def print_results_for_field(dataset, field):
dataset = drop_na(dataset, field)
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(10):
print("run ", i)
ds = get_balanced_split(dataset)
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(notrea_dataset)
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("")
sys.stdout.flush()
for order in print_order:
print("==> ", order, " " * (max_len_order - len(order)), ": ",
list2d_to_4g_str_pm(rez[order]))
def print_results_for_field(dataset, field):
dataset = drop_na(dataset, field)
dataset_notrea_dataset = drop_trea(dataset)
print_order = ["full_xgboost", "notrea_xgboost"]
max_len_order = max(map(len, print_order))
rez = defaultdict(list)
for i in range(20):
ds = get_balanced_split(dataset, field)
if (len(ds) == 0):
continue
rez["full_xgboost"].append(calc_results_simple(*ds, XGBClassifier()))
ds = get_balanced_split(dataset_notrea_dataset, field)
if (len(ds) == 0):
continue
rez["notrea_xgboost"].append(calc_results_simple(*ds, 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]))
output.write("==> " + str(order) + " " * (max_len_order - len(order)) +
": " + str(list_to_4g_str(np.mean(rez[order], axis=0))))
output.write("\n")
pam_types_cat_dataset = pd.merge(metagx_dataset,
pam_types_cat_dataset,
left_on="sample_name",
right_on="sample_name")
pam_types_cat_dataset = drop_na(pam_types_cat_dataset, "posOutcome")
pam_types_cat_dataset_notrea_dataset = drop_trea(pam_types_cat_dataset)
X_full, y_full = prepare_full_dataset(pam_types_cat_dataset)
X_notrea, _ = prepare_full_dataset(pam_types_cat_dataset_notrea_dataset)
kf = StratifiedKFold(n_splits=5, shuffle=True)
max_len_order = max(map(len, print_order))
print("==> posOutcome " + str(dataset))
output.write("==> posOutcome " + str(dataset) + "\n")
rez = defaultdict(list)
for i in range(20):
ds = get_balanced_split(pam_types_cat_dataset, 'posOutcome')
rez["full"].append(calc_results_simple(*ds, XGBClassifier()))
ds = get_balanced_split(pam_types_cat_dataset_notrea_dataset,
'posOutcome')
rez["full_notrea"].append(calc_results_simple(*ds, 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]))
output.write("==> " + str(order) + " " * (max_len_order - len(order)) +