## Ex 10.2

1+1

print("Hello World")

a = 5

a

## Ex 10.3

# URL: https://sbcb.inf.ufrgs.br/data/cumida/Genes/Lung/GSE74706/Lung_GSE74706.csv

import pandas as pd
file_path = "../input/lungcancer/Lung_GSE74706.csv"
lungcancer_df = pd.read_csv(file_path)
lungcancer_df

labels_df = lungcancer_df["type"]
features_df = lungcancer_df.drop(["type", "samples"], axis=1)

features_df.T.describe()

labels_df.value_counts()

features_df.mean().hist()

## Ex 10.4

import numpy as np
from sklearn.svm import LinearSVC
from sklearn.decomposition import PCA
from sklearn.preprocessing import scale
from mlxtend.plotting import plot_decision_regions

X = features_df.to_numpy()
y = np.where(labels_df == "normal", 0, 1)

pca = PCA(n_components=2)
X_std = scale(X)
X_pc2 = pca.fit_transform(X_std)

X_pc2 = scale(X_pc2)
svm = LinearSVC()
svm.fit(X_pc2, y)

plot_decision_regions(X=X_pc2, y=y, clf=svm)