![]() |
![]() |
![]() |
![]() |
In this tutorial, you will learn how to use Fairness Indicators to evaluate embeddings from TF Hub. This notebook uses the Civil Comments dataset.
Setup
Install the required libraries.
!pip install -q -U pip==20.2
!pip install fairness-indicators \
"absl-py==0.8.0" \
"pyarrow==2.0.0" \
"apache-beam==2.27.0" \
"avro-python3==1.9.1"
Import other required libraries.
import os
import tempfile
import apache_beam as beam
from datetime import datetime
import tensorflow as tf
import tensorflow_hub as hub
import tensorflow_model_analysis as tfma
from tensorflow_model_analysis.addons.fairness.view import widget_view
from tensorflow_model_analysis.addons.fairness.post_export_metrics import fairness_indicators
from fairness_indicators import example_model
from fairness_indicators.tutorial_utils import util
Dataset
In this notebook, you work with the Civil Comments dataset which contains approximately 2 million public comments made public by the Civil Comments platform in 2017 for ongoing research. This effort was sponsored by Jigsaw, who have hosted competitions on Kaggle to help classify toxic comments as well as minimize unintended model bias.
Each individual text comment in the dataset has a toxicity label, with the label being 1 if the comment is toxic and 0 if the comment is non-toxic. Within the data, a subset of comments are labeled with a variety of identity attributes, including categories for gender, sexual orientation, religion, and race or ethnicity.
Prepare the data
TensorFlow parses features from data using tf.io.FixedLenFeature
and tf.io.VarLenFeature
. Map out the input feature, output feature, and all other slicing features of interest.
BASE_DIR = tempfile.gettempdir()
# The input and output features of the classifier
TEXT_FEATURE = 'comment_text'
LABEL = 'toxicity'
FEATURE_MAP = {
# input and output features
LABEL: tf.io.FixedLenFeature([], tf.float32),
TEXT_FEATURE: tf.io.FixedLenFeature([], tf.string),
# slicing features
'sexual_orientation': tf.io.VarLenFeature(tf.string),
'gender': tf.io.VarLenFeature(tf.string),
'religion': tf.io.VarLenFeature(tf.string),
'race': tf.io.VarLenFeature(tf.string),
'disability': tf.io.VarLenFeature(tf.string)
}
IDENTITY_TERMS = ['gender', 'sexual_orientation', 'race', 'religion', 'disability']
By default, the notebook downloads a preprocessed version of this dataset, but you may use the original dataset and re-run the processing steps if desired.
In the original dataset, each comment is labeled with the percentage
of raters who believed that a comment corresponds to a particular
identity. For example, a comment might be labeled with the following:
{ male: 0.3, female: 1.0, transgender: 0.0, heterosexual: 0.8,
homosexual_gay_or_lesbian: 1.0 }
.
The processing step groups identity by category (gender,
sexual_orientation, etc.) and removes identities with a score less
than 0.5. So the example above would be converted to the following:
of raters who believed that a comment corresponds to a particular
identity. For example, the comment above would be labeled with the
following:
{ gender: [female], sexual_orientation: [heterosexual,
homosexual_gay_or_lesbian] }
Download the dataset.
download_original_data = False
if download_original_data:
train_tf_file = tf.keras.utils.get_file('train_tf.tfrecord',
'https://storage.googleapis.com/civil_comments_dataset/train_tf.tfrecord')
validate_tf_file = tf.keras.utils.get_file('validate_tf.tfrecord',
'https://storage.googleapis.com/civil_comments_dataset/validate_tf.tfrecord')
# The identity terms list will be grouped together by their categories
# (see 'IDENTITY_COLUMNS') on threshold 0.5. Only the identity term column,
# text column and label column will be kept after processing.
train_tf_file = util.convert_comments_data(train_tf_file)
validate_tf_file = util.convert_comments_data(validate_tf_file)
else:
train_tf_file = tf.keras.utils.get_file('train_tf_processed.tfrecord',
'https://storage.googleapis.com/civil_comments_dataset/train_tf_processed.tfrecord')
validate_tf_file = tf.keras.utils.get_file('validate_tf_processed.tfrecord',
'https://storage.googleapis.com/civil_comments_dataset/validate_tf_processed.tfrecord')
Downloading data from https://storage.googleapis.com/civil_comments_dataset/train_tf_processed.tfrecord 488161280/488153424 [==============================] - 17s 0us/step Downloading data from https://storage.googleapis.com/civil_comments_dataset/validate_tf_processed.tfrecord 324943872/324941336 [==============================] - 1s 0us/step
Create a TensorFlow Model Analysis Pipeline
The Fairness Indicators library operates on TensorFlow Model Analysis (TFMA) models. TFMA models wrap TensorFlow models with additional functionality to evaluate and visualize their results. The actual evaluation occurs inside of an Apache Beam pipeline.
The steps you follow to create a TFMA pipeline are:
- Build a TensorFlow model
- Build a TFMA model on top of the TensorFlow model
- Run the model analysis in an orchestrator. The example model in this notebook uses Apache Beam as the orchestrator.
def embedding_fairness_result(embedding, identity_term='gender'):
model_dir = os.path.join(BASE_DIR, 'train',
datetime.now().strftime('%Y%m%d-%H%M%S'))
print("Training classifier for " + embedding)
classifier = example_model.train_model(model_dir,
train_tf_file,
LABEL,
TEXT_FEATURE,
FEATURE_MAP,
embedding)
# Create a unique path to store the results for this embedding.
embedding_name = embedding.split('/')[-2]
eval_result_path = os.path.join(BASE_DIR, 'eval_result', embedding_name)
example_model.evaluate_model(classifier,
validate_tf_file,
eval_result_path,
identity_term,
LABEL,
FEATURE_MAP)
return tfma.load_eval_result(output_path=eval_result_path)
Run TFMA & Fairness Indicators
Fairness Indicators Metrics
Some of the metrics available with Fairness Indicators are:
- Negative Rate, False Negative Rate (FNR), and True Negative Rate (TNR)
- Positive Rate, False Positive Rate (FPR), and True Positive Rate (TPR)
- Accuracy
- Precision and Recall
- Precision-Recall AUC
- ROC AUC
Text Embeddings
TF-Hub provides several text embeddings. These embeddings will serve as the feature column for the different models. This tutorial uses the following embeddings:
- random-nnlm-en-dim128: random text embeddings, this serves as a convenient baseline.
- nnlm-en-dim128: a text embedding based on A Neural Probabilistic Language Model.
- universal-sentence-encoder: a text embedding based on Universal Sentence Encoder.
Fairness Indicator Results
Compute fairness indicators with the embedding_fairness_result
pipeline, and then render the results in the Fairness Indicator UI widget with widget_view.render_fairness_indicator
for all the above embeddings.
Random NNLM
eval_result_random_nnlm = embedding_fairness_result('https://hub.tensorflow.google.cn/google/random-nnlm-en-dim128/1')
Training classifier for https://hub.tensorflow.google.cn/google/random-nnlm-en-dim128/1 INFO:tensorflow:Using default config. INFO:tensorflow:Using default config. INFO:tensorflow:Using config: {'_model_dir': '/tmp/train/20210211-103023', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true graph_options { rewrite_options { meta_optimizer_iterations: ONE } } , '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1} INFO:tensorflow:Using config: {'_model_dir': '/tmp/train/20210211-103023', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true graph_options { rewrite_options { meta_optimizer_iterations: ONE } } , '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1} WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow/python/training/training_util.py:236: Variable.initialized_value (from tensorflow.python.ops.variables) is deprecated and will be removed in a future version. Instructions for updating: Use Variable.read_value. Variables in 2.X are initialized automatically both in eager and graph (inside tf.defun) contexts. WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow/python/training/training_util.py:236: Variable.initialized_value (from tensorflow.python.ops.variables) is deprecated and will be removed in a future version. Instructions for updating: Use Variable.read_value. Variables in 2.X are initialized automatically both in eager and graph (inside tf.defun) contexts. INFO:tensorflow:Calling model_fn. INFO:tensorflow:Calling model_fn. INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow_estimator/python/estimator/canned/head.py:402: NumericColumn._get_dense_tensor (from tensorflow.python.feature_column.feature_column_v2) is deprecated and will be removed in a future version. Instructions for updating: The old _FeatureColumn APIs are being deprecated. Please use the new FeatureColumn APIs instead. WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow_estimator/python/estimator/canned/head.py:402: NumericColumn._get_dense_tensor (from tensorflow.python.feature_column.feature_column_v2) is deprecated and will be removed in a future version. Instructions for updating: The old _FeatureColumn APIs are being deprecated. Please use the new FeatureColumn APIs instead. WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py:2192: NumericColumn._transform_feature (from tensorflow.python.feature_column.feature_column_v2) is deprecated and will be removed in a future version. Instructions for updating: The old _FeatureColumn APIs are being deprecated. Please use the new FeatureColumn APIs instead. WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py:2192: NumericColumn._transform_feature (from tensorflow.python.feature_column.feature_column_v2) is deprecated and will be removed in a future version. Instructions for updating: The old _FeatureColumn APIs are being deprecated. Please use the new FeatureColumn APIs instead. WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow/python/training/adagrad.py:77: calling Constant.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version. Instructions for updating: Call initializer instance with the dtype argument instead of passing it to the constructor WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow/python/training/adagrad.py:77: calling Constant.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version. Instructions for updating: Call initializer instance with the dtype argument instead of passing it to the constructor INFO:tensorflow:Done calling model_fn. INFO:tensorflow:Done calling model_fn. INFO:tensorflow:Create CheckpointSaverHook. INFO:tensorflow:Create CheckpointSaverHook. INFO:tensorflow:Graph was finalized. INFO:tensorflow:Graph was finalized. INFO:tensorflow:Running local_init_op. INFO:tensorflow:Running local_init_op. INFO:tensorflow:Done running local_init_op. INFO:tensorflow:Done running local_init_op. INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 0... INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 0... INFO:tensorflow:Saving checkpoints for 0 into /tmp/train/20210211-103023/model.ckpt. INFO:tensorflow:Saving checkpoints for 0 into /tmp/train/20210211-103023/model.ckpt. INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0... INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0... INFO:tensorflow:loss = 66.07744, step = 0 INFO:tensorflow:loss = 66.07744, step = 0 INFO:tensorflow:global_step/sec: 21.5906 INFO:tensorflow:global_step/sec: 21.5906 INFO:tensorflow:loss = 68.42206, step = 100 (4.634 sec) INFO:tensorflow:loss = 68.42206, step = 100 (4.634 sec) INFO:tensorflow:global_step/sec: 22.2744 INFO:tensorflow:global_step/sec: 22.2744 INFO:tensorflow:loss = 58.5475, step = 200 (4.489 sec) INFO:tensorflow:loss = 58.5475, step = 200 (4.489 sec) INFO:tensorflow:global_step/sec: 22.5461 INFO:tensorflow:global_step/sec: 22.5461 INFO:tensorflow:loss = 59.866714, step = 300 (4.436 sec) INFO:tensorflow:loss = 59.866714, step = 300 (4.436 sec) INFO:tensorflow:global_step/sec: 22.2658 INFO:tensorflow:global_step/sec: 22.2658 INFO:tensorflow:loss = 62.249905, step = 400 (4.491 sec) INFO:tensorflow:loss = 62.249905, step = 400 (4.491 sec) INFO:tensorflow:global_step/sec: 22.3078 INFO:tensorflow:global_step/sec: 22.3078 INFO:tensorflow:loss = 56.267628, step = 500 (4.483 sec) INFO:tensorflow:loss = 56.267628, step = 500 (4.483 sec) INFO:tensorflow:global_step/sec: 22.9321 INFO:tensorflow:global_step/sec: 22.9321 INFO:tensorflow:loss = 58.21868, step = 600 (4.362 sec) INFO:tensorflow:loss = 58.21868, step = 600 (4.362 sec) INFO:tensorflow:global_step/sec: 22.3868 INFO:tensorflow:global_step/sec: 22.3868 INFO:tensorflow:loss = 60.310432, step = 700 (4.466 sec) INFO:tensorflow:loss = 60.310432, step = 700 (4.466 sec) INFO:tensorflow:global_step/sec: 20.3125 INFO:tensorflow:global_step/sec: 20.3125 INFO:tensorflow:loss = 58.446903, step = 800 (4.923 sec) INFO:tensorflow:loss = 58.446903, step = 800 (4.923 sec) INFO:tensorflow:global_step/sec: 22.2356 INFO:tensorflow:global_step/sec: 22.2356 INFO:tensorflow:loss = 56.405106, step = 900 (4.497 sec) INFO:tensorflow:loss = 56.405106, step = 900 (4.497 sec) INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 1000... INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 1000... INFO:tensorflow:Saving checkpoints for 1000 into /tmp/train/20210211-103023/model.ckpt. INFO:tensorflow:Saving checkpoints for 1000 into /tmp/train/20210211-103023/model.ckpt. INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 1000... INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 1000... INFO:tensorflow:Loss for final step: 60.503784. INFO:tensorflow:Loss for final step: 60.503784. WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow_model_analysis/eval_saved_model/encoding.py:141: build_tensor_info (from tensorflow.python.saved_model.utils_impl) is deprecated and will be removed in a future version. Instructions for updating: This function will only be available through the v1 compatibility library as tf.compat.v1.saved_model.utils.build_tensor_info or tf.compat.v1.saved_model.build_tensor_info. WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow_model_analysis/eval_saved_model/encoding.py:141: build_tensor_info (from tensorflow.python.saved_model.utils_impl) is deprecated and will be removed in a future version. Instructions for updating: This function will only be available through the v1 compatibility library as tf.compat.v1.saved_model.utils.build_tensor_info or tf.compat.v1.saved_model.build_tensor_info. INFO:tensorflow:Calling model_fn. INFO:tensorflow:Calling model_fn. INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow_estimator/python/estimator/canned/head.py:642: auc (from tensorflow.python.ops.metrics_impl) is deprecated and will be removed in a future version. Instructions for updating: The value of AUC returned by this may race with the update so this is deprecated. Please use tf.keras.metrics.AUC instead. WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow_estimator/python/estimator/canned/head.py:642: auc (from tensorflow.python.ops.metrics_impl) is deprecated and will be removed in a future version. Instructions for updating: The value of AUC returned by this may race with the update so this is deprecated. Please use tf.keras.metrics.AUC instead. WARNING:tensorflow:Trapezoidal rule is known to produce incorrect PR-AUCs; please switch to "careful_interpolation" instead. WARNING:tensorflow:Trapezoidal rule is known to produce incorrect PR-AUCs; please switch to "careful_interpolation" instead. WARNING:tensorflow:Trapezoidal rule is known to produce incorrect PR-AUCs; please switch to "careful_interpolation" instead. WARNING:tensorflow:Trapezoidal rule is known to produce incorrect PR-AUCs; please switch to "careful_interpolation" instead. INFO:tensorflow:Done calling model_fn. INFO:tensorflow:Done calling model_fn. INFO:tensorflow:Signatures INCLUDED in export for Classify: None INFO:tensorflow:Signatures INCLUDED in export for Classify: None INFO:tensorflow:Signatures INCLUDED in export for Regress: None INFO:tensorflow:Signatures INCLUDED in export for Regress: None INFO:tensorflow:Signatures INCLUDED in export for Predict: None INFO:tensorflow:Signatures INCLUDED in export for Predict: None INFO:tensorflow:Signatures INCLUDED in export for Train: None INFO:tensorflow:Signatures INCLUDED in export for Train: None INFO:tensorflow:Signatures INCLUDED in export for Eval: ['eval'] INFO:tensorflow:Signatures INCLUDED in export for Eval: ['eval'] WARNING:tensorflow:Export includes no default signature! WARNING:tensorflow:Export includes no default signature! INFO:tensorflow:Restoring parameters from /tmp/train/20210211-103023/model.ckpt-1000 INFO:tensorflow:Restoring parameters from /tmp/train/20210211-103023/model.ckpt-1000 INFO:tensorflow:Assets added to graph. INFO:tensorflow:Assets added to graph. INFO:tensorflow:Assets written to: /tmp/tfma_eval_model/temp-1613039483/assets INFO:tensorflow:Assets written to: /tmp/tfma_eval_model/temp-1613039483/assets INFO:tensorflow:SavedModel written to: /tmp/tfma_eval_model/temp-1613039483/saved_model.pb INFO:tensorflow:SavedModel written to: /tmp/tfma_eval_model/temp-1613039483/saved_model.pb WARNING:absl:Tensorflow version (2.4.1) found. Note that TFMA support for TF 2.0 is currently in beta WARNING:apache_beam.runners.interactive.interactive_environment:Dependencies required for Interactive Beam PCollection visualization are not available, please use: `pip install apache-beam[interactive]` to install necessary dependencies to enable all data visualization features. WARNING:apache_beam.typehints.typehints:Ignoring send_type hint: <class 'NoneType'> WARNING:apache_beam.typehints.typehints:Ignoring return_type hint: <class 'NoneType'> WARNING:apache_beam.typehints.typehints:Ignoring send_type hint: <class 'NoneType'> WARNING:apache_beam.typehints.typehints:Ignoring return_type hint: <class 'NoneType'> WARNING:apache_beam.typehints.typehints:Ignoring send_type hint: <class 'NoneType'> WARNING:apache_beam.typehints.typehints:Ignoring return_type hint: <class 'NoneType'> WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow_model_analysis/eval_saved_model/load.py:169: load (from tensorflow.python.saved_model.loader_impl) is deprecated and will be removed in a future version. Instructions for updating: This function will only be available through the v1 compatibility library as tf.compat.v1.saved_model.loader.load or tf.compat.v1.saved_model.load. There will be a new function for importing SavedModels in Tensorflow 2.0. WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow_model_analysis/eval_saved_model/load.py:169: load (from tensorflow.python.saved_model.loader_impl) is deprecated and will be removed in a future version. Instructions for updating: This function will only be available through the v1 compatibility library as tf.compat.v1.saved_model.loader.load or tf.compat.v1.saved_model.load. There will be a new function for importing SavedModels in Tensorflow 2.0. INFO:tensorflow:Restoring parameters from /tmp/tfma_eval_model/1613039483/variables/variables INFO:tensorflow:Restoring parameters from /tmp/tfma_eval_model/1613039483/variables/variables WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow_model_analysis/eval_saved_model/graph_ref.py:189: get_tensor_from_tensor_info (from tensorflow.python.saved_model.utils_impl) is deprecated and will be removed in a future version. Instructions for updating: This function will only be available through the v1 compatibility library as tf.compat.v1.saved_model.utils.get_tensor_from_tensor_info or tf.compat.v1.saved_model.get_tensor_from_tensor_info. WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow_model_analysis/eval_saved_model/graph_ref.py:189: get_tensor_from_tensor_info (from tensorflow.python.saved_model.utils_impl) is deprecated and will be removed in a future version. Instructions for updating: This function will only be available through the v1 compatibility library as tf.compat.v1.saved_model.utils.get_tensor_from_tensor_info or tf.compat.v1.saved_model.get_tensor_from_tensor_info. WARNING:apache_beam.io.tfrecordio:Couldn't find python-snappy so the implementation of _TFRecordUtil._masked_crc32c is not as fast as it could be. WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow_model_analysis/writers/metrics_plots_and_validations_writer.py:113: tf_record_iterator (from tensorflow.python.lib.io.tf_record) is deprecated and will be removed in a future version. Instructions for updating: Use eager execution and: `tf.data.TFRecordDataset(path)` WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow_model_analysis/writers/metrics_plots_and_validations_writer.py:113: tf_record_iterator (from tensorflow.python.lib.io.tf_record) is deprecated and will be removed in a future version. Instructions for updating: Use eager execution and: `tf.data.TFRecordDataset(path)`
widget_view.render_fairness_indicator(eval_result=eval_result_random_nnlm)
FairnessIndicatorViewer(slicingMetrics=[{'sliceValue': 'Overall', 'slice': 'Overall', 'metrics': {'post_export…
NNLM
eval_result_nnlm = embedding_fairness_result('https://hub.tensorflow.google.cn/google/nnlm-en-dim128/1')
Training classifier for https://hub.tensorflow.google.cn/google/nnlm-en-dim128/1 INFO:tensorflow:Using default config. INFO:tensorflow:Using default config. INFO:tensorflow:Using config: {'_model_dir': '/tmp/train/20210211-103338', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true graph_options { rewrite_options { meta_optimizer_iterations: ONE } } , '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1} INFO:tensorflow:Using config: {'_model_dir': '/tmp/train/20210211-103338', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true graph_options { rewrite_options { meta_optimizer_iterations: ONE } } , '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1} INFO:tensorflow:Calling model_fn. INFO:tensorflow:Calling model_fn. INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Done calling model_fn. INFO:tensorflow:Done calling model_fn. INFO:tensorflow:Create CheckpointSaverHook. INFO:tensorflow:Create CheckpointSaverHook. INFO:tensorflow:Graph was finalized. INFO:tensorflow:Graph was finalized. INFO:tensorflow:Running local_init_op. INFO:tensorflow:Running local_init_op. INFO:tensorflow:Done running local_init_op. INFO:tensorflow:Done running local_init_op. INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 0... INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 0... INFO:tensorflow:Saving checkpoints for 0 into /tmp/train/20210211-103338/model.ckpt. INFO:tensorflow:Saving checkpoints for 0 into /tmp/train/20210211-103338/model.ckpt. INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0... INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0... INFO:tensorflow:loss = 59.43201, step = 0 INFO:tensorflow:loss = 59.43201, step = 0 INFO:tensorflow:global_step/sec: 22.4783 INFO:tensorflow:global_step/sec: 22.4783 INFO:tensorflow:loss = 56.019615, step = 100 (4.451 sec) INFO:tensorflow:loss = 56.019615, step = 100 (4.451 sec) INFO:tensorflow:global_step/sec: 22.5919 INFO:tensorflow:global_step/sec: 22.5919 INFO:tensorflow:loss = 47.15535, step = 200 (4.426 sec) INFO:tensorflow:loss = 47.15535, step = 200 (4.426 sec) INFO:tensorflow:global_step/sec: 22.7122 INFO:tensorflow:global_step/sec: 22.7122 INFO:tensorflow:loss = 55.755352, step = 300 (4.403 sec) INFO:tensorflow:loss = 55.755352, step = 300 (4.403 sec) INFO:tensorflow:global_step/sec: 17.3985 INFO:tensorflow:global_step/sec: 17.3985 INFO:tensorflow:loss = 55.99872, step = 400 (5.748 sec) INFO:tensorflow:loss = 55.99872, step = 400 (5.748 sec) INFO:tensorflow:global_step/sec: 18.6501 INFO:tensorflow:global_step/sec: 18.6501 INFO:tensorflow:loss = 41.616364, step = 500 (5.362 sec) INFO:tensorflow:loss = 41.616364, step = 500 (5.362 sec) INFO:tensorflow:global_step/sec: 21.9067 INFO:tensorflow:global_step/sec: 21.9067 INFO:tensorflow:loss = 45.376034, step = 600 (4.566 sec) INFO:tensorflow:loss = 45.376034, step = 600 (4.566 sec) INFO:tensorflow:global_step/sec: 22.6113 INFO:tensorflow:global_step/sec: 22.6113 INFO:tensorflow:loss = 51.537807, step = 700 (4.420 sec) INFO:tensorflow:loss = 51.537807, step = 700 (4.420 sec) INFO:tensorflow:global_step/sec: 22.5064 INFO:tensorflow:global_step/sec: 22.5064 INFO:tensorflow:loss = 47.600033, step = 800 (4.443 sec) INFO:tensorflow:loss = 47.600033, step = 800 (4.443 sec) INFO:tensorflow:global_step/sec: 23.0248 INFO:tensorflow:global_step/sec: 23.0248 INFO:tensorflow:loss = 48.61444, step = 900 (4.344 sec) INFO:tensorflow:loss = 48.61444, step = 900 (4.344 sec) INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 1000... INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 1000... INFO:tensorflow:Saving checkpoints for 1000 into /tmp/train/20210211-103338/model.ckpt. INFO:tensorflow:Saving checkpoints for 1000 into /tmp/train/20210211-103338/model.ckpt. INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 1000... INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 1000... INFO:tensorflow:Loss for final step: 51.06741. INFO:tensorflow:Loss for final step: 51.06741. INFO:tensorflow:Calling model_fn. INFO:tensorflow:Calling model_fn. INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore WARNING:tensorflow:Trapezoidal rule is known to produce incorrect PR-AUCs; please switch to "careful_interpolation" instead. WARNING:tensorflow:Trapezoidal rule is known to produce incorrect PR-AUCs; please switch to "careful_interpolation" instead. WARNING:tensorflow:Trapezoidal rule is known to produce incorrect PR-AUCs; please switch to "careful_interpolation" instead. WARNING:tensorflow:Trapezoidal rule is known to produce incorrect PR-AUCs; please switch to "careful_interpolation" instead. INFO:tensorflow:Done calling model_fn. INFO:tensorflow:Done calling model_fn. INFO:tensorflow:Signatures INCLUDED in export for Classify: None INFO:tensorflow:Signatures INCLUDED in export for Classify: None INFO:tensorflow:Signatures INCLUDED in export for Regress: None INFO:tensorflow:Signatures INCLUDED in export for Regress: None INFO:tensorflow:Signatures INCLUDED in export for Predict: None INFO:tensorflow:Signatures INCLUDED in export for Predict: None INFO:tensorflow:Signatures INCLUDED in export for Train: None INFO:tensorflow:Signatures INCLUDED in export for Train: None INFO:tensorflow:Signatures INCLUDED in export for Eval: ['eval'] INFO:tensorflow:Signatures INCLUDED in export for Eval: ['eval'] WARNING:tensorflow:Export includes no default signature! WARNING:tensorflow:Export includes no default signature! INFO:tensorflow:Restoring parameters from /tmp/train/20210211-103338/model.ckpt-1000 INFO:tensorflow:Restoring parameters from /tmp/train/20210211-103338/model.ckpt-1000 INFO:tensorflow:Assets added to graph. INFO:tensorflow:Assets added to graph. INFO:tensorflow:Assets written to: /tmp/tfma_eval_model/temp-1613039675/assets INFO:tensorflow:Assets written to: /tmp/tfma_eval_model/temp-1613039675/assets INFO:tensorflow:SavedModel written to: /tmp/tfma_eval_model/temp-1613039675/saved_model.pb INFO:tensorflow:SavedModel written to: /tmp/tfma_eval_model/temp-1613039675/saved_model.pb WARNING:absl:Tensorflow version (2.4.1) found. Note that TFMA support for TF 2.0 is currently in beta WARNING:apache_beam.typehints.typehints:Ignoring send_type hint: <class 'NoneType'> WARNING:apache_beam.typehints.typehints:Ignoring return_type hint: <class 'NoneType'> WARNING:apache_beam.typehints.typehints:Ignoring send_type hint: <class 'NoneType'> WARNING:apache_beam.typehints.typehints:Ignoring return_type hint: <class 'NoneType'> WARNING:apache_beam.typehints.typehints:Ignoring send_type hint: <class 'NoneType'> WARNING:apache_beam.typehints.typehints:Ignoring return_type hint: <class 'NoneType'> INFO:tensorflow:Restoring parameters from /tmp/tfma_eval_model/1613039675/variables/variables INFO:tensorflow:Restoring parameters from /tmp/tfma_eval_model/1613039675/variables/variables
widget_view.render_fairness_indicator(eval_result=eval_result_nnlm)
FairnessIndicatorViewer(slicingMetrics=[{'sliceValue': 'Overall', 'slice': 'Overall', 'metrics': {'post_export…
Universal Sentence Encoder
eval_result_use = embedding_fairness_result('https://hub.tensorflow.google.cn/google/universal-sentence-encoder/2')
Training classifier for https://hub.tensorflow.google.cn/google/universal-sentence-encoder/2 INFO:tensorflow:Using default config. INFO:tensorflow:Using default config. INFO:tensorflow:Using config: {'_model_dir': '/tmp/train/20210211-103650', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true graph_options { rewrite_options { meta_optimizer_iterations: ONE } } , '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1} INFO:tensorflow:Using config: {'_model_dir': '/tmp/train/20210211-103650', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': None, '_save_checkpoints_secs': 600, '_session_config': allow_soft_placement: true graph_options { rewrite_options { meta_optimizer_iterations: ONE } } , '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 100, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1} INFO:tensorflow:Calling model_fn. INFO:tensorflow:Calling model_fn. INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Done calling model_fn. INFO:tensorflow:Done calling model_fn. INFO:tensorflow:Create CheckpointSaverHook. INFO:tensorflow:Create CheckpointSaverHook. INFO:tensorflow:Graph was finalized. INFO:tensorflow:Graph was finalized. INFO:tensorflow:Running local_init_op. INFO:tensorflow:Running local_init_op. INFO:tensorflow:Done running local_init_op. INFO:tensorflow:Done running local_init_op. INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 0... INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 0... INFO:tensorflow:Saving checkpoints for 0 into /tmp/train/20210211-103650/model.ckpt. INFO:tensorflow:Saving checkpoints for 0 into /tmp/train/20210211-103650/model.ckpt. INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0... INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0... INFO:tensorflow:loss = 58.753284, step = 0 INFO:tensorflow:loss = 58.753284, step = 0 INFO:tensorflow:global_step/sec: 8.50431 INFO:tensorflow:global_step/sec: 8.50431 INFO:tensorflow:loss = 48.59803, step = 100 (11.761 sec) INFO:tensorflow:loss = 48.59803, step = 100 (11.761 sec) INFO:tensorflow:global_step/sec: 8.7217 INFO:tensorflow:global_step/sec: 8.7217 INFO:tensorflow:loss = 46.012943, step = 200 (11.466 sec) INFO:tensorflow:loss = 46.012943, step = 200 (11.466 sec) INFO:tensorflow:global_step/sec: 8.72576 INFO:tensorflow:global_step/sec: 8.72576 INFO:tensorflow:loss = 48.555466, step = 300 (11.461 sec) INFO:tensorflow:loss = 48.555466, step = 300 (11.461 sec) INFO:tensorflow:global_step/sec: 8.69595 INFO:tensorflow:global_step/sec: 8.69595 INFO:tensorflow:loss = 44.629684, step = 400 (11.499 sec) INFO:tensorflow:loss = 44.629684, step = 400 (11.499 sec) INFO:tensorflow:global_step/sec: 8.7886 INFO:tensorflow:global_step/sec: 8.7886 INFO:tensorflow:loss = 35.215424, step = 500 (11.378 sec) INFO:tensorflow:loss = 35.215424, step = 500 (11.378 sec) INFO:tensorflow:global_step/sec: 8.77454 INFO:tensorflow:global_step/sec: 8.77454 INFO:tensorflow:loss = 42.30302, step = 600 (11.397 sec) INFO:tensorflow:loss = 42.30302, step = 600 (11.397 sec) INFO:tensorflow:global_step/sec: 8.7314 INFO:tensorflow:global_step/sec: 8.7314 INFO:tensorflow:loss = 40.927437, step = 700 (11.453 sec) INFO:tensorflow:loss = 40.927437, step = 700 (11.453 sec) INFO:tensorflow:global_step/sec: 8.7245 INFO:tensorflow:global_step/sec: 8.7245 INFO:tensorflow:loss = 37.25813, step = 800 (11.462 sec) INFO:tensorflow:loss = 37.25813, step = 800 (11.462 sec) INFO:tensorflow:global_step/sec: 8.68295 INFO:tensorflow:global_step/sec: 8.68295 INFO:tensorflow:loss = 33.05001, step = 900 (11.517 sec) INFO:tensorflow:loss = 33.05001, step = 900 (11.517 sec) INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 1000... INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 1000... INFO:tensorflow:Saving checkpoints for 1000 into /tmp/train/20210211-103650/model.ckpt. INFO:tensorflow:Saving checkpoints for 1000 into /tmp/train/20210211-103650/model.ckpt. INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 1000... INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 1000... INFO:tensorflow:Loss for final step: 47.369293. INFO:tensorflow:Loss for final step: 47.369293. INFO:tensorflow:Calling model_fn. INFO:tensorflow:Calling model_fn. INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore INFO:tensorflow:Saver not created because there are no variables in the graph to restore WARNING:tensorflow:Trapezoidal rule is known to produce incorrect PR-AUCs; please switch to "careful_interpolation" instead. WARNING:tensorflow:Trapezoidal rule is known to produce incorrect PR-AUCs; please switch to "careful_interpolation" instead. WARNING:tensorflow:Trapezoidal rule is known to produce incorrect PR-AUCs; please switch to "careful_interpolation" instead. WARNING:tensorflow:Trapezoidal rule is known to produce incorrect PR-AUCs; please switch to "careful_interpolation" instead. INFO:tensorflow:Done calling model_fn. INFO:tensorflow:Done calling model_fn. INFO:tensorflow:Signatures INCLUDED in export for Classify: None INFO:tensorflow:Signatures INCLUDED in export for Classify: None INFO:tensorflow:Signatures INCLUDED in export for Regress: None INFO:tensorflow:Signatures INCLUDED in export for Regress: None INFO:tensorflow:Signatures INCLUDED in export for Predict: None INFO:tensorflow:Signatures INCLUDED in export for Predict: None INFO:tensorflow:Signatures INCLUDED in export for Train: None INFO:tensorflow:Signatures INCLUDED in export for Train: None INFO:tensorflow:Signatures INCLUDED in export for Eval: ['eval'] INFO:tensorflow:Signatures INCLUDED in export for Eval: ['eval'] WARNING:tensorflow:Export includes no default signature! WARNING:tensorflow:Export includes no default signature! INFO:tensorflow:Restoring parameters from /tmp/train/20210211-103650/model.ckpt-1000 INFO:tensorflow:Restoring parameters from /tmp/train/20210211-103650/model.ckpt-1000 INFO:tensorflow:Assets added to graph. INFO:tensorflow:Assets added to graph. INFO:tensorflow:No assets to write. INFO:tensorflow:No assets to write. INFO:tensorflow:SavedModel written to: /tmp/tfma_eval_model/temp-1613039968/saved_model.pb INFO:tensorflow:SavedModel written to: /tmp/tfma_eval_model/temp-1613039968/saved_model.pb WARNING:absl:Tensorflow version (2.4.1) found. Note that TFMA support for TF 2.0 is currently in beta WARNING:apache_beam.typehints.typehints:Ignoring send_type hint: <class 'NoneType'> WARNING:apache_beam.typehints.typehints:Ignoring return_type hint: <class 'NoneType'> WARNING:apache_beam.typehints.typehints:Ignoring send_type hint: <class 'NoneType'> WARNING:apache_beam.typehints.typehints:Ignoring return_type hint: <class 'NoneType'> WARNING:apache_beam.typehints.typehints:Ignoring send_type hint: <class 'NoneType'> WARNING:apache_beam.typehints.typehints:Ignoring return_type hint: <class 'NoneType'> INFO:tensorflow:Restoring parameters from /tmp/tfma_eval_model/1613039968/variables/variables INFO:tensorflow:Restoring parameters from /tmp/tfma_eval_model/1613039968/variables/variables
widget_view.render_fairness_indicator(eval_result=eval_result_use)
FairnessIndicatorViewer(slicingMetrics=[{'sliceValue': 'Overall', 'slice': 'Overall', 'metrics': {'post_export…
Comparing Embeddings
You can also use Fairness Indicators to compare embeddings directly. For example, compare the models generated from the NNLM and USE embeddings.
widget_view.render_fairness_indicator(multi_eval_results={'nnlm': eval_result_nnlm, 'use': eval_result_use})
FairnessIndicatorViewer(evalName='nnlm', evalNameCompare='use', slicingMetrics=[{'sliceValue': 'Overall', 'sli…