Skip to content

Commit

Permalink
update example higgs notebook for 0.16
Browse files Browse the repository at this point in the history
  • Loading branch information
@beckernick
beckernick committed Sep 3, 2020
1 parent a45046d commit 3a74907
Showing 1 changed file with 26 additions and 44 deletions.
70 changes: 26 additions & 44 deletions tutorials/Higgs_Boson.ipynb
View file
Expand Up @@ -38,25 +38,7 @@
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"--2020-08-31 09:16:09-- https://archive.ics.uci.edu/ml/machine-learning-databases/00280/HIGGS.csv.gz\n",
"Resolving archive.ics.uci.edu (archive.ics.uci.edu)... 128.195.10.252\n",
"Connecting to archive.ics.uci.edu (archive.ics.uci.edu)|128.195.10.252|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 2816407858 (2.6G) [application/x-httpd-php]\n",
"Saving to: ‘./HIGGS.csv.gz’\n",
"\n",
"HIGGS.csv.gz 100%[===================>] 2.62G 102MB/s in 29s \n",
"\n",
"2020-08-31 09:16:38 (93.5 MB/s) - ‘./HIGGS.csv.gz’ saved [2816407858/2816407858]\n",
"\n"
]
}
],
"outputs": [],
"source": [
"# This is a 2.7 GB file.\n",
"# Please make sure you have enough space available before\n",
Expand All @@ -71,7 +53,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
Expand Down Expand Up @@ -102,7 +84,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -119,7 +101,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 5,
"metadata": {},
"outputs": [
{
Expand All @@ -141,30 +123,30 @@
"output_type": "stream",
"text": [
"\n",
"Generation 1 - Current best internal CV score: 0.7103025000000001\n",
"Generation 2 - Current best internal CV score: 0.7103025000000001\n",
"Generation 3 - Current best internal CV score: 0.725755\n",
"Generation 4 - Current best internal CV score: 0.727995\n",
"Generation 5 - Current best internal CV score: 0.727995\n",
"Generation 6 - Current best internal CV score: 0.730315\n",
"Generation 7 - Current best internal CV score: 0.730315\n",
"Generation 8 - Current best internal CV score: 0.730315\n",
"Generation 9 - Current best internal CV score: 0.7308699999999999\n",
"Generation 10 - Current best internal CV score: 0.7347775\n",
"Best pipeline: XGBClassifier(input_matrix, alpha=1, learning_rate=0.1, max_depth=8, min_child_weight=19, n_estimators=100, nthread=1, subsample=0.8, tree_method=gpu_hist)\n",
"CPU times: user 5min 19s, sys: 54.7 s, total: 6min 14s\n",
"Wall time: 6min 17s\n"
"Generation 1 - Current best internal CV score: 0.730335\n",
"Generation 2 - Current best internal CV score: 0.730335\n",
"Generation 3 - Current best internal CV score: 0.730335\n",
"Generation 4 - Current best internal CV score: 0.735615\n",
"Generation 5 - Current best internal CV score: 0.7359375\n",
"Generation 6 - Current best internal CV score: 0.7359375\n",
"Generation 7 - Current best internal CV score: 0.7359375\n",
"Generation 8 - Current best internal CV score: 0.7359375\n",
"Generation 9 - Current best internal CV score: 0.736115\n",
"Generation 10 - Current best internal CV score: 0.7361850000000001\n",
"Best pipeline: XGBClassifier(ZeroCount(SelectPercentile(ZeroCount(input_matrix), percentile=99)), alpha=1, learning_rate=0.1, max_depth=9, min_child_weight=11, n_estimators=100, nthread=1, subsample=0.7000000000000001, tree_method=gpu_hist)\n",
"CPU times: user 8min 15s, sys: 1min 17s, total: 9min 33s\n",
"Wall time: 9min 39s\n"
]
},
{
"data": {
"text/plain": [
"TPOTClassifier(config_dict='TPOT cuML', cv=2, generations=10,\n",
" log_file=<ipykernel.iostream.OutStream object at 0x7fa365211890>,\n",
" log_file=<ipykernel.iostream.OutStream object at 0x7f698a7b5990>,\n",
" population_size=10, random_state=12, verbosity=2)"
]
},
"execution_count": 10,
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
Expand Down Expand Up @@ -193,16 +175,16 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.73669\n",
"CPU times: user 770 ms, sys: 31.7 ms, total: 802 ms\n",
"Wall time: 801 ms\n"
"0.73853\n",
"CPU times: user 950 ms, sys: 36.2 ms, total: 986 ms\n",
"Wall time: 984 ms\n"
]
}
],
Expand Down Expand Up @@ -308,12 +290,12 @@
"metadata": {},
"source": [
"## Performance Comparison\n",
"With the example configuration above (10 generations, population size of 10, two-fold cross validation), the `TPOT cuML` configuration provides a significant speedup while achieving essentially equivalent accuracy.\n",
"With the example configuration above (10 generations, population size of 10, two-fold cross validation), the `TPOT cuML` configuration provided a significant speedup while achieving essentially equivalent accuracy.\n",
"\n",
"The GPU-accelerated version achieves an out-of-sample accuracy of 73.7% in **seven minutes**, while the default version achieves an accuracy of 73.8% after more than **five hours**. This kind of speedup also means you can create larger evolutionary search strategies while **still** obtaining faster results.\n",
"The GPU-accelerated version achieved an out-of-sample accuracy of 73.85% in **fewer than 10 minutes**, while the default version achieved an accuracy of 73.79% after more than **five hours** (specific performance values will vary across runs). This kind of speedup also means you can create larger evolutionary search strategies while **still** obtaining faster results.\n",
"\n",
"### Hardware\n",
"The following hardware was used for this test. Results and speedups will vary.\n",
"The following hardware was used for this test. Results and speedups will vary across systems and configurations.\n",
"\n",
"- CPU: 2x Intel(R) Xeon(R) Platinum 8168 CPU @ 2.70GHz (24 cores)\n",
"- GPU: 1x NVIDIA V100 32GB"
Expand Down

0 comments on commit 3a74907

Please sign in to comment.