【ADHD血液診断】ランダムフォレストによる予測モデル

import time

import pickle

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

import seaborn as sns

from scipy.stats import pearsonr

from sklearn.decomposition import PCA

from sklearn.manifold import TSNE

import umap

from scipy.sparse.csgraph import connected_components

import scipy.stats as st

from scipy.stats import mannwhitneyu

from sklearn.model_selection import train_test_split

from sklearn.ensemble import RandomForestClassifier

from sklearn.metrics import accuracy_score

from sklearn.metrics import roc_curve

from sklearn.metrics import roc_auc_score

from sklearn.model_selection import cross_val_score

from sklearn.model_selection import StratifiedKFold

from sklearn.model_selection import GridSearchCV

import warnings

warnings.filterwarnings('ignore')

X = df_ttest.iloc[:, :-1]

y = df_ttest.iloc[:,-1]

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, stratify=y)

model = RandomForestClassifier()

model.fit(X_train, y_train)

test = model.predict(X_test)

score = accuracy_score(y_test, test)

score

0.8125

prob = model.predict_proba(X_test)

fpr_all, tpr_all, thresholds_all = roc_curve(y_test, prob[:,1], drop_intermediate=False)

plt.plot(fpr_all, tpr_all, marker='o')

plt.xlabel('FPR: False positive rate')

plt.ylabel('TPR: True positive rate')

plt.grid()

roc_auc_score(y_test, prob[:,1])

0.828125