def store_k_evaluation_measures(store_path,
k_list,
k_evaluation_measures,
feature_column_names):
number_of_folds = k_evaluation_measures[0].shape[1]
h5_store = h5_open(store_path + "results.h5")
for fold_index in range(number_of_folds):
data_frame = pd.DataFrame(k_evaluation_measures[0][:, fold_index], columns=["kendall_tau"], index=k_list)
h5store_at(h5_store,
"/data/kendall_tau/fold" + str(fold_index),
data_frame)
data_frame = pd.DataFrame(k_evaluation_measures[1][:, fold_index], columns=["p_value"], index=k_list)
h5store_at(h5_store,
"/data/p_value/fold" + str(fold_index),
data_frame)
data_frame = pd.DataFrame(k_evaluation_measures[2][:, fold_index], columns=["mse"], index=k_list)
h5store_at(h5_store,
"/data/mse/fold" + str(fold_index),
data_frame)
data_frame = pd.DataFrame(k_evaluation_measures[3][:, fold_index], columns=["jaccard"], index=k_list)
h5store_at(h5_store,
"/data/top_k_jaccard/fold" + str(fold_index),
data_frame)
data_frame = pd.DataFrame(k_evaluation_measures[4][:, fold_index, :], columns=feature_column_names, index=k_list)
h5store_at(h5_store,
"/data/feature_importances/fold" + str(fold_index),
data_frame)
h5_close(h5_store)
def store_dataset_k(dataset_k_path, dataset_k, X_k_min_dict, X_t_next_dict,
index):
h5_store = h5_open(dataset_k_path)
for osn_name in dataset_k.keys():
h5store_at(
h5_store, "/data/" + osn_name + "/X_branching",
pd.DataFrame(dataset_k[osn_name]["X_branching"],
columns=sorted(
list(get_branching_feature_names(osn_name)))))
h5store_at(
h5_store, "/data/" + osn_name + "/X_usergraph",
pd.DataFrame(dataset_k[osn_name]["X_usergraph"],
columns=sorted(
list(get_usergraph_feature_names(osn_name)))))
h5store_at(
h5_store, "/data/" + osn_name + "/X_temporal",
pd.DataFrame(dataset_k[osn_name]["X_temporal"],
columns=sorted(
list(get_temporal_feature_names(osn_name)))))
utility_arrays = dict()
utility_arrays["X_k_min_array"] = X_k_min_dict[osn_name]
utility_arrays["X_t_next_array"] = X_t_next_dict[osn_name]
h5store_at(h5_store, "/data/" + osn_name + "/utility_arrays",
pd.DataFrame(utility_arrays))
h5_close(h5_store)
def store_dataset_full(dataset_full_path, dataset_full, index,
branching_feature_names_list_dict,
usergraph_feature_names_list_dict,
temporal_feature_names_list_dict):
h5_store = h5_open(dataset_full_path)
for osn_name in dataset_full.keys():
h5store_at(
h5_store, "/data/" + osn_name + "/X_branching",
pd.DataFrame(dataset_full[osn_name]["X_branching"],
columns=branching_feature_names_list_dict[osn_name]))
h5store_at(
h5_store, "/data/" + osn_name + "/X_usergraph",
pd.DataFrame(dataset_full[osn_name]["X_usergraph"],
columns=usergraph_feature_names_list_dict[osn_name]))
h5store_at(
h5_store, "/data/" + osn_name + "/X_temporal",
pd.DataFrame(dataset_full[osn_name]["X_temporal"],
columns=temporal_feature_names_list_dict[osn_name]))
y_raw_dict = dict()
for target_name in dataset_full[osn_name]["y_raw"].keys():
y_raw_dict[target_name] = dataset_full[osn_name]["y_raw"][
target_name]
h5store_at(h5_store, "/data/" + osn_name + "/y_raw",
pd.DataFrame(y_raw_dict))
h5_close(h5_store)
def store_dataset_k(dataset_k_path,
dataset_k,
X_k_min_dict,
X_t_next_dict,
index):
h5_store = h5_open(dataset_k_path)
for osn_name in dataset_k.keys():
h5store_at(h5_store,
"/data/" + osn_name + "/X_branching",
pd.DataFrame(dataset_k[osn_name]["X_branching"],
columns=sorted(list(get_branching_feature_names(osn_name)))))
h5store_at(h5_store,
"/data/" + osn_name + "/X_usergraph",
pd.DataFrame(dataset_k[osn_name]["X_usergraph"],
columns=sorted(list(get_usergraph_feature_names(osn_name)))))
h5store_at(h5_store,
"/data/" + osn_name + "/X_temporal",
pd.DataFrame(dataset_k[osn_name]["X_temporal"],
columns=sorted(list(get_temporal_feature_names(osn_name)))))
utility_arrays = dict()
utility_arrays["X_k_min_array"] = X_k_min_dict[osn_name]
utility_arrays["X_t_next_array"] = X_t_next_dict[osn_name]
h5store_at(h5_store,
"/data/" + osn_name + "/utility_arrays",
pd.DataFrame(utility_arrays))
h5_close(h5_store)
def store_dataset_full(dataset_full_path,
dataset_full,
index,
branching_feature_names_list_dict,
usergraph_feature_names_list_dict,
temporal_feature_names_list_dict):
h5_store = h5_open(dataset_full_path)
for osn_name in dataset_full.keys():
h5store_at(h5_store,
"/data/" + osn_name + "/X_branching",
pd.DataFrame(dataset_full[osn_name]["X_branching"],
columns=branching_feature_names_list_dict[osn_name]))
h5store_at(h5_store,
"/data/" + osn_name + "/X_usergraph",
pd.DataFrame(dataset_full[osn_name]["X_usergraph"],
columns=usergraph_feature_names_list_dict[osn_name]))
h5store_at(h5_store,
"/data/" + osn_name + "/X_temporal",
pd.DataFrame(dataset_full[osn_name]["X_temporal"],
columns=temporal_feature_names_list_dict[osn_name]))
y_raw_dict = dict()
for target_name in dataset_full[osn_name]["y_raw"].keys():
y_raw_dict[target_name] = dataset_full[osn_name]["y_raw"][target_name]
h5store_at(h5_store,
"/data/" + osn_name + "/y_raw",
pd.DataFrame(y_raw_dict))
h5_close(h5_store)
def store_k_evaluation_measures(store_path, k_list, k_evaluation_measures,
feature_column_names):
number_of_folds = k_evaluation_measures[0].shape[1]
h5_store = h5_open(store_path + "results.h5")
for fold_index in range(number_of_folds):
data_frame = pd.DataFrame(k_evaluation_measures[0][:, fold_index],
columns=["kendall_tau"],
index=k_list)
h5store_at(h5_store, "/data/kendall_tau/fold" + str(fold_index),
data_frame)
data_frame = pd.DataFrame(k_evaluation_measures[1][:, fold_index],
columns=["p_value"],
index=k_list)
h5store_at(h5_store, "/data/p_value/fold" + str(fold_index),
data_frame)
data_frame = pd.DataFrame(k_evaluation_measures[2][:, fold_index],
columns=["mse"],
index=k_list)
h5store_at(h5_store, "/data/mse/fold" + str(fold_index), data_frame)
data_frame = pd.DataFrame(k_evaluation_measures[3][:, fold_index],
columns=["jaccard"],
index=k_list)
h5store_at(h5_store, "/data/top_k_jaccard/fold" + str(fold_index),
data_frame)
data_frame = pd.DataFrame(k_evaluation_measures[4][:, fold_index, :],
columns=feature_column_names,
index=k_list)
h5store_at(h5_store,
"/data/feature_importances/fold" + str(fold_index),
data_frame)
h5_close(h5_store)