-
Notifications
You must be signed in to change notification settings - Fork 0
/
generate_points.py
26 lines (19 loc) · 938 Bytes
/
generate_points.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
# %matplotlib inline
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OrdinalEncoder
from sksurv.datasets import load_gbsg2
from sksurv.preprocessing import OneHotEncoder
from sksurv.ensemble import RandomSurvivalForest
# First, we need to load the data and transform it into numeric values.
X, y = load_gbsg2()
grade_str = X.loc[:, "tgrade"].astype(object).values[:, np.newaxis]
grade_num = OrdinalEncoder(categories=[["I", "II", "III"]]).fit_transform(grade_str)
X_no_grade = X.drop("tgrade", axis=1)
Xt = OneHotEncoder().fit_transform(X_no_grade)
Xt.loc[:, "tgrade"] = grade_num
# Next, the data is split into 75% for training and 25% for testing, so we can determine how well our model generalizes.
random_state = 20
X_train, X_test, y_train, y_test = train_test_split(Xt, y, test_size=0.25, random_state=random_state)