Machine_Learning_In_Obesity/calibration_check_multiclass_all_method.py at master · ayan1c2/Machine_Learning_In_Obesity · GitHub

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
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
# -*- coding: utf-8 -*-
"""
Created on Mon Apr 27 01:41:29 2020

@author: ayanca
"""
import numpy as np
np.random.seed(0)

import matplotlib
matplotlib.use("svg")
import matplotlib.pyplot as plt
from matplotlib import cm

from sklearn import datasets
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import LinearSVC
from sklearn.calibration import calibration_curve, CalibratedClassifierCV
from sklearn.metrics import (brier_score_loss, precision_score, recall_score,
                             f1_score, log_loss)
from sklearn.model_selection import train_test_split


X, y = datasets.make_classification(n_samples=100000, n_features=20,
                                    n_informative=2, n_redundant=10,
                                    random_state=42)

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.99,
                                                    random_state=42)

def plot_calibration_curve(est, name, fig_index):
    """Plot calibration curve for est w/o and with calibration. """
    # Calibrated with isotonic calibration
    isotonic = CalibratedClassifierCV(est, cv=5, method='isotonic')

    # Calibrated with sigmoid calibration
    sigmoid = CalibratedClassifierCV(est, cv=5, method='sigmoid')

    # Logistic regression with no calibration as baseline
    lr = LogisticRegression(C=1., solver='lbfgs')

    fig = plt.figure(fig_index, figsize=(9, 9))
    ax1 = plt.subplot2grid((3, 1), (0, 0), rowspan=2)
    ax2 = plt.subplot2grid((3, 1), (2, 0))

    ax1.plot([0, 1], [0, 1], "k:", label="Perfectly calibrated")
    for clf, name in [(lr, 'Logistic'),
                      (est, name),
                      (isotonic, name + ' + Isotonic'),
                      (sigmoid, name + ' + Sigmoid')]:
        clf.fit(X_train, y_train)
        y_pred = clf.predict(X_test)
        if hasattr(clf, "predict_proba"):
            prob_pos = clf.predict_proba(X_test)[:, 1]
        else:  # use decision function
            prob_pos = clf.decision_function(X_test)
            prob_pos = \
                (prob_pos - prob_pos.min()) / (prob_pos.max() - prob_pos.min())

        clf_score = brier_score_loss(y_test, prob_pos, pos_label=y.max())
        print("%s:" % name)
        print("\tBrier: %1.3f" % (clf_score))
        print("\tPrecision: %1.3f" % precision_score(y_test, y_pred))
        print("\tRecall: %1.3f" % recall_score(y_test, y_pred))
        print("\tF1: %1.3f\n" % f1_score(y_test, y_pred))

        fraction_of_positives, mean_predicted_value = \
            calibration_curve(y_test, prob_pos, n_bins=10)

        ax1.plot(mean_predicted_value, fraction_of_positives, "s-",
                 label="%s (%1.3f)" % (name, clf_score))

        ax2.hist(prob_pos, range=(0, 1), bins=10, label=name,
                 histtype="step", lw=2)

    ax1.set_ylabel("Fraction of positives")
    ax1.set_ylim([-0.05, 1.05])
    ax1.legend(loc="lower right")
    ax1.set_title('Calibration plots  (reliability curve)')

    ax2.set_xlabel("Mean predicted value")
    ax2.set_ylabel("Count")
    ax2.legend(loc="upper center", ncol=2)

    plt.tight_layout()


# Plot calibration cuve for Linear SVC
plot_calibration_curve(LinearSVC(), "SVC", 2)