Skip to content

Commit ecdcfab

Browse files
michael-phillips-datajoshterrill
michael-phillips-data
and
joshterrill
authored
update to 5.2 (#182)
* update to 5.2 * updated cached pickles for 5.2 dataset --------- Co-authored-by: Josh Terrill <[email protected]>
1 parent bf988e7 commit ecdcfab

12 files changed

+6220
-8223
lines changed

‎cached-pickles/example_model.pkl‎

3.46 KB
Binary file not shown.

‎cached-pickles/feature_neutralization.pkl‎

-1.05 KB
Binary file not shown.

‎cached-pickles/hello_numerai.pkl‎

3.46 KB
Binary file not shown.

‎cached-pickles/target_ensemble.pkl‎

-1.06 KB
Binary file not shown.

‎example_model.ipynb‎

Lines changed: 13 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -18,8 +18,8 @@
1818
"id": "Ekw8Z93ljC3v",
1919
"outputId": "bdd16698-2ad0-4423-b090-c5ce55fe3053",
2020
"ExecuteTime": {
21-
"end_time": "2025-10-30T20:48:39.810378Z",
22-
"start_time": "2025-10-30T20:48:39.568630Z"
21+
"end_time": "2025-12-14T21:09:42.696957Z",
22+
"start_time": "2025-12-14T21:09:42.549138Z"
2323
}
2424
},
2525
"source": [
@@ -45,8 +45,8 @@
4545
"id": "yoy_wT1rhMqF",
4646
"outputId": "e038b50f-1b61-4334-be62-28f4dc40a0a0",
4747
"ExecuteTime": {
48-
"end_time": "2025-10-30T20:48:44.681841Z",
49-
"start_time": "2025-10-30T20:48:39.831618Z"
48+
"end_time": "2025-12-14T21:09:44.281889Z",
49+
"start_time": "2025-12-14T21:09:42.698161Z"
5050
}
5151
},
5252
"source": [
@@ -76,8 +76,8 @@
7676
"id": "13hdRk9ghMqI",
7777
"outputId": "d2274374-fd85-4189-f27b-d9d466cc63ca",
7878
"ExecuteTime": {
79-
"end_time": "2025-10-30T21:03:42.084921Z",
80-
"start_time": "2025-10-30T20:48:44.692306Z"
79+
"end_time": "2025-12-14T21:10:08.471862Z",
80+
"start_time": "2025-12-14T21:09:44.283405Z"
8181
}
8282
},
8383
"source": [
@@ -87,7 +87,7 @@
8787
"napi = NumerAPI()\n",
8888
"\n",
8989
"# use one of the latest data versions\n",
90-
"DATA_VERSION = \"v5.1\"\n",
90+
"DATA_VERSION = \"v5.2\"\n",
9191
"\n",
9292
"# Download data\n",
9393
"napi.download_dataset(f\"{DATA_VERSION}/train.parquet\")\n",
@@ -161,22 +161,22 @@
161161
"name": "stderr",
162162
"output_type": "stream",
163163
"text": [
164-
"2025-10-30 13:48:45,438 INFO numerapi.utils: target file already exists\n",
165-
"2025-10-30 13:48:45,443 INFO numerapi.utils: download complete\n",
166-
"2025-10-30 13:48:45,810 INFO numerapi.utils: target file already exists\n",
167-
"2025-10-30 13:48:45,816 INFO numerapi.utils: download complete\n"
164+
"2025-12-14 13:09:45,386 INFO numerapi.utils: target file already exists\n",
165+
"2025-12-14 13:09:45,387 INFO numerapi.utils: download complete\n",
166+
"2025-12-14 13:09:46,291 INFO numerapi.utils: target file already exists\n",
167+
"2025-12-14 13:09:46,291 INFO numerapi.utils: download complete\n"
168168
]
169169
},
170170
{
171171
"name": "stdout",
172172
"output_type": "stream",
173173
"text": [
174-
"[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.015210 seconds.\n",
174+
"[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.001259 seconds.\n",
175175
"You can set `force_row_wise=true` to remove the overhead.\n",
176176
"And if memory is not enough, you can set `force_col_wise=true`.\n",
177177
"[LightGBM] [Info] Total Bins 210\n",
178178
"[LightGBM] [Info] Number of data points in the train set: 688184, number of used features: 42\n",
179-
"[LightGBM] [Info] Start training from score 0.500008\n"
179+
"[LightGBM] [Info] Start training from score 0.499946\n"
180180
]
181181
}
182182
],

‎feature_neutralization.ipynb‎

Lines changed: 569 additions & 422 deletions
Large diffs are not rendered by default.

‎hello_numerai.ipynb‎

Lines changed: 356 additions & 210 deletions
Large diffs are not rendered by default.

‎numerai/example_model.ipynb‎

Lines changed: 20 additions & 19 deletions
Original file line numberDiff line numberDiff line change
@@ -18,8 +18,8 @@
1818
"id": "Ekw8Z93ljC3v",
1919
"outputId": "bdd16698-2ad0-4423-b090-c5ce55fe3053",
2020
"ExecuteTime": {
21-
"end_time": "2025-10-30T20:48:31.494546Z",
22-
"start_time": "2025-10-30T20:48:31.297964Z"
21+
"end_time": "2025-12-14T21:23:24.577253Z",
22+
"start_time": "2025-12-14T21:23:24.420881Z"
2323
}
2424
},
2525
"source": [
@@ -34,7 +34,7 @@
3434
]
3535
}
3636
],
37-
"execution_count": 7
37+
"execution_count": 1
3838
},
3939
{
4040
"cell_type": "code",
@@ -45,8 +45,8 @@
4545
"id": "yoy_wT1rhMqF",
4646
"outputId": "e038b50f-1b61-4334-be62-28f4dc40a0a0",
4747
"ExecuteTime": {
48-
"end_time": "2025-10-30T20:48:33.771995Z",
49-
"start_time": "2025-10-30T20:48:31.497465Z"
48+
"end_time": "2025-12-14T21:23:25.628662Z",
49+
"start_time": "2025-12-14T21:23:24.578722Z"
5050
}
5151
},
5252
"source": [
@@ -64,7 +64,7 @@
6464
]
6565
}
6666
],
67-
"execution_count": 8
67+
"execution_count": 2
6868
},
6969
{
7070
"cell_type": "code",
@@ -76,8 +76,8 @@
7676
"id": "13hdRk9ghMqI",
7777
"outputId": "d2274374-fd85-4189-f27b-d9d466cc63ca",
7878
"ExecuteTime": {
79-
"end_time": "2025-10-30T21:03:41.542550Z",
80-
"start_time": "2025-10-30T20:48:33.776610Z"
79+
"end_time": "2025-12-14T21:28:28.979818Z",
80+
"start_time": "2025-12-14T21:23:25.629875Z"
8181
}
8282
},
8383
"source": [
@@ -87,7 +87,7 @@
8787
"napi = NumerAPI()\n",
8888
"\n",
8989
"# use one of the latest data versions\n",
90-
"DATA_VERSION = \"v5.1\"\n",
90+
"DATA_VERSION = \"v5.2\"\n",
9191
"\n",
9292
"# Download data\n",
9393
"napi.download_dataset(f\"{DATA_VERSION}/train.parquet\")\n",
@@ -161,38 +161,39 @@
161161
"name": "stderr",
162162
"output_type": "stream",
163163
"text": [
164-
"2025-10-30 13:48:34,557 INFO numerapi.utils: target file already exists\n",
165-
"2025-10-30 13:48:34,559 INFO numerapi.utils: download complete\n",
166-
"2025-10-30 13:48:35,037 INFO numerapi.utils: target file already exists\n",
167-
"2025-10-30 13:48:35,038 INFO numerapi.utils: download complete\n"
164+
"2025-12-14 13:23:26,450 INFO numerapi.utils: target file already exists\n",
165+
"2025-12-14 13:23:26,452 INFO numerapi.utils: starting download\n",
166+
"v5.2/train.parquet: 7.67GB [04:40, 27.4MB/s] \n",
167+
"2025-12-14 13:28:07,043 INFO numerapi.utils: target file already exists\n",
168+
"2025-12-14 13:28:07,045 INFO numerapi.utils: download complete\n"
168169
]
169170
},
170171
{
171172
"name": "stdout",
172173
"output_type": "stream",
173174
"text": [
174-
"[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.009704 seconds.\n",
175+
"[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.001209 seconds.\n",
175176
"You can set `force_row_wise=true` to remove the overhead.\n",
176177
"And if memory is not enough, you can set `force_col_wise=true`.\n",
177178
"[LightGBM] [Info] Total Bins 210\n",
178179
"[LightGBM] [Info] Number of data points in the train set: 688184, number of used features: 42\n",
179-
"[LightGBM] [Info] Start training from score 0.500008\n"
180+
"[LightGBM] [Info] Start training from score 0.499946\n"
180181
]
181182
}
182183
],
183-
"execution_count": 9
184+
"execution_count": 3
184185
},
185186
{
186187
"metadata": {
187188
"ExecuteTime": {
188-
"end_time": "2025-10-30T21:03:41.546742Z",
189-
"start_time": "2025-10-30T21:03:41.544691Z"
189+
"end_time": "2025-12-14T21:28:28.982147Z",
190+
"start_time": "2025-12-14T21:28:28.980721Z"
190191
}
191192
},
192193
"cell_type": "code",
193194
"source": "",
194195
"outputs": [],
195-
"execution_count": 9
196+
"execution_count": 3
196197
}
197198
],
198199
"metadata": {

‎numerai/feature_neutralization.ipynb‎

Lines changed: 673 additions & 532 deletions
Large diffs are not rendered by default.

0 commit comments

Comments
 (0)