forked from tensorflow/model-analysis
-
Notifications
You must be signed in to change notification settings - Fork 0
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
Showing
27 changed files
with
1,040 additions
and
4 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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,8 @@ | ||
toc: | ||
- title: Get Started | ||
path: /tfx/model_analysis/get_started | ||
|
||
- heading: Examples | ||
- title: Chicago Taxi (end-to-end) | ||
path: https://github.com/tensorflow/model-analysis/tree/master/examples/chicago_taxi | ||
status: external |
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 +1,74 @@ | ||
# Automatically generated file; please do not edit | ||
toc: | ||
- title: tfma | ||
section: | ||
- title: Overview | ||
path: /tfx/model_analysis/api_docs/python/tfma | ||
- title: EvaluateAndWriteResults | ||
path: /tfx/model_analysis/api_docs/python/tfma/EvaluateAndWriteResults | ||
- title: load_eval_result | ||
path: /tfx/model_analysis/api_docs/python/tfma/load_eval_result | ||
- title: load_eval_results | ||
path: /tfx/model_analysis/api_docs/python/tfma/load_eval_results | ||
- title: make_eval_results | ||
path: /tfx/model_analysis/api_docs/python/tfma/make_eval_results | ||
- title: multiple_data_analysis | ||
path: /tfx/model_analysis/api_docs/python/tfma/multiple_data_analysis | ||
- title: multiple_model_analysis | ||
path: /tfx/model_analysis/api_docs/python/tfma/multiple_model_analysis | ||
- title: run_model_analysis | ||
path: /tfx/model_analysis/api_docs/python/tfma/run_model_analysis | ||
- title: SingleSliceSpec | ||
path: /tfx/model_analysis/api_docs/python/tfma/SingleSliceSpec | ||
- title: tfma.constants | ||
section: | ||
- title: Overview | ||
path: /tfx/model_analysis/api_docs/python/tfma/constants | ||
- title: tfma.export | ||
section: | ||
- title: Overview | ||
path: /tfx/model_analysis/api_docs/python/tfma/export | ||
- title: build_parsing_eval_input_receiver_fn | ||
path: /tfx/model_analysis/api_docs/python/tfma/export/build_parsing_eval_input_receiver_fn | ||
- title: make_export_strategy | ||
path: /tfx/model_analysis/api_docs/python/tfma/export/make_export_strategy | ||
- title: tfma.exporter | ||
section: | ||
- title: Overview | ||
path: /tfx/model_analysis/api_docs/python/tfma/exporter | ||
- title: FinalExporter | ||
path: /tfx/model_analysis/api_docs/python/tfma/exporter/FinalExporter | ||
- title: LatestExporter | ||
path: /tfx/model_analysis/api_docs/python/tfma/exporter/LatestExporter | ||
- title: tfma.post_export_metrics | ||
section: | ||
- title: Overview | ||
path: /tfx/model_analysis/api_docs/python/tfma/post_export_metrics | ||
- title: auc | ||
path: /tfx/model_analysis/api_docs/python/tfma/post_export_metrics/auc | ||
- title: auc_plots | ||
path: /tfx/model_analysis/api_docs/python/tfma/post_export_metrics/auc_plots | ||
- title: calibration_plot_and_prediction_histogram | ||
path: /tfx/model_analysis/api_docs/python/tfma/post_export_metrics/calibration_plot_and_prediction_histogram | ||
- title: confusion_matrix_at_thresholds | ||
path: /tfx/model_analysis/api_docs/python/tfma/post_export_metrics/confusion_matrix_at_thresholds | ||
- title: example_count | ||
path: /tfx/model_analysis/api_docs/python/tfma/post_export_metrics/example_count | ||
- title: example_weight | ||
path: /tfx/model_analysis/api_docs/python/tfma/post_export_metrics/example_weight | ||
- title: precision_recall_at_k | ||
path: /tfx/model_analysis/api_docs/python/tfma/post_export_metrics/precision_recall_at_k | ||
- title: tfma.version | ||
section: | ||
- title: Overview | ||
path: /tfx/model_analysis/api_docs/python/tfma/version | ||
- title: tfma.view | ||
section: | ||
- title: Overview | ||
path: /tfx/model_analysis/api_docs/python/tfma/view | ||
- title: render_plot | ||
path: /tfx/model_analysis/api_docs/python/tfma/view/render_plot | ||
- title: render_slicing_metrics | ||
path: /tfx/model_analysis/api_docs/python/tfma/view/render_slicing_metrics | ||
- title: render_time_series | ||
path: /tfx/model_analysis/api_docs/python/tfma/view/render_time_series |
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 +1,31 @@ | ||
# All symbols in TensorFlow Model Analysis | ||
|
||
* <a href="./tfma.md"><code>tfma</code></a> | ||
* <a href="./tfma/EvaluateAndWriteResults.md"><code>tfma.EvaluateAndWriteResults</code></a> | ||
* <a href="./tfma/SingleSliceSpec.md"><code>tfma.SingleSliceSpec</code></a> | ||
* <a href="./tfma/constants.md"><code>tfma.constants</code></a> | ||
* <a href="./tfma/export.md"><code>tfma.export</code></a> | ||
* <a href="./tfma/export/build_parsing_eval_input_receiver_fn.md"><code>tfma.export.build_parsing_eval_input_receiver_fn</code></a> | ||
* <a href="./tfma/export/make_export_strategy.md"><code>tfma.export.make_export_strategy</code></a> | ||
* <a href="./tfma/exporter.md"><code>tfma.exporter</code></a> | ||
* <a href="./tfma/exporter/FinalExporter.md"><code>tfma.exporter.FinalExporter</code></a> | ||
* <a href="./tfma/exporter/LatestExporter.md"><code>tfma.exporter.LatestExporter</code></a> | ||
* <a href="./tfma/load_eval_result.md"><code>tfma.load_eval_result</code></a> | ||
* <a href="./tfma/load_eval_results.md"><code>tfma.load_eval_results</code></a> | ||
* <a href="./tfma/make_eval_results.md"><code>tfma.make_eval_results</code></a> | ||
* <a href="./tfma/multiple_data_analysis.md"><code>tfma.multiple_data_analysis</code></a> | ||
* <a href="./tfma/multiple_model_analysis.md"><code>tfma.multiple_model_analysis</code></a> | ||
* <a href="./tfma/post_export_metrics.md"><code>tfma.post_export_metrics</code></a> | ||
* <a href="./tfma/post_export_metrics/auc.md"><code>tfma.post_export_metrics.auc</code></a> | ||
* <a href="./tfma/post_export_metrics/auc_plots.md"><code>tfma.post_export_metrics.auc_plots</code></a> | ||
* <a href="./tfma/post_export_metrics/calibration_plot_and_prediction_histogram.md"><code>tfma.post_export_metrics.calibration_plot_and_prediction_histogram</code></a> | ||
* <a href="./tfma/post_export_metrics/confusion_matrix_at_thresholds.md"><code>tfma.post_export_metrics.confusion_matrix_at_thresholds</code></a> | ||
* <a href="./tfma/post_export_metrics/example_count.md"><code>tfma.post_export_metrics.example_count</code></a> | ||
* <a href="./tfma/post_export_metrics/example_weight.md"><code>tfma.post_export_metrics.example_weight</code></a> | ||
* <a href="./tfma/post_export_metrics/precision_recall_at_k.md"><code>tfma.post_export_metrics.precision_recall_at_k</code></a> | ||
* <a href="./tfma/run_model_analysis.md"><code>tfma.run_model_analysis</code></a> | ||
* <a href="./tfma/version.md"><code>tfma.version</code></a> | ||
* <a href="./tfma/view.md"><code>tfma.view</code></a> | ||
* <a href="./tfma/view/render_plot.md"><code>tfma.view.render_plot</code></a> | ||
* <a href="./tfma/view/render_slicing_metrics.md"><code>tfma.view.render_slicing_metrics</code></a> | ||
* <a href="./tfma/view/render_time_series.md"><code>tfma.view.render_time_series</code></a> |
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 +1,54 @@ | ||
<div itemscope itemtype="http://developers.google.com/ReferenceObject"> | ||
<meta itemprop="name" content="tfma" /> | ||
<meta itemprop="path" content="Stable" /> | ||
<meta itemprop="property" content="DATA_CENTRIC_MODE"/> | ||
<meta itemprop="property" content="MODEL_CENTRIC_MODE"/> | ||
<meta itemprop="property" content="VERSION_STRING"/> | ||
</div> | ||
|
||
# Module: tfma | ||
|
||
Init module for TensorFlow Model Analysis on notebook. | ||
|
||
## Modules | ||
|
||
[`constants`](./tfma/constants.md) module: Constants used in TensorFlow Model Analysis. | ||
|
||
[`export`](./tfma/export.md) module: Library for exporting the EvalSavedModel. | ||
|
||
[`exporter`](./tfma/exporter.md) module: `Exporter` class represents different flavors of model export. | ||
|
||
[`post_export_metrics`](./tfma/post_export_metrics.md) module: Library containing helpers for adding post export metrics for evaluation. | ||
|
||
[`version`](./tfma/version.md) module: Contains the version string for this release of TFMA. | ||
|
||
[`view`](./tfma/view.md) module: View API for Tensorflow Model Analysis. | ||
|
||
## Classes | ||
|
||
[`class SingleSliceSpec`](./tfma/SingleSliceSpec.md): Specification for a single slice. | ||
|
||
## Functions | ||
|
||
[`EvaluateAndWriteResults(...)`](./tfma/EvaluateAndWriteResults.md) | ||
|
||
[`load_eval_result(...)`](./tfma/load_eval_result.md): Creates an EvalResult object for use with the visualization functions. | ||
|
||
[`load_eval_results(...)`](./tfma/load_eval_results.md): Run model analysis for a single model on multiple data sets. | ||
|
||
[`make_eval_results(...)`](./tfma/make_eval_results.md): Run model analysis for a single model on multiple data sets. | ||
|
||
[`multiple_data_analysis(...)`](./tfma/multiple_data_analysis.md): Run model analysis for a single model on multiple data sets. | ||
|
||
[`multiple_model_analysis(...)`](./tfma/multiple_model_analysis.md): Run model analysis for multiple models on the same data set. | ||
|
||
[`run_model_analysis(...)`](./tfma/run_model_analysis.md): Runs TensorFlow model analysis. | ||
|
||
## Other Members | ||
|
||
<h3 id="DATA_CENTRIC_MODE"><code>DATA_CENTRIC_MODE</code></h3> | ||
|
||
<h3 id="MODEL_CENTRIC_MODE"><code>MODEL_CENTRIC_MODE</code></h3> | ||
|
||
<h3 id="VERSION_STRING"><code>VERSION_STRING</code></h3> | ||
|
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 +1,14 @@ | ||
<div itemscope itemtype="http://developers.google.com/ReferenceObject"> | ||
<meta itemprop="name" content="tfma.EvaluateAndWriteResults" /> | ||
<meta itemprop="path" content="Stable" /> | ||
</div> | ||
|
||
# tfma.EvaluateAndWriteResults | ||
|
||
``` python | ||
tfma.EvaluateAndWriteResults( | ||
*args, | ||
**kwargs | ||
) | ||
``` | ||
|
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 +1,140 @@ | ||
<div itemscope itemtype="http://developers.google.com/ReferenceObject"> | ||
<meta itemprop="name" content="tfma.SingleSliceSpec" /> | ||
<meta itemprop="path" content="Stable" /> | ||
<meta itemprop="property" content="__eq__"/> | ||
<meta itemprop="property" content="__init__"/> | ||
<meta itemprop="property" content="__ne__"/> | ||
<meta itemprop="property" content="generate_slices"/> | ||
<meta itemprop="property" content="is_overall"/> | ||
<meta itemprop="property" content="is_slice_applicable"/> | ||
</div> | ||
|
||
# tfma.SingleSliceSpec | ||
|
||
## Class `SingleSliceSpec` | ||
|
||
|
||
|
||
Specification for a single slice. | ||
|
||
This is intended to be an immutable class that specifies a single slice. | ||
Use this in conjunction with get_slices_for_features_dict to generate slices | ||
for a dictionary of features. | ||
|
||
Examples: | ||
- columns = ['age'], features = [] | ||
This means to slice by the 'age' column. | ||
- columns = ['age'], features = [('gender', 'female')] | ||
This means to slice by the 'age' column if the 'gender' is 'female'. | ||
- For more examples, refer to the tests in slicer_test.py. | ||
|
||
<h2 id="__init__"><code>__init__</code></h2> | ||
|
||
``` python | ||
__init__( | ||
columns=(), | ||
features=() | ||
) | ||
``` | ||
|
||
Initialises a SingleSliceSpec. | ||
|
||
#### Args: | ||
|
||
* <b>`columns`</b>: an iterable of column names to slice on. | ||
* <b>`features`</b>: a iterable of features to slice on. Each feature is a | ||
(key, value) tuple. Note that the value can be either a string or an | ||
int, and the type is taken into account when comparing values, so | ||
SingleSliceSpec(features=[('age', '5')]) will *not* match a slice | ||
with age=[5] (age is a string in the spec, but an int in the slice). | ||
|
||
|
||
#### Raises: | ||
|
||
* <b>`ValueError`</b>: There was overlap between the columns specified in columns | ||
and those in features. | ||
* <b>`ValueError`</b>: columns or features was a string: they should probably be a | ||
singleton list containing that string. | ||
|
||
|
||
|
||
## Methods | ||
|
||
<h3 id="__eq__"><code>__eq__</code></h3> | ||
|
||
``` python | ||
__eq__(other) | ||
``` | ||
|
||
Return self==value. | ||
|
||
<h3 id="__ne__"><code>__ne__</code></h3> | ||
|
||
``` python | ||
__ne__(other) | ||
``` | ||
|
||
Return self!=value. | ||
|
||
<h3 id="generate_slices"><code>generate_slices</code></h3> | ||
|
||
``` python | ||
generate_slices(accessor) | ||
``` | ||
|
||
Generates all slices that match this specification from the data. | ||
|
||
Should only be called within this file. | ||
|
||
Examples: | ||
- columns = [], features = [] | ||
slice accessor has features age=[5], gender=['f'], interest=['knitting'] | ||
returns [[]] | ||
- columns = ['age'], features = [('gender', 'f')] | ||
slice accessor has features age=[5], gender=['f'], interest=['knitting'] | ||
returns [[('age', 5), ('gender, 'f')]] | ||
- columns = ['interest'], features = [('gender', 'f')] | ||
slice accessor has features age=[5], gender=['f'], | ||
interest=['knitting', 'games'] | ||
returns [[('gender', 'f'), ('interest, 'knitting')], | ||
[('gender', 'f'), ('interest, 'games')]] | ||
|
||
#### Args: | ||
|
||
* <b>`accessor`</b>: slice accessor. | ||
|
||
|
||
#### Yields: | ||
|
||
A SliceKeyType for each slice that matches this specification. Nothing | ||
will be yielded if there no slices matched this specification. The entries | ||
in the yielded SliceKeyTypes are guaranteed to be sorted by key names (and | ||
then values, if necessary), ascending. | ||
|
||
<h3 id="is_overall"><code>is_overall</code></h3> | ||
|
||
``` python | ||
is_overall() | ||
``` | ||
|
||
Returns True if this specification represents the overall slice. | ||
|
||
<h3 id="is_slice_applicable"><code>is_slice_applicable</code></h3> | ||
|
||
``` python | ||
is_slice_applicable(slice_key) | ||
``` | ||
|
||
Determines if this slice spec is applicable to a slice of data. | ||
|
||
#### Args: | ||
|
||
* <b>`slice_key`</b>: The slice as a SliceKeyType | ||
|
||
|
||
#### Returns: | ||
|
||
True if the slice_spec is applicable to the given slice, False otherwise. | ||
|
||
|
||
|
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 +1,29 @@ | ||
<div itemscope itemtype="http://developers.google.com/ReferenceObject"> | ||
<meta itemprop="name" content="tfma.constants" /> | ||
<meta itemprop="path" content="Stable" /> | ||
<meta itemprop="property" content="DATA_CENTRIC_MODE"/> | ||
<meta itemprop="property" content="FEATURES_PREDICTIONS_LABELS_KEY"/> | ||
<meta itemprop="property" content="MODEL_CENTRIC_MODE"/> | ||
<meta itemprop="property" content="SLICE_KEYS"/> | ||
<meta itemprop="property" content="SLICE_KEYS_MATERIALIZED"/> | ||
<meta itemprop="property" content="UNKNOWN_EVAL_MODE"/> | ||
</div> | ||
|
||
# Module: tfma.constants | ||
|
||
Constants used in TensorFlow Model Analysis. | ||
|
||
## Other Members | ||
|
||
<h3 id="DATA_CENTRIC_MODE"><code>DATA_CENTRIC_MODE</code></h3> | ||
|
||
<h3 id="FEATURES_PREDICTIONS_LABELS_KEY"><code>FEATURES_PREDICTIONS_LABELS_KEY</code></h3> | ||
|
||
<h3 id="MODEL_CENTRIC_MODE"><code>MODEL_CENTRIC_MODE</code></h3> | ||
|
||
<h3 id="SLICE_KEYS"><code>SLICE_KEYS</code></h3> | ||
|
||
<h3 id="SLICE_KEYS_MATERIALIZED"><code>SLICE_KEYS_MATERIALIZED</code></h3> | ||
|
||
<h3 id="UNKNOWN_EVAL_MODE"><code>UNKNOWN_EVAL_MODE</code></h3> | ||
|
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 +1,20 @@ | ||
<div itemscope itemtype="http://developers.google.com/ReferenceObject"> | ||
<meta itemprop="name" content="tfma.export" /> | ||
<meta itemprop="path" content="Stable" /> | ||
<meta itemprop="property" content="EvalInputReceiverType"/> | ||
</div> | ||
|
||
# Module: tfma.export | ||
|
||
Library for exporting the EvalSavedModel. | ||
|
||
## Functions | ||
|
||
[`build_parsing_eval_input_receiver_fn(...)`](../tfma/export/build_parsing_eval_input_receiver_fn.md): Build a eval_input_receiver_fn expecting fed tf.Examples. | ||
|
||
[`make_export_strategy(...)`](../tfma/export/make_export_strategy.md): Create an ExportStrategy for EvalSavedModel. | ||
|
||
## Other Members | ||
|
||
<h3 id="EvalInputReceiverType"><code>EvalInputReceiverType</code></h3> | ||
|
Oops, something went wrong.