+{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Fastdup Tutorial","metadata":{}},{"cell_type":"markdown","source":"In this notebook we illustrate how to gain insights quickly from a new dataset.","metadata":{}},{"cell_type":"markdown","source":"[Visit our GitHub Project Page](http://https://github.com/visualdatabase/fastdup)","metadata":{}},{"cell_type":"code","source":"!pip install -U fastdup","metadata":{"execution":{"iopub.status.busy":"2022-06-18T07:22:42.343766Z","iopub.execute_input":"2022-06-18T07:22:42.344710Z","iopub.status.idle":"2022-06-18T07:23:00.687276Z","shell.execute_reply.started":"2022-06-18T07:22:42.344580Z","shell.execute_reply":"2022-06-18T07:23:00.685732Z"},"trusted":true},"execution_count":1,"outputs":[]},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"code","source":"import fastdup\nfastdup.__version__","metadata":{"execution":{"iopub.status.busy":"2022-06-18T07:23:12.868823Z","iopub.execute_input":"2022-06-18T07:23:12.869350Z","iopub.status.idle":"2022-06-18T07:23:13.214692Z","shell.execute_reply.started":"2022-06-18T07:23:12.869304Z","shell.execute_reply":"2022-06-18T07:23:13.213657Z"},"trusted":true},"execution_count":2,"outputs":[]},{"cell_type":"markdown","source":"Click +Add data and add the pistachio image dataset","metadata":{}},{"cell_type":"code","source":"!ls /kaggle/input/pistachio-image-dataset","metadata":{"execution":{"iopub.status.busy":"2022-06-18T07:24:54.627012Z","iopub.execute_input":"2022-06-18T07:24:54.627561Z","iopub.status.idle":"2022-06-18T07:24:55.397665Z","shell.execute_reply.started":"2022-06-18T07:24:54.627515Z","shell.execute_reply":"2022-06-18T07:24:55.396350Z"},"trusted":true},"execution_count":7,"outputs":[]},{"cell_type":"code","source":"fastdup.run('/kaggle/input/pistachio-image-dataset', work_dir='out')","metadata":{"execution":{"iopub.status.busy":"2022-06-18T07:25:25.450907Z","iopub.execute_input":"2022-06-18T07:25:25.451464Z","iopub.status.idle":"2022-06-18T07:25:44.236601Z","shell.execute_reply.started":"2022-06-18T07:25:25.451415Z","shell.execute_reply":"2022-06-18T07:25:44.235333Z"},"trusted":true},"execution_count":8,"outputs":[]},{"cell_type":"code","source":"fastdup.create_duplicates_gallery('out/similarity.csv',save_path='.', num_images=20)","metadata":{"execution":{"iopub.status.busy":"2022-06-18T07:27:17.356996Z","iopub.execute_input":"2022-06-18T07:27:17.357837Z","iopub.status.idle":"2022-06-18T07:27:18.047554Z","shell.execute_reply.started":"2022-06-18T07:27:17.357786Z","shell.execute_reply":"2022-06-18T07:27:18.046544Z"},"trusted":true},"execution_count":9,"outputs":[]},{"cell_type":"code","source":"from IPython.display import HTML\nHTML('similarity.html')","metadata":{"execution":{"iopub.status.busy":"2022-06-18T07:27:24.698645Z","iopub.execute_input":"2022-06-18T07:27:24.699230Z","iopub.status.idle":"2022-06-18T07:27:24.734113Z","shell.execute_reply.started":"2022-06-18T07:27:24.699174Z","shell.execute_reply":"2022-06-18T07:27:24.733153Z"},"trusted":true},"execution_count":10,"outputs":[]},{"cell_type":"code","source":"fastdup.create_outliers_gallery('out/outliers.csv',save_path='.', num_images=20)","metadata":{"execution":{"iopub.status.busy":"2022-06-18T07:27:59.847630Z","iopub.execute_input":"2022-06-18T07:27:59.848809Z","iopub.status.idle":"2022-06-18T07:28:00.130310Z","shell.execute_reply.started":"2022-06-18T07:27:59.848758Z","shell.execute_reply":"2022-06-18T07:28:00.129097Z"},"trusted":true},"execution_count":11,"outputs":[]},{"cell_type":"code","source":"HTML('outliers.html')","metadata":{"execution":{"iopub.status.busy":"2022-06-18T07:28:07.086792Z","iopub.execute_input":"2022-06-18T07:28:07.087311Z","iopub.status.idle":"2022-06-18T07:28:07.102264Z","shell.execute_reply.started":"2022-06-18T07:28:07.087267Z","shell.execute_reply":"2022-06-18T07:28:07.101100Z"},"trusted":true},"execution_count":12,"outputs":[]},{"cell_type":"code","source":"from IPython import display\ndisplay.Image('log/sprite.png')","metadata":{"execution":{"iopub.status.busy":"2022-06-18T07:44:42.970745Z","iopub.execute_input":"2022-06-18T07:44:42.971186Z","iopub.status.idle":"2022-06-18T07:44:43.085584Z","shell.execute_reply.started":"2022-06-18T07:44:42.971152Z","shell.execute_reply":"2022-06-18T07:44:43.084738Z"},"trusted":true},"execution_count":43,"outputs":[]},{"cell_type":"code","source":"fastdup.create_components_gallery('out','.')","metadata":{"execution":{"iopub.status.busy":"2022-06-18T07:57:00.723747Z","iopub.execute_input":"2022-06-18T07:57:00.724159Z","iopub.status.idle":"2022-06-18T07:57:07.564405Z","shell.execute_reply.started":"2022-06-18T07:57:00.724117Z","shell.execute_reply":"2022-06-18T07:57:07.563279Z"},"trusted":true},"execution_count":52,"outputs":[]},{"cell_type":"code","source":"HTML('./components.html')","metadata":{"execution":{"iopub.status.busy":"2022-06-18T07:57:27.331968Z","iopub.execute_input":"2022-06-18T07:57:27.332410Z","iopub.status.idle":"2022-06-18T07:57:27.352738Z","shell.execute_reply.started":"2022-06-18T07:57:27.332374Z","shell.execute_reply":"2022-06-18T07:57:27.352018Z"},"trusted":true},"execution_count":53,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}
0 commit comments