Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
0d105c8
commit 76d5957
Showing
7 changed files
with
300 additions
and
27 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
47 changes: 47 additions & 0 deletions
47
docs/source/checks/nlp/model_evaluation/plot_confusion_matrix_report.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,47 @@ | ||
# -*- coding: utf-8 -*- | ||
""" | ||
.. _plot_tabular_confusion_matrix_report: | ||
Confusion Matrix Report | ||
*********************** | ||
This notebook provides an overview for using and understanding the Confusion Matrix Report check for NLP tasks. | ||
**Structure:** | ||
* `What is the Confusion Matrix Report? <#what-is-the-confusion-matrix-report>`__ | ||
* `Generate data & model <#generate-data-model>`__ | ||
* `Run the check <#run-the-check>`__ | ||
What is the Confusion Matrix Report? | ||
====================================== | ||
The ``ConfusionMatrixReport`` produces a confusion matrix visualization which summarizes the | ||
performance of the model. The confusion matrix contains the TP (true positive), FP (false positive), | ||
TN (true negative) and FN (false negative), from which we can derive the relevant metrics, | ||
such as accuracy, precision, recall etc. (`confusion matrix <https://en.wikipedia.org/wiki/Confusion_matrix>`__). | ||
""" | ||
|
||
#%% | ||
# Generate data & model | ||
# ======================= | ||
from deepchecks.nlp import TextData | ||
from deepchecks.nlp.checks import ConfusionMatrixReport | ||
from deepchecks.nlp.datasets.classification.tweet_emotion import load_data, load_precalculated_predictions | ||
|
||
tweets_data = load_data(data_format='DataFrame', as_train_test=False) | ||
tweets_dataset = TextData(tweets_data.text, label=tweets_data['label'], | ||
task_type='text_classification') | ||
|
||
predictions = load_precalculated_predictions(as_train_test=False) | ||
|
||
|
||
#%% | ||
# Run the check | ||
# =============== | ||
|
||
check = ConfusionMatrixReport() | ||
result = check.run(tweets_dataset, predictions=predictions) | ||
result.show() | ||
|
||
#%% |
112 changes: 112 additions & 0 deletions
112
docs/source/checks/nlp/model_evaluation/plot_metadata_segments_performance.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,112 @@ | ||
# -*- coding: utf-8 -*- | ||
""" | ||
Metadata Segments Performance | ||
************************* | ||
This notebook provides an overview for using and understanding the metadata segment performance check. | ||
**Structure:** | ||
* `What is the purpose of the check? <#what-is-the-purpose-of-the-check>`__ | ||
* `Automatically detecting weak segments <#automatically-detecting-weak-segments>`__ | ||
* `Generate data & model <#generate-data-model>`__ | ||
* `Run the check <#run-the-check>`__ | ||
* `Define a condition <#define-a-condition>`__ | ||
What is the purpose of the check? | ||
================================== | ||
The check is designed to help you easily identify the model's weakest segments based on the provided | ||
:func:`metadata <deepchecks.nlp.text_data.TextData.set_metadata>`. In addition, | ||
it enables to provide a sublist of the metadata columns, thus limiting the check to search in | ||
interesting subspaces. | ||
Automatically detecting weak segments | ||
===================================== | ||
The check contains several steps: | ||
#. We calculate loss for each sample in the dataset using the provided model via either log-loss or MSE according | ||
to the task type. | ||
#. Select a subset of features for the weak segment search. This is done by selecting the features with the | ||
highest feature importance to the model provided (within the features selected for check, if limited). | ||
#. We train multiple simple tree based models, each one is trained using exactly two | ||
features (out of the ones selected above) to predict the per sample error calculated before. | ||
#. We extract the corresponding data samples for each of the leaves in each of the trees (data segments) and calculate | ||
the model performance on them. For the weakest data segments detected we also calculate the model's | ||
performance on data segments surrounding them. | ||
""" | ||
#%% | ||
# Generate data & model | ||
# ===================== | ||
|
||
from deepchecks.nlp.datasets.classification.tweet_emotion import load_data, load_precalculated_predictions | ||
|
||
_, test_dataset = load_data(data_format='TextData') | ||
_, test_probas = load_precalculated_predictions(pred_format='probabilities') | ||
|
||
test_dataset.metadata.head(3) | ||
|
||
#%% | ||
# Run the check | ||
# ============= | ||
# | ||
# The check has several key parameters (that are all optional) that affect the behavior of the | ||
# check and especially its output. | ||
# | ||
# ``columns / ignore_columns``: Controls which columns should be searched for weak segments. By default, | ||
# uses all columns. | ||
# | ||
# ``alternative_scorer``: Determines the metric to be used as the performance measurement of the model on different | ||
# segments. It is important to select a metric that is relevant to the data domain and task you are performing. | ||
# For additional information on scorers and how to use them see | ||
# :doc:`Metrics Guide </user-guide/general/metrics_guide>`. | ||
# | ||
# ``segment_minimum_size_ratio``: Determines the minimum size of segments that are of interest. The check will | ||
# return data segments that contain at least this fraction of the total data samples. It is recommended to | ||
# try different configurations | ||
# of this parameter as larger segments can be of interest even the model performance on them is superior. | ||
# | ||
# ``categorical_aggregation_threshold``: By default the check will combine rare categories into a single category called | ||
# "Other". This parameter determines the frequency threshold for categories to be mapped into to the "other" category. | ||
# | ||
# see :class:`API reference <deepchecks.tabular.checks.model_evaluation.WeakSegmentsPerformance>` for more details. | ||
|
||
from deepchecks.nlp.checks import MetadataSegmentsPerformance | ||
from sklearn.metrics import make_scorer, f1_score | ||
|
||
scorer = {'f1': make_scorer(f1_score, average='micro')} | ||
check = MetadataSegmentsPerformance(alternative_scorer=scorer, | ||
segment_minimum_size_ratio=0.03) | ||
result = check.run(test_dataset, probabilities=test_probas) | ||
result.show() | ||
|
||
#%% | ||
# Observe the check's output | ||
# -------------------------- | ||
# | ||
# We see in the results that the check indeed found several segments on which the model performance is below average. | ||
# In the heatmap display we can see model performance on the weakest segments and their environment with respect to the | ||
# two features that are relevant to the segment. In order to get the full list of weak segments found we will inspect | ||
# the ``result.value`` attribute. Shown below are the 3 segments with the worst performance. | ||
|
||
|
||
result.value['weak_segments_list'].head(3) | ||
|
||
#%% | ||
# Define a condition | ||
# ================== | ||
# | ||
# We can add a condition that will validate the model's performance on the weakest segment detected is above a certain | ||
# threshold. A scenario where this can be useful is when we want to make sure that the model is not under performing | ||
# on a subset of the data that is of interest to us, for example for specific age or gender groups. | ||
|
||
# Let's add a condition and re-run the check: | ||
|
||
check = MetadataSegmentsPerformance(alternative_scorer=scorer, segment_minimum_size_ratio=0.03) | ||
check.add_condition_segments_relative_performance_greater_than(0.1) | ||
result = check.run(test_dataset, probabilities=test_probas) | ||
result.show(show_additional_outputs=False) |
112 changes: 112 additions & 0 deletions
112
docs/source/checks/nlp/model_evaluation/plot_property_segments_performance.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,112 @@ | ||
# -*- coding: utf-8 -*- | ||
""" | ||
Property Segments Performance | ||
************************* | ||
This notebook provides an overview for using and understanding the property segment performance check. | ||
**Structure:** | ||
* `What is the purpose of the check? <#what-is-the-purpose-of-the-check>`__ | ||
* `Automatically detecting weak segments <#automatically-detecting-weak-segments>`__ | ||
* `Generate data & model <#generate-data-model>`__ | ||
* `Run the check <#run-the-check>`__ | ||
* `Define a condition <#define-a-condition>`__ | ||
What is the purpose of the check? | ||
================================== | ||
The check is designed to help you easily identify the model's weakest segments based on the provided | ||
:func:`properties <deepchecks.nlp.text_data.TextData.set_properties>`. In addition, | ||
it enables to provide a sublist of the metadata columns, thus limiting the check to search in | ||
interesting subspaces. | ||
Automatically detecting weak segments | ||
===================================== | ||
The check contains several steps: | ||
#. We calculate loss for each sample in the dataset using the provided model via either log-loss or MSE according | ||
to the task type. | ||
#. Select a subset of features for the weak segment search. This is done by selecting the features with the | ||
highest feature importance to the model provided (within the features selected for check, if limited). | ||
#. We train multiple simple tree based models, each one is trained using exactly two | ||
features (out of the ones selected above) to predict the per sample error calculated before. | ||
#. We extract the corresponding data samples for each of the leaves in each of the trees (data segments) and calculate | ||
the model performance on them. For the weakest data segments detected we also calculate the model's | ||
performance on data segments surrounding them. | ||
""" | ||
#%% | ||
# Generate data & model | ||
# ===================== | ||
|
||
from deepchecks.nlp.datasets.classification.tweet_emotion import load_data, load_precalculated_predictions | ||
|
||
_, test_dataset = load_data(data_format='TextData') | ||
_, test_probas = load_precalculated_predictions(pred_format='probabilities') | ||
|
||
test_dataset.properties.head(3) | ||
|
||
#%% | ||
# Run the check | ||
# ============= | ||
# | ||
# The check has several key parameters (that are all optional) that affect the behavior of the | ||
# check and especially its output. | ||
# | ||
# ``properties / ignore_properties``: Controls which properties should be searched for weak segments. By default, | ||
# uses all properties data provided. | ||
# | ||
# ``alternative_scorer``: Determines the metric to be used as the performance measurement of the model on different | ||
# segments. It is important to select a metric that is relevant to the data domain and task you are performing. | ||
# For additional information on scorers and how to use them see | ||
# :doc:`Metrics Guide </user-guide/general/metrics_guide>`. | ||
# | ||
# ``segment_minimum_size_ratio``: Determines the minimum size of segments that are of interest. The check will | ||
# return data segments that contain at least this fraction of the total data samples. It is recommended to | ||
# try different configurations | ||
# of this parameter as larger segments can be of interest even the model performance on them is superior. | ||
# | ||
# ``categorical_aggregation_threshold``: By default the check will combine rare categories into a single category called | ||
# "Other". This parameter determines the frequency threshold for categories to be mapped into to the "other" category. | ||
# | ||
# see :class:`API reference <deepchecks.tabular.checks.model_evaluation.WeakSegmentsPerformance>` for more details. | ||
|
||
from deepchecks.nlp.checks import PropertySegmentsPerformance | ||
from sklearn.metrics import make_scorer, f1_score | ||
|
||
scorer = {'f1': make_scorer(f1_score, average='micro')} | ||
check = PropertySegmentsPerformance(alternative_scorer=scorer, | ||
segment_minimum_size_ratio=0.03) | ||
result = check.run(test_dataset, probabilities=test_probas) | ||
result.show() | ||
|
||
#%% | ||
# Observe the check's output | ||
# -------------------------- | ||
# | ||
# We see in the results that the check indeed found several segments on which the model performance is below average. | ||
# In the heatmap display we can see model performance on the weakest segments and their environment with respect to the | ||
# two features that are relevant to the segment. In order to get the full list of weak segments found we will inspect | ||
# the ``result.value`` attribute. Shown below are the 3 segments with the worst performance. | ||
|
||
|
||
result.value['weak_segments_list'].head(3) | ||
|
||
#%% | ||
# Define a condition | ||
# ================== | ||
# | ||
# We can add a condition that will validate the model's performance on the weakest segment detected is above a certain | ||
# threshold. A scenario where this can be useful is when we want to make sure that the model is not under performing | ||
# on a subset of the data that is of interest to us. | ||
|
||
# Let's add a condition and re-run the check: | ||
|
||
check = PropertySegmentsPerformance(alternative_scorer=scorer, segment_minimum_size_ratio=0.03) | ||
check.add_condition_segments_relative_performance_greater_than(0.1) | ||
result = check.run(test_dataset, probabilities=test_probas) | ||
result.show(show_additional_outputs=False) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.