# in this case we link to the directory containing the preprocessing package
import sys
from os.path import dirname
sys.path.append(
dirname("/Users/dominiquepaul/xCoding/classification_tool/Main/"))
sys.path.append(
dirname("/Users/dominiquepaul/xCoding/classification_tool/Main/modules/"))
from regressionclass import Logistic_regression, Lasso_regression
from label_interpretation import load_industry_labels, create_feature_df
import pandas as pd
import numpy as np
OBJECT_NAME = "apparel"
industry_labels = load_industry_labels(
file_path="../industry_dicts/selection_ApparelAccessoriesandLuxuryGoods.csv"
)
# instantiate a new empty logistic regression model
log_reg2 = Logistic_regression()
# load the previously saved model from our disk
log_reg2.load_model("./example_output_folder/Logistic_regression_model.pkl")
new_images, names = np.load(
"./example_output_folder/unlabelled_data_image_package_no_labels_0.npy")
# load the new data
x_test_df = create_feature_df(imgs=new_images,
object_name=OBJECT_NAME,
ind_labels=industry_labels,
k_labels=10,
# option 1 for loading other modules
# this doesnt work when run in a REPL environment
main_path = os.path.dirname(__file__)
module_path = os.path.join(main_path, "modules/")
sys.path.append(dirname(module_path))
### an alternative menthod for handling file paths is by using the absolute path ###
# sys.path.append(dirname("/Users/dominiquepaul/xCoding/classification_tool/Main/modules/"))
from regressionclass import Logistic_regression, Lasso_regression
# folder where different label evaluations are saved
FOLDER_PATH_SAVE = "../Data/wnet_hyperopt_datasets"
# path with the industry dict folders
ind_labels = load_industry_labels(
file_path="./industry_dicts/selection_AutomobileManufacturers.csv")
OBJECT = "car"
automotive_pckgs = ["../Data/np_files/car_image_package_train_test_split0.npy"]
x_train, y_train, x_test, y_test, conversion = join_npy_data(automotive_pckgs)
n_label_list = [3, 5, 8, 10, 15, 20, 25, 50]
# transform or load the data if necessary
for label_amount in tqdm(n_label_list):
x_train_df = create_feature_df(imgs=x_train,
object_name=OBJECT,
ind_labels=ind_labels,
k_labels=label_amount)
x_test_df = create_feature_df(imgs=x_test,
object_name=OBJECT,
object_name=object_name,
method_type="oob_network_eval",
data_type=data_type,
augmented=augmented)
################################################################################
########################### Run through all tests ##############################
################################################################################
EVAL_OUT_FILE = './out_files/master_out.csv'
PREDICTIONS_MASTER_OUT_FILE = './out_files/master_predictions.csv'
OBJECT_NAME = "food"
DATA_FOLDER_PATH = "../Data"
ind_labels = load_industry_labels(
file_path="./industry_dicts/selection_PackagedFoodsandMeats.csv")
x_test, y_test, names, _ = np.load(
os.path.join(DATA_FOLDER_PATH,
"np_files_final/food_final_testing_dataset.npy"))
x_test_df_20 = create_feature_df(imgs=x_test,
object_name=OBJECT_NAME,
ind_labels=ind_labels,
k_labels=20)
x_test_df_50 = create_feature_df(imgs=x_test,
object_name=OBJECT_NAME,
ind_labels=ind_labels,
k_labels=50)
ALL_PREDICTIONS_DF = pd.DataFrame({"names": names})