# upgrade pip to its latest version
python3.XX -m pip install -U pip
# install fastdup
python3.XX -m pip install fastdup

from fastdup.engine import Fastdup

fd = Fastdup()
fd.run()

# Use .summary() to get a quick overview of your data:
fd.summary()

# Now you have access to all analysis and galleries using the Fastdup object:
similarity_df = fd.similarity()
outliers_df = fd.outliers()

import fastdup
fastdup.run(input_dir="/path/to/your/folder", work_dir='out', nearest_neighbors_k=5, turi_param='ccthreshold=0.96')    #main running function.
fastdup.create_duplicates_gallery('out/similarity.csv', save_path='.')     #create a visual gallery of found duplicates
fastdup.create_outliers_gallery('out/outliers.csv',   save_path='.')       #create a visual gallery of anomalies
fastdup.create_components_gallery('out', save_path='.')                    #create visualiaiton of connected components
fastdup.create_stats_gallery('out', save_path='.', metric='blur')          #create visualization of images stastics (for example blur)
fastdup.create_similarity_gallery('out', save_path='.',get_label_func=lambda x: x.split('/')[-2])     #create visualization of top_k similar images assuming data have labels which are in the folder name
fastdup.create_aspect_ratio_gallery('out', save_path='.')                  #create aspect ratio gallery