def write_feature_importance_files(n_est=10, max_depth=None):
profile_ids = map(lambda x: int(x.split("_")[1]), os.listdir(param.FEATURE_AGG_PATH))
profile_ids.sort()
user_feature_df = loader.read_csv_dataset(profile_ids=profile_ids)
print "user feature data set is loaded"
# mod_feature_dfs = {mod: loader.read_csv_dataset(profile_ids=profile_ids, modality=mod)
# for mod in info.FREE_MODE_LIST}
# print "each modality feature data sets are loaded"
p_df = loader.load_profile_info()
print "profile information is loaded"
target_labels = info.LABEL_LIST
# target_labels = ['gender', 'age', 'job', 'religion', 'marriage', 'numberOfChildren', 'income', 'education']
# target_label = 'religion'
ranking_limits = [-1]
# min_not_nans = [-1, 10]
if not os.path.isdir(param.IMPORTANCE_PATH):
os.makedirs(param.IMPORTANCE_PATH)
for target_label in target_labels:
features_powers_lr = fimp.compute_randomized_lr_score(user_feature_df, p_df, target_label)
# features_powers_mi = fimp.compute_mics(user_feature_df, p_df, target_label)
# features_powers_fs_10 = fimp.compute_fscore(user_feature_df, p_df, target_label, min_not_nan=10)
for r_l in ranking_limits:
features_powers_lr.iloc[:r_l].to_csv(
"%s/%s_%s_%s-%s.csv" % (param.IMPORTANCE_PATH, target_label, "withAppFeat",
"LR", r_l if r_l > -1 else "all"))
if split_modal is True:
for modal in modalities:
x = df_filtered.loc[modal].dropna(how='all')
compute(x)
else:
x = df_filtered.dropna(how='all')
compute(x)
feature_importances.sort_values('importance', ascending=False, inplace=True, na_position='last')
return feature_importances
if __name__ == '__main__':
profile_ids = map(lambda x: int(x.split("_")[1]), os.listdir(param.FEATURE_AGG_PATH))[:20]
user_feature_df = data_loader.read_csv_dataset(profile_ids=profile_ids)
# user_feature_df = ida_data_loader.read_csv_dataset(file_name=csv_file)
print "user feature data set is loaded"
# mod_feature_dfs = {mod: ida_data_loader.read_csv_dataset(profile_ids=profile_ids, modality=mod)
# for mod in info.FREE_MODE_LIST}
# print "each modality feature data sets are loaded"
profile_df = data_loader.load_profile_info()
print "profile information is loaded"
# target_labels = info.LABEL_LIST
target_labels = [info.LABEL_GEN, info.LABEL_AGE]
# target_labels = ['gender', 'age', 'job', 'religion', 'marriage', 'numberOfChildren', 'income', 'education']
compute_randomized_lr_score(user_feature_df, profile_df)
# compute_fscore(user_feature_df, profile_df)
#
