diff --git a/examples/simple-mag/confusion-matrix.png b/examples/simple-mag/confusion-matrix.png deleted file mode 100644 index b152adf..0000000 Binary files a/examples/simple-mag/confusion-matrix.png and /dev/null differ diff --git a/examples/simple-mag/mag-confusion.png b/examples/simple-mag/mag-confusion.png new file mode 100644 index 0000000..e1d3718 Binary files /dev/null and b/examples/simple-mag/mag-confusion.png differ diff --git a/examples/simple-mag/train/index.html b/examples/simple-mag/train/index.html index 65bb54d..2f0c6bd 100644 --- a/examples/simple-mag/train/index.html +++ b/examples/simple-mag/train/index.html @@ -1868,8 +1868,8 @@ y_test = [d[1] for d in test_data]
100%|██████████| 84000/84000 [00:08<00:00, 9514.74it/s] -100%|██████████| 22399/22399 [00:02<00:00, 7728.92it/s] +100%|██████████| 84000/84000 [00:16<00:00, 4964.08it/s] +100%|██████████| 22399/22399 [00:05<00:00, 3847.04it/s]
100%|██████████| 12332/12332 [01:27<00:00, 141.08it/s] +100%|██████████| 12272/12272 [01:10<00:00, 174.77it/s]
precision recall f1-score support - Art 0.43 0.35 0.39 125 - Biology 0.77 0.83 0.80 1209 - Business 0.50 0.71 0.59 312 - Chemistry 0.80 0.67 0.73 1194 - Computer Science 0.77 0.76 0.77 1293 - Economics 0.64 0.58 0.61 251 - Engineering 0.55 0.53 0.54 815 -Environmental Science 0.54 0.56 0.55 230 - Geography 0.54 0.44 0.48 277 - Geology 0.76 0.67 0.71 228 - History 0.29 0.21 0.24 102 - Materials Science 0.73 0.81 0.77 1053 - Mathematics 0.80 0.70 0.75 551 - Medicine 0.95 0.77 0.85 2794 - Philosophy 0.61 0.12 0.21 88 - Physics 0.67 0.76 0.72 605 - Political Science 0.43 0.52 0.47 297 - Psychology 0.53 0.80 0.63 600 - Sociology 0.32 0.60 0.42 308 + Art 0.54 0.38 0.45 126 + Biology 0.77 0.84 0.80 1215 + Business 0.47 0.73 0.57 311 + Chemistry 0.82 0.67 0.74 1205 + Computer Science 0.77 0.76 0.76 1277 + Economics 0.69 0.55 0.61 270 + Engineering 0.55 0.52 0.53 754 +Environmental Science 0.56 0.55 0.55 227 + Geography 0.54 0.39 0.45 276 + Geology 0.74 0.67 0.70 265 + History 0.35 0.18 0.24 140 + Materials Science 0.72 0.81 0.76 1011 + Mathematics 0.77 0.70 0.74 498 + Medicine 0.96 0.77 0.86 2835 + Philosophy 0.57 0.06 0.10 71 + Physics 0.66 0.75 0.70 611 + Political Science 0.44 0.61 0.51 291 + Psychology 0.52 0.84 0.64 574 + Sociology 0.33 0.59 0.42 315 - accuracy 0.71 12332 - macro avg 0.61 0.60 0.59 12332 - weighted avg 0.73 0.71 0.71 12332 + accuracy 0.71 12272 + macro avg 0.62 0.60 0.59 12272 + weighted avg 0.74 0.71 0.71 12272
from sklearn.model_selection import GridSearchCV
+import pandas as pd
optimisation_pipeline = GridSearchCV(
create_pipeline(),
@@ -2150,6 +2151,7 @@ def create_pipeline() -> Pipeline:
results.sort_values("rank_test_score")
---------------------------------------------------------------------------- -NameError Traceback (most recent call last) -/data/projects/great-ai/docs/examples/simple/train.ipynb Cell 6 in <cell line: 18>() - <a href='vscode-notebook-cell:/data/projects/great-ai/docs/examples/simple/train.ipynb#ch0000005?line=2'>3</a> optimisation_pipeline = GridSearchCV( - <a href='vscode-notebook-cell:/data/projects/great-ai/docs/examples/simple/train.ipynb#ch0000005?line=3'>4</a> create_pipeline(), - <a href='vscode-notebook-cell:/data/projects/great-ai/docs/examples/simple/train.ipynb#ch0000005?line=4'>5</a> { - (...) - <a href='vscode-notebook-cell:/data/projects/great-ai/docs/examples/simple/train.ipynb#ch0000005?line=13'>14</a> verbose=1, - <a href='vscode-notebook-cell:/data/projects/great-ai/docs/examples/simple/train.ipynb#ch0000005?line=14'>15</a> ) - <a href='vscode-notebook-cell:/data/projects/great-ai/docs/examples/simple/train.ipynb#ch0000005?line=15'>16</a> optimisation_pipeline.fit(X, y) ----> <a href='vscode-notebook-cell:/data/projects/great-ai/docs/examples/simple/train.ipynb#ch0000005?line=17'>18</a> results = pd.DataFrame(optimisation_pipeline.cv_results_) - <a href='vscode-notebook-cell:/data/projects/great-ai/docs/examples/simple/train.ipynb#ch0000005?line=18'>19</a> results.sort_values("rank_test_score") -NameError: name 'pd' is not defined+
| + | mean_fit_time | +std_fit_time | +mean_score_time | +std_score_time | +param_classifier__alpha | +param_classifier__fit_prior | +param_vectorizer__max_df | +param_vectorizer__min_df | +params | +split0_test_score | +split1_test_score | +split2_test_score | +mean_test_score | +std_test_score | +rank_test_score | +
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 7 | +14.549476 | +0.361685 | +8.476837 | +0.222398 | +0.5 | +False | +0.05 | +20 | +{'classifier__alpha': 0.5, 'classifier__fit_pr... | +0.518061 | +0.514842 | +0.511599 | +0.514834 | +0.002638 | +1 | +
| 10 | +11.235289 | +0.130426 | +4.092868 | +0.082518 | +0.5 | +False | +0.1 | +20 | +{'classifier__alpha': 0.5, 'classifier__fit_pr... | +0.513897 | +0.515661 | +0.507867 | +0.512475 | +0.003337 | +2 | +
| 19 | +7.383645 | +0.138110 | +4.130709 | +0.250048 | +1 | +False | +0.05 | +20 | +{'classifier__alpha': 1, 'classifier__fit_prio... | +0.496825 | +0.501045 | +0.496854 | +0.498241 | +0.001983 | +3 | +
| 11 | +10.435154 | +0.305144 | +3.882101 | +0.128886 | +0.5 | +False | +0.1 | +100 | +{'classifier__alpha': 0.5, 'classifier__fit_pr... | +0.493247 | +0.497814 | +0.502245 | +0.497769 | +0.003674 | +4 | +
| 8 | +13.643193 | +0.310696 | +4.173707 | +0.142980 | +0.5 | +False | +0.05 | +100 | +{'classifier__alpha': 0.5, 'classifier__fit_pr... | +0.489609 | +0.495207 | +0.498154 | +0.494323 | +0.003544 | +5 | +
| 22 | +7.048340 | +0.050070 | +3.172948 | +0.152418 | +1 | +False | +0.1 | +20 | +{'classifier__alpha': 1, 'classifier__fit_prio... | +0.487456 | +0.493865 | +0.491157 | +0.490826 | +0.002627 | +6 | +
| 23 | +7.564685 | +0.146092 | +2.374111 | +0.285026 | +1 | +False | +0.1 | +100 | +{'classifier__alpha': 1, 'classifier__fit_prio... | +0.485160 | +0.494039 | +0.490127 | +0.489776 | +0.003633 | +7 | +
| 20 | +7.172353 | +0.212599 | +3.747219 | +0.130217 | +1 | +False | +0.05 | +100 | +{'classifier__alpha': 1, 'classifier__fit_prio... | +0.481303 | +0.490002 | +0.488269 | +0.486524 | +0.003759 | +8 | +
| 6 | +14.276345 | +0.456576 | +8.318859 | +0.268701 | +0.5 | +False | +0.05 | +5 | +{'classifier__alpha': 0.5, 'classifier__fit_pr... | +0.482429 | +0.487735 | +0.484888 | +0.485017 | +0.002168 | +9 | +
| 2 | +14.902358 | +0.737693 | +5.975091 | +0.171150 | +0.5 | +True | +0.05 | +100 | +{'classifier__alpha': 0.5, 'classifier__fit_pr... | +0.469598 | +0.474490 | +0.473637 | +0.472575 | +0.002134 | +10 | +
| 9 | +12.677349 | +0.145143 | +4.374204 | +0.175674 | +0.5 | +False | +0.1 | +5 | +{'classifier__alpha': 0.5, 'classifier__fit_pr... | +0.468872 | +0.476451 | +0.470921 | +0.472082 | +0.003201 | +11 | +
| 5 | +13.423686 | +0.482872 | +8.008324 | +0.442975 | +0.5 | +True | +0.1 | +100 | +{'classifier__alpha': 0.5, 'classifier__fit_pr... | +0.465726 | +0.474548 | +0.471879 | +0.470718 | +0.003694 | +12 | +
| 1 | +13.819117 | +0.838347 | +6.161175 | +0.336590 | +0.5 | +True | +0.05 | +20 | +{'classifier__alpha': 0.5, 'classifier__fit_pr... | +0.463395 | +0.473982 | +0.471262 | +0.469546 | +0.004489 | +13 | +
| 4 | +13.281476 | +0.588822 | +8.335852 | +0.254627 | +0.5 | +True | +0.1 | +20 | +{'classifier__alpha': 0.5, 'classifier__fit_pr... | +0.458734 | +0.468053 | +0.464418 | +0.463735 | +0.003835 | +14 | +
| 14 | +7.282247 | +0.444940 | +3.567094 | +0.044519 | +1 | +True | +0.05 | +100 | +{'classifier__alpha': 1, 'classifier__fit_prio... | +0.438189 | +0.450160 | +0.446180 | +0.444843 | +0.004978 | +15 | +
| 17 | +7.098797 | +0.196241 | +3.838628 | +0.091128 | +1 | +True | +0.1 | +100 | +{'classifier__alpha': 1, 'classifier__fit_prio... | +0.436488 | +0.444503 | +0.445900 | +0.442297 | +0.004147 | +16 | +
| 18 | +7.492791 | +0.288889 | +3.843224 | +0.073438 | +1 | +False | +0.05 | +5 | +{'classifier__alpha': 1, 'classifier__fit_prio... | +0.428196 | +0.431945 | +0.430160 | +0.430100 | +0.001531 | +17 | +
| 21 | +7.229826 | +0.099823 | +3.656332 | +0.073780 | +1 | +False | +0.1 | +5 | +{'classifier__alpha': 1, 'classifier__fit_prio... | +0.403130 | +0.410170 | +0.409801 | +0.407700 | +0.003235 | +18 | +
| 13 | +7.158370 | +0.169818 | +3.765632 | +0.082924 | +1 | +True | +0.05 | +20 | +{'classifier__alpha': 1, 'classifier__fit_prio... | +0.399237 | +0.412872 | +0.407982 | +0.406697 | +0.005640 | +19 | +
| 16 | +7.064643 | +0.119529 | +3.810983 | +0.125897 | +1 | +True | +0.1 | +20 | +{'classifier__alpha': 1, 'classifier__fit_prio... | +0.388060 | +0.399247 | +0.396325 | +0.394544 | +0.004737 | +20 | +
| 0 | +13.749660 | +0.465174 | +6.407841 | +0.549166 | +0.5 | +True | +0.05 | +5 | +{'classifier__alpha': 0.5, 'classifier__fit_pr... | +0.384852 | +0.386487 | +0.386796 | +0.386045 | +0.000853 | +21 | +
| 3 | +15.954147 | +0.318013 | +6.337361 | +0.261697 | +0.5 | +True | +0.1 | +5 | +{'classifier__alpha': 0.5, 'classifier__fit_pr... | +0.369785 | +0.375645 | +0.375858 | +0.373763 | +0.002814 | +22 | +
| 12 | +7.120198 | +0.050452 | +3.833905 | +0.069540 | +1 | +True | +0.05 | +5 | +{'classifier__alpha': 1, 'classifier__fit_prio... | +0.277741 | +0.280564 | +0.285337 | +0.281214 | +0.003135 | +23 | +
| 15 | +7.497707 | +0.183054 | +3.870714 | +0.062888 | +1 | +True | +0.1 | +5 | +{'classifier__alpha': 1, 'classifier__fit_prio... | +0.255578 | +0.263381 | +0.266184 | +0.261714 | +0.004487 | +24 | +
Fetching cached versions of small-domain-prediction -Copying file for small-domain-prediction-1 -Compressing small-domain-prediction-1 -Model small-domain-prediction uploaded with version 1 +Copying file for small-domain-prediction-2 +Compressing small-domain-prediction-2 +Model small-domain-prediction uploaded with version 2
'small-domain-prediction:1'+
'small-domain-prediction:2'
| \n", + " | mean_fit_time | \n", + "std_fit_time | \n", + "mean_score_time | \n", + "std_score_time | \n", + "param_classifier__alpha | \n", + "param_classifier__fit_prior | \n", + "param_vectorizer__max_df | \n", + "param_vectorizer__min_df | \n", + "params | \n", + "split0_test_score | \n", + "split1_test_score | \n", + "split2_test_score | \n", + "mean_test_score | \n", + "std_test_score | \n", + "rank_test_score | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 7 | \n", + "14.549476 | \n", + "0.361685 | \n", + "8.476837 | \n", + "0.222398 | \n", + "0.5 | \n", + "False | \n", + "0.05 | \n", + "20 | \n", + "{'classifier__alpha': 0.5, 'classifier__fit_pr... | \n", + "0.518061 | \n", + "0.514842 | \n", + "0.511599 | \n", + "0.514834 | \n", + "0.002638 | \n", + "1 | \n", + "
| 10 | \n", + "11.235289 | \n", + "0.130426 | \n", + "4.092868 | \n", + "0.082518 | \n", + "0.5 | \n", + "False | \n", + "0.1 | \n", + "20 | \n", + "{'classifier__alpha': 0.5, 'classifier__fit_pr... | \n", + "0.513897 | \n", + "0.515661 | \n", + "0.507867 | \n", + "0.512475 | \n", + "0.003337 | \n", + "2 | \n", + "
| 19 | \n", + "7.383645 | \n", + "0.138110 | \n", + "4.130709 | \n", + "0.250048 | \n", + "1 | \n", + "False | \n", + "0.05 | \n", + "20 | \n", + "{'classifier__alpha': 1, 'classifier__fit_prio... | \n", + "0.496825 | \n", + "0.501045 | \n", + "0.496854 | \n", + "0.498241 | \n", + "0.001983 | \n", + "3 | \n", + "
| 11 | \n", + "10.435154 | \n", + "0.305144 | \n", + "3.882101 | \n", + "0.128886 | \n", + "0.5 | \n", + "False | \n", + "0.1 | \n", + "100 | \n", + "{'classifier__alpha': 0.5, 'classifier__fit_pr... | \n", + "0.493247 | \n", + "0.497814 | \n", + "0.502245 | \n", + "0.497769 | \n", + "0.003674 | \n", + "4 | \n", + "
| 8 | \n", + "13.643193 | \n", + "0.310696 | \n", + "4.173707 | \n", + "0.142980 | \n", + "0.5 | \n", + "False | \n", + "0.05 | \n", + "100 | \n", + "{'classifier__alpha': 0.5, 'classifier__fit_pr... | \n", + "0.489609 | \n", + "0.495207 | \n", + "0.498154 | \n", + "0.494323 | \n", + "0.003544 | \n", + "5 | \n", + "
| 22 | \n", + "7.048340 | \n", + "0.050070 | \n", + "3.172948 | \n", + "0.152418 | \n", + "1 | \n", + "False | \n", + "0.1 | \n", + "20 | \n", + "{'classifier__alpha': 1, 'classifier__fit_prio... | \n", + "0.487456 | \n", + "0.493865 | \n", + "0.491157 | \n", + "0.490826 | \n", + "0.002627 | \n", + "6 | \n", + "
| 23 | \n", + "7.564685 | \n", + "0.146092 | \n", + "2.374111 | \n", + "0.285026 | \n", + "1 | \n", + "False | \n", + "0.1 | \n", + "100 | \n", + "{'classifier__alpha': 1, 'classifier__fit_prio... | \n", + "0.485160 | \n", + "0.494039 | \n", + "0.490127 | \n", + "0.489776 | \n", + "0.003633 | \n", + "7 | \n", + "
| 20 | \n", + "7.172353 | \n", + "0.212599 | \n", + "3.747219 | \n", + "0.130217 | \n", + "1 | \n", + "False | \n", + "0.05 | \n", + "100 | \n", + "{'classifier__alpha': 1, 'classifier__fit_prio... | \n", + "0.481303 | \n", + "0.490002 | \n", + "0.488269 | \n", + "0.486524 | \n", + "0.003759 | \n", + "8 | \n", + "
| 6 | \n", + "14.276345 | \n", + "0.456576 | \n", + "8.318859 | \n", + "0.268701 | \n", + "0.5 | \n", + "False | \n", + "0.05 | \n", + "5 | \n", + "{'classifier__alpha': 0.5, 'classifier__fit_pr... | \n", + "0.482429 | \n", + "0.487735 | \n", + "0.484888 | \n", + "0.485017 | \n", + "0.002168 | \n", + "9 | \n", + "
| 2 | \n", + "14.902358 | \n", + "0.737693 | \n", + "5.975091 | \n", + "0.171150 | \n", + "0.5 | \n", + "True | \n", + "0.05 | \n", + "100 | \n", + "{'classifier__alpha': 0.5, 'classifier__fit_pr... | \n", + "0.469598 | \n", + "0.474490 | \n", + "0.473637 | \n", + "0.472575 | \n", + "0.002134 | \n", + "10 | \n", + "
| 9 | \n", + "12.677349 | \n", + "0.145143 | \n", + "4.374204 | \n", + "0.175674 | \n", + "0.5 | \n", + "False | \n", + "0.1 | \n", + "5 | \n", + "{'classifier__alpha': 0.5, 'classifier__fit_pr... | \n", + "0.468872 | \n", + "0.476451 | \n", + "0.470921 | \n", + "0.472082 | \n", + "0.003201 | \n", + "11 | \n", + "
| 5 | \n", + "13.423686 | \n", + "0.482872 | \n", + "8.008324 | \n", + "0.442975 | \n", + "0.5 | \n", + "True | \n", + "0.1 | \n", + "100 | \n", + "{'classifier__alpha': 0.5, 'classifier__fit_pr... | \n", + "0.465726 | \n", + "0.474548 | \n", + "0.471879 | \n", + "0.470718 | \n", + "0.003694 | \n", + "12 | \n", + "
| 1 | \n", + "13.819117 | \n", + "0.838347 | \n", + "6.161175 | \n", + "0.336590 | \n", + "0.5 | \n", + "True | \n", + "0.05 | \n", + "20 | \n", + "{'classifier__alpha': 0.5, 'classifier__fit_pr... | \n", + "0.463395 | \n", + "0.473982 | \n", + "0.471262 | \n", + "0.469546 | \n", + "0.004489 | \n", + "13 | \n", + "
| 4 | \n", + "13.281476 | \n", + "0.588822 | \n", + "8.335852 | \n", + "0.254627 | \n", + "0.5 | \n", + "True | \n", + "0.1 | \n", + "20 | \n", + "{'classifier__alpha': 0.5, 'classifier__fit_pr... | \n", + "0.458734 | \n", + "0.468053 | \n", + "0.464418 | \n", + "0.463735 | \n", + "0.003835 | \n", + "14 | \n", + "
| 14 | \n", + "7.282247 | \n", + "0.444940 | \n", + "3.567094 | \n", + "0.044519 | \n", + "1 | \n", + "True | \n", + "0.05 | \n", + "100 | \n", + "{'classifier__alpha': 1, 'classifier__fit_prio... | \n", + "0.438189 | \n", + "0.450160 | \n", + "0.446180 | \n", + "0.444843 | \n", + "0.004978 | \n", + "15 | \n", + "
| 17 | \n", + "7.098797 | \n", + "0.196241 | \n", + "3.838628 | \n", + "0.091128 | \n", + "1 | \n", + "True | \n", + "0.1 | \n", + "100 | \n", + "{'classifier__alpha': 1, 'classifier__fit_prio... | \n", + "0.436488 | \n", + "0.444503 | \n", + "0.445900 | \n", + "0.442297 | \n", + "0.004147 | \n", + "16 | \n", + "
| 18 | \n", + "7.492791 | \n", + "0.288889 | \n", + "3.843224 | \n", + "0.073438 | \n", + "1 | \n", + "False | \n", + "0.05 | \n", + "5 | \n", + "{'classifier__alpha': 1, 'classifier__fit_prio... | \n", + "0.428196 | \n", + "0.431945 | \n", + "0.430160 | \n", + "0.430100 | \n", + "0.001531 | \n", + "17 | \n", + "
| 21 | \n", + "7.229826 | \n", + "0.099823 | \n", + "3.656332 | \n", + "0.073780 | \n", + "1 | \n", + "False | \n", + "0.1 | \n", + "5 | \n", + "{'classifier__alpha': 1, 'classifier__fit_prio... | \n", + "0.403130 | \n", + "0.410170 | \n", + "0.409801 | \n", + "0.407700 | \n", + "0.003235 | \n", + "18 | \n", + "
| 13 | \n", + "7.158370 | \n", + "0.169818 | \n", + "3.765632 | \n", + "0.082924 | \n", + "1 | \n", + "True | \n", + "0.05 | \n", + "20 | \n", + "{'classifier__alpha': 1, 'classifier__fit_prio... | \n", + "0.399237 | \n", + "0.412872 | \n", + "0.407982 | \n", + "0.406697 | \n", + "0.005640 | \n", + "19 | \n", + "
| 16 | \n", + "7.064643 | \n", + "0.119529 | \n", + "3.810983 | \n", + "0.125897 | \n", + "1 | \n", + "True | \n", + "0.1 | \n", + "20 | \n", + "{'classifier__alpha': 1, 'classifier__fit_prio... | \n", + "0.388060 | \n", + "0.399247 | \n", + "0.396325 | \n", + "0.394544 | \n", + "0.004737 | \n", + "20 | \n", + "
| 0 | \n", + "13.749660 | \n", + "0.465174 | \n", + "6.407841 | \n", + "0.549166 | \n", + "0.5 | \n", + "True | \n", + "0.05 | \n", + "5 | \n", + "{'classifier__alpha': 0.5, 'classifier__fit_pr... | \n", + "0.384852 | \n", + "0.386487 | \n", + "0.386796 | \n", + "0.386045 | \n", + "0.000853 | \n", + "21 | \n", + "
| 3 | \n", + "15.954147 | \n", + "0.318013 | \n", + "6.337361 | \n", + "0.261697 | \n", + "0.5 | \n", + "True | \n", + "0.1 | \n", + "5 | \n", + "{'classifier__alpha': 0.5, 'classifier__fit_pr... | \n", + "0.369785 | \n", + "0.375645 | \n", + "0.375858 | \n", + "0.373763 | \n", + "0.002814 | \n", + "22 | \n", + "
| 12 | \n", + "7.120198 | \n", + "0.050452 | \n", + "3.833905 | \n", + "0.069540 | \n", + "1 | \n", + "True | \n", + "0.05 | \n", + "5 | \n", + "{'classifier__alpha': 1, 'classifier__fit_prio... | \n", + "0.277741 | \n", + "0.280564 | \n", + "0.285337 | \n", + "0.281214 | \n", + "0.003135 | \n", + "23 | \n", + "
| 15 | \n", + "7.497707 | \n", + "0.183054 | \n", + "3.870714 | \n", + "0.062888 | \n", + "1 | \n", + "True | \n", + "0.1 | \n", + "5 | \n", + "{'classifier__alpha': 1, 'classifier__fit_prio... | \n", + "0.255578 | \n", + "0.263381 | \n", + "0.266184 | \n", + "0.261714 | \n", + "0.004487 | \n", + "24 | \n", + "