from matplotlib import pyplot as plt
from sklearn.metrics import  RocCurveDisplay
from sklearn.svm import SVC
import numpy as np
from numpy.random import RandomState
import pandas as pd

rndst1 = RandomState(1)
rndst2 = RandomState(2)

def load_data():
    negs = [
        0.14,
        0.59,
        1.13,
        2.60,
        2.92,
        2.98,
        3.99,
        4.08,
        4.43,
        7.73,
        10.98,
    ]
    poss = [
        1.84,
        2.15,
        2.73,
        3.46,
        3.59,
        3.63,
        3.67,
        3.75,
        4.49,
        5.22,
        5.33,
        5.35,
        5.51,
        5.69,
        5.72,
        5.90,
        5.98,
        6.29,
        7.96,
        7.98,
        8.21,
        8.62,
        9.27,
        10.88,
        11.84,
        13.11,
        19.12,
        20.09,
        21.99,
        25.00,
        35.00,
    ]

    return pd.DataFrame(
        {
            "Class": np.concat([["NEG"] * len(negs), ["POS"] * len(poss)]),
            "ScoreA": np.concat([negs, poss]),
        }
    )

model1 = SVC(probability=True, kernel="rbf", random_state=rndst1)
model2 = SVC(probability=True, kernel="rbf", random_state=rndst2)

data = load_data()
data.sort_values(by="ScoreA", inplace=True)

Xs = data[["ScoreA"]]
ys = data["Class"]

model1.fit(Xs, ys)
model2.fit(Xs, ys)

probs1 = model1.predict_proba(Xs)[:, 1]
probs2 = model2.predict_proba(Xs)[:, 1]
probs=pd.DataFrame({"probs1":probs1, "probs2":probs2})
display(probs.describe().style.format(precision=2))
fig, axs = plt.subplots(2, 2, figsize=(10,10))
fig.tight_layout()
RocCurveDisplay.from_predictions(y_pred=probs1, y_true=ys, pos_label="POS", ax=axs[0,0])
RocCurveDisplay.from_predictions(y_pred=probs2, y_true=ys, pos_label="POS", ax=axs[0,1])
xv = np.arange(len(probs1))
axs[1,0].plot(xv, probs1)
axs[1,1].plot(xv, probs2)