importtimeimporttracemallocimportnumpyasnpimportpandasaspdfromsklearn.datasetsimportfetch_20newsgroups_vectorizedfromsklearn.decompositionimportIncrementalPCAdefmeasure_performance(func,*args,**kwargs):tracemalloc.start()start=time.perf_counter()result=func(*args,**kwargs)elapsed=time.perf_counter()-start_,peak=tracemalloc.get_traced_memory()tracemalloc.stop()return {"time_s":elapsed,"peak_mb":peak/ (1024**2)},resultdefsparse_ipca_arpack(X):ipca=IncrementalPCA(n_components=20,svd_solver="arpack")coords=ipca.fit_transform(X)returnipca,coordsdefdense_ipca_arpack(X):X_dense=X.toarray()ipca=IncrementalPCA(n_components=20,svd_solver="arpack")coords=ipca.fit_transform(X_dense)returnipca,coordsdefdense_ipca_full(X):X_dense=X.toarray()ipca=IncrementalPCA(n_components=20,svd_solver="full")coords=ipca.fit_transform(X_dense)returnipca,coordsdefmain():n_samples=3000X,_=fetch_20newsgroups_vectorized(return_X_y=True)X=X[:n_samples]methods= [        ("Sparse ARPACK",sparse_ipca_arpack),        ("Dense ARPACK",dense_ipca_arpack),        ("Dense Full",dense_ipca_full),    ]metrics= {}models= {}coords= {}print()print(f"\033[1mBenchmarking on{n_samples} samples...\033[0m")forname,funcinmethods:print(f"Running{name}...",end=" ",flush=True)stats,output=measure_performance(func,X)model,coord=outputmetrics[name]=statsmodels[name]=modelcoords[name]=coordprint(f"Time ={stats['time_s']:.3f}s, Peak Memory ={stats['peak_mb']:.2f}MB")print()print("\033[1mVerifying results...\033[0m")base="Dense Full"base_model=models[base]forname,_inmethods:ifname==base:continuemodel=models[name]assertnp.allclose(base_model.components_,model.components_)assertnp.allclose(base_model.explained_variance_,model.explained_variance_)assertnp.allclose(base_model.singular_values_,model.singular_values_)print(f"-{base} vs{name}: OK")print("All results are equivalent! ✅")print()print("\033[1mSummarizing performance and memory usage...\033[0m")base_stats=metrics[base]fornameinmethods:key=name[0]ifkey==base:metrics[key]["speedup"]=1.0metrics[key]["memory_saving"]=1.0else:t=metrics[key]["time_s"]m=metrics[key]["peak_mb"]metrics[key]["speedup"]=base_stats["time_s"]/tmetrics[key]["memory_saving"]=base_stats["peak_mb"]/mdf=pd.DataFrame(metrics).Tdf=df[["time_s","peak_mb","speedup","memory_saving"]]print(df.round(3))if__name__=="__main__":main()