def test_balanced_random_forest_oob(imbalanced_dataset):
X, y = imbalanced_dataset
X_train, X_test, y_train, y_test = train_test_split(X,
y,
random_state=42,
stratify=y)
est = BalancedRandomForestClassifier(
oob_score=True,
random_state=0,
n_estimators=1000,
min_samples_leaf=2,
)
est.fit(X_train, y_train)
test_score = est.score(X_test, y_test)
assert abs(test_score - est.oob_score_) < 0.1
# Check warning if not enough estimators
est = BalancedRandomForestClassifier(oob_score=True,
random_state=0,
n_estimators=1,
bootstrap=True)
with pytest.warns(UserWarning) and np.errstate(divide="ignore",
invalid="ignore"):
est.fit(X, y)
def test_balanced_random_forest_oob(imbalanced_dataset):
X, y = imbalanced_dataset
est = BalancedRandomForestClassifier(oob_score=True, random_state=0)
n_samples = X.shape[0]
est.fit(X[:n_samples // 2, :], y[:n_samples // 2])
test_score = est.score(X[n_samples // 2:, :], y[n_samples // 2:])
assert abs(test_score - est.oob_score_) < 0.1
# Check warning if not enough estimators
est = BalancedRandomForestClassifier(oob_score=True, random_state=0,
n_estimators=1, bootstrap=True)
with pytest.warns(UserWarning) and np.errstate(divide="ignore",
invalid="ignore"):
est.fit(X, y)
train_accuracy = []
validation_accuracy = []
label_prop = []
#
#
# NO Propagation labels
#
#
x_tr, y_tr, x_te, y_te, x_va, y_va = load_known_data()
model_name.append("Balanced Random Forest")
label_prop.append("No Propagation")
rfb = BalancedRandomForestClassifier(max_depth=2)
rfb.fit(x_tr, y_tr)
train_accuracy.append(rfb.score(x_tr, y_tr))
test_accuracy.append(rfb.score(x_te, y_te))
validation_accuracy.append(rfb.score(x_va, y_va))
model_name.append("Easy Ensemble")
label_prop.append("No Propagation")
clf = EasyEnsembleClassifier(random_state=0)
clf.fit(x_tr, y_tr)
clf.predict(x_tr)
train_accuracy.append(clf.score(x_tr, y_tr))
test_accuracy.append(clf.score(x_te, y_te))
validation_accuracy.append(clf.score(x_va, y_va))
#
#
# Propagation labels
cl = KNeighborsClassifier(n_neighbors=3)
cl.fit(X_train, y_train)
clf = BalancedRandomForestClassifier(max_depth=2, random_state=0)
clf.fit(X_train, y_train)
loo = KFold(n_splits=10)
scores = cross_val_score(clf,
X_resampled,
y_resampled,
scoring="accuracy",
cv=loo)
print(scores)
print(scores.mean())
print("Before{} ".format(clf.score(X_test, y_test)))
print("BeforeNei{} ".format(cl.score(X_test, y_test)))
score = fisher_score.fisher_score(X_train, y_train)
print(len(score))
idx = fisher_score.feature_ranking(score)
print(idx)
num_fea = 6
X1 = X_resampled.iloc[:, [
idx[0], idx[1], idx[2], idx[3], idx[4], idx[5], idx[6], idx[7], idx[8],
idx[9], idx[10], idx[11]
]]
#X1 = X_resampled.iloc[:, [idx[0], idx[1], idx[2], idx[3], idx[4],idx[5]]]
X1 = pd.DataFrame(X1)
print("Selected features {}".format(X1.columns.values))
def BalancedRF_classifier(df, y_column, feature_columns, test_rate):
# 不均衡クラス分類用ランダムフォレスト
# 混合行列や重要度の高い変数を可視化する
# 説明変数、目的変数の作成
X = df.loc[:, feature_columns].values
Y = df.loc[:, y_column].values
# 学習用、検証用データに分割
(X_train, X_test, Y_train, Y_test) = train_test_split(X,
Y,
test_size=test_rate,
random_state=123,
shuffle=True)
'''
# モデル構築、パラメータはデフォルト
parameters = {
'n_estimators' : [5, 10, 20, 30, 50],
'max_features' : [3, 5, 10, 15, 20],
'random_state' : [0],
'n_jobs' : [2],
'min_samples_split' : [3, 5, 10, 15, 20, 25, 30],
'max_depth' : [3, 5, 10, 15, 20, 25, 30, 50, 100]
}
clf = GridSearchCV(RandomForestClassifier(), parameters)
clf.fit(X_train, Y_train)
print(clf.best_estimator_)'''
model = BalancedRandomForestClassifier(n_jobs=1,
n_estimators=30,
sampling_strategy='not minority')
print(model.get_params())
model.fit(X_train, Y_train)
# 正解率
print("正解率 : " + str(model.score(X_test, Y_test) * 100) + "%")
print("訓練データの正解率 : " + str(model.score(X_train, Y_train) * 100) + "%")
# confusion matrix を確認する
print("confusion matrix")
prediction = model.predict(X_test)
labels = list(set(Y))
print_cmx(Y_test, prediction, labels)
# 効いてる変数を調べる
importances = None
i = np.array([e.feature_importances_ for e in model.estimators_])
avg_i = np.array([e.feature_importances_
for e in model.estimators_]).mean(axis=0)
importances = pd.DataFrame({
'variable': feature_columns,
'importance': avg_i
}).sort_values('importance', ascending=False).reset_index(drop=True)
display(importances)
IMP = importances.copy()
plt.figure(figsize=(5, 7))
plt.plot(IMP.importance,
sorted([i + 1 for i in range(IMP.shape[0])], reverse=True), 'o-')
plt.yticks(sorted([i + 1 for i in range(IMP.shape[0])], reverse=True),
IMP.variable)
plt.xlabel('importance')
# plt.xlabel('重要度')
plt.show()
return model, importances, (X_train, X_test, Y_train, Y_test)
print("_____________________________________")
#%% BALANCED random forest classifier - Random undersampling of the majority class in reach bootstrap sample.
from imblearn.ensemble import BalancedRandomForestClassifier
print("_____________________________________ \n Balanced Random Forest")
# all features
clf_brf_all = BalancedRandomForestClassifier(n_estimators=1000,
random_state=0,
n_jobs=-1,
max_depth=4,
min_samples_split=0.05).fit(
X_train,
y_train.values.ravel())
print(f"All features results: \n",
f"{list(loss_intensity.columns.values)[0]} - All training score is",
clf_brf_all.score(X_train, y_train.values.ravel()))
print(f"{list(loss_intensity.columns.values)[0]} - All test score is",
clf_brf_all.score(X_test, y_test.values.ravel()))
y_pred = clf_brf_all.predict(X_test)
#select most important ones
sel = SelectFromModel(BalancedRandomForestClassifier(n_estimators=1000,
random_state=0),
max_features=5)
sel.fit(X_train, y_train.values.ravel())
selected_feat = X_train.columns[(sel.get_support())]
print("\n Balanced Random Forest \n The selected features are",
len(selected_feat), selected_feat.values)
# transform
X_train_selected = sel.transform(X_train)
X_test_selected = sel.transform(X_test)
