mhjensen
44 lines
1.5 KiB
Python
44 lines
1.5 KiB
Python
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
|
|
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)
|
|
|
|
logreg = LogisticRegression()
|
|
logreg.fit(X_train, y_train)
|
|
|
|
#svm = SVC(C=100)
|
|
#svm.fit(X_train, y_train)
|
|
print("Test set accuracy: {:.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)
|
|
|
|
print("Feature min values before scaling:\n {}".format(X_train.min(axis=0)))
|
|
print("Feature max values before scaling:\n {}".format(X_train.max(axis=0)))
|
|
|
|
print("Feature min values before scaling:\n {}".format(X_train_scaled.min(axis=0)))
|
|
print("Feature max values before scaling:\n {}".format(X_train_scaled.max(axis=0)))
|
|
|
|
logreg.fit(X_train_scaled, y_train)
|
|
#svm.fit(X_train_scaled, y_train)
|
|
print("Test set accuracy scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
|
|
|
|
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)
|
|
#svm.fit(X_train_scaled, y_train)
|
|
print("Test set accuracy scaled data: {:.2f}".format(logreg.score(X_test_scaled,y_test)))
|