PyCaretを使った分類（教師あり）

!pip install numba==0.53 # 依存関係エラー対応
# https://stackoverflow.com/questions/70148065/numba-needs-numpy-1-20-or-less-for-shapley-import

!pip install pandas-profiling==3.1.0 # エラー対応 実行後にランタイム再起動

!pip install pycaret
from pycaret.utils import enable_colab
enable_colab()

import pandas as pd
from sklearn.datasets import load_breast_cancer
load_data = load_breast_cancer()
tg_df_all = pd.DataFrame(load_data.data, columns = load_data.feature_names)
tg_df_all['y'] = load_data.target
tg_df_all

---

	mean radius	mean texture	mean perimeter	mean area	mean smoothness	mean compactness	mean concavity	mean concave points	mean symmetry	mean fractal dimension	...	worst texture	worst perimeter	worst area	worst smoothness	worst compactness	worst concavity	worst concave points	worst symmetry	worst fractal dimension	y
0	17.99	10.38	122.80	1001.0	0.11840	0.27760	0.30010	0.14710	0.2419	0.07871	...	17.33	184.60	2019.0	0.16220	0.66560	0.7119	0.2654	0.4601	0.11890	0
1	20.57	17.77	132.90	1326.0	0.08474	0.07864	0.08690	0.07017	0.1812	0.05667	...	23.41	158.80	1956.0	0.12380	0.18660	0.2416	0.1860	0.2750	0.08902	0
2	19.69	21.25	130.00	1203.0	0.10960	0.15990	0.19740	0.12790	0.2069	0.05999	...	25.53	152.50	1709.0	0.14440	0.42450	0.4504	0.2430	0.3613	0.08758	0
3	11.42	20.38	77.58	386.1	0.14250	0.28390	0.24140	0.10520	0.2597	0.09744	...	26.50	98.87	567.7	0.20980	0.86630	0.6869	0.2575	0.6638	0.17300	0
4	20.29	14.34	135.10	1297.0	0.10030	0.13280	0.19800	0.10430	0.1809	0.05883	...	16.67	152.20	1575.0	0.13740	0.20500	0.4000	0.1625	0.2364	0.07678	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
564	21.56	22.39	142.00	1479.0	0.11100	0.11590	0.24390	0.13890	0.1726	0.05623	...	26.40	166.10	2027.0	0.14100	0.21130	0.4107	0.2216	0.2060	0.07115	0
565	20.13	28.25	131.20	1261.0	0.09780	0.10340	0.14400	0.09791	0.1752	0.05533	...	38.25	155.00	1731.0	0.11660	0.19220	0.3215	0.1628	0.2572	0.06637	0
566	16.60	28.08	108.30	858.1	0.08455	0.10230	0.09251	0.05302	0.1590	0.05648	...	34.12	126.70	1124.0	0.11390	0.30940	0.3403	0.1418	0.2218	0.07820	0
567	20.60	29.33	140.10	1265.0	0.11780	0.27700	0.35140	0.15200	0.2397	0.07016	...	39.42	184.60	1821.0	0.16500	0.86810	0.9387	0.2650	0.4087	0.12400	0
568	7.76	24.54	47.92	181.0	0.05263	0.04362	0.00000	0.00000	0.1587	0.05884	...	30.37	59.16	268.6	0.08996	0.06444	0.0000	0.0000	0.2871	0.07039	1

# 未見データの取り分け
tg_df = tg_df_all.sample(frac=0.90, random_state = 0).reset_index(drop = True)
tg_df_unseen = tg_df_all.drop(tg_df.index).reset_index(drop = True)
print('All data: ' + str(tg_df.shape))
print('Data for Modeling: ' + str(tg_df.shape))
print('Unseen Data for Predictions: ' + str(tg_df_unseen.shape))

-----

All data: (569, 31)
Data for Modeling: (512, 31)
Unseen Data for Predictions: (57, 31)

# 分類を読み込み
from pycaret.classification import *

# 前処理
ret = setup(data = tg_df,
            target = 'y', # 分類のターゲット
            session_id = 0,
            normalize = False,
            train_size = 0.6, # train/testの分割数指定
            silent = True) # 型推定の確認をスキップ

# 分類方法の一覧
models()

-----

	Name	Reference	Turbo
ID			
lr	Logistic Regression	sklearn.linear_model._logistic.LogisticRegression	True
knn	K Neighbors Classifier	sklearn.neighbors._classification.KNeighborsCl...	True
nb	Naive Bayes	sklearn.naive_bayes.GaussianNB	True
dt	Decision Tree Classifier	sklearn.tree._classes.DecisionTreeClassifier	True
svm	SVM - Linear Kernel	sklearn.linear_model._stochastic_gradient.SGDC...	True
rbfsvm	SVM - Radial Kernel	sklearn.svm._classes.SVC	False
gpc	Gaussian Process Classifier	sklearn.gaussian_process._gpc.GaussianProcessC...	False
mlp	MLP Classifier	sklearn.neural_network._multilayer_perceptron....	False
ridge	Ridge Classifier	sklearn.linear_model._ridge.RidgeClassifier	True
rf	Random Forest Classifier	sklearn.ensemble._forest.RandomForestClassifier	True
qda	Quadratic Discriminant Analysis	sklearn.discriminant_analysis.QuadraticDiscrim...	True
ada	Ada Boost Classifier	sklearn.ensemble._weight_boosting.AdaBoostClas...	True
gbc	Gradient Boosting Classifier	sklearn.ensemble._gb.GradientBoostingClassifier	True
lda	Linear Discriminant Analysis	sklearn.discriminant_analysis.LinearDiscrimina...	True
et	Extra Trees Classifier	sklearn.ensemble._forest.ExtraTreesClassifier	True
lightgbm	Light Gradient Boosting Machine	lightgbm.sklearn.LGBMClassifier	True
dummy	Dummy Classifier	sklearn.dummy.DummyClassifier	True

# F1の値をソート軸に比較する
compare_models(sort = "F1", fold = 10)

ridge = create_model("ridge", fold = 10)

# ridgeをチューニング
tuned_ridge = tune_model(ridge,
                         optimize = 'F1',
                         fold = 10,
                         n_iter = 100)
tuned_ridge

# 分類モデルの評価
evaluate_model(tuned_ridge)

# ナビゲーションをクリックで評価を確認できる

# 特徴量の影響を確認する
plot_model(tuned_ridge, "feature")

# 混同マトリクス
plot_model(tuned_ridge, plot = "confusion_matrix")

plot_model(tuned_ridge, "error")

# モデルの確定
final_ridge = finalize_model(tuned_ridge)

# 最終モデルを使った予測
predict_model(final_ridge)

# 未見データに対して予測
predictions = predict_model(final_ridge, data = tg_df_unseen)
print(predictions)