mhjensen
45 lines
1.5 KiB
Python
45 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.linear_model import LogisticRegression
|
|
cancer = load_breast_cancer()
|
|
import pandas as pd
|
|
|
|
cancerpd = pd.DataFrame(cancer.data, columns=cancer.feature_names)
|
|
|
|
|
|
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)
|
|
EigValues, EigVectors = np.linalg.eig(correlation_matrix)
|
|
print(EigValues)
|
|
|
|
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)))
|
|
|
|
#thereafter we do a PCA with Scikit-learn
|
|
from sklearn.decomposition import PCA
|
|
pca = PCA(n_components = 2)
|
|
X2D_train = pca.fit_transform(X_train_scaled)
|
|
X2D_test = pca.fit_transform(X_test_scaled)
|
|
|
|
logreg.fit(X2D_train,y_train)
|
|
print("Test set accuracy scaled data: {:.2f}".format(logreg.score(X2D_test,y_test)))
|