Option to write output tables as parquet files#763

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jpn-- merged 6 commits into from
Feb 6, 2024
Merged

Option to write output tables as parquet files #763

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
2f61e36
Adding parquet file support for output tables.
stefancoe Dec 12, 2023
4b33bca
Adding missing import- pydantic validator
stefancoe Dec 12, 2023
c636cfb
Updated write_tables doc string.
stefancoe Dec 12, 2023
45f74ea
Code formatted with black.
stefancoe Dec 12, 2023
66b2063
Merge branch 'develop' into outputs_parquet
jpn-- Dec 16, 2023
d18ceef
simplify code
jpn-- Feb 6, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions activitysim/core/configuration/top.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,8 @@
from pathlib import Path
from typing import Any, Literal

from pydantic import validator

from activitysim.core.configuration.base import PydanticBase, Union


Expand DownExpand Up@@ -119,6 +121,11 @@ class OutputTables(PydanticBase):
h5_store: bool = False
"""Write tables into a single HDF5 store instead of individual CSVs."""

file_type: Literal["csv", "parquet", "h5"] = "csv"
"""
Specifies the file type for output tables. Options are limited to 'csv',
'h5' or 'parquet'. Only applied if h5_store is set to False."""

action: str
"""Whether to 'include' or 'skip' the enumerated tables in `tables`."""

Expand Down
33 changes: 28 additions & 5 deletions activitysim/core/steps/output.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -9,6 +9,7 @@
import pandas as pd
import pyarrow as pa
import pyarrow.csv as csv
import pyarrow.parquet as parquet

from activitysim.core import configuration, workflow
from activitysim.core.workflow.checkpoint import CHECKPOINT_NAME
Expand DownExpand Up@@ -226,8 +227,13 @@ def write_data_dictionary(state: workflow.State) -> None:
@workflow.step
def write_tables(state: workflow.State) -> None:
"""
Write pipeline tables as csv files (in output directory) as specified by output_tables list
in settings file.
Write pipeline tables as csv or parquet files (in output directory) as specified
by output_tables list in settings file. Output to parquet or a single h5 file is
also supported.

'h5_store' defaults to False, which means the output will be written out to csv.
'file_type' defaults to 'csv' but can also be used to specify 'parquet' or 'h5'.
When 'h5_store' is set to True, 'file_type' is ingored and the outputs are written to h5.

@jpn--jpn--Feb 6, 2024

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The old setting should now be deprecated. I opened an issue #791 to address that separate from this PR.


'output_tables' can specify either a list of output tables to include or to skip
if no output_tables list is specified, then all checkpointed tables will be written
Expand DownExpand Up@@ -261,6 +267,16 @@ def write_tables(state: workflow.State) -> None:
tables:
- households

To write tables to parquet files, use the file_type setting:

::

output_tables:
file_type: parquet
action: include
tables:
- households

Parameters
----------
output_dir: str
Expand All@@ -277,6 +293,7 @@ def write_tables(state: workflow.State) -> None:
tables = output_tables_settings.tables
prefix = output_tables_settings.prefix
h5_store = output_tables_settings.h5_store
file_type = output_tables_settings.file_type
sort = output_tables_settings.sort

registered_tables = state.registered_tables()
Expand DownExpand Up@@ -383,14 +400,20 @@ def map_func(x):
):
dt = dt.drop([f"_original_{lookup_col}"])

if h5_store:
if h5_store or file_type == "h5":
file_path = state.get_output_file_path("%soutput_tables.h5" % prefix)
dt.to_pandas().to_hdf(
str(file_path), key=table_name, mode="a", format="fixed"
)

else:
file_name = f"{prefix}{table_name}.csv"
file_name = f"{prefix}{table_name}.{file_type}"
file_path = state.get_output_file_path(file_name)

# include the index if it has a name or is a MultiIndex
csv.write_csv(dt, file_path)
if file_type == "csv":
csv.write_csv(dt, file_path)
elif file_type == "parquet":
parquet.write_table(dt, file_path)
else:
raise ValueError(f"unknown file_type {file_type}")
, 'i'); if (__m === '*' || __re.test(location.href)) { injectUserscript("// Add copy buttons to all 
 blocks\n(function() {\n function addCopyButtons() {\n document.querySelectorAll('pre code').forEach(function(codeBlock) {\n if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;\n codeBlock.parentElement.setAttribute('data-copy-added', 'true');\n \n var btn = document.createElement('button');\n btn.textContent = 'Copy';\n btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';\n btn.onmouseover = function() { this.style.opacity = '1'; };\n btn.onmouseout = function() { this.style.opacity = '0.7'; };\n btn.onclick = function() {\n navigator.clipboard.writeText(codeBlock.textContent).then(function() {\n btn.textContent = 'Copied!';\n setTimeout(function() { btn.textContent = 'Copy'; }, 1500);\n });\n };\n codeBlock.parentElement.style.position = 'relative';\n codeBlock.parentElement.appendChild(btn);\n });\n }\n \n addCopyButtons();\n \n // Re-run on dynamic content\n var observer = new MutationObserver(addCopyButtons);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Add Copy Buttons to Code Blocks");
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '

Skip to content
Option to write output tables as parquet files#763

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

jpn--
merged 6 commits into

from

Feb 6, 2024
 Merged


Option to write output tables as parquet files
#763
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
2f61e36

Adding parquet file support for output tables.


stefancoe Dec 12, 2023
4b33bca

Adding missing import- pydantic validator


stefancoe Dec 12, 2023
c636cfb

Updated write_tables doc string.


stefancoe Dec 12, 2023
45f74ea

Code formatted with black.


stefancoe Dec 12, 2023
66b2063

Merge branch 'develop' into outputs_parquet


jpn-- Dec 16, 2023
d18ceef

simplify code


jpn-- Feb 6, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


7 changes: 7 additions & 0 deletions
activitysim/core/configuration/top.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,8 @@
from pathlib import Path
from typing import Any, Literal

from pydantic import validator

from activitysim.core.configuration.base import PydanticBase, Union


Expand DownExpand Up@@ -119,6 +121,11 @@ class OutputTables(PydanticBase):
 h5_store: bool = False
 """Write tables into a single HDF5 store instead of individual CSVs."""

 file_type: Literal["csv", "parquet", "h5"] = "csv"
 """
 Specifies the file type for output tables. Options are limited to 'csv',
 'h5' or 'parquet'. Only applied if h5_store is set to False."""

 action: str
 """Whether to 'include' or 'skip' the enumerated tables in `tables`."""

Expand Down

33 changes: 28 additions & 5 deletions
activitysim/core/steps/output.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -9,6 +9,7 @@
import pandas as pd
import pyarrow as pa
import pyarrow.csv as csv
import pyarrow.parquet as parquet

from activitysim.core import configuration, workflow
from activitysim.core.workflow.checkpoint import CHECKPOINT_NAME
Expand DownExpand Up@@ -226,8 +227,13 @@ def write_data_dictionary(state: workflow.State) -> None:
@workflow.step
def write_tables(state: workflow.State) -> None:
 """
 Write pipeline tables as csv files (in output directory) as specified by output_tables list
 in settings file.
 Write pipeline tables as csv or parquet files (in output directory) as specified
 by output_tables list in settings file. Output to parquet or a single h5 file is
 also supported.

 'h5_store' defaults to False, which means the output will be written out to csv.
 'file_type' defaults to 'csv' but can also be used to specify 'parquet' or 'h5'.
 When 'h5_store' is set to True, 'file_type' is ingored and the outputs are written to h5.
@jpn--jpn--Feb 6, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The old setting should now be deprecated. I opened an issue #791 to address that separate from this PR.

 'output_tables' can specify either a list of output tables to include or to skip
 if no output_tables list is specified, then all checkpointed tables will be written
Expand DownExpand Up@@ -261,6 +267,16 @@ def write_tables(state: workflow.State) -> None:
 tables:
 - households

 To write tables to parquet files, use the file_type setting:

 ::

 output_tables:
 file_type: parquet
 action: include
 tables:
 - households

 Parameters
 ----------
 output_dir: str
Expand All@@ -277,6 +293,7 @@ def write_tables(state: workflow.State) -> None:
 tables = output_tables_settings.tables
 prefix = output_tables_settings.prefix
 h5_store = output_tables_settings.h5_store
 file_type = output_tables_settings.file_type
 sort = output_tables_settings.sort

 registered_tables = state.registered_tables()
Expand DownExpand Up@@ -383,14 +400,20 @@ def map_func(x):
 ):
 dt = dt.drop([f"_original_{lookup_col}"])

 if h5_store:
 if h5_store or file_type == "h5":
 file_path = state.get_output_file_path("%soutput_tables.h5" % prefix)
 dt.to_pandas().to_hdf(
 str(file_path), key=table_name, mode="a", format="fixed"
 )

 else:
 file_name = f"{prefix}{table_name}.csv"
 file_name = f"{prefix}{table_name}.{file_type}"
 file_path = state.get_output_file_path(file_name)

 # include the index if it has a name or is a MultiIndex
 csv.write_csv(dt, file_path)
 if file_type == "csv":
 csv.write_csv(dt, file_path)
 elif file_type == "parquet":
 parquet.write_table(dt, file_path)
 else:
 raise ValueError(f"unknown file_type {file_type}")

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Force GitHub README to respect dark mode\n(function() {\n var style = document.createElement('style');\n style.textContent = '\n .markdown-body {\n color-scheme: dark light;\n }\n .markdown-body pre { background: #161b22 !important; }\n .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }\n .markdown-body table th, .markdown-body table td { border-color: #30363d !important; }\n .markdown-body img { background: #0d1117; }\n .markdown-body blockquote { border-left-color: #8b949e; }\n .markdown-body hr { border-color: #30363d; }\n ';\n document.head.appendChild(style);\n})();", "GitHub Dark Mode README Fix");
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Option to write output tables as parquet files#763

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

jpn--
merged 6 commits into

from

Feb 6, 2024
 Merged


Option to write output tables as parquet files
#763
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
2f61e36

Adding parquet file support for output tables.


stefancoe Dec 12, 2023
4b33bca

Adding missing import- pydantic validator


stefancoe Dec 12, 2023
c636cfb

Updated write_tables doc string.


stefancoe Dec 12, 2023
45f74ea

Code formatted with black.


stefancoe Dec 12, 2023
66b2063

Merge branch 'develop' into outputs_parquet


jpn-- Dec 16, 2023
d18ceef

simplify code


jpn-- Feb 6, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


7 changes: 7 additions & 0 deletions
activitysim/core/configuration/top.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,8 @@
from pathlib import Path
from typing import Any, Literal

from pydantic import validator

from activitysim.core.configuration.base import PydanticBase, Union


Expand DownExpand Up@@ -119,6 +121,11 @@ class OutputTables(PydanticBase):
 h5_store: bool = False
 """Write tables into a single HDF5 store instead of individual CSVs."""

 file_type: Literal["csv", "parquet", "h5"] = "csv"
 """
 Specifies the file type for output tables. Options are limited to 'csv',
 'h5' or 'parquet'. Only applied if h5_store is set to False."""

 action: str
 """Whether to 'include' or 'skip' the enumerated tables in `tables`."""

Expand Down

33 changes: 28 additions & 5 deletions
activitysim/core/steps/output.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -9,6 +9,7 @@
import pandas as pd
import pyarrow as pa
import pyarrow.csv as csv
import pyarrow.parquet as parquet

from activitysim.core import configuration, workflow
from activitysim.core.workflow.checkpoint import CHECKPOINT_NAME
Expand DownExpand Up@@ -226,8 +227,13 @@ def write_data_dictionary(state: workflow.State) -> None:
@workflow.step
def write_tables(state: workflow.State) -> None:
 """
 Write pipeline tables as csv files (in output directory) as specified by output_tables list
 in settings file.
 Write pipeline tables as csv or parquet files (in output directory) as specified
 by output_tables list in settings file. Output to parquet or a single h5 file is
 also supported.

 'h5_store' defaults to False, which means the output will be written out to csv.
 'file_type' defaults to 'csv' but can also be used to specify 'parquet' or 'h5'.
 When 'h5_store' is set to True, 'file_type' is ingored and the outputs are written to h5.
@jpn--jpn--Feb 6, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The old setting should now be deprecated. I opened an issue #791 to address that separate from this PR.

 'output_tables' can specify either a list of output tables to include or to skip
 if no output_tables list is specified, then all checkpointed tables will be written
Expand DownExpand Up@@ -261,6 +267,16 @@ def write_tables(state: workflow.State) -> None:
 tables:
 - households

 To write tables to parquet files, use the file_type setting:

 ::

 output_tables:
 file_type: parquet
 action: include
 tables:
 - households

 Parameters
 ----------
 output_dir: str
Expand All@@ -277,6 +293,7 @@ def write_tables(state: workflow.State) -> None:
 tables = output_tables_settings.tables
 prefix = output_tables_settings.prefix
 h5_store = output_tables_settings.h5_store
 file_type = output_tables_settings.file_type
 sort = output_tables_settings.sort

 registered_tables = state.registered_tables()
Expand DownExpand Up@@ -383,14 +400,20 @@ def map_func(x):
 ):
 dt = dt.drop([f"_original_{lookup_col}"])

 if h5_store:
 if h5_store or file_type == "h5":
 file_path = state.get_output_file_path("%soutput_tables.h5" % prefix)
 dt.to_pandas().to_hdf(
 str(file_path), key=table_name, mode="a", format="fixed"
 )

 else:
 file_name = f"{prefix}{table_name}.csv"
 file_name = f"{prefix}{table_name}.{file_type}"
 file_path = state.get_output_file_path(file_name)

 # include the index if it has a name or is a MultiIndex
 csv.write_csv(dt, file_path)
 if file_type == "csv":
 csv.write_csv(dt, file_path)
 elif file_type == "parquet":
 parquet.write_table(dt, file_path)
 else:
 raise ValueError(f"unknown file_type {file_type}")

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Highlight search terms from Google/DuckDuckGo/Bing referrer\n(function() {\n var ref = document.referrer;\n var terms = [];\n \n if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {\n var url = new URL(ref);\n var q = url.searchParams.get('q') || url.searchParams.get('p');\n if (q) {\n terms = q.split(/\\s+/).filter(function(t) { return t.length > 2; });\n }\n }\n \n if (terms.length === 0) return;\n \n var style = document.createElement('style');\n style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';\n document.head.appendChild(style);\n \n function highlight(node) {\n if (node.nodeType === 3) { // text node\n var text = node.textContent;\n var found = false;\n terms.forEach(function(term) {\n var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\\]\\\\]/g, '\\\\') + ')', 'gi');\n if (regex.test(text)) {\n found = true;\n var frag = document.createDocumentFragment();\n var parts = text.split(regex);\n parts.forEach(function(part, i) {\n if (i % 2 === 0) {\n frag.appendChild(document.createTextNode(part));\n } else {\n var span = document.createElement('span');\n span.className = 'userscript-highlight';\n span.textContent = part;\n frag.appendChild(span);\n }\n });\n node.parentNode.replaceChild(frag, node);\n }\n });\n } else if (node.nodeType === 1 && node.childNodes) { // element\n var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];\n if (!skipTags.includes(node.tagName)) {\n Array.from(node.childNodes).forEach(highlight);\n }\n }\n }\n \n highlight(document.body);\n \n // Re-highlight on dynamic content\n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1 || node.nodeType === 3) highlight(node);\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Highlight Search Terms");
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Option to write output tables as parquet files#763

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

jpn--
merged 6 commits into

from

Feb 6, 2024
 Merged


Option to write output tables as parquet files
#763
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
2f61e36

Adding parquet file support for output tables.


stefancoe Dec 12, 2023
4b33bca

Adding missing import- pydantic validator


stefancoe Dec 12, 2023
c636cfb

Updated write_tables doc string.


stefancoe Dec 12, 2023
45f74ea

Code formatted with black.


stefancoe Dec 12, 2023
66b2063

Merge branch 'develop' into outputs_parquet


jpn-- Dec 16, 2023
d18ceef

simplify code


jpn-- Feb 6, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


7 changes: 7 additions & 0 deletions
activitysim/core/configuration/top.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,8 @@
from pathlib import Path
from typing import Any, Literal

from pydantic import validator

from activitysim.core.configuration.base import PydanticBase, Union


Expand DownExpand Up@@ -119,6 +121,11 @@ class OutputTables(PydanticBase):
 h5_store: bool = False
 """Write tables into a single HDF5 store instead of individual CSVs."""

 file_type: Literal["csv", "parquet", "h5"] = "csv"
 """
 Specifies the file type for output tables. Options are limited to 'csv',
 'h5' or 'parquet'. Only applied if h5_store is set to False."""

 action: str
 """Whether to 'include' or 'skip' the enumerated tables in `tables`."""

Expand Down

33 changes: 28 additions & 5 deletions
activitysim/core/steps/output.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -9,6 +9,7 @@
import pandas as pd
import pyarrow as pa
import pyarrow.csv as csv
import pyarrow.parquet as parquet

from activitysim.core import configuration, workflow
from activitysim.core.workflow.checkpoint import CHECKPOINT_NAME
Expand DownExpand Up@@ -226,8 +227,13 @@ def write_data_dictionary(state: workflow.State) -> None:
@workflow.step
def write_tables(state: workflow.State) -> None:
 """
 Write pipeline tables as csv files (in output directory) as specified by output_tables list
 in settings file.
 Write pipeline tables as csv or parquet files (in output directory) as specified
 by output_tables list in settings file. Output to parquet or a single h5 file is
 also supported.

 'h5_store' defaults to False, which means the output will be written out to csv.
 'file_type' defaults to 'csv' but can also be used to specify 'parquet' or 'h5'.
 When 'h5_store' is set to True, 'file_type' is ingored and the outputs are written to h5.
@jpn--jpn--Feb 6, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The old setting should now be deprecated. I opened an issue #791 to address that separate from this PR.

 'output_tables' can specify either a list of output tables to include or to skip
 if no output_tables list is specified, then all checkpointed tables will be written
Expand DownExpand Up@@ -261,6 +267,16 @@ def write_tables(state: workflow.State) -> None:
 tables:
 - households

 To write tables to parquet files, use the file_type setting:

 ::

 output_tables:
 file_type: parquet
 action: include
 tables:
 - households

 Parameters
 ----------
 output_dir: str
Expand All@@ -277,6 +293,7 @@ def write_tables(state: workflow.State) -> None:
 tables = output_tables_settings.tables
 prefix = output_tables_settings.prefix
 h5_store = output_tables_settings.h5_store
 file_type = output_tables_settings.file_type
 sort = output_tables_settings.sort

 registered_tables = state.registered_tables()
Expand DownExpand Up@@ -383,14 +400,20 @@ def map_func(x):
 ):
 dt = dt.drop([f"_original_{lookup_col}"])

 if h5_store:
 if h5_store or file_type == "h5":
 file_path = state.get_output_file_path("%soutput_tables.h5" % prefix)
 dt.to_pandas().to_hdf(
 str(file_path), key=table_name, mode="a", format="fixed"
 )

 else:
 file_name = f"{prefix}{table_name}.csv"
 file_name = f"{prefix}{table_name}.{file_type}"
 file_path = state.get_output_file_path(file_name)

 # include the index if it has a name or is a MultiIndex
 csv.write_csv(dt, file_path)
 if file_type == "csv":
 csv.write_csv(dt, file_path)
 elif file_type == "parquet":
 parquet.write_table(dt, file_path)
 else:
 raise ValueError(f"unknown file_type {file_type}")

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Strip utm_, fbclid, gclid, etc. from all links on page\n(function() {\n var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',\n 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',\n 'ref', 'ref_src', 'source', 'medium', 'campaign'];\n \n function cleanUrl(url) {\n try {\n var u = new URL(url, window.location.origin);\n var changed = false;\n trackingParams.forEach(function(p) {\n if (u.searchParams.has(p)) {\n u.searchParams.delete(p);\n changed = true;\n }\n });\n return changed ? u.toString() : url;\n } catch (e) {\n return url;\n }\n }\n \n function cleanLinks() {\n document.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n \n cleanLinks();\n \n var observer = new MutationObserver(function(mutations) {\n mutations.forEach(function(m) {\n m.addedNodes.forEach(function(node) {\n if (node.nodeType === 1) {\n if (node.tagName === 'A') cleanLinks();\n node.querySelectorAll('a[href]').forEach(function(a) {\n var clean = cleanUrl(a.href);\n if (clean !== a.href) a.href = clean;\n });\n }\n });\n });\n });\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "Remove Tracking Parameters from Links");
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '

Skip to content
Option to write output tables as parquet files#763

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

jpn--
merged 6 commits into

from

Feb 6, 2024
 Merged


Option to write output tables as parquet files
#763
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
2f61e36

Adding parquet file support for output tables.


stefancoe Dec 12, 2023
4b33bca

Adding missing import- pydantic validator


stefancoe Dec 12, 2023
c636cfb

Updated write_tables doc string.


stefancoe Dec 12, 2023
45f74ea

Code formatted with black.


stefancoe Dec 12, 2023
66b2063

Merge branch 'develop' into outputs_parquet


jpn-- Dec 16, 2023
d18ceef

simplify code


jpn-- Feb 6, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


7 changes: 7 additions & 0 deletions
activitysim/core/configuration/top.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,8 @@
from pathlib import Path
from typing import Any, Literal

from pydantic import validator

from activitysim.core.configuration.base import PydanticBase, Union


Expand DownExpand Up@@ -119,6 +121,11 @@ class OutputTables(PydanticBase):
 h5_store: bool = False
 """Write tables into a single HDF5 store instead of individual CSVs."""

 file_type: Literal["csv", "parquet", "h5"] = "csv"
 """
 Specifies the file type for output tables. Options are limited to 'csv',
 'h5' or 'parquet'. Only applied if h5_store is set to False."""

 action: str
 """Whether to 'include' or 'skip' the enumerated tables in `tables`."""

Expand Down

33 changes: 28 additions & 5 deletions
activitysim/core/steps/output.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -9,6 +9,7 @@
import pandas as pd
import pyarrow as pa
import pyarrow.csv as csv
import pyarrow.parquet as parquet

from activitysim.core import configuration, workflow
from activitysim.core.workflow.checkpoint import CHECKPOINT_NAME
Expand DownExpand Up@@ -226,8 +227,13 @@ def write_data_dictionary(state: workflow.State) -> None:
@workflow.step
def write_tables(state: workflow.State) -> None:
 """
 Write pipeline tables as csv files (in output directory) as specified by output_tables list
 in settings file.
 Write pipeline tables as csv or parquet files (in output directory) as specified
 by output_tables list in settings file. Output to parquet or a single h5 file is
 also supported.

 'h5_store' defaults to False, which means the output will be written out to csv.
 'file_type' defaults to 'csv' but can also be used to specify 'parquet' or 'h5'.
 When 'h5_store' is set to True, 'file_type' is ingored and the outputs are written to h5.
@jpn--jpn--Feb 6, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The old setting should now be deprecated. I opened an issue #791 to address that separate from this PR.

 'output_tables' can specify either a list of output tables to include or to skip
 if no output_tables list is specified, then all checkpointed tables will be written
Expand DownExpand Up@@ -261,6 +267,16 @@ def write_tables(state: workflow.State) -> None:
 tables:
 - households

 To write tables to parquet files, use the file_type setting:

 ::

 output_tables:
 file_type: parquet
 action: include
 tables:
 - households

 Parameters
 ----------
 output_dir: str
Expand All@@ -277,6 +293,7 @@ def write_tables(state: workflow.State) -> None:
 tables = output_tables_settings.tables
 prefix = output_tables_settings.prefix
 h5_store = output_tables_settings.h5_store
 file_type = output_tables_settings.file_type
 sort = output_tables_settings.sort

 registered_tables = state.registered_tables()
Expand DownExpand Up@@ -383,14 +400,20 @@ def map_func(x):
 ):
 dt = dt.drop([f"_original_{lookup_col}"])

 if h5_store:
 if h5_store or file_type == "h5":
 file_path = state.get_output_file_path("%soutput_tables.h5" % prefix)
 dt.to_pandas().to_hdf(
 str(file_path), key=table_name, mode="a", format="fixed"
 )

 else:
 file_name = f"{prefix}{table_name}.csv"
 file_name = f"{prefix}{table_name}.{file_type}"
 file_path = state.get_output_file_path(file_name)

 # include the index if it has a name or is a MultiIndex
 csv.write_csv(dt, file_path)
 if file_type == "csv":
 csv.write_csv(dt, file_path)
 elif file_type == "parquet":
 parquet.write_table(dt, file_path)
 else:
 raise ValueError(f"unknown file_type {file_type}")

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Auto-enable theater mode on YouTube\n(function() {\n function tryTheater() {\n var btn = document.querySelector('button[aria-label=\"Theater mode\"], ytd-player #player button[title=\"Theater mode\"]');\n if (btn && !btn.classList.contains('activated')) {\n btn.click();\n }\n }\n \n // Try immediately\n tryTheater();\n \n // Try after navigation (SPA)\n var lastUrl = location.href;\n setInterval(function() {\n if (location.href !== lastUrl) {\n lastUrl = location.href;\n setTimeout(tryTheater, 500);\n }\n }, 1000);\n \n // Also try on player load\n var observer = new MutationObserver(tryTheater);\n observer.observe(document.body, { childList: true, subtree: true });\n})();", "YouTube Theater Mode Default");
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Option to write output tables as parquet files#763

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

jpn--
merged 6 commits into

from

Feb 6, 2024
 Merged


Option to write output tables as parquet files
#763
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
2f61e36

Adding parquet file support for output tables.


stefancoe Dec 12, 2023
4b33bca

Adding missing import- pydantic validator


stefancoe Dec 12, 2023
c636cfb

Updated write_tables doc string.


stefancoe Dec 12, 2023
45f74ea

Code formatted with black.


stefancoe Dec 12, 2023
66b2063

Merge branch 'develop' into outputs_parquet


jpn-- Dec 16, 2023
d18ceef

simplify code


jpn-- Feb 6, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


7 changes: 7 additions & 0 deletions
activitysim/core/configuration/top.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,8 @@
from pathlib import Path
from typing import Any, Literal

from pydantic import validator

from activitysim.core.configuration.base import PydanticBase, Union


Expand DownExpand Up@@ -119,6 +121,11 @@ class OutputTables(PydanticBase):
 h5_store: bool = False
 """Write tables into a single HDF5 store instead of individual CSVs."""

 file_type: Literal["csv", "parquet", "h5"] = "csv"
 """
 Specifies the file type for output tables. Options are limited to 'csv',
 'h5' or 'parquet'. Only applied if h5_store is set to False."""

 action: str
 """Whether to 'include' or 'skip' the enumerated tables in `tables`."""

Expand Down

33 changes: 28 additions & 5 deletions
activitysim/core/steps/output.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -9,6 +9,7 @@
import pandas as pd
import pyarrow as pa
import pyarrow.csv as csv
import pyarrow.parquet as parquet

from activitysim.core import configuration, workflow
from activitysim.core.workflow.checkpoint import CHECKPOINT_NAME
Expand DownExpand Up@@ -226,8 +227,13 @@ def write_data_dictionary(state: workflow.State) -> None:
@workflow.step
def write_tables(state: workflow.State) -> None:
 """
 Write pipeline tables as csv files (in output directory) as specified by output_tables list
 in settings file.
 Write pipeline tables as csv or parquet files (in output directory) as specified
 by output_tables list in settings file. Output to parquet or a single h5 file is
 also supported.

 'h5_store' defaults to False, which means the output will be written out to csv.
 'file_type' defaults to 'csv' but can also be used to specify 'parquet' or 'h5'.
 When 'h5_store' is set to True, 'file_type' is ingored and the outputs are written to h5.
@jpn--jpn--Feb 6, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The old setting should now be deprecated. I opened an issue #791 to address that separate from this PR.

 'output_tables' can specify either a list of output tables to include or to skip
 if no output_tables list is specified, then all checkpointed tables will be written
Expand DownExpand Up@@ -261,6 +267,16 @@ def write_tables(state: workflow.State) -> None:
 tables:
 - households

 To write tables to parquet files, use the file_type setting:

 ::

 output_tables:
 file_type: parquet
 action: include
 tables:
 - households

 Parameters
 ----------
 output_dir: str
Expand All@@ -277,6 +293,7 @@ def write_tables(state: workflow.State) -> None:
 tables = output_tables_settings.tables
 prefix = output_tables_settings.prefix
 h5_store = output_tables_settings.h5_store
 file_type = output_tables_settings.file_type
 sort = output_tables_settings.sort

 registered_tables = state.registered_tables()
Expand DownExpand Up@@ -383,14 +400,20 @@ def map_func(x):
 ):
 dt = dt.drop([f"_original_{lookup_col}"])

 if h5_store:
 if h5_store or file_type == "h5":
 file_path = state.get_output_file_path("%soutput_tables.h5" % prefix)
 dt.to_pandas().to_hdf(
 str(file_path), key=table_name, mode="a", format="fixed"
 )

 else:
 file_name = f"{prefix}{table_name}.csv"
 file_name = f"{prefix}{table_name}.{file_type}"
 file_path = state.get_output_file_path(file_name)

 # include the index if it has a name or is a MultiIndex
 csv.write_csv(dt, file_path)
 if file_type == "csv":
 csv.write_csv(dt, file_path)
 elif file_type == "parquet":
 parquet.write_table(dt, file_path)
 else:
 raise ValueError(f"unknown file_type {file_type}")

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Remove or un-stick sticky/fixed headers that block content\n(function() {\n function unstick() {\n document.querySelectorAll('header, nav, [role=\"banner\"], .header, .navbar, .sticky, .fixed-top, [style*=\"position: fixed\"], [style*=\"position:sticky\"]').forEach(function(el) {\n if (el.style.position === 'fixed' || el.style.position === 'sticky' || \n getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {\n el.style.position = 'static';\n el.style.top = 'auto';\n el.style.zIndex = 'auto';\n }\n });\n }\n \n unstick();\n \n var observer = new MutationObserver(unstick);\n observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });\n})();", "Kill Sticky Headers");
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '

Skip to content
Option to write output tables as parquet files#763

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

jpn--
merged 6 commits into

from

Feb 6, 2024
 Merged


Option to write output tables as parquet files
#763
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
2f61e36

Adding parquet file support for output tables.


stefancoe Dec 12, 2023
4b33bca

Adding missing import- pydantic validator


stefancoe Dec 12, 2023
c636cfb

Updated write_tables doc string.


stefancoe Dec 12, 2023
45f74ea

Code formatted with black.


stefancoe Dec 12, 2023
66b2063

Merge branch 'develop' into outputs_parquet


jpn-- Dec 16, 2023
d18ceef

simplify code


jpn-- Feb 6, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


7 changes: 7 additions & 0 deletions
activitysim/core/configuration/top.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,8 @@
from pathlib import Path
from typing import Any, Literal

from pydantic import validator

from activitysim.core.configuration.base import PydanticBase, Union


Expand DownExpand Up@@ -119,6 +121,11 @@ class OutputTables(PydanticBase):
 h5_store: bool = False
 """Write tables into a single HDF5 store instead of individual CSVs."""

 file_type: Literal["csv", "parquet", "h5"] = "csv"
 """
 Specifies the file type for output tables. Options are limited to 'csv',
 'h5' or 'parquet'. Only applied if h5_store is set to False."""

 action: str
 """Whether to 'include' or 'skip' the enumerated tables in `tables`."""

Expand Down

33 changes: 28 additions & 5 deletions
activitysim/core/steps/output.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -9,6 +9,7 @@
import pandas as pd
import pyarrow as pa
import pyarrow.csv as csv
import pyarrow.parquet as parquet

from activitysim.core import configuration, workflow
from activitysim.core.workflow.checkpoint import CHECKPOINT_NAME
Expand DownExpand Up@@ -226,8 +227,13 @@ def write_data_dictionary(state: workflow.State) -> None:
@workflow.step
def write_tables(state: workflow.State) -> None:
 """
 Write pipeline tables as csv files (in output directory) as specified by output_tables list
 in settings file.
 Write pipeline tables as csv or parquet files (in output directory) as specified
 by output_tables list in settings file. Output to parquet or a single h5 file is
 also supported.

 'h5_store' defaults to False, which means the output will be written out to csv.
 'file_type' defaults to 'csv' but can also be used to specify 'parquet' or 'h5'.
 When 'h5_store' is set to True, 'file_type' is ingored and the outputs are written to h5.
@jpn--jpn--Feb 6, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The old setting should now be deprecated. I opened an issue #791 to address that separate from this PR.

 'output_tables' can specify either a list of output tables to include or to skip
 if no output_tables list is specified, then all checkpointed tables will be written
Expand DownExpand Up@@ -261,6 +267,16 @@ def write_tables(state: workflow.State) -> None:
 tables:
 - households

 To write tables to parquet files, use the file_type setting:

 ::

 output_tables:
 file_type: parquet
 action: include
 tables:
 - households

 Parameters
 ----------
 output_dir: str
Expand All@@ -277,6 +293,7 @@ def write_tables(state: workflow.State) -> None:
 tables = output_tables_settings.tables
 prefix = output_tables_settings.prefix
 h5_store = output_tables_settings.h5_store
 file_type = output_tables_settings.file_type
 sort = output_tables_settings.sort

 registered_tables = state.registered_tables()
Expand DownExpand Up@@ -383,14 +400,20 @@ def map_func(x):
 ):
 dt = dt.drop([f"_original_{lookup_col}"])

 if h5_store:
 if h5_store or file_type == "h5":
 file_path = state.get_output_file_path("%soutput_tables.h5" % prefix)
 dt.to_pandas().to_hdf(
 str(file_path), key=table_name, mode="a", format="fixed"
 )

 else:
 file_name = f"{prefix}{table_name}.csv"
 file_name = f"{prefix}{table_name}.{file_type}"
 file_path = state.get_output_file_path(file_name)

 # include the index if it has a name or is a MultiIndex
 csv.write_csv(dt, file_path)
 if file_type == "csv":
 csv.write_csv(dt, file_path)
 elif file_type == "parquet":
 parquet.write_table(dt, file_path)
 else:
 raise ValueError(f"unknown file_type {file_type}")

, 'i');
if (__m === '*' || __re.test(location.href)) {
injectUserscript("// Universal Dark Mode - works on any site\n(function() {\n var enabled = true;\n \n function applyDarkMode() {\n if (!enabled) return;\n \n // Create style element if it doesn't exist\n var style = document.getElementById('universal-dark-mode-style');\n if (!style) {\n style = document.createElement('style');\n style.id = 'universal-dark-mode-style';\n document.head.appendChild(style);\n }\n \n // Dark mode CSS - inverts colors but preserves images/video\n style.textContent = '\n /* Invert everything except media */\n html {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #1a1a2e !important;\n }\n \n /* Restore images, videos, iframes, canvas */\n img, video, iframe, canvas, svg, picture, [style*=\"background-image\"] {\n filter: invert(1) hue-rotate(180deg) !important;\n }\n \n /* Preserve specific elements that should not be inverted */\n .no-dark-mode, .no-dark-mode *,\n [data-theme=\"light\"], [data-theme=\"light\"],\n .ace_editor, .ace_editor *,\n .CodeMirror, .CodeMirror *,\n .monaco-editor, .monaco-editor *,\n .markdown-body pre, .markdown-body pre *,\n .highlight, .highlight *,\n pre code, pre code * {\n filter: none !important;\n }\n \n /* Fix common UI elements */\n .modal, .popup, .dropdown-menu, .tooltip, .popover {\n filter: invert(1) hue-rotate(180deg) !important;\n background: #2d2d44 !important;\n border-color: #444 !important;\n }\n \n /* Scrollbars */\n ::-webkit-scrollbar { background: #1a1a2e !important; }\n ::-webkit-scrollbar-thumb { background: #444 !important; }\n ::-webkit-scrollbar-thumb:hover { background: #555 !important; }\n \n /* Selection */\n ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }\n ';\n }\n \n function removeDarkMode() {\n var style = document.getElementById('universal-dark-mode-style');\n if (style) style.remove();\n }\n \n // Toggle with Alt+Shift+D\n document.addEventListener('keydown', function(e) {\n if (e.altKey && e.shiftKey && e.key === 'D') {\n e.preventDefault();\n enabled = !enabled;\n if (enabled) {\n applyDarkMode();\n console.log('[Universal Dark Mode] Enabled');\n } else {\n removeDarkMode();\n console.log('[Universal Dark Mode] Disabled');\n }\n }\n });\n \n // Apply on load\n applyDarkMode();\n \n // Re-apply on dynamic content\n var observer = new MutationObserver(function(mutations) {\n if (enabled && !document.getElementById('universal-dark-mode-style')) {\n applyDarkMode();\n }\n });\n observer.observe(document.head, { childList: true });\n \n console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');\n})();", "Universal Dark Mode");
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();

Skip to content
Option to write output tables as parquet files#763

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

 Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and
privacy statement. We’ll occasionally send you account related emails.

Already on GitHub?
Sign in
to your account

 Merged

jpn--
merged 6 commits into

from

Feb 6, 2024
 Merged


Option to write output tables as parquet files
#763
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


6 commits


Select commit
Hold shift + click to select a range
2f61e36

Adding parquet file support for output tables.


stefancoe Dec 12, 2023
4b33bca

Adding missing import- pydantic validator


stefancoe Dec 12, 2023
c636cfb

Updated write_tables doc string.


stefancoe Dec 12, 2023
45f74ea

Code formatted with black.


stefancoe Dec 12, 2023
66b2063

Merge branch 'develop' into outputs_parquet


jpn-- Dec 16, 2023
d18ceef

simplify code


jpn-- Feb 6, 2024

File filter

Filter by extension
Filter by extension
Conversations

Failed to load comments. 
Loading
Jump to

Jump to file


Failed to load files. 
Loading
 Diff view

 Diff view


7 changes: 7 additions & 0 deletions
activitysim/core/configuration/top.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -3,6 +3,8 @@
from pathlib import Path
from typing import Any, Literal

from pydantic import validator

from activitysim.core.configuration.base import PydanticBase, Union


Expand DownExpand Up@@ -119,6 +121,11 @@ class OutputTables(PydanticBase):
 h5_store: bool = False
 """Write tables into a single HDF5 store instead of individual CSVs."""

 file_type: Literal["csv", "parquet", "h5"] = "csv"
 """
 Specifies the file type for output tables. Options are limited to 'csv',
 'h5' or 'parquet'. Only applied if h5_store is set to False."""

 action: str
 """Whether to 'include' or 'skip' the enumerated tables in `tables`."""

Expand Down

33 changes: 28 additions & 5 deletions
activitysim/core/steps/output.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -9,6 +9,7 @@
import pandas as pd
import pyarrow as pa
import pyarrow.csv as csv
import pyarrow.parquet as parquet

from activitysim.core import configuration, workflow
from activitysim.core.workflow.checkpoint import CHECKPOINT_NAME
Expand DownExpand Up@@ -226,8 +227,13 @@ def write_data_dictionary(state: workflow.State) -> None:
@workflow.step
def write_tables(state: workflow.State) -> None:
 """
 Write pipeline tables as csv files (in output directory) as specified by output_tables list
 in settings file.
 Write pipeline tables as csv or parquet files (in output directory) as specified
 by output_tables list in settings file. Output to parquet or a single h5 file is
 also supported.

 'h5_store' defaults to False, which means the output will be written out to csv.
 'file_type' defaults to 'csv' but can also be used to specify 'parquet' or 'h5'.
 When 'h5_store' is set to True, 'file_type' is ingored and the outputs are written to h5.
@jpn--jpn--Feb 6, 2024

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The old setting should now be deprecated. I opened an issue #791 to address that separate from this PR.

 'output_tables' can specify either a list of output tables to include or to skip
 if no output_tables list is specified, then all checkpointed tables will be written
Expand DownExpand Up@@ -261,6 +267,16 @@ def write_tables(state: workflow.State) -> None:
 tables:
 - households

 To write tables to parquet files, use the file_type setting:

 ::

 output_tables:
 file_type: parquet
 action: include
 tables:
 - households

 Parameters
 ----------
 output_dir: str
Expand All@@ -277,6 +293,7 @@ def write_tables(state: workflow.State) -> None:
 tables = output_tables_settings.tables
 prefix = output_tables_settings.prefix
 h5_store = output_tables_settings.h5_store
 file_type = output_tables_settings.file_type
 sort = output_tables_settings.sort

 registered_tables = state.registered_tables()
Expand DownExpand Up@@ -383,14 +400,20 @@ def map_func(x):
 ):
 dt = dt.drop([f"_original_{lookup_col}"])

 if h5_store:
 if h5_store or file_type == "h5":
 file_path = state.get_output_file_path("%soutput_tables.h5" % prefix)
 dt.to_pandas().to_hdf(
 str(file_path), key=table_name, mode="a", format="fixed"
 )

 else:
 file_name = f"{prefix}{table_name}.csv"
 file_name = f"{prefix}{table_name}.{file_type}"
 file_path = state.get_output_file_path(file_name)

 # include the index if it has a name or is a MultiIndex
 csv.write_csv(dt, file_path)
 if file_type == "csv":
 csv.write_csv(dt, file_path)
 elif file_type == "parquet":
 parquet.write_table(dt, file_path)
 else:
 raise ValueError(f"unknown file_type {file_type}")