# installing pixl
!pip install pixl
from pixl.utils import Pixl
from sklearn.cluster import KMeans
import pandas as pd
from shutil import unpack_archive
import os
# setting directory of sample images
category = 'animals'
img_dir = './assets/' + category
# grabbing file_names
filenames = []
for file in os.listdir(img_dir):
filenames.append(os.fsdecode(file))
filenames
# instantiate a pixl object
p_object = Pixl()
def get_vec(img_dir, filenames):
"""
Returns a list of vectors and a list of labels.
Args:
filenames (str): string specifying the name of each file.
Returns:
vectors (lst): list of vectors representing image files.
labels (lst): list of labels taken from file names.
"""
vectors = []
labels = []
for file in filenames:
vec = p_object.get_vec(img_dir + '/' + file)
vectors.append(vec)
label = file.split('.')[0]
labels.append(label)
return labels, vectors
labels, vectors = get_vec(img_dir, filenames)
# examining a label and vector
print(labels[0], vectors[0])
ids = range(len(vectors))
img_embedd_df = pd.DataFrame(index = ids)
img_embedd_df['Labels'] = labels
img_embedd_df['Vectors'] = vectors
print(img_embedd_df)
# setting n_clusters to 2 because we know we only want to cluster 2 classes
km = KMeans(n_clusters=2)
# fitting to the list of vectors from get_vec func
km.fit(vectors)
# grabbing a list of clusters
clusters = km.labels_.tolist()
# column cluter for each cluster
img_embedd_df["Cluster"] = clusters
# displaying counts per cluster
print(img_embedd_df['Cluster'].value_counts())
# displaying our df to see how we did!
print(img_embedd_df)
