Fairness Indicators on TF-Hub Text Embeddings

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==0.12.0" \
  "pyarrow==2.0.0" \
  "apache-beam==2.34.0" \
  "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

ERROR: 
Traceback (most recent call last):
  File "/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/apache_beam/io/gcp/bigquery.py", line 341, in <module>
    import google.cloud.bigquery_storage_v1 as bq_storage
ModuleNotFoundError: No module named 'google.cloud.bigquery_storage_v1'

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 [==============================] - 2s 0us/step
488169472/488153424 [==============================] - 2s 0us/step
Downloading data from https://storage.googleapis.com/civil_comments_dataset/validate_tf_processed.tfrecord
324943872/324941336 [==============================] - 9s 0us/step
324952064/324941336 [==============================] - 9s 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:

1. Build a TensorFlow model
2. Build a TFMA model on top of the TensorFlow model
3. 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.

Note: You may need to run the widget_view.render_fairness_indicator cells twice for the visualization to be displayed.

Random NNLM

eval_result_random_nnlm = embedding_fairness_result('https://tfhub.dev/google/random-nnlm-en-dim128/1')

Training classifier for https://tfhub.dev/google/random-nnlm-en-dim128/1
INFO:tensorflow:Using default config.
INFO:tensorflow:Using default config.
INFO:tensorflow:Using config: {'_model_dir': '/tmp/train/20220107-182244', '_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/20220107-182244', '_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/python3.7/site-packages/tensorflow/python/training/training_util.py:397: 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/python3.7/site-packages/tensorflow/python/training/training_util.py:397: 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
2022-01-07 18:22:54.196242: W tensorflow/core/common_runtime/graph_constructor.cc:1511] Importing a graph with a lower producer version 26 into an existing graph with producer version 987. Shape inference will have run different parts of the graph with different producer versions.
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/python3.7/site-packages/tensorflow_estimator/python/estimator/canned/head.py:400: 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/python3.7/site-packages/tensorflow_estimator/python/estimator/canned/head.py:400: 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/python3.7/site-packages/tensorflow/python/feature_column/feature_column.py:2188: 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/python3.7/site-packages/tensorflow/python/feature_column/feature_column.py:2188: 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/python3.7/site-packages/tensorflow/python/training/adagrad.py:139: 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/python3.7/site-packages/tensorflow/python/training/adagrad.py:139: 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/20220107-182244/model.ckpt.
INFO:tensorflow:Saving checkpoints for 0 into /tmp/train/20220107-182244/model.ckpt.
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0...
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0...
INFO:tensorflow:loss = 60.23522, step = 0
INFO:tensorflow:loss = 60.23522, step = 0
INFO:tensorflow:global_step/sec: 78.2958
INFO:tensorflow:global_step/sec: 78.2958
INFO:tensorflow:loss = 67.36491, step = 100 (1.279 sec)
INFO:tensorflow:loss = 67.36491, step = 100 (1.279 sec)
INFO:tensorflow:global_step/sec: 85.8245
INFO:tensorflow:global_step/sec: 85.8245
INFO:tensorflow:loss = 57.875557, step = 200 (1.165 sec)
INFO:tensorflow:loss = 57.875557, step = 200 (1.165 sec)
INFO:tensorflow:global_step/sec: 83.7495
INFO:tensorflow:global_step/sec: 83.7495
INFO:tensorflow:loss = 61.091763, step = 300 (1.194 sec)
INFO:tensorflow:loss = 61.091763, step = 300 (1.194 sec)
INFO:tensorflow:global_step/sec: 83.0013
INFO:tensorflow:global_step/sec: 83.0013
INFO:tensorflow:loss = 62.251183, step = 400 (1.205 sec)
INFO:tensorflow:loss = 62.251183, step = 400 (1.205 sec)
INFO:tensorflow:global_step/sec: 83.4782
INFO:tensorflow:global_step/sec: 83.4782
INFO:tensorflow:loss = 56.21132, step = 500 (1.198 sec)
INFO:tensorflow:loss = 56.21132, step = 500 (1.198 sec)
INFO:tensorflow:global_step/sec: 87.0099
INFO:tensorflow:global_step/sec: 87.0099
INFO:tensorflow:loss = 57.211937, step = 600 (1.149 sec)
INFO:tensorflow:loss = 57.211937, step = 600 (1.149 sec)
INFO:tensorflow:global_step/sec: 86.7988
INFO:tensorflow:global_step/sec: 86.7988
INFO:tensorflow:loss = 62.16255, step = 700 (1.152 sec)
INFO:tensorflow:loss = 62.16255, step = 700 (1.152 sec)
INFO:tensorflow:global_step/sec: 88.1099
INFO:tensorflow:global_step/sec: 88.1099
INFO:tensorflow:loss = 58.081688, step = 800 (1.135 sec)
INFO:tensorflow:loss = 58.081688, step = 800 (1.135 sec)
INFO:tensorflow:global_step/sec: 85.3134
INFO:tensorflow:global_step/sec: 85.3134
INFO:tensorflow:loss = 57.763985, step = 900 (1.172 sec)
INFO:tensorflow:loss = 57.763985, step = 900 (1.172 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/20220107-182244/model.ckpt.
INFO:tensorflow:Saving checkpoints for 1000 into /tmp/train/20220107-182244/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: 59.963802.
INFO:tensorflow:Loss for final step: 59.963802.
WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow_model_analysis/eval_saved_model/encoding.py:132: 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/python3.7/site-packages/tensorflow_model_analysis/eval_saved_model/encoding.py:132: 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
2022-01-07 18:23:11.033169: W tensorflow/core/common_runtime/graph_constructor.cc:1511] Importing a graph with a lower producer version 26 into an existing graph with producer version 987. Shape inference will have run different parts of the graph with different producer versions.
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/python3.7/site-packages/tensorflow_estimator/python/estimator/canned/head.py:640: 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/python3.7/site-packages/tensorflow_estimator/python/estimator/canned/head.py:640: 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/20220107-182244/model.ckpt-1000
INFO:tensorflow:Restoring parameters from /tmp/train/20220107-182244/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-1641579790/assets
INFO:tensorflow:Assets written to: /tmp/tfma_eval_model/temp-1641579790/assets
INFO:tensorflow:SavedModel written to: /tmp/tfma_eval_model/temp-1641579790/saved_model.pb
INFO:tensorflow:SavedModel written to: /tmp/tfma_eval_model/temp-1641579790/saved_model.pb
WARNING:absl:Tensorflow version (2.8.0-rc0) 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:root:Make sure that locally built Python SDK docker image has Python 3.7 interpreter.
WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow_model_analysis/eval_saved_model/load.py:164: 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/python3.7/site-packages/tensorflow_model_analysis/eval_saved_model/load.py:164: 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/1641579790/variables/variables
INFO:tensorflow:Restoring parameters from /tmp/tfma_eval_model/1641579790/variables/variables
WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow_model_analysis/eval_saved_model/graph_ref.py:184: 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/python3.7/site-packages/tensorflow_model_analysis/eval_saved_model/graph_ref.py:184: 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/python3.7/site-packages/tensorflow_model_analysis/writers/metrics_plots_and_validations_writer.py:107: 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/python3.7/site-packages/tensorflow_model_analysis/writers/metrics_plots_and_validations_writer.py:107: 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://tfhub.dev/google/nnlm-en-dim128/1')

Training classifier for https://tfhub.dev/google/nnlm-en-dim128/1
INFO:tensorflow:Using default config.
INFO:tensorflow:Using default config.
INFO:tensorflow:Using config: {'_model_dir': '/tmp/train/20220107-182524', '_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/20220107-182524', '_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
2022-01-07 18:25:24.785154: W tensorflow/core/common_runtime/graph_constructor.cc:1511] Importing a graph with a lower producer version 26 into an existing graph with producer version 987. Shape inference will have run different parts of the graph with different producer versions.
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/20220107-182524/model.ckpt.
INFO:tensorflow:Saving checkpoints for 0 into /tmp/train/20220107-182524/model.ckpt.
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0...
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0...
INFO:tensorflow:loss = 58.637047, step = 0
INFO:tensorflow:loss = 58.637047, step = 0
INFO:tensorflow:global_step/sec: 75.6907
INFO:tensorflow:global_step/sec: 75.6907
INFO:tensorflow:loss = 56.208035, step = 100 (1.323 sec)
INFO:tensorflow:loss = 56.208035, step = 100 (1.323 sec)
INFO:tensorflow:global_step/sec: 85.4193
INFO:tensorflow:global_step/sec: 85.4193
INFO:tensorflow:loss = 47.563675, step = 200 (1.170 sec)
INFO:tensorflow:loss = 47.563675, step = 200 (1.170 sec)
INFO:tensorflow:global_step/sec: 85.3916
INFO:tensorflow:global_step/sec: 85.3916
INFO:tensorflow:loss = 56.227097, step = 300 (1.171 sec)
INFO:tensorflow:loss = 56.227097, step = 300 (1.171 sec)
INFO:tensorflow:global_step/sec: 85.7359
INFO:tensorflow:global_step/sec: 85.7359
INFO:tensorflow:loss = 55.668434, step = 400 (1.166 sec)
INFO:tensorflow:loss = 55.668434, step = 400 (1.166 sec)
INFO:tensorflow:global_step/sec: 85.6231
INFO:tensorflow:global_step/sec: 85.6231
INFO:tensorflow:loss = 41.7245, step = 500 (1.168 sec)
INFO:tensorflow:loss = 41.7245, step = 500 (1.168 sec)
INFO:tensorflow:global_step/sec: 85.1399
INFO:tensorflow:global_step/sec: 85.1399
INFO:tensorflow:loss = 45.596313, step = 600 (1.174 sec)
INFO:tensorflow:loss = 45.596313, step = 600 (1.174 sec)
INFO:tensorflow:global_step/sec: 83.6346
INFO:tensorflow:global_step/sec: 83.6346
INFO:tensorflow:loss = 51.108143, step = 700 (1.196 sec)
INFO:tensorflow:loss = 51.108143, step = 700 (1.196 sec)
INFO:tensorflow:global_step/sec: 85.4834
INFO:tensorflow:global_step/sec: 85.4834
INFO:tensorflow:loss = 47.63583, step = 800 (1.170 sec)
INFO:tensorflow:loss = 47.63583, step = 800 (1.170 sec)
INFO:tensorflow:global_step/sec: 86.7353
INFO:tensorflow:global_step/sec: 86.7353
INFO:tensorflow:loss = 48.044117, step = 900 (1.153 sec)
INFO:tensorflow:loss = 48.044117, step = 900 (1.153 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/20220107-182524/model.ckpt.
INFO:tensorflow:Saving checkpoints for 1000 into /tmp/train/20220107-182524/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: 50.57175.
INFO:tensorflow:Loss for final step: 50.57175.
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
2022-01-07 18:25:40.091474: W tensorflow/core/common_runtime/graph_constructor.cc:1511] Importing a graph with a lower producer version 26 into an existing graph with producer version 987. Shape inference will have run different parts of the graph with different producer versions.
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/20220107-182524/model.ckpt-1000
INFO:tensorflow:Restoring parameters from /tmp/train/20220107-182524/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-1641579940/assets
INFO:tensorflow:Assets written to: /tmp/tfma_eval_model/temp-1641579940/assets
INFO:tensorflow:SavedModel written to: /tmp/tfma_eval_model/temp-1641579940/saved_model.pb
INFO:tensorflow:SavedModel written to: /tmp/tfma_eval_model/temp-1641579940/saved_model.pb
WARNING:absl:Tensorflow version (2.8.0-rc0) found. Note that TFMA support for TF 2.0 is currently in beta
WARNING:root:Make sure that locally built Python SDK docker image has Python 3.7 interpreter.
INFO:tensorflow:Restoring parameters from /tmp/tfma_eval_model/1641579940/variables/variables
INFO:tensorflow:Restoring parameters from /tmp/tfma_eval_model/1641579940/variables/variables

widget_view.render_fairness_indicator(eval_result=eval_result_nnlm)

FairnessIndicatorViewer(slicingMetrics=[{'sliceValue': 'Overall', 'slice': 'Overall', 'metrics': {'label/mean'…

Universal Sentence Encoder

eval_result_use = embedding_fairness_result('https://tfhub.dev/google/universal-sentence-encoder/2')

Training classifier for https://tfhub.dev/google/universal-sentence-encoder/2
INFO:tensorflow:Using default config.
INFO:tensorflow:Using default config.
INFO:tensorflow:Using config: {'_model_dir': '/tmp/train/20220107-182759', '_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/20220107-182759', '_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.
2022-01-07 18:28:15.955057: W tensorflow/core/common_runtime/graph_constructor.cc:1511] Importing a graph with a lower producer version 26 into an existing graph with producer version 987. Shape inference will have run different parts of the graph with different producer versions.
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/20220107-182759/model.ckpt.
INFO:tensorflow:Saving checkpoints for 0 into /tmp/train/20220107-182759/model.ckpt.
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0...
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0...
INFO:tensorflow:loss = 59.228935, step = 0
INFO:tensorflow:loss = 59.228935, step = 0
INFO:tensorflow:global_step/sec: 8.64079
INFO:tensorflow:global_step/sec: 8.64079
INFO:tensorflow:loss = 50.28162, step = 100 (11.575 sec)
INFO:tensorflow:loss = 50.28162, step = 100 (11.575 sec)
INFO:tensorflow:global_step/sec: 8.72597
INFO:tensorflow:global_step/sec: 8.72597
INFO:tensorflow:loss = 46.290745, step = 200 (11.460 sec)
INFO:tensorflow:loss = 46.290745, step = 200 (11.460 sec)
INFO:tensorflow:global_step/sec: 9.02825
INFO:tensorflow:global_step/sec: 9.02825
INFO:tensorflow:loss = 48.490734, step = 300 (11.076 sec)
INFO:tensorflow:loss = 48.490734, step = 300 (11.076 sec)
INFO:tensorflow:global_step/sec: 9.01342
INFO:tensorflow:global_step/sec: 9.01342
INFO:tensorflow:loss = 44.54372, step = 400 (11.095 sec)
INFO:tensorflow:loss = 44.54372, step = 400 (11.095 sec)
INFO:tensorflow:global_step/sec: 8.952
INFO:tensorflow:global_step/sec: 8.952
INFO:tensorflow:loss = 35.568554, step = 500 (11.171 sec)
INFO:tensorflow:loss = 35.568554, step = 500 (11.171 sec)
INFO:tensorflow:global_step/sec: 9.09908
INFO:tensorflow:global_step/sec: 9.09908
INFO:tensorflow:loss = 42.5132, step = 600 (10.990 sec)
INFO:tensorflow:loss = 42.5132, step = 600 (10.990 sec)
INFO:tensorflow:global_step/sec: 9.02127
INFO:tensorflow:global_step/sec: 9.02127
INFO:tensorflow:loss = 40.52431, step = 700 (11.085 sec)
INFO:tensorflow:loss = 40.52431, step = 700 (11.085 sec)
INFO:tensorflow:global_step/sec: 9.09376
INFO:tensorflow:global_step/sec: 9.09376
INFO:tensorflow:loss = 37.5485, step = 800 (10.996 sec)
INFO:tensorflow:loss = 37.5485, step = 800 (10.996 sec)
INFO:tensorflow:global_step/sec: 9.11679
INFO:tensorflow:global_step/sec: 9.11679
INFO:tensorflow:loss = 32.65558, step = 900 (10.968 sec)
INFO:tensorflow:loss = 32.65558, step = 900 (10.968 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/20220107-182759/model.ckpt.
INFO:tensorflow:Saving checkpoints for 1000 into /tmp/train/20220107-182759/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: 46.92047.
INFO:tensorflow:Loss for final step: 46.92047.
INFO:tensorflow:Calling model_fn.
INFO:tensorflow:Calling model_fn.
2022-01-07 18:30:32.176628: W tensorflow/core/common_runtime/graph_constructor.cc:1511] Importing a graph with a lower producer version 26 into an existing graph with producer version 987. Shape inference will have run different parts of the graph with different producer versions.
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/20220107-182759/model.ckpt-1000
INFO:tensorflow:Restoring parameters from /tmp/train/20220107-182759/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-1641580231/saved_model.pb
INFO:tensorflow:SavedModel written to: /tmp/tfma_eval_model/temp-1641580231/saved_model.pb
WARNING:absl:Tensorflow version (2.8.0-rc0) found. Note that TFMA support for TF 2.0 is currently in beta
WARNING:root:Make sure that locally built Python SDK docker image has Python 3.7 interpreter.
INFO:tensorflow:Restoring parameters from /tmp/tfma_eval_model/1641580231/variables/variables
INFO:tensorflow:Restoring parameters from /tmp/tfma_eval_model/1641580231/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…