ASLRecognition/scripts/create_csv.py

'''
USAGE:
python create_csv.py
'''
import pandas as pd
import numpy as np
import os
import joblib
from sklearn.preprocessing import LabelBinarizer
from tqdm import tqdm
from imutils import paths

# get all the image paths
image_paths = list(paths.list_images('preprocessed_image'))
# create a DataFrame
data = pd.DataFrame()
labels = []
for i, image_path in tqdm(enumerate(image_paths), total=len(image_paths)):
    label = image_path.split(os.path.sep)[-2]
    # save the relative path for mapping image to target
    data.loc[i, 'image_path'] = image_path
    labels.append(label)
labels = np.array(labels)
# one hot encode the labels
lb = LabelBinarizer()
labels = lb.fit_transform(labels)
print(f"The first one hot encoded labels: {labels[0]}")
print(f"Mapping the first one hot encoded label to its category: {lb.classes_[0]}")
print(f"Total instances: {len(labels)}")
for i in range(len(labels)):
    index = np.argmax(labels[i])
    data.loc[i, 'target'] = int(index)
# shuffle the dataset
data = data.sample(frac=1).reset_index(drop=True)
# save as CSV file
data.to_csv('data.csv', index=False)
# pickle the binarized labels
print('Saving the binarized labels as pickled file')
joblib.dump(lb, 'lb.pkl')
print(data.head(5))