Merge pull request #212 from lucasimi/develop

Develop

Author: lucasimi

app/requirements.txt

@@ -1,7 +1,7 @@
-streamlit>=1.40.0
-numpy>=1.25.2
-scikit-learn>=1.5.0
-umap-learn>=0.5.7
-pandas>=2.1.0
-tda-mapper==0.9.0
-plotly < 6.0.0
+streamlit>=1.40.0,<2.0.0
+numpy>=1.25.2,<2.0.0
+scikit-learn>=1.5.0,<1.6.0
+umap-learn>=0.5.7,<0.6.0
+pandas>=2.1.0,<3.0.0
+tda-mapper>=0.9.0,<0.10.0
+plotly>=6.0.0,<7.0.0

benchmarks/benchmark.py

@@ -1,17 +1,15 @@
 import time
 
-import pandas as pd
+import gtda.mapper as gm
+import kmapper as km
 import numpy as np
-
-from sklearn.decomposition import PCA
-from sklearn.datasets import fetch_openml, load_digits
+import pandas as pd
 from sklearn.base import ClusterMixin
-
-from tdamapper.clustering import TrivialClustering
+from sklearn.datasets import fetch_openml, load_digits
+from sklearn.decomposition import PCA
 
 import tdamapper as tm
-import gtda.mapper as gm
-import kmapper as km
+from tdamapper.clustering import TrivialClustering
 
 
 def _segment(cardinality, dimension, noise=0.1, start=None, end=None):
@@ -40,17 +38,17 @@ def digits(k):
 
 
 def mnist(k):
-    X = _load_openml('mnist_784')
+    X = _load_openml("mnist_784")
     return PCA(k).fit_transform(X)
 
 
 def cifar10(k):
-    X = _load_openml('CIFAR_10')
+    X = _load_openml("CIFAR_10")
     return PCA(k).fit_transform(X)
 
 
 def fashion_mnist(k):
-    X = _load_openml('Fashion-MNIST')
+    X = _load_openml("Fashion-MNIST")
     return PCA(k).fit_transform(X)
 
 
@@ -73,9 +71,7 @@ def run_gm(X, n, p):
     t0 = time.time()
     pipe = gm.make_mapper_pipeline(
         filter_func=lambda x: x,
-        cover=gm.CubicalCover(
-            n_intervals=n,
-            overlap_frac=p),
+        cover=gm.CubicalCover(n_intervals=n, overlap_frac=p),
         clusterer=TrivialEstimator(),
     )
     mapper_graph = pipe.fit_transform(X)
@@ -89,10 +85,10 @@ def run_tm(X, n, p):
         cover=tm.cover.CubicalCover(
             n_intervals=n,
             overlap_frac=p,
-            #leaf_capacity=1000,
-            #leaf_radius=1.0 / (2.0 - 2.0 * p),
-            #kind='hierarchical',
-            #pivoting='random',
+            # leaf_capacity=1000,
+            # leaf_radius=1.0 / (2.0 - 2.0 * p),
+            # kind='hierarchical',
+            # pivoting='random',
         ),
         clustering=TrivialEstimator(),
     ).fit_transform(X, X)
@@ -106,25 +102,24 @@ def run_km(X, n, p):
     graph = mapper.map(
         lens=X,
         X=X,
-        cover=km.Cover(
-            n_cubes=n,
-            perc_overlap=p
-        ),
+        cover=km.Cover(n_cubes=n, perc_overlap=p),
         clusterer=TrivialEstimator(),
     )
     t1 = time.time()
     return t1 - t0
 
 
 def run_bench(benches, datasets, dimensions, overlaps, intervals):
-    df_bench = pd.DataFrame({
-        'bench': [],
-        'dataset': [],
-        'p': [],
-        'n': [],
-        'k': [],
-        'time': [],
-    })
+    df_bench = pd.DataFrame(
+        {
+            "bench": [],
+            "dataset": [],
+            "p": [],
+            "n": [],
+            "k": [],
+            "time": [],
+        }
+    )
     launch_time = int(time.time())
     for bench_name, bench in benches:
         for dataset_name, dataset in datasets:
@@ -133,34 +128,33 @@ def run_bench(benches, datasets, dimensions, overlaps, intervals):
                 for p in overlaps:
                     for n in intervals:
                         t = bench(X, n, p)
-                        df_delta = pd.DataFrame({
-                            'bench': bench_name,
-                            'dataset': dataset_name,
-                            'p': p,
-                            'n': n,
-                            'k': k,
-                            'time': t,
-                          }, index=[0])
+                        df_delta = pd.DataFrame(
+                            {
+                                "bench": bench_name,
+                                "dataset": dataset_name,
+                                "p": p,
+                                "n": n,
+                                "k": k,
+                                "time": t,
+                            },
+                            index=[0],
+                        )
                         print(df_delta)
                         df_bench = pd.concat([df_bench, df_delta], ignore_index=True)
-                        df_bench.to_csv(f'./benchmark_{launch_time}.csv', index=False)
+                        df_bench.to_csv(f"./benchmark_{launch_time}.csv", index=False)
 
 
-if __name__ == '__main__':
-    run_tm(line(1), 1, 0.5) # fist run to jit-compile numba decorated functions
+if __name__ == "__main__":
+    run_tm(line(1), 1, 0.5)  # fist run to jit-compile numba decorated functions
 
     run_bench(
-        overlaps=[
-            0.125,
-            0.25,
-            0.5
-        ],
+        overlaps=[0.125, 0.25, 0.5],
         datasets=[
-            ('line', line),
-            ('digits', digits),
-            ('mnist', mnist),
-            ('cifar10', cifar10),
-            ('fashion_mnist', fashion_mnist),
+            ("line", line),
+            ("digits", digits),
+            ("mnist", mnist),
+            ("cifar10", cifar10),
+            ("fashion_mnist", fashion_mnist),
         ],
         intervals=[
             10,
@@ -172,9 +166,9 @@ def run_bench(benches, datasets, dimensions, overlaps, intervals):
             4,
             5,
         ],
-        benches = [
-            ('tda-mapper', run_tm),
-            ('kepler-mapper', run_km),
-            ('giotto-tda', run_gm),
+        benches=[
+            ("tda-mapper", run_tm),
+            ("kepler-mapper", run_km),
+            ("giotto-tda", run_gm),
         ],
-    )
+    )