45; text-decoration: underline">sns</span>
correlation_matrix = cancerpd.corr().round(<span style="color: #B452CD">1</span>)
<span style="color: #228B22"># use the heatmap function from seaborn to plot the correlation matrix</span>
<span style="color: #228B22"># annot = True to print the values inside the square</span>
sns.heatmap(data=correlation_matrix, annot=<span style="color: #658b00">True</span>)
plt.show()
<span style="color: #228B22">#split into train and test and then scale thereafter</span>
X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,random_state=<span style="color: #B452CD">0</span>)
<span style="color: #228B22"># Perform Logistic Regression </span>
<span style="color: #8B008B; font-weight: bold">print</span>(X_train.shape)
<span style="color: #8B008B; font-weight: bold">print</span>(X_test.shape)
logreg = LogisticRegression()
logreg.fit(X_train, y_train)
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">&quot;Test set accuracy: {:.2f}&quot;</span>.format(logreg.score(X_test,y_test)))
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">&quot;Test set accuracy from Logistic Regression: {:.2f}&quot;</span>.format(logreg.score(X_test,y_test)))
<span style="color: #228B22"># Scale data</span>
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.preprocessing</span> <span style="color: #8B008B; font-weight: bold">import</span> StandardScaler
<span style="color: #8B008B; font-weight: bold">from</span> <span style="color: #008b45; text-decoration: underline">sklearn.preprocessing</span> <span style="color: #8B008B; font-weight: bold">import</span> MinMaxScaler, StandardScaler
scaler = StandardScaler()
scaler.fit(X_train)
X_train_scaled = scaler.transform(X_train)
X_test_scaled = scaler.transform(X_test)
logreg.fit(X_train_scaled, y_train)
<span style="color: #8B008B; font-weight: bold">print</span>(<span style="color: #CD5555">&quot;Test set accuracy scaled data: {:.2f}&quot;</span>.format(logreg.score(X_test_scaled,y_test)))
</pre></div>
doc/pub/DimRed/html/DimRed.html
+23 -9
View File
@@ -408,6 +408,9 @@ logreg<span style="color: #666666">.</span>fit(X_train_scaled, y_train)
<h2 id="___sec6">Why should we think of reducing the dimensionality </h2>
<p>
In addition to the plot of the features, we study now also the covariance (or rather the correlation matrix).
We use also <b>Pandas</b> to compute the correlation matrix.
<p>
<!-- code=python (!bc pycod) typeset with pygments style "default" -->
@@ -417,16 +420,19 @@ logreg<span style="color: #666666">.</span>fit(X_train_scaled, y_train)
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.datasets</span> <span style="color: #008000; font-weight: bold">import</span> load_breast_cancer
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.linear_model</span> <span style="color: #008000; font-weight: bold">import</span> LogisticRegression
cancer <span style="color: #666666">=</span> load_breast_cancer()
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">pandas</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">pd</span>
<span style="color: #408080; font-style: italic"># Making a data frame</span>
cancerpd <span style="color: #666666">=</span> pd<span style="color: #666666">.</span>DataFrame(cancer<span style="color: #666666">.</span>data, columns<span style="color: #666666">=</span>cancer<span style="color: #666666">.</span>feature_names)
fig, axes <span style="color: #666666">=</span> plt<span style="color: #666666">.</span>subplots(<span style="color: #666666">15</span>,<span style="color: #666666">2</span>,figsize<span style="color: #666666">=</span>(<span style="color: #666666">10</span>,<span style="color: #666666">20</span>))
male <span style="color: #666666">=</span> cancer<span style="color: #666666">.</span>data[cancer<span style="color: #666666">.</span>target <span style="color: #666666">==</span> <span style="color: #666666">0</span>]
bene <span style="color: #666666">=</span> cancer<span style="color: #666666">.</span>data[cancer<span style="color: #666666">.</span>target <span style="color: #666666">==</span> <span style="color: #666666">1</span>]
malignant <span style="color: #666666">=</span> cancer<span style="color: #666666">.</span>data[cancer<span style="color: #666666">.</span>target <span style="color: #666666">==</span> <span style="color: #666666">0</span>]
benign <span style="color: #666666">=</span> cancer<span style="color: #666666">.</span>data[cancer<span style="color: #666666">.</span>target <span style="color: #666666">==</span> <span style="color: #666666">1</span>]
ax <span style="color: #666666">=</span> axes<span style="color: #666666">.</span>ravel()
<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>(<span style="color: #666666">30</span>):
_, bins <span style="color: #666666">=</span> np<span style="color: #666666">.</span>histogram(cancer<span style="color: #666666">.</span>data[:,i], bins <span style="color: #666666">=50</span>)
ax[i]<span style="color: #666666">.</span>hist(male[:,i], bins <span style="color: #666666">=</span> bins, alpha <span style="color: #666666">=</span> <span style="color: #666666">0.5</span>)
ax[i]<span style="color: #666666">.</span>hist(bene[:,i], bins <span style="color: #666666">=</span> bins, alpha <span style="color: #666666">=</span> <span style="color: #666666">0.5</span>)
ax[i]<span style="color: #666666">.</span>hist(malignant[:,i], bins <span style="color: #666666">=</span> bins, alpha <span style="color: #666666">=</span> <span style="color: #666666">0.5</span>)
ax[i]<span style="color: #666666">.</span>hist(benign[:,i], bins <span style="color: #666666">=</span> bins, alpha <span style="color: #666666">=</span> <span style="color: #666666">0.5</span>)
ax[i]<span style="color: #666666">.</span>set_title(cancer<span style="color: #666666">.</span>feature_names[i])
ax[i]<span style="color: #666666">.</span>set_yticks(())
ax[<span style="color: #666666">0</span>]<span style="color: #666666">.</span>set_xlabel(<span style="color: #BA2121">&quot;Feature magnitude&quot;</span>)
@@ -435,19 +441,27 @@ ax[<span style="color: #666666">0</span>]<span style="color: #666666">.</span>le
fig<span style="color: #666666">.</span>tight_layout()
plt<span style="color: #666666">.</span>show()
<span style="color: #408080; font-style: italic"># Set up training data</span>
<span style="color: #008000; font-weight: bold">import</span> <span style="color: #0000FF; font-weight: bold">seaborn</span> <span style="color: #008000; font-weight: bold">as</span> <span style="color: #0000FF; font-weight: bold">sns</span>
correlation_matrix <span style="color: #666666">=</span> cancerpd<span style="color: #666666">.</span>corr()<span style="color: #666666">.</span>round(<span style="color: #666666">1</span>)
<span style="color: #408080; font-style: italic"># use the heatmap function from seaborn to plot the correlation matrix</span>
<span style="color: #408080; font-style: italic"># annot = True to print the values inside the square</span>
sns<span style="color: #666666">.</span>heatmap(data<span style="color: #666666">=</span>correlation_matrix, annot<span style="color: #666666">=</span><span style="color: #008000">True</span>)
plt<span style="color: #666666">.</span>show()
<span style="color: #408080; font-style: italic">#split into train and test and then scale thereafter</span>
X_train, X_test, y_train, y_test <span style="color: #666666">=</span> train_test_split(cancer<span style="color: #666666">.</span>data,cancer<span style="color: #666666">.</span>target,random_state<span style="color: #666666">=0</span>)
<span style="color: #408080; font-style: italic"># Perform Logistic Regression </span>
<span style="color: #008000; font-weight: bold">print</span>(X_train<span style="color: #666666">.</span>shape)
<span style="color: #008000; font-weight: bold">print</span>(X_test<span style="color: #666666">.</span>shape)
logreg <span style="color: #666666">=</span> LogisticRegression()
logreg<span style="color: #666666">.</span>fit(X_train, y_train)
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&quot;Test set accuracy: {:.2f}&quot;</span><span style="color: #666666">.</span>format(logreg<span style="color: #666666">.</span>score(X_test,y_test)))
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&quot;Test set accuracy from Logistic Regression: {:.2f}&quot;</span><span style="color: #666666">.</span>format(logreg<span style="color: #666666">.</span>score(X_test,y_test)))
<span style="color: #408080; font-style: italic"># Scale data</span>
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.preprocessing</span> <span style="color: #008000; font-weight: bold">import</span> StandardScaler
<span style="color: #008000; font-weight: bold">from</span> <span style="color: #0000FF; font-weight: bold">sklearn.preprocessing</span> <span style="color: #008000; font-weight: bold">import</span> MinMaxScaler, StandardScaler
scaler <span style="color: #666666">=</span> StandardScaler()
scaler<span style="color: #666666">.</span>fit(X_train)
X_train_scaled <span style="color: #666666">=</span> scaler<span style="color: #666666">.</span>transform(X_train)
X_test_scaled <span style="color: #666666">=</span> scaler<span style="color: #666666">.</span>transform(X_test)
logreg<span style="color: #666666">.</span>fit(X_train_scaled, y_train)
<span style="color: #008000; font-weight: bold">print</span>(<span style="color: #BA2121">&quot;Test set accuracy scaled data: {:.2f}&quot;</span><span style="color: #666666">.</span>format(logreg<span style="color: #666666">.</span>score(X_test_scaled,y_test)))
</pre></div>
doc/pub/DimRed/ipynb/DimRed.ipynb
+24 -10
View File
@@ -283,7 +283,10 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"## Why should we think of reducing the dimensionality"
"## Why should we think of reducing the dimensionality\n",
"\n",
"In addition to the plot of the features, we study now also the covariance (or rather the correlation matrix).\n",
"We use also **Pandas** to compute the correlation matrix."
]
},
{
@@ -300,16 +303,19 @@
"from sklearn.datasets import load_breast_cancer\n",
"from sklearn.linear_model import LogisticRegression\n",
"cancer = load_breast_cancer()\n",
"import pandas as pd\n",
"# Making a data frame\n",
"cancerpd = pd.DataFrame(cancer.data, columns=cancer.feature_names)\n",
"\n",
"fig, axes = plt.subplots(15,2,figsize=(10,20))\n",
"male = cancer.data[cancer.target == 0]\n",
"bene = cancer.data[cancer.target == 1]\n",
"malignant = cancer.data[cancer.target == 0]\n",
"benign = cancer.data[cancer.target == 1]\n",
"ax = axes.ravel()\n",
"\n",
"for i in range(30):\n",
" _, bins = np.histogram(cancer.data[:,i], bins =50)\n",
" ax[i].hist(male[:,i], bins = bins, alpha = 0.5)\n",
" ax[i].hist(bene[:,i], bins = bins, alpha = 0.5)\n",
" ax[i].hist(malignant[:,i], bins = bins, alpha = 0.5)\n",
" ax[i].hist(benign[:,i], bins = bins, alpha = 0.5)\n",
" ax[i].set_title(cancer.feature_names[i])\n",
" ax[i].set_yticks(())\n",
"ax[0].set_xlabel(\"Feature magnitude\")\n",
@@ -318,19 +324,27 @@
"fig.tight_layout()\n",
"plt.show()\n",
"\n",
"# Set up training data\n",
"import seaborn as sns\n",
"correlation_matrix = cancerpd.corr().round(1)\n",
"# use the heatmap function from seaborn to plot the correlation matrix\n",
"# annot = True to print the values inside the square\n",
"sns.heatmap(data=correlation_matrix, annot=True)\n",
"plt.show()\n",
"#split into train and test and then scale thereafter\n",
"X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,random_state=0)\n",
"# Perform Logistic Regression \n",
"print(X_train.shape)\n",
"print(X_test.shape)\n",
"\n",
"logreg = LogisticRegression()\n",
"logreg.fit(X_train, y_train)\n",
"print(\"Test set accuracy: {:.2f}\".format(logreg.score(X_test,y_test)))\n",
"print(\"Test set accuracy from Logistic Regression: {:.2f}\".format(logreg.score(X_test,y_test)))\n",
"\n",
"# Scale data\n",
"from sklearn.preprocessing import StandardScaler\n",
"from sklearn.preprocessing import MinMaxScaler, StandardScaler\n",
"scaler = StandardScaler()\n",
"scaler.fit(X_train)\n",
"X_train_scaled = scaler.transform(X_train)\n",
"X_test_scaled = scaler.transform(X_test)\n",
"\n",
"logreg.fit(X_train_scaled, y_train)\n",
"print(\"Test set accuracy scaled data: {:.2f}\".format(logreg.score(X_test_scaled,y_test)))"
]
doc/pub/DimRed/ipynb/ipynb-DimRed-src.tar.gz
BIN
View File
Binary file not shown.
doc/pub/DimRed/pdf/DimRed-minted.pdf
BIN
View File
Binary file not shown.
doc/src/DimRed/DimRed.do.txt
+26 -9
View File
@@ -251,6 +251,8 @@ print("Test set accuracy scaled data: {:.2f}".format(logreg.score(X_test_scaled,
!split
===== Why should we think of reducing the dimensionality =====
In addition to the plot of the features, we study now also the covariance (or rather the correlation matrix).
We use also _Pandas_ to compute the correlation matrix.
!bc pycod
import matplotlib.pyplot as plt
import numpy as np
@@ -258,16 +260,19 @@ from sklearn.model_selection import train_test_split
from sklearn.datasets import load_breast_cancer
from sklearn.linear_model import LogisticRegression
cancer = load_breast_cancer()
import pandas as pd
# Making a data frame
cancerpd = pd.DataFrame(cancer.data, columns=cancer.feature_names)
fig, axes = plt.subplots(15,2,figsize=(10,20))
male = cancer.data[cancer.target == 0]
bene = cancer.data[cancer.target == 1]
malignant = cancer.data[cancer.target == 0]
benign = cancer.data[cancer.target == 1]
ax = axes.ravel()
for i in range(30):
_, bins = np.histogram(cancer.data[:,i], bins =50)
ax[i].hist(male[:,i], bins = bins, alpha = 0.5)
ax[i].hist(bene[:,i], bins = bins, alpha = 0.5)
ax[i].hist(malignant[:,i], bins = bins, alpha = 0.5)
ax[i].hist(benign[:,i], bins = bins, alpha = 0.5)
ax[i].set_title(cancer.feature_names[i])
ax[i].set_yticks(())
ax[0].set_xlabel("Feature magnitude")
@@ -276,22 +281,34 @@ ax[0].legend(["Malignant", "Benign"], loc ="best")
fig.tight_layout()
plt.show()
# Set up training data
import seaborn as sns
correlation_matrix = cancerpd.corr().round(1)
# use the heatmap function from seaborn to plot the correlation matrix
# annot = True to print the values inside the square
sns.heatmap(data=correlation_matrix, annot=True)
plt.show()
#split into train and test and then scale thereafter
X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,random_state=0)
# Perform Logistic Regression
print(X_train.shape)
print(X_test.shape)
logreg = LogisticRegression()
logreg.fit(X_train, y_train)
print("Test set accuracy: {:.2f}".format(logreg.score(X_test,y_test)))
print("Test set accuracy from Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
# Scale data
from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import MinMaxScaler, StandardScaler
scaler = StandardScaler()
scaler.fit(X_train)
X_train_scaled = scaler.transform(X_train)
X_test_scaled = scaler.transform(X_test)
logreg.fit(X_train_scaled, y_train)
print("Test set accuracy scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
!ec
doc/src/DimRed/PCAcancer.py
+53
View File
@@ -0,0 +1,53 @@
import matplotlib.pyplot as plt
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_breast_cancer
from sklearn.linear_model import LogisticRegression
cancer = load_breast_cancer()
import pandas as pd
cancerpd = pd.DataFrame(cancer.data, columns=cancer.feature_names)
fig, axes = plt.subplots(15,2,figsize=(10,20))
malignant = cancer.data[cancer.target == 0]
benign = cancer.data[cancer.target == 1]
ax = axes.ravel()
for i in range(30):
_, bins = np.histogram(cancer.data[:,i], bins =50)
ax[i].hist(malignant[:,i], bins = bins, alpha = 0.5)
ax[i].hist(benign[:,i], bins = bins, alpha = 0.5)
ax[i].set_title(cancer.feature_names[i])
ax[i].set_yticks(())
ax[0].set_xlabel("Feature magnitude")
ax[0].set_ylabel("Frequency")
ax[0].legend(["Malignant", "Benign"], loc ="best")
fig.tight_layout()
plt.show()
import seaborn as sns
correlation_matrix = cancerpd.corr().round(1)
# use the heatmap function from seaborn to plot the correlation matrix
# annot = True to print the values inside the square
sns.heatmap(data=correlation_matrix, annot=True)
plt.show()
X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,random_state=0)
print(X_train.shape)
print(X_test.shape)
logreg = LogisticRegression()
logreg.fit(X_train, y_train)
print("Test set accuracy from Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
from sklearn.preprocessing import MinMaxScaler, StandardScaler
scaler = StandardScaler()
scaler.fit(X_train)
X_train_scaled = scaler.transform(X_train)
X_test_scaled = scaler.transform(X_test)
logreg.fit(X_train_scaled, y_train)
print("Test set accuracy scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))