kmeans and logreg update

md-shafiul-alam · md-shafiul-alam · commit 7348b4287090 · 2024-10-01T16:56:52.000-07:00
diff --git a/configs/spmd/large_scale/kmeans.json b/configs/spmd/large_scale/kmeans.json
@@ -12,9 +12,8 @@
 	},
 	"synthetic data": {
                 "data": [
-                        { "source": "make_blobs", "generation_kwargs": { "n_samples": 5000000,  "n_features": 10, "centers": 10 }, "algorithm": { "n_clusters": 10, "max_iter": 10 } },
-	                { "source": "make_blobs", "generation_kwargs": { "n_samples": 30000,  "n_features": 1000, "centers": 10 }, "algorithm": { "n_clusters": 10, "max_iter": 10 } },
-			{ "source": "make_blobs", "generation_kwargs": { "n_samples": 1000000,  "n_features": 100, "centers": 100 }, "algorithm": { "n_clusters": 100, "max_iter": 100 } }
+                        { "source": "make_blobs", "generation_kwargs": { "n_samples": 3750000,  "n_features": 10, "centers": 10 }, "algorithm": { "n_clusters": 10, "max_iter": 10 } },
+	                { "source": "make_blobs", "generation_kwargs": { "n_samples": 18750,  "n_features": 1000, "centers": 10 }, "algorithm": { "n_clusters": 10, "max_iter": 10 } }
                 ]
         }
     },
diff --git a/configs/spmd/large_scale/logreg.json b/configs/spmd/large_scale/logreg.json
@@ -11,7 +11,8 @@
         "synthetic data": {
             "data": [
 		        { "source": "make_classification", "split_kwargs": { "train_size": 5000000, "test_size": 1000 },    "generation_kwargs": {  "n_samples": 5001000, "n_features": 10, "n_classes": 2 } },
-                { "source": "make_classification", "split_kwargs": { "train_size": 100000, "test_size": 1000 },    "generation_kwargs": {  "n_samples": 101000, "n_features": 1000, "n_classes": 2 } }
+                { "source": "make_classification", "split_kwargs": { "train_size": 100000, "test_size": 1000 },    "generation_kwargs": {  "n_samples": 101000, "n_features": 1000, "n_classes": 2 } },
+                { "source": "make_classification", "split_kwargs": { "train_size": 500000, "test_size": 1000 },    "generation_kwargs": {  "n_samples": 501000, "n_features": 200, "n_classes":2, "n_clusters_per_class": 3, "flip_y":0.05 } }
             ]
         }
     },

Original file line number	Diff line number	Diff line change
`@@ -12,9 +12,8 @@`
`12`	`12`	`},`
`13`	`13`	`"synthetic data": {`
`14`	`14`	`"data": [`
`15`		`- { "source": "make_blobs", "generation_kwargs": { "n_samples": 5000000, "n_features": 10, "centers": 10 }, "algorithm": { "n_clusters": 10, "max_iter": 10 } },`
`16`		`- { "source": "make_blobs", "generation_kwargs": { "n_samples": 30000, "n_features": 1000, "centers": 10 }, "algorithm": { "n_clusters": 10, "max_iter": 10 } },`
`17`		`- { "source": "make_blobs", "generation_kwargs": { "n_samples": 1000000, "n_features": 100, "centers": 100 }, "algorithm": { "n_clusters": 100, "max_iter": 100 } }`
	`15`	`+ { "source": "make_blobs", "generation_kwargs": { "n_samples": 3750000, "n_features": 10, "centers": 10 }, "algorithm": { "n_clusters": 10, "max_iter": 10 } },`
	`16`	`+ { "source": "make_blobs", "generation_kwargs": { "n_samples": 18750, "n_features": 1000, "centers": 10 }, "algorithm": { "n_clusters": 10, "max_iter": 10 } }`
`18`	`17`	`]`
`19`	`18`	`}`
`20`	`19`	`},`
Original file line number	Diff line number	Diff line change
`@@ -11,7 +11,8 @@`
`11`	`11`	`"synthetic data": {`
`12`	`12`	`"data": [`
`13`	`13`	`{ "source": "make_classification", "split_kwargs": { "train_size": 5000000, "test_size": 1000 }, "generation_kwargs": { "n_samples": 5001000, "n_features": 10, "n_classes": 2 } },`
`14`		`- { "source": "make_classification", "split_kwargs": { "train_size": 100000, "test_size": 1000 }, "generation_kwargs": { "n_samples": 101000, "n_features": 1000, "n_classes": 2 } }`
	`14`	`+ { "source": "make_classification", "split_kwargs": { "train_size": 100000, "test_size": 1000 }, "generation_kwargs": { "n_samples": 101000, "n_features": 1000, "n_classes": 2 } },`
	`15`	`+ { "source": "make_classification", "split_kwargs": { "train_size": 500000, "test_size": 1000 }, "generation_kwargs": { "n_samples": 501000, "n_features": 200, "n_classes":2, "n_clusters_per_class": 3, "flip_y":0.05 } }`
`15`	`16`	`]`
`16`	`17`	`}`
`17`	`18`	`},`