€•;M      Œdocutils.nodes”Œdocument”“”)}”’”}”(Œ
attributes”}”(Œbackrefs”]”Œids”]”Œclasses”]”Œsource”Œ<D:\Mariano\misc\ecg-kit\help\sphinx\source\first_example.rst”Œnames”]”Œdupnames”]”uŒids”}”Œa-first-example”h Œsection”“”)}”’”}”(h}”(h]”Œa first example”ah]”h
]”hah]”h]”uŒtagname”hŒsource”hhhŒ	rawsource”Œ ”Œline”KŒchildren”]”(h Œtitle”“”)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#h*h$hhhh%ŒA first example”h'Kh(]”h ŒText”“”ŒA first example”…”}”’”}”(h%h5Œparent”h-ubah>hubh Œcompound”“”)}”’”}”(h}”(h]”h]”h
]”h]”Œtoctree-wrapper”ah]”uh#h?h$hhhh%h&h'Nh(]”Œsphinx.addnodes”Œtoctree”“”)}”’”}”(h}”(h
]”Œincludefiles”]”Œexamples”aŒnumbered”K Œincludehidden”‰h]”Œ
titlesonly”‰Œglob”‰Œcaption”Nh]”h]”Œmaxdepth”Jÿÿÿÿh>Œfirst_example”h]”Œhidden”ˆŒentries”]”ŒAnother example”hV†”auh#hMh$hh%h&h'Kh(]”h>hBubah>hubh Œ	paragraph”“”)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hhhh%XX  The script ``/examples/first_simple_example.m`` shows the use of the ECGkit
in multimodal-cardiovascular recordings included with this kit in the ``recordings`` folder.
These recordings include arterial blood pressure (ABP), plethysmographic (PPG)
and electrocardiogram (ECG) signals. The following
tasks will be performed in the first example:”h'K	h(]”(h8ŒThe script ”…”}”’”}”(h%ŒThe script ”h>hkubh Œliteral”“”)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#h{h%Œ$``/examples/first_simple_example.m``”h(]”h8Œ /examples/first_simple_example.m”…”}”’”}”(h%h&h>h~ubah>hkubh8Œc shows the use of the ECGkit
in multimodal-cardiovascular recordings included with this kit in the ”…”}”’”}”(h%Œc shows the use of the ECGkit
in multimodal-cardiovascular recordings included with this kit in the ”h>hkubh|)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#h{h%Œ``recordings``”h(]”h8Œ
recordings”…”}”’”}”(h%h&h>h”ubah>hkubh8Œ¸ folder.
These recordings include arterial blood pressure (ABP), plethysmographic (PPG)
and electrocardiogram (ECG) signals. The following
tasks will be performed in the first example:”…”}”’”}”(h%Œ¸ folder.
These recordings include arterial blood pressure (ABP), plethysmographic (PPG)
and electrocardiogram (ECG) signals. The following
tasks will be performed in the first example:”h>hkubeh>hubh Œbullet_list”“”)}”’”}”(h}”(h]”h
]”h]”h]”Œbullet”Œ-”h]”uh#h©h$hhhh%h&h'Kh(]”(h Œ	list_item”“”)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#h·h$hhhh%Œ8:ref:`Heartbeat/QRS detection <QRS_automatic_detection>`”h'Nh(]”hi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hh%hÂh'Kh(]”hLŒpending_xref”“”)}”’”}”(h}”(h]”Œrefwarn”ˆh
]”h]”Œreftype”Œref”Œrefdoc”h`h]”Œrefexplicit”ˆh]”Œ	refdomain”Œstd”Œ	reftarget”Œqrs_automatic_detection”uh#hÎh$hh%hÂh'Kh(]”h Œinline”“”)}”’”}”(h}”(h]”h]”h
]”h]”(Œxref”hßŒstd-ref”eh]”uh#hãh%hÂh(]”h8ŒHeartbeat/QRS detection”…”}”’”}”(h%h&h>hæubah>hÑubah>hÅubah>hºubah>h¬ubh¸)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#h·h$hhhh%Œ8:ref:`ABP/PPG pulse detection <PPG_ABP_pulse_detection>`”h'Nh(]”hi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hh%hÿh'Kh(]”hÏ)}”’”}”(h}”(h]”hÕˆh
]”h]”Œreftype”Œref”hÚh`h]”Œrefexplicit”ˆh]”Œ	refdomain”Œstd”hàŒppg_abp_pulse_detection”uh#hÎh$hh%hÿh'Kh(]”hä)}”’”}”(h}”(h]”h]”h
]”h]”(híj  Œstd-ref”eh]”uh#hãh%hÿh(]”h8ŒABP/PPG pulse detection”…”}”’”}”(h%h&h>j  ubah>j  ubah>j  ubah>h÷ubah>h¬ubh¸)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#h·h$hhhh%Œ7:ref:`ECG wave delineation <ECG_automatic_delineation>`”h'Nh(]”hi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hh%j4  h'Kh(]”hÏ)}”’”}”(h}”(h]”hÕˆh
]”h]”Œreftype”Œref”hÚh`h]”Œrefexplicit”ˆh]”Œ	refdomain”Œstd”hàŒecg_automatic_delineation”uh#hÎh$hh%j4  h'Kh(]”hä)}”’”}”(h}”(h]”h]”h
]”h]”(híjM  Œstd-ref”eh]”uh#hãh%j4  h(]”h8ŒECG wave delineation”…”}”’”}”(h%h&h>jQ  ubah>jA  ubah>j7  ubah>j,  ubah>h¬ubh¸)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#h·h$hhhh%ŒD:ref:`Heartbeat classification <Automatic_Heartbeat_classification>`”h'Nh(]”hi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hh%ji  h'Kh(]”hÏ)}”’”}”(h}”(h]”hÕˆh
]”h]”Œreftype”Œref”hÚh`h]”Œrefexplicit”ˆh]”Œ	refdomain”Œstd”hàŒ"automatic_heartbeat_classification”uh#hÎh$hh%ji  h'Kh(]”hä)}”’”}”(h}”(h]”h]”h
]”h]”(híj‚  Œstd-ref”eh]”uh#hãh%ji  h(]”h8ŒHeartbeat classification”…”}”’”}”(h%h&h>j†  ubah>jv  ubah>jl  ubah>ja  ubah>h¬ubh¸)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#h·h$hhhh%Œ;:ref:`Report generation <Visual_inspection_of_the_signal>`
”h'Nh(]”hi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hh%Œ::ref:`Report generation <Visual_inspection_of_the_signal>`”h'Kh(]”hÏ)}”’”}”(h}”(h]”hÕˆh
]”h]”Œreftype”Œref”hÚh`h]”Œrefexplicit”ˆh]”Œ	refdomain”Œstd”hàŒvisual_inspection_of_the_signal”uh#hÎh$hh%j©  h'Kh(]”hä)}”’”}”(h}”(h]”h]”h
]”h]”(híj¸  Œstd-ref”eh]”uh#hãh%j©  h(]”h8ŒReport generation”…”}”’”}”(h%h&h>j¼  ubah>j¬  ubah>j¡  ubah>j–  ubah>h¬ubeh>hubhi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hhhh%ŒßThe script is prepared to perform visual inspection of the automatic algorithms, with
the ``bGUICorrection`` flag, but it is disabled by default. In the following listing,
you can see a typical output of the example script.”h'Kh(]”(h8ŒZThe script is prepared to perform visual inspection of the automatic algorithms, with
the ”…”}”’”}”(h%ŒZThe script is prepared to perform visual inspection of the automatic algorithms, with
the ”h>jÌ  ubh|)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#h{h%Œ``bGUICorrection``”h(]”h8ŒbGUICorrection”…”}”’”}”(h%h&h>jÝ  ubah>jÌ  ubh8Œs flag, but it is disabled by default. In the following listing,
you can see a typical output of the example script.”…”}”’”}”(h%Œs flag, but it is disabled by default. In the following listing,
you can see a typical output of the example script.”h>jÌ  ubeh>hubh Œliteral_block”“”)}”’”}”(h}”(h]”Œlanguage”Œnone”h
]”h]”Œlinenos”‰Œhighlight_args”}”h]”h]”Œ	xml:space”Œpreserve”uh#jò  h$hhhh%X´  >> first_simple_example()

Description of the process:
 + Recording: \your_path\ecg-kit\recordings\208.hea
 + Task name: QRS_detection

Processing QRS detector gqrs
Processing QRS detector wavedet
No multilead strategy used, instead using the delineation of lead MLII.
Processing QRS detector wqrs

##############
# Work done! #
##############


Results saved in
 + \your_path\ecg-kit\recordings\208_my_experiment_name_QRS_detection.mat”h'Kh(]”h8X´  >> first_simple_example()

Description of the process:
 + Recording: \your_path\ecg-kit\recordings\208.hea
 + Task name: QRS_detection

Processing QRS detector gqrs
Processing QRS detector wavedet
No multilead strategy used, instead using the delineation of lead MLII.
Processing QRS detector wqrs

##############
# Work done! #
##############


Results saved in
 + \your_path\ecg-kit\recordings\208_my_experiment_name_QRS_detection.mat”…”}”’”}”(h%h&h>jõ  ubah>hubhi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hhhh%Œ¿The script starts with the QRS complex detection, producing a result file, which can be
used later by other tasks, or to access results. Then the script follows with the pulse
detection task:”h'K/h(]”h8Œ¿The script starts with the QRS complex detection, producing a result file, which can be
used later by other tasks, or to access results. Then the script follows with the pulse
detection task:”…”}”’”}”(h%j  h>j  ubah>hubjó  )}”’”}”(h}”(h]”jù  Œnone”h
]”h]”jý  ‰jþ  }”h]”h]”j  j  uh#jò  h$hhhh%X  ##############
# Work done! #
##############


Results saved in
 + \your_path\ecg-kit\recordings\208_my_experiment_name_QRS_detection.mat


Description of the process:
 + Recording: \your_path\ecg-kit\recordings\208.hea
 + Task name: PPG_ABP_detector

Could not find any PPG/ABP signal, check the lead description of the recording:
 +  MLII
 +  V1

Requirements not satisfied in \your_path\ecg-kit\recordings\208.hea for task PPG_ABP_detector.

######################
# Nothing to do here #
######################”h'K3h(]”h8X  ##############
# Work done! #
##############


Results saved in
 + \your_path\ecg-kit\recordings\208_my_experiment_name_QRS_detection.mat


Description of the process:
 + Recording: \your_path\ecg-kit\recordings\208.hea
 + Task name: PPG_ABP_detector

Could not find any PPG/ABP signal, check the lead description of the recording:
 +  MLII
 +  V1

Requirements not satisfied in \your_path\ecg-kit\recordings\208.hea for task PPG_ABP_detector.

######################
# Nothing to do here #
######################”…”}”’”}”(h%h&h>j  ubah>hubhi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hhhh%Œ×As the default recording pointed by the script is the 208 from the MIT arrhythmia database, the task
exits without finding any pulsatile signal, such as ABP or PPG. After exiting, it starts with the
delineation task”h'KMh(]”h8Œ×As the default recording pointed by the script is the 208 from the MIT arrhythmia database, the task
exits without finding any pulsatile signal, such as ABP or PPG. After exiting, it starts with the
delineation task”…”}”’”}”(h%j6  h>j.  ubah>hubjó  )}”’”}”(h}”(h]”jù  Œnone”h
]”h]”jý  ‰jþ  }”h]”h]”j  j  uh#jò  h$hhhh%Xf   Description of the process:
 + Recording: \your_path\ecg-kit\recordings\208.hea
 + Task name: ECG_delineation

Processing ECG delineator wavedet
No multilead strategy used, instead using the delineation of lead MLII.

##############
# Work done! #
##############


Results saved in
 + \your_path\ecg-kit\recordings\208_my_experiment_name_ECG_delineation.mat”h'KQh(]”h8Xf   Description of the process:
 + Recording: \your_path\ecg-kit\recordings\208.hea
 + Task name: ECG_delineation

Processing ECG delineator wavedet
No multilead strategy used, instead using the delineation of lead MLII.

##############
# Work done! #
##############


Results saved in
 + \your_path\ecg-kit\recordings\208_my_experiment_name_ECG_delineation.mat”…”}”’”}”(h%h&h>j>  ubah>hubhi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hhhh%X¨  The result produced is exactly the same as the QRS detection task. This can be convenient for backing up
intermediate results and reproducing experiment results. Other interesting aspect to differentiate experiments
is the ``user_string`` property of the ECGwrapper object. Note that the results produced retain the
user string suffix. After that, the example performs heartbeat classification and finally produces a report.”h'Kch(]”(h8ŒßThe result produced is exactly the same as the QRS detection task. This can be convenient for backing up
intermediate results and reproducing experiment results. Other interesting aspect to differentiate experiments
is the ”…”}”’”}”(h%ŒßThe result produced is exactly the same as the QRS detection task. This can be convenient for backing up
intermediate results and reproducing experiment results. Other interesting aspect to differentiate experiments
is the ”h>jP  ubh|)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#h{h%Œ``user_string``”h(]”h8Œuser_string”…”}”’”}”(h%h&h>ja  ubah>jP  ubh8Œº property of the ECGwrapper object. Note that the results produced retain the
user string suffix. After that, the example performs heartbeat classification and finally produces a report.”…”}”’”}”(h%Œº property of the ECGwrapper object. Note that the results produced retain the
user string suffix. After that, the example performs heartbeat classification and finally produces a report.”h>jP  ubeh>hubjó  )}”’”}”(h}”(h]”jù  Œnone”h
]”h]”jý  ‰jþ  }”h]”h]”j  j  uh#jò  h$hhhh%X¨  Description of the process:
 + Recording: \your_path\ecg-kit\recordings\208.hea
 + Task name: ECG_heartbeat_classifier

 + Using gqrs_MLII detections.

15-Apr-2015
Configuration
-------------
+ Recording:  (AHA)
+ Mode: auto (12 clusters, 1 iterations, 75% cluster-presence)

##############
# Work done! #
##############


Results saved in
 + \your_path\ecg-kit\recordings\208_my_experiment_name_ECG_heartbeat_classifier.mat”h'Khh(]”h8X¨  Description of the process:
 + Recording: \your_path\ecg-kit\recordings\208.hea
 + Task name: ECG_heartbeat_classifier

 + Using gqrs_MLII detections.

15-Apr-2015
Configuration
-------------
+ Recording:  (AHA)
+ Mode: auto (12 clusters, 1 iterations, 75% cluster-presence)

##############
# Work done! #
##############


Results saved in
 + \your_path\ecg-kit\recordings\208_my_experiment_name_ECG_heartbeat_classifier.mat”…”}”’”}”(h%h&h>jw  ubah>hubhi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hhhh%Œ`As a result, the report found in ``\your_path\ecg-kit\recordings\208_full.pdf`` looks like this:”h'Kh(]”(h8Œ!As a result, the report found in ”…”}”’”}”(h%Œ!As a result, the report found in ”h>j‰  ubh|)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#h{h%Œ.``\your_path\ecg-kit\recordings\208_full.pdf``”h(]”h8Œ*\your_path\ecg-kit\recordings\208_full.pdf”…”}”’”}”(h%h&h>jš  ubah>j‰  ubh8Œ looks like this:”…”}”’”}”(h%Œ looks like this:”h>j‰  ubeh>hubh Œimage”“”)}”’”}”(h}”(h]”h
]”h]”Œuri”Œ208_full_03.png”Œ
candidates”}”Œ*”j¹  sh]”h]”uh#j¯  h$hhhh%Œ.. image:: 208_full_03.png
”h'K‚h(]”h>hubhi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hhhh%Œ<First in the report you will find an overview of the signal.”h'Kƒh(]”h8Œ<First in the report you will find an overview of the signal.”…”}”’”}”(h%jÊ  h>jÂ  ubah>hubj°  )}”’”}”(h}”(h]”h
]”h]”Œuri”Œ208_full_14.png”jº  }”j¼  jÙ  sh]”h]”uh#j¯  h$hhhh%Œ.. image:: 208_full_14.png
”h'K†h(]”h>hubhi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hhhh%X'  A more detailed view can be found in the last part of the report, you will find the results of the QRS detection, delineation and heartbeat
classification. In the top right of the chart you will find the references for interpreting the results
displayed. For example, QRS detection legend indicates a colour-code for the dotted lines with triangles in the extremes,
placed around the QRS complexes. As recording 208 does not presents much controversy respect QRS detection,
all detections are clustered around each heartbeat, but the legend indicates:”h'K‡h(]”h8X'  A more detailed view can be found in the last part of the report, you will find the results of the QRS detection, delineation and heartbeat
classification. In the top right of the chart you will find the references for interpreting the results
displayed. For example, QRS detection legend indicates a colour-code for the dotted lines with triangles in the extremes,
placed around the QRS complexes. As recording 208 does not presents much controversy respect QRS detection,
all detections are clustered around each heartbeat, but the legend indicates:”…”}”’”}”(h%jè  h>jà  ubah>hubh Œblock_quote”“”)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#jï  h$Nhhh%h&h'Nh(]”hª)}”’”}”(h}”(h]”h
]”h]”h]”h³h´h]”uh#h©h%h&h(]”(h¸)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#h·h%Œ**global*, the wavedet multilead detection.”h(]”hi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hh%j  h'Kh(]”(h Œemphasis”“”)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#j  h%Œ*global*”h(]”h8Œglobal”…”}”’”}”(h%h&h>j  ubah>j  ubh8Œ", the wavedet multilead detection.”…”}”’”}”(h%Œ", the wavedet multilead detection.”h>j  ubeh>j  ubah>jü  ubh¸)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#h·h%Œ@*hb_classifier*, the detection used by the heartbeat classifier.”h(]”hi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hh%j;  h'KŽh(]”(j  )}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#j  h%Œ*hb_classifier*”h(]”h8Œhb_classifier”…”}”’”}”(h%h&h>jH  ubah>j>  ubh8Œ1, the detection used by the heartbeat classifier.”…”}”’”}”(h%Œ1, the detection used by the heartbeat classifier.”h>j>  ubeh>j3  ubah>jü  ubh¸)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#h·h%ŒE*included*, the gold-standard, visually-audited Physionet detections.”h(]”hi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hh%jf  h'Kh(]”(j  )}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#j  h%Œ
*included*”h(]”h8Œincluded”…”}”’”}”(h%h&h>js  ubah>ji  ubh8Œ;, the gold-standard, visually-audited Physionet detections.”…”}”’”}”(h%Œ;, the gold-standard, visually-audited Physionet detections.”h>ji  ubeh>j^  ubah>jü  ubh¸)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#h·h%Œ>*gqrs_MLII*, the detections of *gqrs* algorithm in lead MLII.
”h(]”hi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hh%Œ=*gqrs_MLII*, the detections of *gqrs* algorithm in lead MLII.”h'Kh(]”(j  )}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#j  h%Œ*gqrs_MLII*”h(]”h8Œ	gqrs_MLII”…”}”’”}”(h%h&h>jŸ  ubah>j”  ubh8Œ, the detections of ”…”}”’”}”(h%Œ, the detections of ”h>j”  ubj  )}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#j  h%Œ*gqrs*”h(]”h8Œgqrs”…”}”’”}”(h%h&h>jµ  ubah>j”  ubh8Œ algorithm in lead MLII.”…”}”’”}”(h%Œ algorithm in lead MLII.”h>j”  ubeh>j‰  ubah>jü  ubeh>jò  ubah>hubhi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hhhh%X¥  Above the legend of QRS detections, it is the delineation legend, with a colour-code for identifying each wave.
For example in pink you can see several QRS complexes correctly segmented, but three of them are wrong.
If you pay attention to the extreme widened ventricular beats, they are very underestimated. T-waves in orange,
seems quite correctly measured, and P-waves as you can see are not correctly measured at all.”h'K’h(]”h8X¥  Above the legend of QRS detections, it is the delineation legend, with a colour-code for identifying each wave.
For example in pink you can see several QRS complexes correctly segmented, but three of them are wrong.
If you pay attention to the extreme widened ventricular beats, they are very underestimated. T-waves in orange,
seems quite correctly measured, and P-waves as you can see are not correctly measured at all.”…”}”’”}”(h%jÓ  h>jË  ubah>hubhi)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#hhh$hhhh%Œ‡You can experiment with the ``/examples/second_simple_example.m`` to see how to extend this experiment to a
multiprocessor environment.”h'K˜h(]”(h8ŒYou can experiment with the ”…”}”’”}”(h%ŒYou can experiment with the ”h>jÛ  ubh|)}”’”}”(h}”(h]”h]”h
]”h]”h]”uh#h{h%Œ%``/examples/second_simple_example.m``”h(]”h8Œ!/examples/second_simple_example.m”…”}”’”}”(h%h&h>jì  ubah>jÛ  ubh8ŒF to see how to extend this experiment to a
multiprocessor environment.”…”}”’”}”(h%ŒF to see how to extend this experiment to a
multiprocessor environment.”h>jÛ  ubeh>hubeh>hubsŒautofootnote_refs”]”Œcurrent_source”NŒrefnames”}”Œid_start”KŒtransform_messages”]”Œsettings”Œdocutils.frontend”ŒValues”“”)}”’”}”(Œpep_base_url”Œ https://www.python.org/dev/peps/”Œembed_stylesheet”‰Œexpose_internals”NŒinput_encoding_error_handler”Œstrict”Œdebug”NŒstrip_comments”NŒ_disable_config”NŒpep_references”NŒsource_link”NŒfootnote_backlinks”KŒrfc_references”NŒsyntax_highlight”Œlong”Œstrict_visitor”NŒfile_insertion_enabled”ˆŒ_config_files”]”Œinput_encoding”Œ	utf-8-sig”Œlanguage_code”Œen”Œdump_internals”NŒ_source”hŒwarning_stream”NŒoutput_encoding_error_handler”j  Œstrip_classes”NŒ	datestamp”NŒraw_enabled”KŒ	generator”NŒrecord_dependencies”NŒsectnum_xform”KŒgettext_compact”ˆŒcloak_email_addresses”ˆŒsmart_quotes”‰Œrfc_base_url”Œhttps://tools.ietf.org/html/”Œdocinfo_xform”KŒerror_encoding_error_handler”Œbackslashreplace”Œpep_file_url_template”Œpep-%04d”Œerror_encoding”Œcp850”Œconfig”NŒ
halt_level”KŒdump_settings”NŒdump_transforms”NŒ_destination”NŒauto_id_prefix”Œid”Œtoc_backlinks”Œentry”Œsectsubtitle_xform”‰Œ	id_prefix”h&Œoutput_encoding”Œutf-8”Œ	tab_width”KŒtrim_footnote_reference_space”‰Œexit_status_level”KŒstrip_elements_with_classes”NŒ
source_url”Nh*NŒ	traceback”ˆŒdump_pseudo_xml”NŒreport_level”KŒdoctitle_xform”‰Œenv”NubŒfootnote_refs”}”Œsubstitution_names”}”Œ	nametypes”}”hNsŒsymbol_footnote_refs”]”Œcurrent_line”NŒindirect_targets”]”hhŒsubstitution_defs”}”Œnameids”}”hhsŒsymbol_footnotes”]”h#hŒparse_messages”]”Œrefids”}”Œreporter”Nh%h&Œsymbol_footnote_start”K Œtransformer”NŒ	footnotes”]”Œcitation_refs”}”Œ	citations”]”Œautofootnotes”]”Œautofootnote_start”KŒ
decoration”Nh(]”haub.