-
diff --git a/doc/pub/DecisionTrees/html/._DecisionTrees-bs001.html b/doc/pub/DecisionTrees/html/._DecisionTrees-bs001.html index ecec6e052..9c06d6c60 100644 --- a/doc/pub/DecisionTrees/html/._DecisionTrees-bs001.html +++ b/doc/pub/DecisionTrees/html/._DecisionTrees-bs001.html @@ -85,8 +85,7 @@ Automatically generated HTML file from DocOnce source ('Final regressor code', 2, None, '___sec28'), ('Pros and cons of trees, pros', 2, None, '___sec29'), ('Disadvantages', 2, None, '___sec30'), - ('From a Single Tree to Many Trees, that is meet the Jungle of ' - 'Methods', + ('From a Single Tree to Many Trees, Meet the Jungle of Methods', 2, None, '___sec31'), @@ -101,8 +100,14 @@ Automatically generated HTML file from DocOnce source ('Now Bagging', 2, None, '___sec37'), ('Random forests', 2, None, '___sec38'), ('Random Forest Algorithm', 2, None, '___sec39'), - ('A simple scikit-learn example', 2, None, '___sec40'), - ('Then random forests', 2, None, '___sec41'), + ('Random Forests Compared with other Methods on the Cancer Data', + 2, + None, + '___sec40'), + ('Compare Bagging on Trees with Random Forests', + 2, + None, + '___sec41'), ('Feature Importance', 2, None, '___sec42'), ("Boosting, a Bird'e Eye", 2, None, '___sec43'), ('Adaptive boosting: AdaBoost, Basic Algorithm', @@ -187,7 +192,7 @@ MathJax.Hub.Config({
As stated above and seen in many of the examples discussed here about @@ -236,7 +241,7 @@ This leads us to a set of different methods that can combine different machine learning algorithms or just use one of them to construct forests and jungles of trees, homogeneous ones or heterogenous ones. These methods are recognized by different names which we will try to explain here. These are
-
diff --git a/doc/pub/DecisionTrees/html/DecisionTrees-reveal.html b/doc/pub/DecisionTrees/html/DecisionTrees-reveal.html index af922e8f1..11ddd11e0 100644 --- a/doc/pub/DecisionTrees/html/DecisionTrees-reveal.html +++ b/doc/pub/DecisionTrees/html/DecisionTrees-reveal.html @@ -148,7 +148,7 @@ MathJax.Hub.Config({
-
@@ -1439,7 +1439,7 @@ However, by aggregating many decision trees, using methods like bagging, random
As stated above and seen in many of the examples discussed here about
@@ -1452,7 +1452,7 @@ This leads us to a set of different methods that can combine different
machine learning algorithms or just use one of them to construct forests and jungles of trees, homogeneous ones or heterogenous ones. These methods are recognized by different names which we will try to explain here. These are
+We will grow of forest of say \( M \) trees.
+
+
+
-
diff --git a/doc/pub/DecisionTrees/html/DecisionTrees-solarized.html b/doc/pub/DecisionTrees/html/DecisionTrees-solarized.html
index 56336a6f5..19099da6f 100644
--- a/doc/pub/DecisionTrees/html/DecisionTrees-solarized.html
+++ b/doc/pub/DecisionTrees/html/DecisionTrees-solarized.html
@@ -105,8 +105,7 @@ div { text-align: justify; text-justify: inter-word; }
('Final regressor code', 2, None, '___sec28'),
('Pros and cons of trees, pros', 2, None, '___sec29'),
('Disadvantages', 2, None, '___sec30'),
- ('From a Single Tree to Many Trees, that is meet the Jungle of '
- 'Methods',
+ ('From a Single Tree to Many Trees, Meet the Jungle of Methods',
2,
None,
'___sec31'),
@@ -121,8 +120,14 @@ div { text-align: justify; text-justify: inter-word; }
('Now Bagging', 2, None, '___sec37'),
('Random forests', 2, None, '___sec38'),
('Random Forest Algorithm', 2, None, '___sec39'),
- ('A simple scikit-learn example', 2, None, '___sec40'),
- ('Then random forests', 2, None, '___sec41'),
+ ('Random Forests Compared with other Methods on the Cancer Data',
+ 2,
+ None,
+ '___sec40'),
+ ('Compare Bagging on Trees with Random Forests',
+ 2,
+ None,
+ '___sec41'),
('Feature Importance', 2, None, '___sec42'),
("Boosting, a Bird'e Eye", 2, None, '___sec43'),
('Adaptive boosting: AdaBoost, Basic Algorithm',
@@ -180,7 +185,7 @@ MathJax.Hub.Config({
-
As stated above and seen in many of the examples discussed here about
@@ -1444,7 +1449,7 @@ This leads us to a set of different methods that can combine different
machine learning algorithms or just use one of them to construct forests and jungles of trees, homogeneous ones or heterogenous ones. These methods are recognized by different names which we will try to explain here. These are
+We will grow of forest of say \( M \) trees.
+
+
-
diff --git a/doc/pub/DecisionTrees/html/DecisionTrees.html b/doc/pub/DecisionTrees/html/DecisionTrees.html
index c0ce80a23..1456bf337 100644
--- a/doc/pub/DecisionTrees/html/DecisionTrees.html
+++ b/doc/pub/DecisionTrees/html/DecisionTrees.html
@@ -110,8 +110,7 @@ div { text-align: justify; text-justify: inter-word; }
('Final regressor code', 2, None, '___sec28'),
('Pros and cons of trees, pros', 2, None, '___sec29'),
('Disadvantages', 2, None, '___sec30'),
- ('From a Single Tree to Many Trees, that is meet the Jungle of '
- 'Methods',
+ ('From a Single Tree to Many Trees, Meet the Jungle of Methods',
2,
None,
'___sec31'),
@@ -126,8 +125,14 @@ div { text-align: justify; text-justify: inter-word; }
('Now Bagging', 2, None, '___sec37'),
('Random forests', 2, None, '___sec38'),
('Random Forest Algorithm', 2, None, '___sec39'),
- ('A simple scikit-learn example', 2, None, '___sec40'),
- ('Then random forests', 2, None, '___sec41'),
+ ('Random Forests Compared with other Methods on the Cancer Data',
+ 2,
+ None,
+ '___sec40'),
+ ('Compare Bagging on Trees with Random Forests',
+ 2,
+ None,
+ '___sec41'),
('Feature Importance', 2, None, '___sec42'),
("Boosting, a Bird'e Eye", 2, None, '___sec43'),
('Adaptive boosting: AdaBoost, Basic Algorithm',
@@ -185,7 +190,7 @@ MathJax.Hub.Config({
-
As stated above and seen in many of the examples discussed here about
@@ -1449,7 +1454,7 @@ This leads us to a set of different methods that can combine different
machine learning algorithms or just use one of them to construct forests and jungles of trees, homogeneous ones or heterogenous ones. These methods are recognized by different names which we will try to explain here. These are
+We will grow of forest of say \( M \) trees.
+
+
-
diff --git a/doc/pub/DecisionTrees/ipynb/DecisionTrees.ipynb b/doc/pub/DecisionTrees/ipynb/DecisionTrees.ipynb
index 7cf60d741..a8f87d819 100644
--- a/doc/pub/DecisionTrees/ipynb/DecisionTrees.ipynb
+++ b/doc/pub/DecisionTrees/ipynb/DecisionTrees.ipynb
@@ -10,7 +10,7 @@
" \n",
"**Morten Hjorth-Jensen**, Department of Physics, University of Oslo and Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University\n",
"\n",
- "Date: **Nov 4, 2019**\n",
+ "Date: **Nov 5, 2019**\n",
"\n",
"Copyright 1999-2019, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license\n",
"\n",
@@ -1397,7 +1397,7 @@
"However, by aggregating many decision trees, using methods like bagging, random forests, and boosting, the predictive performance of trees can be substantially improved. \n",
"\n",
"\n",
- "## From a Single Tree to Many Trees, that is meet the Jungle of Methods\n",
+ "## From a Single Tree to Many Trees, Meet the Jungle of Methods\n",
"\n",
"As stated above and seen in many of the examples discussed here about\n",
"a single decision tree, we often end up overfitting our training\n",
@@ -1406,7 +1406,7 @@
"\n",
"This leads us to a set of different methods that can combine different\n",
"machine learning algorithms or just use one of them to construct forests and jungles of trees, homogeneous ones or heterogenous ones. These methods are recognized by different names which we will try to explain here. These are\n",
- "1. Votign classifiers\n",
+ "1. Voting classifiers\n",
"\n",
"2. Bagging and Pasting\n",
"\n",
@@ -1766,7 +1766,24 @@
"## Random Forest Algorithm\n",
"The algorithm described here can be applied to both classification and regression problems.\n",
"\n",
- "## A simple scikit-learn example"
+ "We will grow of forest of say $M$ trees.\n",
+ "1. For $m=1:M$ we\n",
+ "\n",
+ " * Draw a bootstrap sample of from the training data organized in our $\\boldsymbol{X}$ matrix.\n",
+ "\n",
+ " * We grow then a random forest tree $T_m$ based on the bootstrapped data by repeating the steps outlined till we reach the maximum node size is reached\n",
+ "\n",
+ "1. we select $m \\le p$ varibales at random from the $p$ predictors/features\n",
+ "\n",
+ "2. pick the best split point among the $m$ features using either the CART algorithm or the ID3 for classification and create a new node\n",
+ "\n",
+ "3. split the node into daughter nodes\n",
+ "\n",
+ "\n",
+ "\n",
+ "4. Output then the ensemble of trees $\\{T_m\\}_1^{M}$ and make predictions for either a regression type of problem or a classification type of problem. \n",
+ "\n",
+ "## Random Forests Compared with other Methods on the Cancer Data"
]
},
{
@@ -1777,23 +1794,79 @@
},
"outputs": [],
"source": [
+ "import matplotlib.pyplot as plt\n",
+ "import numpy as np\n",
+ "from sklearn.model_selection import train_test_split \n",
+ "from sklearn.datasets import load_breast_cancer\n",
+ "from sklearn.svm import SVC\n",
+ "from sklearn.linear_model import LogisticRegression\n",
+ "from sklearn.tree import DecisionTreeClassifier\n",
+ "\n",
+ "# Load the data\n",
+ "cancer = load_breast_cancer()\n",
+ "\n",
+ "X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,random_state=0)\n",
+ "print(X_train.shape)\n",
+ "print(X_test.shape)\n",
+ "# Logistic Regression\n",
+ "logreg = LogisticRegression(solver='lbfgs')\n",
+ "logreg.fit(X_train, y_train)\n",
+ "print(\"Test set accuracy with Logistic Regression: {:.2f}\".format(logreg.score(X_test,y_test)))\n",
+ "# Support vector machine\n",
+ "svm = SVC(gamma='auto', C=100)\n",
+ "svm.fit(X_train, y_train)\n",
+ "print(\"Test set accuracy with SVM: {:.2f}\".format(svm.score(X_test,y_test)))\n",
+ "# Decision Trees\n",
+ "deep_tree_clf = DecisionTreeClassifier(max_depth=None)\n",
+ "deep_tree_clf.fit(X_train, y_train)\n",
+ "print(\"Test set accuracy with Decision Trees: {:.2f}\".format(deep_tree_clf.score(X_test,y_test)))\n",
+ "#now scale the data\n",
+ "from sklearn.preprocessing import 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",
+ "# Logistic Regression\n",
+ "logreg.fit(X_train_scaled, y_train)\n",
+ "print(\"Test set accuracy Logistic Regression with scaled data: {:.2f}\".format(logreg.score(X_test_scaled,y_test)))\n",
+ "# Support Vector Machine\n",
+ "svm.fit(X_train_scaled, y_train)\n",
+ "print(\"Test set accuracy SVM with scaled data: {:.2f}\".format(logreg.score(X_test_scaled,y_test)))\n",
+ "# Decision Trees\n",
+ "deep_tree_clf.fit(X_train_scaled, y_train)\n",
+ "print(\"Test set accuracy with Decision Trees and scaled data: {:.2f}\".format(deep_tree_clf.score(X_test_scaled,y_test)))\n",
+ "\n",
+ "\n",
"from sklearn.ensemble import RandomForestClassifier\n",
"from sklearn.preprocessing import LabelEncoder\n",
"from sklearn.model_selection import cross_validate\n",
"# Data set not specificied\n",
- "X = dataset.XXX\n",
- "Y = dataset.YYY\n",
- "#Instantiate the model with 100 trees and entropy as splitting criteria\n",
- "Random_Forest_model = RandomForestClassifier(n_estimators=100,criterion=\"entropy\")\n",
+ "#Instantiate the model with 500 trees and entropy as splitting criteria\n",
+ "Random_Forest_model = RandomForestClassifier(n_estimators=500,criterion=\"entropy\")\n",
+ "Random_Forest_model.fit(X_train_scaled, y_train)\n",
"#Cross validation\n",
- "accuracy = cross_validate(Random_Forest_model,X,Y,cv=10)['test_score']"
+ "accuracy = cross_validate(Random_Forest_model,X_test_scaled,y_test,cv=10)['test_score']\n",
+ "print(accuracy)\n",
+ "print(\"Test set accuracy with Random Forests and scaled data: {:.2f}\".format(Random_Forest_model.score(X_test_scaled,y_test)))\n",
+ "\n",
+ "\n",
+ "import scikitplot as skplt\n",
+ "y_pred = Random_Forest_model.predict(X_test_scaled)\n",
+ "skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)\n",
+ "#From a Single Tree to Many Trees, that is meet the Jungle of Methods
+From a Single Tree to Many Trees, Meet the Jungle of Methods
-
Random Forest Algorithm
The algorithm described here can be applied to both classification and regression problems.
+
+
+
+
+
+
+
+
+A simple scikit-learn example
+Random Forests Compared with other Methods on the Cancer Data
from sklearn.ensemble import RandomForestClassifier
+
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.svm import SVC
+from sklearn.linear_model import LogisticRegression
+from sklearn.tree import DecisionTreeClassifier
+
+# Load the data
+cancer = load_breast_cancer()
+
+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)
+# Logistic Regression
+logreg = LogisticRegression(solver='lbfgs')
+logreg.fit(X_train, y_train)
+print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
+# Support vector machine
+svm = SVC(gamma='auto', C=100)
+svm.fit(X_train, y_train)
+print("Test set accuracy with SVM: {:.2f}".format(svm.score(X_test,y_test)))
+# Decision Trees
+deep_tree_clf = DecisionTreeClassifier(max_depth=None)
+deep_tree_clf.fit(X_train, y_train)
+print("Test set accuracy with Decision Trees: {:.2f}".format(deep_tree_clf.score(X_test,y_test)))
+#now scale the data
+from sklearn.preprocessing import StandardScaler
+scaler = StandardScaler()
+scaler.fit(X_train)
+X_train_scaled = scaler.transform(X_train)
+X_test_scaled = scaler.transform(X_test)
+# Logistic Regression
+logreg.fit(X_train_scaled, y_train)
+print("Test set accuracy Logistic Regression with scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
+# Support Vector Machine
+svm.fit(X_train_scaled, y_train)
+print("Test set accuracy SVM with scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
+# Decision Trees
+deep_tree_clf.fit(X_train_scaled, y_train)
+print("Test set accuracy with Decision Trees and scaled data: {:.2f}".format(deep_tree_clf.score(X_test_scaled,y_test)))
+
+
+from sklearn.ensemble import RandomForestClassifier
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import cross_validate
# Data set not specificied
-X = dataset.XXX
-Y = dataset.YYY
-#Instantiate the model with 100 trees and entropy as splitting criteria
-Random_Forest_model = RandomForestClassifier(n_estimators=100,criterion="entropy")
+#Instantiate the model with 500 trees and entropy as splitting criteria
+Random_Forest_model = RandomForestClassifier(n_estimators=500,criterion="entropy")
+Random_Forest_model.fit(X_train_scaled, y_train)
#Cross validation
-accuracy = cross_validate(Random_Forest_model,X,Y,cv=10)['test_score']
+accuracy = cross_validate(Random_Forest_model,X_test_scaled,y_test,cv=10)['test_score']
+print(accuracy)
+print("Test set accuracy with Random Forests and scaled data: {:.2f}".format(Random_Forest_model.score(X_test_scaled,y_test)))
+
+
+import scikitplot as skplt
+y_pred = Random_Forest_model.predict(X_test_scaled)
+skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)
+#<matplotlib.axes._subplots.AxesSubplot object at 0x7fe967d64490>
+plt.show()
+y_probas = Random_Forest_model.predict_proba(X_test_scaled)
+skplt.metrics.plot_roc(y_test, y_probas)
+plt.show()
+skplt.metrics.plot_cumulative_gain(y_test, y_probas)
+plt.show()
Then random forests
+Compare Bagging on Trees with Random Forests
Nov 4, 2019
Nov 5, 2019
@@ -1431,7 +1436,7 @@ However, by aggregating many decision trees, using methods like bagging, random
-From a Single Tree to Many Trees, that is meet the Jungle of Methods
+From a Single Tree to Many Trees, Meet the Jungle of Methods
-
+
+
+
+
+
+
+
+
-A simple scikit-learn example
+Random Forests Compared with other Methods on the Cancer Data
from sklearn.ensemble import RandomForestClassifier
+
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.svm import SVC
+from sklearn.linear_model import LogisticRegression
+from sklearn.tree import DecisionTreeClassifier
+
+# Load the data
+cancer = load_breast_cancer()
+
+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)
+# Logistic Regression
+logreg = LogisticRegression(solver='lbfgs')
+logreg.fit(X_train, y_train)
+print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
+# Support vector machine
+svm = SVC(gamma='auto', C=100)
+svm.fit(X_train, y_train)
+print("Test set accuracy with SVM: {:.2f}".format(svm.score(X_test,y_test)))
+# Decision Trees
+deep_tree_clf = DecisionTreeClassifier(max_depth=None)
+deep_tree_clf.fit(X_train, y_train)
+print("Test set accuracy with Decision Trees: {:.2f}".format(deep_tree_clf.score(X_test,y_test)))
+#now scale the data
+from sklearn.preprocessing import StandardScaler
+scaler = StandardScaler()
+scaler.fit(X_train)
+X_train_scaled = scaler.transform(X_train)
+X_test_scaled = scaler.transform(X_test)
+# Logistic Regression
+logreg.fit(X_train_scaled, y_train)
+print("Test set accuracy Logistic Regression with scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
+# Support Vector Machine
+svm.fit(X_train_scaled, y_train)
+print("Test set accuracy SVM with scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
+# Decision Trees
+deep_tree_clf.fit(X_train_scaled, y_train)
+print("Test set accuracy with Decision Trees and scaled data: {:.2f}".format(deep_tree_clf.score(X_test_scaled,y_test)))
+
+
+from sklearn.ensemble import RandomForestClassifier
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import cross_validate
# Data set not specificied
-X = dataset.XXX
-Y = dataset.YYY
-#Instantiate the model with 100 trees and entropy as splitting criteria
-Random_Forest_model = RandomForestClassifier(n_estimators=100,criterion="entropy")
+#Instantiate the model with 500 trees and entropy as splitting criteria
+Random_Forest_model = RandomForestClassifier(n_estimators=500,criterion="entropy")
+Random_Forest_model.fit(X_train_scaled, y_train)
#Cross validation
-accuracy = cross_validate(Random_Forest_model,X,Y,cv=10)['test_score']
+accuracy = cross_validate(Random_Forest_model,X_test_scaled,y_test,cv=10)['test_score']
+print(accuracy)
+print("Test set accuracy with Random Forests and scaled data: {:.2f}".format(Random_Forest_model.score(X_test_scaled,y_test)))
+
+
+import scikitplot as skplt
+y_pred = Random_Forest_model.predict(X_test_scaled)
+skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)
+#<matplotlib.axes._subplots.AxesSubplot object at 0x7fe967d64490>
+plt.show()
+y_probas = Random_Forest_model.predict_proba(X_test_scaled)
+skplt.metrics.plot_roc(y_test, y_probas)
+plt.show()
+skplt.metrics.plot_cumulative_gain(y_test, y_probas)
+plt.show()
-Then random forests
+Compare Bagging on Trees with Random Forests
Nov 4, 2019
Nov 5, 2019
@@ -1436,7 +1441,7 @@ However, by aggregating many decision trees, using methods like bagging, random
-From a Single Tree to Many Trees, that is meet the Jungle of Methods
+From a Single Tree to Many Trees, Meet the Jungle of Methods
-
+
+
+
+
+
+
+
+
-A simple scikit-learn example
+Random Forests Compared with other Methods on the Cancer Data
from sklearn.ensemble import RandomForestClassifier
+
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.svm import SVC
+from sklearn.linear_model import LogisticRegression
+from sklearn.tree import DecisionTreeClassifier
+
+# Load the data
+cancer = load_breast_cancer()
+
+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)
+# Logistic Regression
+logreg = LogisticRegression(solver='lbfgs')
+logreg.fit(X_train, y_train)
+print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test)))
+# Support vector machine
+svm = SVC(gamma='auto', C=100)
+svm.fit(X_train, y_train)
+print("Test set accuracy with SVM: {:.2f}".format(svm.score(X_test,y_test)))
+# Decision Trees
+deep_tree_clf = DecisionTreeClassifier(max_depth=None)
+deep_tree_clf.fit(X_train, y_train)
+print("Test set accuracy with Decision Trees: {:.2f}".format(deep_tree_clf.score(X_test,y_test)))
+#now scale the data
+from sklearn.preprocessing import StandardScaler
+scaler = StandardScaler()
+scaler.fit(X_train)
+X_train_scaled = scaler.transform(X_train)
+X_test_scaled = scaler.transform(X_test)
+# Logistic Regression
+logreg.fit(X_train_scaled, y_train)
+print("Test set accuracy Logistic Regression with scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
+# Support Vector Machine
+svm.fit(X_train_scaled, y_train)
+print("Test set accuracy SVM with scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
+# Decision Trees
+deep_tree_clf.fit(X_train_scaled, y_train)
+print("Test set accuracy with Decision Trees and scaled data: {:.2f}".format(deep_tree_clf.score(X_test_scaled,y_test)))
+
+
+from sklearn.ensemble import RandomForestClassifier
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import cross_validate
# Data set not specificied
-X = dataset.XXX
-Y = dataset.YYY
-#Instantiate the model with 100 trees and entropy as splitting criteria
-Random_Forest_model = RandomForestClassifier(n_estimators=100,criterion="entropy")
+#Instantiate the model with 500 trees and entropy as splitting criteria
+Random_Forest_model = RandomForestClassifier(n_estimators=500,criterion="entropy")
+Random_Forest_model.fit(X_train_scaled, y_train)
#Cross validation
-accuracy = cross_validate(Random_Forest_model,X,Y,cv=10)['test_score']
+accuracy = cross_validate(Random_Forest_model,X_test_scaled,y_test,cv=10)['test_score']
+print(accuracy)
+print("Test set accuracy with Random Forests and scaled data: {:.2f}".format(Random_Forest_model.score(X_test_scaled,y_test)))
+
+
+import scikitplot as skplt
+y_pred = Random_Forest_model.predict(X_test_scaled)
+skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)
+#<matplotlib.axes._subplots.AxesSubplot object at 0x7fe967d64490>
+plt.show()
+y_probas = Random_Forest_model.predict_proba(X_test_scaled)
+skplt.metrics.plot_roc(y_test, y_probas)
+plt.show()
+skplt.metrics.plot_cumulative_gain(y_test, y_probas)
+plt.show()
-Then random forests
+Compare Bagging on Trees with Random Forests