From 3d2c7c905a31d6c7448763d23d55ba302236fc1f Mon Sep 17 00:00:00 2001 From: Morten Hjorth-Jensen Date: Fri, 23 Sep 2022 07:35:16 +0200 Subject: [PATCH] taking out and cleaning some codes --- doc/pub/week38/html/._week38-bs026.html | 9 - doc/pub/week38/html/._week38-bs029.html | 17 +- doc/pub/week38/html/week38-reveal.html | 26 +- doc/pub/week38/html/week38-solarized.html | 26 +- doc/pub/week38/html/week38.html | 26 +- doc/pub/week38/ipynb/ipynb-week38-src.tar.gz | Bin 193 -> 192 bytes doc/pub/week38/ipynb/week38.ipynb | 302 +++++++++---------- doc/src/week38/week38.do.txt | 26 +- 8 files changed, 162 insertions(+), 270 deletions(-) diff --git a/doc/pub/week38/html/._week38-bs026.html b/doc/pub/week38/html/._week38-bs026.html index 5fd0e6c7d..a1ad018a3 100644 --- a/doc/pub/week38/html/._week38-bs026.html +++ b/doc/pub/week38/html/._week38-bs026.html @@ -262,15 +262,6 @@ X_train, X_test, y_train, y_test = train_tes 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))) diff --git a/doc/pub/week38/html/._week38-bs029.html b/doc/pub/week38/html/._week38-bs029.html index e5254da59..f2011227c 100644 --- a/doc/pub/week38/html/._week38-bs029.html +++ b/doc/pub/week38/html/._week38-bs029.html @@ -256,30 +256,21 @@ X_train, X_test, y_train, y_test = train_tes 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'] +accuracy = cross_validate(logreg,X_test,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))) +print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test))) import scikitplot as skplt -y_pred = logreg.predict(X_test_scaled) +y_pred = logreg.predict(X_test) skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True) plt.show() -y_probas = logreg.predict_proba(X_test_scaled) +y_probas = logreg.predict_proba(X_test) skplt.metrics.plot_roc(y_test, y_probas) plt.show() skplt.metrics.plot_cumulative_gain(y_test, y_probas) diff --git a/doc/pub/week38/html/week38-reveal.html b/doc/pub/week38/html/week38-reveal.html index 42a926b75..1ef4b71b3 100644 --- a/doc/pub/week38/html/week38-reveal.html +++ b/doc/pub/week38/html/week38-reveal.html @@ -1099,15 +1099,6 @@ X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,ra 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))) @@ -1284,30 +1275,21 @@ X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,ra 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'] +accuracy = cross_validate(logreg,X_test,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))) +print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test))) import scikitplot as skplt -y_pred = logreg.predict(X_test_scaled) +y_pred = logreg.predict(X_test) skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True) plt.show() -y_probas = logreg.predict_proba(X_test_scaled) +y_probas = logreg.predict_proba(X_test) skplt.metrics.plot_roc(y_test, y_probas) plt.show() skplt.metrics.plot_cumulative_gain(y_test, y_probas) diff --git a/doc/pub/week38/html/week38-solarized.html b/doc/pub/week38/html/week38-solarized.html index 839f2af20..b5fa54032 100644 --- a/doc/pub/week38/html/week38-solarized.html +++ b/doc/pub/week38/html/week38-solarized.html @@ -1014,15 +1014,6 @@ X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,ra 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))) @@ -1198,30 +1189,21 @@ X_train, X_test, y_train, y_test = train_test_split(cancer.data,cancer.target,ra 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'] +accuracy = cross_validate(logreg,X_test,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))) +print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test))) import scikitplot as skplt -y_pred = logreg.predict(X_test_scaled) +y_pred = logreg.predict(X_test) skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True) plt.show() -y_probas = logreg.predict_proba(X_test_scaled) +y_probas = logreg.predict_proba(X_test) skplt.metrics.plot_roc(y_test, y_probas) plt.show() skplt.metrics.plot_cumulative_gain(y_test, y_probas) diff --git a/doc/pub/week38/html/week38.html b/doc/pub/week38/html/week38.html index ea25103ed..23a6046f5 100644 --- a/doc/pub/week38/html/week38.html +++ b/doc/pub/week38/html/week38.html @@ -1091,15 +1091,6 @@ X_train, X_test, y_train, y_test = train_tes 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))) @@ -1275,30 +1266,21 @@ X_train, X_test, y_train, y_test = train_tes 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'] +accuracy = cross_validate(logreg,X_test,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))) +print("Test set accuracy with Logistic Regression: {:.2f}".format(logreg.score(X_test,y_test))) import scikitplot as skplt -y_pred = logreg.predict(X_test_scaled) +y_pred = logreg.predict(X_test) skplt.metrics.plot_confusion_matrix(y_test, y_pred, normalize=True) plt.show() -y_probas = logreg.predict_proba(X_test_scaled) +y_probas = logreg.predict_proba(X_test) skplt.metrics.plot_roc(y_test, y_probas) plt.show() skplt.metrics.plot_cumulative_gain(y_test, y_probas) diff --git a/doc/pub/week38/ipynb/ipynb-week38-src.tar.gz b/doc/pub/week38/ipynb/ipynb-week38-src.tar.gz index 319093a9383a41c361c67f6c67d362311ee2fb5c..ba2f69d5f5267714da93f4f5b72adeef9f6d03c9 100644 GIT binary patch literal 192 zcmV;x06+g9iwFRKMJ;0h1MSbv3c@f92k@Qu6nTP?uHE!1xPu2l#24sT=c=xqZHMmd z-3RDN@iIi{@A4-kgk+zs*4r#{cNfeC5mUxs$VHlriSbmA2uXl2N@&dD6cLcngrouB zd?&rM)^XFHQdcLTtWfXf`mwV7uxEM&p7|#Zm9((gb*|D1ly)N5`V2QA&U6{crc*f- uTG*ilMqFEI1aQ>>FAC|TR{Rn+Mjs8YZ500c8PD@P?`sb{&J1h-2mkuHia9|^nxu6r*o6y0#0#V}wXrs-Ns9LN z_5r$5+!PV=ZGMIshM7aQ-t4l--CeL4git~$jF~2EN)*ra1Y-u65=>%>SxNw5!r~+V zwA@KAopsy{r!>`BC@a*vxnZm1TYQ-;MYxK$R#zx_