def print_results_for_field(dataset, field, prefix):
dataset = drop_na(dataset, field)
dataset_notrea_dataset = drop_trea(dataset)
print_order = [
"full_xgboost", "full_logi", "notrea_xgboost", "notrea_logi"
]
max_len_order = max(map(len, print_order))
rez = defaultdict(list)
for i in range(100):
ds = get_balanced_split(dataset, field)
rez["full_xgboost"].append(calc_results_simple(*ds, XGBClassifier()))
rez["full_logi"].append(
calc_results_simple(*ds, LogisticRegression(max_iter=1000)))
ds = get_balanced_split(dataset_notrea_dataset, field)
rez["notrea_xgboost"].append(calc_results_simple(*ds, XGBClassifier()))
rez["notrea_logi"].append(
calc_results_simple(*ds, LogisticRegression(max_iter=1000)))
# for order in print_order:
# print(order, " "*(max_len_order - len(order)), ": ", list_to_4g_str(rez[order][-1]))
# print ("")
for order in print_order:
print("==> ", field, prefix, order, " " * (max_len_order - len(order)),
": ", list2d_to_4g_str_pm(rez[order]))
def print_results_get_mean_acc(ds1, ds2):
l1 = len(ds1)
l2 = len(ds2)
bias_acc = max(l1,l2) / (l1 + l2)
print(f"bias_accuracy: {bias_acc : .3f}")
X_set1, _ = prepare_full_dataset(ds1)
X_set2, _ = prepare_full_dataset(ds2)
y_set1 = np.zeros(l1)
y_set2 = np.ones(l2)
X_full = np.concatenate([X_set1, X_set2])
y_full = np.concatenate([y_set1, y_set2])
kf = RepeatedStratifiedKFold(n_splits=5, n_repeats=1)
rez = []
for i, (train_index, test_index) in enumerate(kf.split(X_full, y_full)):
X_train, X_test = X_full[train_index], X_full[test_index]
y_train, y_test = y_full[train_index], y_full[test_index]
rez.append(calc_results_simple(X_train, X_test, y_train, y_test, XGBClassifier()))
print(list2d_to_4g_str_pm(rez))
return np.mean(np.array(rez)[:,0])
def print_results(dataset, set1, set2):
X_set1, y_set1 = prepare_full_dataset(
dataset.loc[dataset['patient_ID'].isin(set1)])
X_set2, y_set2 = prepare_full_dataset(
dataset.loc[dataset['patient_ID'].isin(set2)])
# X_set1 = np.random.rand(*X_set1.shape)
# X_set2 = np.random.rand(*X_set2.shape)
X_set1_wf = add_one_features(X_set1, 0)
X_set2_wf = add_one_features(X_set2, 1)
X_genes = np.concatenate([X_set1, X_set2])
X_genes_wf = np.concatenate([X_set1_wf, X_set2_wf])
y_all = np.concatenate([y_set1, y_set2])
Xs = X_genes_wf[:, :1]
kf = RepeatedStratifiedKFold(n_splits=5, n_repeats=10)
print_order = [
"genes", "genes_set", "genes_biased", "genes_double", "study"
]
max_len_order = max(map(len, print_order))
rez = defaultdict(list)
for i, (train_index, test_index) in enumerate(kf.split(X_genes, y_all)):
rez["genes"].append(
calc_results_for_fold(X_genes, y_all, train_index, test_index,
XGBClassifier()))
rez["genes_set"].append(
calc_results_for_fold(X_genes_wf, y_all, train_index, test_index,
XGBClassifier()))
rez["genes_biased"].append(
calc_results_for_fold(X_genes_wf, y_all, train_index, test_index,
BiasedXgboost()))
rez["genes_double"].append(
calc_results_for_fold(X_genes_wf, y_all, train_index, test_index,
DoubleXgboost()))
rez["study"].append(
calc_results_for_fold(Xs, y_all, train_index, test_index,
XGBClassifier()))
for order in print_order:
print(order, " " * (max_len_order - len(order)), ": ",
list_to_4g_str(rez[order][-1]))
print("")
for order in print_order:
print("==> ", order, " " * (max_len_order - len(order)), ": ",
list2d_to_4g_str_pm(rez[order]))
def print_results(dataset, set1, set2):
X_set1, y_set1 = prepare_full_dataset(
dataset.loc[dataset['patient_ID'].isin(set1)])
X_set2, y_set2 = prepare_full_dataset(
dataset.loc[dataset['patient_ID'].isin(set2)])
X_set1_wf = add_one_features(X_set1, 0)
X_set2_wf = add_one_features(X_set2, 1)
X_full = np.concatenate([X_set1, X_set2])
X_full_wf = np.concatenate([X_set1_wf, X_set2_wf])
y_full = np.concatenate([y_set1, y_set2])
Xs = X_full_wf[:, :1]
kf = RepeatedStratifiedKFold(n_splits=5, n_repeats=1)
rez = []
rez_wf = []
rez_s = []
print_order = ["base", "studyf", "studyf_l", "only_study"]
max_len_order = max(map(len, print_order))
rez = defaultdict(list)
for i, (train_index, test_index) in enumerate(kf.split(X_full, y_full)):
rez["base"].append(
calc_results_for_fold(X_full, y_full, train_index, test_index,
XGBClassifier()))
rez["studyf"].append(
calc_results_for_fold(X_full_wf, y_full, train_index, test_index,
XGBClassifier()))
rez["studyf_l"].append(
calc_results_for_fold(X_full_wf, y_full, train_index, test_index,
XGBClassifier("binary:logistic")))
rez["only_study"].append(
calc_results_for_fold(Xs, y_full, train_index, test_index,
XGBClassifier()))
for order in print_order:
print(order, " " * (max_len_order - len(order)), ": ",
list_to_4g_str(rez[order][-1]))
print("")
for order in print_order:
print("==> ", order, " " * (max_len_order - len(order)), ": ",
list2d_to_4g_str_pm(rez[order]))
def print_results(dataset, set1, set2):
bias_acc = max(len(set1), len(set2)) / (len(set1) + len(set2))
print(len(set1), len(set2))
print(f"bias_accuracy: {bias_acc : .3f}")
X_set1, _ = prepare_full_dataset(dataset.loc[dataset['patient_ID'].isin(set1)])
X_set2, _ = prepare_full_dataset(dataset.loc[dataset['patient_ID'].isin(set2)])
y_set1 = np.zeros(len(set1))
y_set2 = np.ones(len(set2))
X_full = np.concatenate([X_set1, X_set2])
y_full = np.concatenate([y_set1, y_set2])
kf = RepeatedStratifiedKFold(n_splits=5, n_repeats=10)
rez = []
for i, (train_index, test_index) in enumerate(kf.split(X_full, y_full)):
X_train, X_test = X_full[train_index], X_full[test_index]
y_train, y_test = y_full[train_index], y_full[test_index]
rez.append(calc_results_simple(X_train, X_test, y_train, y_test, XGBClassifier()))
print(list2d_to_4g_str_pm(rez))
def print_results(dataset, set1, set2):
bias_acc = max(len(set1), len(set2)) / (len(set1) + len(set2))
print(len(set1), len(set2))
print(f"bias_accuracy: {bias_acc : .3f}")
X_set1, _ = prepare_full_dataset(
dataset.loc[dataset['patient_ID'].isin(set1)])
X_set2, _ = prepare_full_dataset(
dataset.loc[dataset['patient_ID'].isin(set2)])
y_set1 = np.zeros(len(set1))
y_set2 = np.ones(len(set2))
X_full = np.concatenate([X_set1, X_set2])
y_full = np.concatenate([y_set1, y_set2])
kf = RepeatedStratifiedKFold(n_splits=5, n_repeats=1)
rez = []
for i, (train_index, test_index) in enumerate(kf.split(X_full, y_full)):
X_train, X_test = X_full[train_index], X_full[test_index]
y_train, y_test = y_full[train_index], y_full[test_index]
clf = XGBClassifier()
rez.append(calc_results_simple(X_train, X_test, y_train, y_test, clf))
clf.fit(X_train, y_train)
print(np.argsort(-1 * clf.feature_importances_)[:20])
print(np.sort(-1 * clf.feature_importances_)[:20])
for i in np.argsort(-1 * clf.feature_importances_)[:20]:
print(
list(
dataset.drop(columns=[
'study', 'patient_ID', 'pCR', 'RFS', 'DFS',
'posOutcome'
]))[i])
print(list2d_to_4g_str_pm(rez))
def _print_results_set1set2(X_set1, y_set1, X_set2, y_set2):
X_set1_wf = add_one_features(X_set1, 0)
X_set2_wf = add_one_features(X_set2, 1)
X_genes_wf = np.concatenate([X_set1_wf, X_set2_wf])
y_all = np.concatenate([y_set1, y_set2])
kf = RepeatedStratifiedKFold(n_splits=5, n_repeats=10)
print_order = ["set1", "stack"]
max_len_order = max(map(len, print_order))
rez = defaultdict(list)
for i, (train_index, test_index) in enumerate(kf.split(X_genes_wf, y_all)):
rez["stack"].append(
calc_results_for_fold(X_genes_wf, y_all, train_index, test_index,
XGBClassifier()))
for i, (train_index, test_index) in enumerate(kf.split(X_set1, y_set1)):
rez["set1"].append(
calc_results_for_fold(X_set1, y_set1, train_index, test_index,
XGBClassifier()))
for order in print_order:
print("==> ", order, " " * (max_len_order - len(order)), ": ",
list2d_to_4g_str_pm(rez[order]))
def print_results(dataset, set1, set2):
X_set1, y_set1 = prepare_full_dataset(
dataset.loc[dataset['patient_ID'].isin(set1)])
X_set2, y_set2 = prepare_full_dataset(
dataset.loc[dataset['patient_ID'].isin(set2)])
# X_set1 = np.random.rand(*X_set1.shape)
# X_set2 = np.random.rand(*X_set2.shape)
X_set1_wf = add_one_features(X_set1, 0)
X_set2_wf = add_one_features(X_set2, 1)
X_genes_wf = np.concatenate([X_set1_wf, X_set2_wf])
y_all = np.concatenate([y_set1, y_set2])
kf = RepeatedStratifiedKFold(n_splits=5, n_repeats=10)
print_order = [
"genes", "genes_set", "genes_biased", "genes_double", "study"
]
max_len_order = max(map(len, print_order))
rez = defaultdict(list)
for i, (train_index, test_index) in enumerate(kf.split(X_genes_wf, y_all)):
X_genes_wf_train, X_genes_wf_test = X_genes_wf[
train_index], X_genes_wf[test_index]
y_train, y_test = y_all[train_index], y_all[test_index]
print("before balanced")
print_count_two_sets(X_genes_wf_train[:, 0], y_train)
print_count_two_sets(X_genes_wf_test[:, 0], y_test)
# print("counter before balance", Counter(X_genes_wf_train[:,0]), Counter(X_genes_wf_test[:,0]), Counter(y_train), Counter(y_test))
X_genes_wf_train, y_train = random_upsample_balance(
X_genes_wf_train, y_train)
X_genes_wf_test, y_test = random_upsample_balance(
X_genes_wf_test, y_test)
# print("counter after balance", Counter(X_genes_wf_train[:,0]), Counter(X_genes_wf_test[:,0]), Counter(y_train), Counter(y_test))
print("after balanced")
print_count_two_sets(X_genes_wf_train[:, 0], y_train)
print_count_two_sets(X_genes_wf_test[:, 0], y_test)
X_genes_train = X_genes_wf_train[:, 1:]
X_genes_test = X_genes_wf_test[:, 1:]
Xs_train = X_genes_wf_train[:, :1]
Xs_test = X_genes_wf_test[:, :1]
rez["genes"].append(
calc_results_simple(X_genes_train, X_genes_test, y_train, y_test,
XGBClassifier()))
rez["genes_set"].append(
calc_results_simple(X_genes_wf_train, X_genes_wf_test, y_train,
y_test, XGBClassifier()))
rez["genes_biased"].append(
calc_results_simple(X_genes_wf_train, X_genes_wf_test, y_train,
y_test, BiasedXgboost()))
rez["genes_double"].append(
calc_results_simple(X_genes_wf_train, X_genes_wf_test, y_train,
y_test, DoubleXgboost()))
rez["study"].append(
calc_results_simple(Xs_train, Xs_test, y_train, y_test,
XGBClassifier()))
for order in print_order:
print(order, " " * (max_len_order - len(order)), ": ",
list_to_4g_str(rez[order][-1]))
print("")
for order in print_order:
print("==> ", order, " " * (max_len_order - len(order)), ": ",
list2d_to_4g_str_pm(rez[order]))
