def objective(trial):
iris = load_iris()
X, y = cudf.DataFrame(pd.DataFrame(
iris.data.astype('float32'))), cudf.DataFrame(
pd.DataFrame(iris.target.astype('float32')))
solver = trial.suggest_categorical("solver", ["qn"])
C = trial.suggest_uniform("C", 0.0, 1.0)
if solver == "qn":
penalty = trial.suggest_categorical("penalty", ["l1", "l2"])
else:
# 'penalty' parameter isn't relevant for this solver,
# so we always specify 'l2' as the dummy value.
penalty = "l2"
classifier = LogisticRegression(max_iter=200,
solver=solver,
C=C,
penalty=penalty)
X_train, X_valid, y_train, y_valid = train_test_split(X, y)
classifier.fit(X_train, y_train)
score = classifier.score(X_valid, y_valid)
return score
def run_log_reg(scaled_df):
raw_train_arr = []
raw_test_arr = []
# Init metrics
metrics = ['accuracy', 'f1', 'roc_auc_ovr']
# Set c vals and penalty
C_vals = range(-8, 5)
C_vals = [10**val for val in C_vals]
penalty = ['none', 'l1', 'l2']
# Init params
params = {'penalty': penalty, 'C': C_vals}
# Over five trials
for i in range(5):
# Train test split
X_train, X_test, y_train, y_test = train_test_split(
scaled_df.iloc[:, :-1], scaled_df.y, train_size=5000)
# Init clf
clf = LogisticRegression()
# Init gridsearch and run
search_results = GridSearchCV(clf,
params,
scoring=metrics,
refit=False)
search_results.fit(X_train, y_train)
# Get results and organize
results = pd.DataFrame(search_results.cv_results_['params'])
results['mean_accuracy'] = search_results.cv_results_[
'mean_test_accuracy']
results['mean_f1'] = search_results.cv_results_['mean_test_f1']
results['mean_auc'] = search_results.cv_results_[
'mean_test_roc_auc_ovr']
# Get optimal clfs
opt_acc_inf = results.sort_values(by='mean_accuracy',
ascending=False).iloc[0]
opt_f1_inf = results.sort_values(by='mean_f1', ascending=False).iloc[0]
opt_auc_inf = results.sort_values(by='mean_auc',
ascending=False).iloc[0]
# Init optimal clfs
opt_acc_clf = LogisticRegression(C=opt_acc_inf.C,
penalty=opt_acc_inf.penalty,
max_iter=100000)
opt_f1_clf = LogisticRegression(C=opt_f1_inf.C,
penalty=opt_f1_inf.penalty,
max_iter=100000)
opt_auc_clf = LogisticRegression(C=opt_auc_inf.C,
penalty=opt_auc_inf.penalty,
max_iter=100000)
# Fit clfs
opt_acc_clf.fit(X_train, y_train)
opt_f1_clf.fit(X_train, y_train)
opt_auc_clf.fit(X_train, y_train)
# Get train and test metrics
train_score_acc = opt_acc_clf.score(X_train, y_train)
train_score_f1 = f1_score(y_train, opt_f1_clf.predict(X_train))
train_score_auc = roc_auc_score(y_train, opt_auc_clf.predict(X_train))
test_score_acc = opt_acc_clf.score(X_test, y_test)
test_score_f1 = f1_score(y_test, opt_f1_clf.predict(X_test))
test_score_auc = roc_auc_score(y_test, opt_auc_clf.predict(X_test))
raw_train_arr.append(
[train_score_acc, train_score_f1, train_score_auc])
raw_test_arr.append([test_score_acc, test_score_f1, test_score_auc])
# Create dataframe from results
raw_train_arr = np.array(raw_train_arr).reshape(5, 3)
raw_test_arr = np.array(raw_test_arr).reshape(5, 3)
raw_train_df = pd.DataFrame(data=raw_train_arr,
columns=['accuracy', 'f1', 'auc'])
raw_test_df = pd.DataFrame(data=raw_test_arr,
columns=['accuracy', 'f1', 'auc'])
# Return results
return raw_train_df, raw_test_df