From 8079f3fab653525dbbfc9ec3c5c03e3af4176f4c Mon Sep 17 00:00:00 2001 From: mhjensen Date: Fri, 18 Sep 2020 05:36:18 +0200 Subject: [PATCH] added dot files --- doc/pub/week38/html/._week38-bs040.html | 294 ++++++++++++++++++++++++ 1 file changed, 294 insertions(+) create mode 100644 doc/pub/week38/html/._week38-bs040.html diff --git a/doc/pub/week38/html/._week38-bs040.html b/doc/pub/week38/html/._week38-bs040.html new file mode 100644 index 000000000..de5e38927 --- /dev/null +++ b/doc/pub/week38/html/._week38-bs040.html @@ -0,0 +1,294 @@ + + + + + + + + +Data Analysis and Machine Learning: Logistic Regression + + + + + + + + + + + + + + + + + + + + + + + +
+
+ + Data Analysis and Machine Learning: Logistic Regression +
+ +
+ +
+
+ + +
+ +

 

 

 

+ + + + +

Other measures in classification studies: Cancer Data again

+

+ + +

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
+
+# 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)))
+#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)))
+
+
+from sklearn.preprocessing import LabelEncoder
+from sklearn.model_selection import cross_validate
+#Cross validation
+accuracy = cross_validate(logreg,X_test_scaled,y_test,cv=10)['test_score']
+print(accuracy)
+print("Test set accuracy with Logistic Regression  and scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
+
+
+import scikitplot as skplt
+y_pred = logreg.predict(X_test_scaled)
+skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True)
+plt.show()
+y_probas = logreg.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()
+
+

+ +

+ +

+ + +
+ + + + + + + +
+ +
+ + + + + +