Getting Started¶
Alpha-AutoML is integrated with Jupyter Notebooks. The Jupyter notebooks provide an interactive computing environment where you can generate models using Alpha-AutoML, and explore them using PipelineProfiler which is an interactive visualization aimed at producing detailed visualizations of end-to-end machine learning pipelines. Alpha-AutoML has two main components: model generation and model exploration.
First, import the class AutoMLClassifier (for classification problems). If you plan to use Alpha-AutoML for other ML tasks, please see these other examples.
[1]:
from alpha_automl import AutoMLClassifier
Model Generation¶
The model generation component provides methods to search pipelines.
In this example, we are generating pipelines for a CSV dataset. The 299_libras_move dataset is used for this example. This dataset contains 15 classes, where each class references to a hand movement type in LIBRAS. LIBRAS, acronym of the Portuguese name “LIngua BRAsileira de Sinais”, is the official brazilian sign language.
[2]:
import pandas as pd
train_dataset = pd.read_csv('../../examples/datasets/299_libras_move/train_data.csv')
test_dataset = pd.read_csv('../../examples/datasets/299_libras_move/test_data.csv')
Removing the target column from the features for the train dataset
[3]:
target_column = 'class'
X_train = train_dataset.drop(columns=[target_column])
X_train
[3]:
| xcoord1 | ycoord1 | xcoord2 | ycoord2 | xcoord3 | ycoord3 | xcoord4 | ycoord4 | xcoord5 | ycoord5 | ... | xcoord41 | ycoord41 | xcoord42 | ycoord42 | xcoord43 | ycoord43 | xcoord44 | ycoord44 | xcoord45 | ycoord45 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0.82979 | 0.76620 | 0.82979 | 0.76620 | 0.82979 | 0.77083 | 0.82785 | 0.77083 | 0.82979 | 0.76620 | ... | 0.41199 | 0.45370 | 0.37524 | 0.43750 | 0.33269 | 0.43056 | 0.29787 | 0.44213 | 0.26886 | 0.47222 |
| 1 | 0.80271 | 0.54630 | 0.80077 | 0.54398 | 0.80271 | 0.54398 | 0.80271 | 0.54630 | 0.80271 | 0.54398 | ... | 0.20503 | 0.64583 | 0.20503 | 0.68056 | 0.20696 | 0.71296 | 0.21083 | 0.74537 | 0.21277 | 0.77315 |
| 2 | 0.78917 | 0.59028 | 0.79110 | 0.59028 | 0.79110 | 0.59028 | 0.79304 | 0.59028 | 0.79110 | 0.59028 | ... | 0.20503 | 0.57407 | 0.19149 | 0.57176 | 0.18569 | 0.57407 | 0.18956 | 0.57639 | 0.19149 | 0.56944 |
| 3 | 0.88395 | 0.61574 | 0.88201 | 0.61806 | 0.87234 | 0.62037 | 0.87041 | 0.61574 | 0.84526 | 0.61574 | ... | 0.27079 | 0.65972 | 0.26886 | 0.62731 | 0.27660 | 0.59259 | 0.27660 | 0.56250 | 0.27853 | 0.53009 |
| 4 | 0.60155 | 0.77315 | 0.59768 | 0.77315 | 0.59961 | 0.77315 | 0.59381 | 0.77083 | 0.58801 | 0.75000 | ... | 0.63830 | 0.47917 | 0.63250 | 0.52778 | 0.63830 | 0.57407 | 0.63830 | 0.63194 | 0.63830 | 0.68750 |
| ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
| 283 | 0.85300 | 0.57639 | 0.85493 | 0.57407 | 0.85300 | 0.57639 | 0.85300 | 0.57407 | 0.85493 | 0.56944 | ... | 0.19923 | 0.80787 | 0.17021 | 0.79630 | 0.14313 | 0.75231 | 0.12959 | 0.69213 | 0.12959 | 0.62037 |
| 284 | 0.66925 | 0.78009 | 0.66925 | 0.78009 | 0.66925 | 0.78009 | 0.67118 | 0.78009 | 0.66925 | 0.78009 | ... | 0.67311 | 0.28704 | 0.66925 | 0.26389 | 0.66731 | 0.24306 | 0.66731 | 0.22454 | 0.66538 | 0.20602 |
| 285 | 0.57060 | 0.65741 | 0.57060 | 0.65741 | 0.57060 | 0.65509 | 0.56867 | 0.65046 | 0.54739 | 0.64120 | ... | 0.36944 | 0.62500 | 0.42166 | 0.62269 | 0.47389 | 0.62269 | 0.52418 | 0.63194 | 0.56286 | 0.64120 |
| 286 | 0.62282 | 0.65278 | 0.62476 | 0.65046 | 0.62669 | 0.64815 | 0.61315 | 0.63426 | 0.55319 | 0.60185 | ... | 0.28433 | 0.66435 | 0.30754 | 0.63889 | 0.33462 | 0.61574 | 0.37331 | 0.58102 | 0.42747 | 0.54398 |
| 287 | 0.65571 | 0.51157 | 0.65571 | 0.51389 | 0.65571 | 0.51157 | 0.65571 | 0.51389 | 0.65571 | 0.51157 | ... | 0.64603 | 0.46296 | 0.65377 | 0.48843 | 0.65571 | 0.49074 | 0.64990 | 0.46296 | 0.65377 | 0.45833 |
288 rows × 90 columns
Selecting the target column for the train dataset
[4]:
y_train = train_dataset[[target_column]]
y_train
[4]:
| class | |
|---|---|
| 0 | 12 |
| 1 | 15 |
| 2 | 7 |
| 3 | 12 |
| 4 | 3 |
| ... | ... |
| 283 | 12 |
| 284 | 8 |
| 285 | 2 |
| 286 | 1 |
| 287 | 9 |
288 rows × 1 columns
The AutoMLClassifier class needs the following parameters: the output path to be used and the maximum running time (time_bound) in minutes. To perform the search of pipelines, we need to call the fit method, which receives the features and labels columns.
[5]:
automl = AutoMLClassifier(time_bound=1)
automl.fit(X_train, y_train)
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:03, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.125
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:04, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.2638888888888889
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:04, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.19444444444444445
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:04, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.18055555555555555
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:05, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.19444444444444445
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:05, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5555555555555556
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:05, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.7777777777777778
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:05, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5416666666666666
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:05, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.6805555555555556
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:12, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5555555555555556
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:12, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5416666666666666
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:12, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5416666666666666
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:12, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5416666666666666
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:12, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4444444444444444
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:12, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.027777777777777776
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:12, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.1388888888888889
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:12, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.027777777777777776
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:12, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.25
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:12, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.19444444444444445
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:13, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.7361111111111112
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:13, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.027777777777777776
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:13, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5416666666666666
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:13, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5972222222222222
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:13, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.6805555555555556
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:13, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.25
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:13, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4166666666666667
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:13, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.09722222222222222
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:13, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.18055555555555555
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:13, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.19444444444444445
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:13, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.20833333333333334
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:13, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.18055555555555555
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:14, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.75
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:14, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.3194444444444444
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:14, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.20833333333333334
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:14, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.19444444444444445
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:14, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.125
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:14, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.7916666666666666
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:14, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.25
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:15, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.25
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:15, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.75
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:15, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4583333333333333
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:15, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4444444444444444
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:15, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4444444444444444
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:15, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.125
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:15, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.3472222222222222
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:15, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.19444444444444445
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:15, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4166666666666667
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:16, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:16, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.6666666666666666
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:16, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.125
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:16, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.19444444444444445
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:16, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.2638888888888889
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:16, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4166666666666667
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:16, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4305555555555556
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:16, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:16, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.125
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:16, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.25
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:16, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5555555555555556
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:16, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.19444444444444445
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:18, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.375
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:18, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.3194444444444444
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:18, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.3888888888888889
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:19, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4305555555555556
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:19, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.18055555555555555
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:19, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.7361111111111112
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:19, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.6111111111111112
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:19, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.6805555555555556
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:19, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.7638888888888888
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:19, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.19444444444444445
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:20, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.6944444444444444
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:20, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.6111111111111112
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:20, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5555555555555556
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:20, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5416666666666666
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:20, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.2916666666666667
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:21, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.19444444444444445
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:21, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4027777777777778
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:21, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.25
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:21, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.25
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:22, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.19444444444444445
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:22, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.027777777777777776
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:22, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4583333333333333
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:22, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.06944444444444445
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:23, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4305555555555556
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:23, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.25
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:23, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.2222222222222222
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:23, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4444444444444444
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:23, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4444444444444444
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:23, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.18055555555555555
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:23, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.3333333333333333
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:23, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4305555555555556
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:23, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4861111111111111
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:23, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.125
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:23, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5555555555555556
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:30, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5833333333333334
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:32, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.19444444444444445
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:32, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.7361111111111112
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:32, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.027777777777777776
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:32, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.1388888888888889
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:32, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.027777777777777776
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:34, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4166666666666667
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:34, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.3055555555555556
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:34, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.027777777777777776
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:34, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4444444444444444
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:34, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.08333333333333333
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:34, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5416666666666666
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:40, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5833333333333334
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:40, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.027777777777777776
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:40, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.375
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:40, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.2777777777777778
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:40, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.1388888888888889
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:41, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5138888888888888
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:41, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.7361111111111112
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:41, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5694444444444444
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:41, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.25
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:41, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4305555555555556
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:41, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.3055555555555556
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:41, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4444444444444444
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:41, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4722222222222222
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:41, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.09722222222222222
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:42, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5416666666666666
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:42, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5277777777777778
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:42, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.3611111111111111
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:42, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.125
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:42, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.19444444444444445
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:42, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.6388888888888888
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:42, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.09722222222222222
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:42, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.7361111111111112
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:42, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.2222222222222222
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:42, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.7638888888888888
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:42, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.75
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:43, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.6388888888888888
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:43, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.6111111111111112
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:43, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.6111111111111112
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:43, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.20833333333333334
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:44, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.19444444444444445
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:44, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.18055555555555555
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:44, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4722222222222222
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:44, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5972222222222222
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:44, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.08333333333333333
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:44, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.6388888888888888
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:44, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.5277777777777778
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:44, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.2361111111111111
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:44, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.7638888888888888
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:45, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.6111111111111112
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:45, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.1388888888888889
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:45, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.7916666666666666
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:45, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.4166666666666667
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:45, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.6944444444444444
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:45, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.06944444444444445
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:45, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.09722222222222222
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:45, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.6111111111111112
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:45, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.3472222222222222
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:50, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.3472222222222222
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:50, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.3472222222222222
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:53, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.25
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:53, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.1527777777777778
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:56, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.19444444444444445
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:56, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.18055555555555555
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:56, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.09722222222222222
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:56, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.1527777777777778
INFO:alpha_automl.automl_api:Found pipeline, time=0:00:56, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.25
INFO:alpha_automl.automl_api:Found pipeline, time=0:01:03, scoring...
INFO:alpha_automl.automl_api:Scored pipeline, score=0.1388888888888889
INFO:alpha_automl.automl_api:Found 162 pipelines
After the pipeline search is complete, we can display the leaderboard:
[6]:
automl.plot_leaderboard()
[6]:
| ranking | pipeline | accuracy_score |
|---|---|---|
| 1 | StandardScaler, ExtraTreesClassifier | 0.792 |
| 2 | StandardScaler, LogisticRegression | 0.792 |
| 3 | MaxAbsScaler, ExtraTreesClassifier | 0.778 |
| 4 | MaxAbsScaler, SVC | 0.764 |
| 5 | SVC | 0.764 |
| 6 | StandardScaler, RandomForestClassifier | 0.764 |
| 7 | ExtraTreesClassifier | 0.750 |
| 8 | RobustScaler, ExtraTreesClassifier | 0.750 |
| 9 | StandardScaler, SVC | 0.750 |
| 10 | MaxAbsScaler, LinearSVC | 0.736 |
| 11 | MaxAbsScaler, RandomForestClassifier | 0.736 |
| 12 | LinearSVC | 0.736 |
| 13 | StandardScaler, LinearSVC | 0.736 |
| 14 | RandomForestClassifier | 0.736 |
| 15 | MaxAbsScaler, BaggingClassifier | 0.694 |
| 16 | StandardScaler, BaggingClassifier | 0.694 |
| 17 | MaxAbsScaler, KNeighborsClassifier | 0.681 |
| 18 | MaxAbsScaler, LogisticRegression | 0.681 |
| 19 | StandardScaler, KNeighborsClassifier | 0.681 |
| 20 | KNeighborsClassifier | 0.667 |
| 21 | LogisticRegression | 0.639 |
| 22 | BaggingClassifier | 0.639 |
| 23 | StandardScaler, SGDClassifier | 0.639 |
| 24 | MaxAbsScaler, LGBMClassifier | 0.611 |
| 25 | MaxAbsScaler, XGBClassifier | 0.611 |
| 26 | XGBClassifier | 0.611 |
| 27 | LGBMClassifier | 0.611 |
| 28 | StandardScaler, LGBMClassifier | 0.611 |
| 29 | StandardScaler, XGBClassifier | 0.611 |
| 30 | MaxAbsScaler, DecisionTreeClassifier | 0.597 |
| 31 | StandardScaler, PassiveAggressiveClassifier | 0.597 |
| 32 | GradientBoostingClassifier | 0.583 |
| 33 | StandardScaler, GradientBoostingClassifier | 0.583 |
| 34 | DecisionTreeClassifier | 0.569 |
| 35 | MaxAbsScaler, LinearDiscriminantAnalysis | 0.556 |
| 36 | MaxAbsScaler, GradientBoostingClassifier | 0.556 |
| 37 | LinearDiscriminantAnalysis | 0.556 |
| 38 | StandardScaler, LinearDiscriminantAnalysis | 0.556 |
| 39 | RobustScaler, LinearDiscriminantAnalysis | 0.556 |
| 40 | MaxAbsScaler, GaussianNB | 0.542 |
| 41 | GaussianNB | 0.542 |
| 42 | StandardScaler, GaussianNB | 0.542 |
| 43 | RobustScaler, GaussianNB | 0.542 |
| 44 | MaxAbsScaler, MultinomialNB | 0.542 |
| 45 | MaxAbsScaler, PassiveAggressiveClassifier | 0.542 |
| 46 | MultinomialNB | 0.542 |
| 47 | SGDClassifier | 0.542 |
| 48 | StandardScaler, BernoulliNB | 0.528 |
| 49 | StandardScaler, DecisionTreeClassifier | 0.528 |
| 50 | MaxAbsScaler, SelectKBest, RandomForestClassifier | 0.514 |
| 51 | StandardScaler, SelectKBest, ExtraTreesClassifier | 0.500 |
| 52 | RobustScaler, SelectKBest, ExtraTreesClassifier | 0.500 |
| 53 | MaxAbsScaler, SelectPercentile, XGBClassifier | 0.486 |
| 54 | MaxAbsScaler, SelectKBest, XGBClassifier | 0.472 |
| 55 | PassiveAggressiveClassifier | 0.472 |
| 56 | MaxAbsScaler, SelectKBest, ExtraTreesClassifier | 0.458 |
| 57 | MaxAbsScaler, SelectPercentile, DecisionTreeClassifier | 0.458 |
| 58 | MaxAbsScaler, SelectPercentile, ExtraTreesClassifier | 0.444 |
| 59 | SelectPercentile, ExtraTreesClassifier | 0.444 |
| 60 | SelectKBest, ExtraTreesClassifier | 0.444 |
| 61 | MaxAbsScaler, SelectPercentile, RandomForestClassifier | 0.444 |
| 62 | MaxAbsScaler, SelectPercentile, LGBMClassifier | 0.444 |
| 63 | MaxAbsScaler, SelectKBest, DecisionTreeClassifier | 0.444 |
| 64 | MaxAbsScaler, SelectKBest, BaggingClassifier | 0.444 |
| 65 | RobustScaler, SelectPercentile, ExtraTreesClassifier | 0.431 |
| 66 | MaxAbsScaler, SGDClassifier | 0.431 |
| 67 | MaxAbsScaler, SelectPercentile, QuadraticDiscriminantAnalysis | 0.431 |
| 68 | MaxAbsScaler, SelectPercentile, BaggingClassifier | 0.431 |
| 69 | MaxAbsScaler, SelectKBest, LGBMClassifier | 0.431 |
| 70 | MaxAbsScaler, SelectPercentile, KNeighborsClassifier | 0.417 |
| 71 | StandardScaler, SelectPercentile, ExtraTreesClassifier | 0.417 |
| 72 | MaxAbsScaler, SelectKBest, KNeighborsClassifier | 0.417 |
| 73 | MaxAbsScaler, SelectKBest, GradientBoostingClassifier | 0.417 |
| 74 | StandardScaler, QuadraticDiscriminantAnalysis | 0.417 |
| 75 | SelectPercentile, KNeighborsClassifier | 0.403 |
| 76 | MaxAbsScaler, QuadraticDiscriminantAnalysis | 0.389 |
| 77 | MaxAbsScaler, SelectPercentile, GradientBoostingClassifier | 0.375 |
| 78 | MaxAbsScaler, SelectKBest, QuadraticDiscriminantAnalysis | 0.375 |
| 79 | QuadraticDiscriminantAnalysis | 0.361 |
| 80 | MaxAbsScaler, SelectKBest, GaussianNB | 0.347 |
| 81 | SelectKBest, GaussianNB | 0.347 |
| 82 | StandardScaler, SelectKBest, GaussianNB | 0.347 |
| 83 | RobustScaler, SelectKBest, GaussianNB | 0.347 |
| 84 | MaxAbsScaler, SelectPercentile, SVC | 0.333 |
| 85 | MaxAbsScaler, SelectPercentile, LinearDiscriminantAnalysis | 0.319 |
| 86 | MaxAbsScaler, SelectKBest, LinearDiscriminantAnalysis | 0.319 |
| 87 | MaxAbsScaler, SelectKBest, LinearSVC | 0.306 |
| 88 | MaxAbsScaler, SelectKBest, SVC | 0.306 |
| 89 | MaxAbsScaler, SelectPercentile, LinearSVC | 0.292 |
| 90 | MaxAbsScaler, SelectKBest, LogisticRegression | 0.278 |
| 91 | MaxAbsScaler, GenericUnivariateSelect, ExtraTreesClassifier | 0.264 |
| 92 | RobustScaler, GenericUnivariateSelect, ExtraTreesClassifier | 0.264 |
| 93 | MaxAbsScaler, GenericUnivariateSelect, DecisionTreeClassifier | 0.250 |
| 94 | MaxAbsScaler, SelectPercentile, GaussianNB | 0.250 |
| 95 | GenericUnivariateSelect, ExtraTreesClassifier | 0.250 |
| 96 | StandardScaler, GenericUnivariateSelect, ExtraTreesClassifier | 0.250 |
| 97 | SelectPercentile, GaussianNB | 0.250 |
| 98 | StandardScaler, SelectPercentile, GaussianNB | 0.250 |
| 99 | RobustScaler, SelectPercentile, GaussianNB | 0.250 |
| 100 | MaxAbsScaler, SelectPercentile, LogisticRegression | 0.250 |
| 101 | GenericUnivariateSelect, DecisionTreeClassifier | 0.250 |
| 102 | StandardScaler, GenericUnivariateSelect, DecisionTreeClassifier | 0.250 |
| 103 | RobustScaler, GenericUnivariateSelect, DecisionTreeClassifier | 0.250 |
| 104 | GenericUnivariateSelect, BaggingClassifier | 0.236 |
| 105 | MaxAbsScaler, SelectPercentile, SGDClassifier | 0.222 |
| 106 | GenericUnivariateSelect, RandomForestClassifier | 0.222 |
| 107 | MaxAbsScaler, GenericUnivariateSelect, LGBMClassifier | 0.208 |
| 108 | MaxAbsScaler, GenericUnivariateSelect, BaggingClassifier | 0.208 |
| 109 | GenericUnivariateSelect, LGBMClassifier | 0.208 |
| 110 | MaxAbsScaler, GenericUnivariateSelect, GaussianNB | 0.194 |
| 111 | MaxAbsScaler, GenericUnivariateSelect, GradientBoostingClassifier | 0.194 |
| 112 | MaxAbsScaler, GenericUnivariateSelect, QuadraticDiscriminantAnalysis | 0.194 |
| 113 | MaxAbsScaler, GenericUnivariateSelect, RandomForestClassifier | 0.194 |
| 114 | MaxAbsScaler, GenericUnivariateSelect, XGBClassifier | 0.194 |
| 115 | GenericUnivariateSelect, GaussianNB | 0.194 |
| 116 | StandardScaler, GenericUnivariateSelect, GaussianNB | 0.194 |
| 117 | RobustScaler, GenericUnivariateSelect, GaussianNB | 0.194 |
| 118 | StandardScaler, GenericUnivariateSelect, KNeighborsClassifier | 0.194 |
| 119 | GenericUnivariateSelect, GradientBoostingClassifier | 0.194 |
| 120 | StandardScaler, GenericUnivariateSelect, GradientBoostingClassifier | 0.194 |
| 121 | RobustScaler, GenericUnivariateSelect, GradientBoostingClassifier | 0.194 |
| 122 | GenericUnivariateSelect, QuadraticDiscriminantAnalysis | 0.194 |
| 123 | GenericUnivariateSelect, XGBClassifier | 0.194 |
| 124 | StandardScaler, GenericUnivariateSelect, QuadraticDiscriminantAnalysis | 0.194 |
| 125 | MaxAbsScaler, GenericUnivariateSelect, KNeighborsClassifier | 0.181 |
| 126 | MaxAbsScaler, GenericUnivariateSelect, SGDClassifier | 0.181 |
| 127 | MaxAbsScaler, GenericUnivariateSelect, SVC | 0.181 |
| 128 | GenericUnivariateSelect, KNeighborsClassifier | 0.181 |
| 129 | RobustScaler, GenericUnivariateSelect, KNeighborsClassifier | 0.181 |
| 130 | GenericUnivariateSelect, SVC | 0.181 |
| 131 | StandardScaler, GenericUnivariateSelect, SVC | 0.181 |
| 132 | StandardScaler, GenericUnivariateSelect, LogisticRegression | 0.153 |
| 133 | RobustScaler, GenericUnivariateSelect, LogisticRegression | 0.153 |
| 134 | MaxAbsScaler, GenericUnivariateSelect, LinearSVC | 0.139 |
| 135 | GenericUnivariateSelect, LinearSVC | 0.139 |
| 136 | MaxAbsScaler, SelectKBest, SGDClassifier | 0.139 |
| 137 | StandardScaler, GenericUnivariateSelect, LinearSVC | 0.139 |
| 138 | RobustScaler, GenericUnivariateSelect, LinearSVC | 0.139 |
| 139 | MaxAbsScaler, GenericUnivariateSelect, LinearDiscriminantAnalysis | 0.125 |
| 140 | MaxAbsScaler, GenericUnivariateSelect, PassiveAggressiveClassifier | 0.125 |
| 141 | GenericUnivariateSelect, LinearDiscriminantAnalysis | 0.125 |
| 142 | StandardScaler, GenericUnivariateSelect, LinearDiscriminantAnalysis | 0.125 |
| 143 | RobustScaler, GenericUnivariateSelect, LinearDiscriminantAnalysis | 0.125 |
| 144 | MaxAbsScaler, SelectPercentile, PassiveAggressiveClassifier | 0.125 |
| 145 | GenericUnivariateSelect, SGDClassifier | 0.125 |
| 146 | MaxAbsScaler, GenericUnivariateSelect, LogisticRegression | 0.097 |
| 147 | MaxAbsScaler, SelectKBest, PassiveAggressiveClassifier | 0.097 |
| 148 | GenericUnivariateSelect, LogisticRegression | 0.097 |
| 149 | StandardScaler, GenericUnivariateSelect, SGDClassifier | 0.097 |
| 150 | RobustScaler, GenericUnivariateSelect, SGDClassifier | 0.097 |
| 151 | MaxAbsScaler, SelectKBest, MultinomialNB | 0.083 |
| 152 | GenericUnivariateSelect, PassiveAggressiveClassifier | 0.083 |
| 153 | MaxAbsScaler, SelectPercentile, MultinomialNB | 0.069 |
| 154 | StandardScaler, GenericUnivariateSelect, BernoulliNB | 0.069 |
| 155 | MaxAbsScaler, GenericUnivariateSelect, BernoulliNB | 0.028 |
| 156 | MaxAbsScaler, GenericUnivariateSelect, MultinomialNB | 0.028 |
| 157 | MaxAbsScaler, BernoulliNB | 0.028 |
| 158 | MaxAbsScaler, SelectPercentile, BernoulliNB | 0.028 |
| 159 | BernoulliNB | 0.028 |
| 160 | GenericUnivariateSelect, BernoulliNB | 0.028 |
| 161 | MaxAbsScaler, SelectKBest, BernoulliNB | 0.028 |
| 162 | GenericUnivariateSelect, MultinomialNB | 0.028 |
Model Exploration¶
In order to explore the produced pipelines, we can use PipelineProfiler. PipelineProfiler is a visualization that enables users to compare and explore the pipelines generated by the AutoML systems.
After the pipeline search process is completed, we can use PipelineProfiler with:
Note
You can partially interact with this visualization. Try it in Jupyter Notebook to get full access to all features.
[7]:
automl.plot_comparison_pipelines()
PipelineProfiler shows the produced pipelines as a matrix, where the pipelines are represented as rows, and primitives as columns.
The score view displays performance metrics (i.e. accuracy, F1) of the evaluated pipelines. It can also visualize the training time of each of the pipelines.
The Primitive Contribution view shows the correlation between primitive usage and the pipeline scores.
The Pipeline Comparison view highlights the differences between selected pipelines. It presents a node-link representation of the selected pipelines. Multiple pipelines can be selected by shift-clicking the matrix rows.
For more information about how to use PipelineProfiler, click here. There is also a video demo available here.
Separating the features and target columns for the test dataset.
[8]:
X_test = test_dataset.drop(columns=[target_column])
y_test = test_dataset[[target_column]]
The best pipeline’s predictions are accessed with:
[9]:
y_pred = automl.predict(X_test)
y_pred
[9]:
array([ 2, 9, 12, 3, 14, 11, 14, 14, 9, 4, 1, 7, 1, 8, 5, 12, 12,
5, 11, 11, 3, 11, 11, 7, 15, 9, 13, 3, 15, 12, 10, 12, 15, 8,
9, 8, 12, 7, 11, 4, 2, 10, 3, 6, 15, 13, 6, 10, 9, 14, 9,
2, 1, 3, 10, 9, 5, 8, 15, 7, 13, 5, 15, 6, 15, 2, 4, 5,
7, 6, 14, 2])
The best pipeline can be evaluated against a held out dataset with the function call:
[10]:
automl.score(X_test, y_test)
INFO:alpha_automl.automl_api:Metric: accuracy_score, Score: 0.8333333333333334
[10]:
{'metric': 'accuracy_score', 'score': 0.8333333333333334}
Download this example as a jupyter notebook file ( .ipynb ).