parquet pipeline#649

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

Closed
jpn-- wants to merge 1 commit into from
Closed

parquet pipeline #649

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
98 changes: 76 additions & 22 deletions activitysim/core/pipeline.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -4,6 +4,7 @@
import logging
import os
from builtins import map, next, object
from pathlib import Path

import pandas as pd
from orca import orca
Expand DownExpand Up@@ -37,7 +38,7 @@ class Pipeline(object):
def __init__(self):
self.init_state()

def init_state(self):
def init_state(self, pipeline_file_format="parquet"):

# most recent checkpoint
self.last_checkpoint = {}
Expand DownExpand Up@@ -72,7 +73,7 @@ def is_open():
def is_readonly():
if is_open():
store = get_pipeline_store()
if store and store._mode == "r":
if store and not isinstance(store, Path) and store._mode == "r":
return True
return False

Expand All@@ -99,7 +100,11 @@ def close_open_files():

def open_pipeline_store(overwrite=False, mode="a"):
"""
Open the pipeline checkpoint store
Open the pipeline checkpoint store.

If the pipeline_file_name setting ends in ".h5", then the pandas
HDFStore file format is used, otherwise pipeline files are stored
as parquet files organized in regular file system directories.

@dhensledhensleFeb 25, 2023

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

I assume documentation on this setting will to be addressed in the other Pydantic task?


Parameters
----------
Expand All@@ -125,23 +130,36 @@ def open_pipeline_store(overwrite=False, mode="a"):
inject.get_injectable("pipeline_file_name")
)

if overwrite:
try:
if os.path.isfile(pipeline_file_path):
logger.debug("removing pipeline store: %s" % pipeline_file_path)
os.unlink(pipeline_file_path)
except Exception as e:
print(e)
logger.warning("Error removing %s: %s" % (pipeline_file_path, e))
if pipeline_file_path.endswith(".h5"):

if overwrite:
try:
if os.path.isfile(pipeline_file_path):
logger.debug("removing pipeline store: %s" % pipeline_file_path)
os.unlink(pipeline_file_path)
except Exception as e:
print(e)
logger.warning("Error removing %s: %s" % (pipeline_file_path, e))

_PIPELINE.pipeline_store = pd.HDFStore(pipeline_file_path, mode=mode)
_PIPELINE.pipeline_store = pd.HDFStore(pipeline_file_path, mode=mode)

else:
_PIPELINE.pipeline_store = Path(pipeline_file_path)

logger.debug(f"opened pipeline_store {pipeline_file_path}")


def get_pipeline_store():
"""
Return the open pipeline hdf5 checkpoint store or return None if it not been opened
Get the pipeline store.

If the pipeline filename ends in ".h5" then the legacy HDF5 pipeline
is used, otherwise the faster parquet format is used, and the value
returned here is just the path to the pipeline directory.

Returns
-------
pd.HDFStore or Path
"""
return _PIPELINE.pipeline_store

Expand DownExpand Up@@ -181,7 +199,12 @@ def read_df(table_name, checkpoint_name=None):
"""

store = get_pipeline_store()
df = store[pipeline_table_key(table_name, checkpoint_name)]
if isinstance(store, Path):
df = pd.read_parquet(
store.joinpath(table_name, f"{checkpoint_name}.parquet"),
)
else:
df = store[pipeline_table_key(table_name, checkpoint_name)]

return df

Expand All@@ -193,7 +216,11 @@ def write_df(df, table_name, checkpoint_name=None):
We store multiple versions of all simulation tables, for every checkpoint in which they change,
so we need to know both the table_name and the checkpoint_name to label the saved table

The only exception is the checkpoints dataframe, which just has a table_name
The only exception is the checkpoints dataframe, which just has a table_name,
although when using the parquet storage format this file is stored as "None.parquet"
to maintain a simple consistent file directory structure.

If the

@dhensledhensleFeb 25, 2023

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

Looks like unfinished thought here...


Parameters
----------
Expand All@@ -209,10 +236,28 @@ def write_df(df, table_name, checkpoint_name=None):
df.columns = df.columns.astype(str)

store = get_pipeline_store()

store[pipeline_table_key(table_name, checkpoint_name)] = df

store.flush()
if isinstance(store, Path):
store.joinpath(table_name).mkdir(parents=True, exist_ok=True)
df.to_parquet(store.joinpath(table_name, f"{checkpoint_name}.parquet"))
else:
complib = config.setting("pipeline_complib", None)

@dhensledhensleFeb 25, 2023

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

Another setting to not get lost in the Pydantic task.

if complib is None or len(df.columns) == 0:
# tables with no columns can't be compressed successfully, so to
# avoid them getting just lost and dropped they are instead written
# in fixed format with no compression, which should be just fine
# since they have no data anyhow.
store.put(
pipeline_table_key(table_name, checkpoint_name),
df,
)
else:
store.put(
pipeline_table_key(table_name, checkpoint_name),
df,
"table",
complib=complib,
)
store.flush()


def rewrap(table_name, df=None):
Expand DownExpand Up@@ -615,7 +660,8 @@ def close_pipeline():

close_open_files()

_PIPELINE.pipeline_store.close()
if not isinstance(_PIPELINE.pipeline_store, Path):
_PIPELINE.pipeline_store.close()

_PIPELINE.init_state()

Expand DownExpand Up@@ -789,12 +835,20 @@ def get_checkpoints():
store = get_pipeline_store()

if store is not None:
df = store[CHECKPOINT_TABLE_NAME]
if isinstance(store, Path):
df = pd.read_parquet(store.joinpath(CHECKPOINT_TABLE_NAME, "None.parquet"))
else:
df = store[CHECKPOINT_TABLE_NAME]
else:
pipeline_file_path = config.pipeline_file_path(
orca.get_injectable("pipeline_file_name")
)
df = pd.read_hdf(pipeline_file_path, CHECKPOINT_TABLE_NAME)
if pipeline_file_path.endswith(".h5"):
df = pd.read_hdf(pipeline_file_path, CHECKPOINT_TABLE_NAME)
else:
df = pd.read_parquet(
Path(pipeline_file_path).joinpath(CHECKPOINT_TABLE_NAME, "None.parquet")
)

# non-table columns first (column order in df is random because created from a dict)
table_names = [name for name in df.columns.values if name not in NON_TABLE_COLUMNS]
Expand Down
, '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
parquet pipeline#649

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

 Closed

jpn--
wants to merge
1
commit into

from

 Closed


parquet pipeline
#649
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


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


98 changes: 76 additions & 22 deletions
activitysim/core/pipeline.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,6 +4,7 @@
import logging
import os
from builtins import map, next, object
from pathlib import Path

import pandas as pd
from orca import orca
Expand DownExpand Up@@ -37,7 +38,7 @@ class Pipeline(object):
 def __init__(self):
 self.init_state()

 def init_state(self):
 def init_state(self, pipeline_file_format="parquet"):

 # most recent checkpoint
 self.last_checkpoint = {}
Expand DownExpand Up@@ -72,7 +73,7 @@ def is_open():
def is_readonly():
 if is_open():
 store = get_pipeline_store()
 if store and store._mode == "r":
 if store and not isinstance(store, Path) and store._mode == "r":
 return True
 return False

Expand All@@ -99,7 +100,11 @@ def close_open_files():

def open_pipeline_store(overwrite=False, mode="a"):
 """
 Open the pipeline checkpoint store
 Open the pipeline checkpoint store.

 If the pipeline_file_name setting ends in ".h5", then the pandas
 HDFStore file format is used, otherwise pipeline files are stored
 as parquet files organized in regular file system directories.
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

I assume documentation on this setting will to be addressed in the other Pydantic task?

 Parameters
 ----------
Expand All@@ -125,23 +130,36 @@ def open_pipeline_store(overwrite=False, mode="a"):
 inject.get_injectable("pipeline_file_name")
 )

 if overwrite:
 try:
 if os.path.isfile(pipeline_file_path):
 logger.debug("removing pipeline store: %s" % pipeline_file_path)
 os.unlink(pipeline_file_path)
 except Exception as e:
 print(e)
 logger.warning("Error removing %s: %s" % (pipeline_file_path, e))
 if pipeline_file_path.endswith(".h5"):

 if overwrite:
 try:
 if os.path.isfile(pipeline_file_path):
 logger.debug("removing pipeline store: %s" % pipeline_file_path)
 os.unlink(pipeline_file_path)
 except Exception as e:
 print(e)
 logger.warning("Error removing %s: %s" % (pipeline_file_path, e))

 _PIPELINE.pipeline_store = pd.HDFStore(pipeline_file_path, mode=mode)
 _PIPELINE.pipeline_store = pd.HDFStore(pipeline_file_path, mode=mode)

 else:
 _PIPELINE.pipeline_store = Path(pipeline_file_path)

 logger.debug(f"opened pipeline_store {pipeline_file_path}")


def get_pipeline_store():
 """
 Return the open pipeline hdf5 checkpoint store or return None if it not been opened
 Get the pipeline store.

 If the pipeline filename ends in ".h5" then the legacy HDF5 pipeline
 is used, otherwise the faster parquet format is used, and the value
 returned here is just the path to the pipeline directory.

 Returns
 -------
 pd.HDFStore or Path
 """
 return _PIPELINE.pipeline_store

Expand DownExpand Up@@ -181,7 +199,12 @@ def read_df(table_name, checkpoint_name=None):
 """

 store = get_pipeline_store()
 df = store[pipeline_table_key(table_name, checkpoint_name)]
 if isinstance(store, Path):
 df = pd.read_parquet(
 store.joinpath(table_name, f"{checkpoint_name}.parquet"),
 )
 else:
 df = store[pipeline_table_key(table_name, checkpoint_name)]

 return df

Expand All@@ -193,7 +216,11 @@ def write_df(df, table_name, checkpoint_name=None):
 We store multiple versions of all simulation tables, for every checkpoint in which they change,
 so we need to know both the table_name and the checkpoint_name to label the saved table

 The only exception is the checkpoints dataframe, which just has a table_name
 The only exception is the checkpoints dataframe, which just has a table_name,
 although when using the parquet storage format this file is stored as "None.parquet"
 to maintain a simple consistent file directory structure.

 If the
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Looks like unfinished thought here...

 Parameters
 ----------
Expand All@@ -209,10 +236,28 @@ def write_df(df, table_name, checkpoint_name=None):
 df.columns = df.columns.astype(str)

 store = get_pipeline_store()

 store[pipeline_table_key(table_name, checkpoint_name)] = df

 store.flush()
 if isinstance(store, Path):
 store.joinpath(table_name).mkdir(parents=True, exist_ok=True)
 df.to_parquet(store.joinpath(table_name, f"{checkpoint_name}.parquet"))
 else:
 complib = config.setting("pipeline_complib", None)
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Another setting to not get lost in the Pydantic task.
 if complib is None or len(df.columns) == 0:
 # tables with no columns can't be compressed successfully, so to
 # avoid them getting just lost and dropped they are instead written
 # in fixed format with no compression, which should be just fine
 # since they have no data anyhow.
 store.put(
 pipeline_table_key(table_name, checkpoint_name),
 df,
 )
 else:
 store.put(
 pipeline_table_key(table_name, checkpoint_name),
 df,
 "table",
 complib=complib,
 )
 store.flush()


def rewrap(table_name, df=None):
Expand DownExpand Up@@ -615,7 +660,8 @@ def close_pipeline():

 close_open_files()

 _PIPELINE.pipeline_store.close()
 if not isinstance(_PIPELINE.pipeline_store, Path):
 _PIPELINE.pipeline_store.close()

 _PIPELINE.init_state()

Expand DownExpand Up@@ -789,12 +835,20 @@ def get_checkpoints():
 store = get_pipeline_store()

 if store is not None:
 df = store[CHECKPOINT_TABLE_NAME]
 if isinstance(store, Path):
 df = pd.read_parquet(store.joinpath(CHECKPOINT_TABLE_NAME, "None.parquet"))
 else:
 df = store[CHECKPOINT_TABLE_NAME]
 else:
 pipeline_file_path = config.pipeline_file_path(
 orca.get_injectable("pipeline_file_name")
 )
 df = pd.read_hdf(pipeline_file_path, CHECKPOINT_TABLE_NAME)
 if pipeline_file_path.endswith(".h5"):
 df = pd.read_hdf(pipeline_file_path, CHECKPOINT_TABLE_NAME)
 else:
 df = pd.read_parquet(
 Path(pipeline_file_path).joinpath(CHECKPOINT_TABLE_NAME, "None.parquet")
 )

 # non-table columns first (column order in df is random because created from a dict)
 table_names = [name for name in df.columns.values if name not in NON_TABLE_COLUMNS]
Expand Down

, '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
parquet pipeline#649

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

 Closed

jpn--
wants to merge
1
commit into

from

 Closed


parquet pipeline
#649
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


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


98 changes: 76 additions & 22 deletions
activitysim/core/pipeline.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,6 +4,7 @@
import logging
import os
from builtins import map, next, object
from pathlib import Path

import pandas as pd
from orca import orca
Expand DownExpand Up@@ -37,7 +38,7 @@ class Pipeline(object):
 def __init__(self):
 self.init_state()

 def init_state(self):
 def init_state(self, pipeline_file_format="parquet"):

 # most recent checkpoint
 self.last_checkpoint = {}
Expand DownExpand Up@@ -72,7 +73,7 @@ def is_open():
def is_readonly():
 if is_open():
 store = get_pipeline_store()
 if store and store._mode == "r":
 if store and not isinstance(store, Path) and store._mode == "r":
 return True
 return False

Expand All@@ -99,7 +100,11 @@ def close_open_files():

def open_pipeline_store(overwrite=False, mode="a"):
 """
 Open the pipeline checkpoint store
 Open the pipeline checkpoint store.

 If the pipeline_file_name setting ends in ".h5", then the pandas
 HDFStore file format is used, otherwise pipeline files are stored
 as parquet files organized in regular file system directories.
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

I assume documentation on this setting will to be addressed in the other Pydantic task?

 Parameters
 ----------
Expand All@@ -125,23 +130,36 @@ def open_pipeline_store(overwrite=False, mode="a"):
 inject.get_injectable("pipeline_file_name")
 )

 if overwrite:
 try:
 if os.path.isfile(pipeline_file_path):
 logger.debug("removing pipeline store: %s" % pipeline_file_path)
 os.unlink(pipeline_file_path)
 except Exception as e:
 print(e)
 logger.warning("Error removing %s: %s" % (pipeline_file_path, e))
 if pipeline_file_path.endswith(".h5"):

 if overwrite:
 try:
 if os.path.isfile(pipeline_file_path):
 logger.debug("removing pipeline store: %s" % pipeline_file_path)
 os.unlink(pipeline_file_path)
 except Exception as e:
 print(e)
 logger.warning("Error removing %s: %s" % (pipeline_file_path, e))

 _PIPELINE.pipeline_store = pd.HDFStore(pipeline_file_path, mode=mode)
 _PIPELINE.pipeline_store = pd.HDFStore(pipeline_file_path, mode=mode)

 else:
 _PIPELINE.pipeline_store = Path(pipeline_file_path)

 logger.debug(f"opened pipeline_store {pipeline_file_path}")


def get_pipeline_store():
 """
 Return the open pipeline hdf5 checkpoint store or return None if it not been opened
 Get the pipeline store.

 If the pipeline filename ends in ".h5" then the legacy HDF5 pipeline
 is used, otherwise the faster parquet format is used, and the value
 returned here is just the path to the pipeline directory.

 Returns
 -------
 pd.HDFStore or Path
 """
 return _PIPELINE.pipeline_store

Expand DownExpand Up@@ -181,7 +199,12 @@ def read_df(table_name, checkpoint_name=None):
 """

 store = get_pipeline_store()
 df = store[pipeline_table_key(table_name, checkpoint_name)]
 if isinstance(store, Path):
 df = pd.read_parquet(
 store.joinpath(table_name, f"{checkpoint_name}.parquet"),
 )
 else:
 df = store[pipeline_table_key(table_name, checkpoint_name)]

 return df

Expand All@@ -193,7 +216,11 @@ def write_df(df, table_name, checkpoint_name=None):
 We store multiple versions of all simulation tables, for every checkpoint in which they change,
 so we need to know both the table_name and the checkpoint_name to label the saved table

 The only exception is the checkpoints dataframe, which just has a table_name
 The only exception is the checkpoints dataframe, which just has a table_name,
 although when using the parquet storage format this file is stored as "None.parquet"
 to maintain a simple consistent file directory structure.

 If the
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Looks like unfinished thought here...

 Parameters
 ----------
Expand All@@ -209,10 +236,28 @@ def write_df(df, table_name, checkpoint_name=None):
 df.columns = df.columns.astype(str)

 store = get_pipeline_store()

 store[pipeline_table_key(table_name, checkpoint_name)] = df

 store.flush()
 if isinstance(store, Path):
 store.joinpath(table_name).mkdir(parents=True, exist_ok=True)
 df.to_parquet(store.joinpath(table_name, f"{checkpoint_name}.parquet"))
 else:
 complib = config.setting("pipeline_complib", None)
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Another setting to not get lost in the Pydantic task.
 if complib is None or len(df.columns) == 0:
 # tables with no columns can't be compressed successfully, so to
 # avoid them getting just lost and dropped they are instead written
 # in fixed format with no compression, which should be just fine
 # since they have no data anyhow.
 store.put(
 pipeline_table_key(table_name, checkpoint_name),
 df,
 )
 else:
 store.put(
 pipeline_table_key(table_name, checkpoint_name),
 df,
 "table",
 complib=complib,
 )
 store.flush()


def rewrap(table_name, df=None):
Expand DownExpand Up@@ -615,7 +660,8 @@ def close_pipeline():

 close_open_files()

 _PIPELINE.pipeline_store.close()
 if not isinstance(_PIPELINE.pipeline_store, Path):
 _PIPELINE.pipeline_store.close()

 _PIPELINE.init_state()

Expand DownExpand Up@@ -789,12 +835,20 @@ def get_checkpoints():
 store = get_pipeline_store()

 if store is not None:
 df = store[CHECKPOINT_TABLE_NAME]
 if isinstance(store, Path):
 df = pd.read_parquet(store.joinpath(CHECKPOINT_TABLE_NAME, "None.parquet"))
 else:
 df = store[CHECKPOINT_TABLE_NAME]
 else:
 pipeline_file_path = config.pipeline_file_path(
 orca.get_injectable("pipeline_file_name")
 )
 df = pd.read_hdf(pipeline_file_path, CHECKPOINT_TABLE_NAME)
 if pipeline_file_path.endswith(".h5"):
 df = pd.read_hdf(pipeline_file_path, CHECKPOINT_TABLE_NAME)
 else:
 df = pd.read_parquet(
 Path(pipeline_file_path).joinpath(CHECKPOINT_TABLE_NAME, "None.parquet")
 )

 # non-table columns first (column order in df is random because created from a dict)
 table_names = [name for name in df.columns.values if name not in NON_TABLE_COLUMNS]
Expand Down

, '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
parquet pipeline#649

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

 Closed

jpn--
wants to merge
1
commit into

from

 Closed


parquet pipeline
#649
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


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


98 changes: 76 additions & 22 deletions
activitysim/core/pipeline.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,6 +4,7 @@
import logging
import os
from builtins import map, next, object
from pathlib import Path

import pandas as pd
from orca import orca
Expand DownExpand Up@@ -37,7 +38,7 @@ class Pipeline(object):
 def __init__(self):
 self.init_state()

 def init_state(self):
 def init_state(self, pipeline_file_format="parquet"):

 # most recent checkpoint
 self.last_checkpoint = {}
Expand DownExpand Up@@ -72,7 +73,7 @@ def is_open():
def is_readonly():
 if is_open():
 store = get_pipeline_store()
 if store and store._mode == "r":
 if store and not isinstance(store, Path) and store._mode == "r":
 return True
 return False

Expand All@@ -99,7 +100,11 @@ def close_open_files():

def open_pipeline_store(overwrite=False, mode="a"):
 """
 Open the pipeline checkpoint store
 Open the pipeline checkpoint store.

 If the pipeline_file_name setting ends in ".h5", then the pandas
 HDFStore file format is used, otherwise pipeline files are stored
 as parquet files organized in regular file system directories.
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

I assume documentation on this setting will to be addressed in the other Pydantic task?

 Parameters
 ----------
Expand All@@ -125,23 +130,36 @@ def open_pipeline_store(overwrite=False, mode="a"):
 inject.get_injectable("pipeline_file_name")
 )

 if overwrite:
 try:
 if os.path.isfile(pipeline_file_path):
 logger.debug("removing pipeline store: %s" % pipeline_file_path)
 os.unlink(pipeline_file_path)
 except Exception as e:
 print(e)
 logger.warning("Error removing %s: %s" % (pipeline_file_path, e))
 if pipeline_file_path.endswith(".h5"):

 if overwrite:
 try:
 if os.path.isfile(pipeline_file_path):
 logger.debug("removing pipeline store: %s" % pipeline_file_path)
 os.unlink(pipeline_file_path)
 except Exception as e:
 print(e)
 logger.warning("Error removing %s: %s" % (pipeline_file_path, e))

 _PIPELINE.pipeline_store = pd.HDFStore(pipeline_file_path, mode=mode)
 _PIPELINE.pipeline_store = pd.HDFStore(pipeline_file_path, mode=mode)

 else:
 _PIPELINE.pipeline_store = Path(pipeline_file_path)

 logger.debug(f"opened pipeline_store {pipeline_file_path}")


def get_pipeline_store():
 """
 Return the open pipeline hdf5 checkpoint store or return None if it not been opened
 Get the pipeline store.

 If the pipeline filename ends in ".h5" then the legacy HDF5 pipeline
 is used, otherwise the faster parquet format is used, and the value
 returned here is just the path to the pipeline directory.

 Returns
 -------
 pd.HDFStore or Path
 """
 return _PIPELINE.pipeline_store

Expand DownExpand Up@@ -181,7 +199,12 @@ def read_df(table_name, checkpoint_name=None):
 """

 store = get_pipeline_store()
 df = store[pipeline_table_key(table_name, checkpoint_name)]
 if isinstance(store, Path):
 df = pd.read_parquet(
 store.joinpath(table_name, f"{checkpoint_name}.parquet"),
 )
 else:
 df = store[pipeline_table_key(table_name, checkpoint_name)]

 return df

Expand All@@ -193,7 +216,11 @@ def write_df(df, table_name, checkpoint_name=None):
 We store multiple versions of all simulation tables, for every checkpoint in which they change,
 so we need to know both the table_name and the checkpoint_name to label the saved table

 The only exception is the checkpoints dataframe, which just has a table_name
 The only exception is the checkpoints dataframe, which just has a table_name,
 although when using the parquet storage format this file is stored as "None.parquet"
 to maintain a simple consistent file directory structure.

 If the
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Looks like unfinished thought here...

 Parameters
 ----------
Expand All@@ -209,10 +236,28 @@ def write_df(df, table_name, checkpoint_name=None):
 df.columns = df.columns.astype(str)

 store = get_pipeline_store()

 store[pipeline_table_key(table_name, checkpoint_name)] = df

 store.flush()
 if isinstance(store, Path):
 store.joinpath(table_name).mkdir(parents=True, exist_ok=True)
 df.to_parquet(store.joinpath(table_name, f"{checkpoint_name}.parquet"))
 else:
 complib = config.setting("pipeline_complib", None)
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Another setting to not get lost in the Pydantic task.
 if complib is None or len(df.columns) == 0:
 # tables with no columns can't be compressed successfully, so to
 # avoid them getting just lost and dropped they are instead written
 # in fixed format with no compression, which should be just fine
 # since they have no data anyhow.
 store.put(
 pipeline_table_key(table_name, checkpoint_name),
 df,
 )
 else:
 store.put(
 pipeline_table_key(table_name, checkpoint_name),
 df,
 "table",
 complib=complib,
 )
 store.flush()


def rewrap(table_name, df=None):
Expand DownExpand Up@@ -615,7 +660,8 @@ def close_pipeline():

 close_open_files()

 _PIPELINE.pipeline_store.close()
 if not isinstance(_PIPELINE.pipeline_store, Path):
 _PIPELINE.pipeline_store.close()

 _PIPELINE.init_state()

Expand DownExpand Up@@ -789,12 +835,20 @@ def get_checkpoints():
 store = get_pipeline_store()

 if store is not None:
 df = store[CHECKPOINT_TABLE_NAME]
 if isinstance(store, Path):
 df = pd.read_parquet(store.joinpath(CHECKPOINT_TABLE_NAME, "None.parquet"))
 else:
 df = store[CHECKPOINT_TABLE_NAME]
 else:
 pipeline_file_path = config.pipeline_file_path(
 orca.get_injectable("pipeline_file_name")
 )
 df = pd.read_hdf(pipeline_file_path, CHECKPOINT_TABLE_NAME)
 if pipeline_file_path.endswith(".h5"):
 df = pd.read_hdf(pipeline_file_path, CHECKPOINT_TABLE_NAME)
 else:
 df = pd.read_parquet(
 Path(pipeline_file_path).joinpath(CHECKPOINT_TABLE_NAME, "None.parquet")
 )

 # non-table columns first (column order in df is random because created from a dict)
 table_names = [name for name in df.columns.values if name not in NON_TABLE_COLUMNS]
Expand Down

, '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
parquet pipeline#649

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

 Closed

jpn--
wants to merge
1
commit into

from

 Closed


parquet pipeline
#649
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


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


98 changes: 76 additions & 22 deletions
activitysim/core/pipeline.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,6 +4,7 @@
import logging
import os
from builtins import map, next, object
from pathlib import Path

import pandas as pd
from orca import orca
Expand DownExpand Up@@ -37,7 +38,7 @@ class Pipeline(object):
 def __init__(self):
 self.init_state()

 def init_state(self):
 def init_state(self, pipeline_file_format="parquet"):

 # most recent checkpoint
 self.last_checkpoint = {}
Expand DownExpand Up@@ -72,7 +73,7 @@ def is_open():
def is_readonly():
 if is_open():
 store = get_pipeline_store()
 if store and store._mode == "r":
 if store and not isinstance(store, Path) and store._mode == "r":
 return True
 return False

Expand All@@ -99,7 +100,11 @@ def close_open_files():

def open_pipeline_store(overwrite=False, mode="a"):
 """
 Open the pipeline checkpoint store
 Open the pipeline checkpoint store.

 If the pipeline_file_name setting ends in ".h5", then the pandas
 HDFStore file format is used, otherwise pipeline files are stored
 as parquet files organized in regular file system directories.
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

I assume documentation on this setting will to be addressed in the other Pydantic task?

 Parameters
 ----------
Expand All@@ -125,23 +130,36 @@ def open_pipeline_store(overwrite=False, mode="a"):
 inject.get_injectable("pipeline_file_name")
 )

 if overwrite:
 try:
 if os.path.isfile(pipeline_file_path):
 logger.debug("removing pipeline store: %s" % pipeline_file_path)
 os.unlink(pipeline_file_path)
 except Exception as e:
 print(e)
 logger.warning("Error removing %s: %s" % (pipeline_file_path, e))
 if pipeline_file_path.endswith(".h5"):

 if overwrite:
 try:
 if os.path.isfile(pipeline_file_path):
 logger.debug("removing pipeline store: %s" % pipeline_file_path)
 os.unlink(pipeline_file_path)
 except Exception as e:
 print(e)
 logger.warning("Error removing %s: %s" % (pipeline_file_path, e))

 _PIPELINE.pipeline_store = pd.HDFStore(pipeline_file_path, mode=mode)
 _PIPELINE.pipeline_store = pd.HDFStore(pipeline_file_path, mode=mode)

 else:
 _PIPELINE.pipeline_store = Path(pipeline_file_path)

 logger.debug(f"opened pipeline_store {pipeline_file_path}")


def get_pipeline_store():
 """
 Return the open pipeline hdf5 checkpoint store or return None if it not been opened
 Get the pipeline store.

 If the pipeline filename ends in ".h5" then the legacy HDF5 pipeline
 is used, otherwise the faster parquet format is used, and the value
 returned here is just the path to the pipeline directory.

 Returns
 -------
 pd.HDFStore or Path
 """
 return _PIPELINE.pipeline_store

Expand DownExpand Up@@ -181,7 +199,12 @@ def read_df(table_name, checkpoint_name=None):
 """

 store = get_pipeline_store()
 df = store[pipeline_table_key(table_name, checkpoint_name)]
 if isinstance(store, Path):
 df = pd.read_parquet(
 store.joinpath(table_name, f"{checkpoint_name}.parquet"),
 )
 else:
 df = store[pipeline_table_key(table_name, checkpoint_name)]

 return df

Expand All@@ -193,7 +216,11 @@ def write_df(df, table_name, checkpoint_name=None):
 We store multiple versions of all simulation tables, for every checkpoint in which they change,
 so we need to know both the table_name and the checkpoint_name to label the saved table

 The only exception is the checkpoints dataframe, which just has a table_name
 The only exception is the checkpoints dataframe, which just has a table_name,
 although when using the parquet storage format this file is stored as "None.parquet"
 to maintain a simple consistent file directory structure.

 If the
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Looks like unfinished thought here...

 Parameters
 ----------
Expand All@@ -209,10 +236,28 @@ def write_df(df, table_name, checkpoint_name=None):
 df.columns = df.columns.astype(str)

 store = get_pipeline_store()

 store[pipeline_table_key(table_name, checkpoint_name)] = df

 store.flush()
 if isinstance(store, Path):
 store.joinpath(table_name).mkdir(parents=True, exist_ok=True)
 df.to_parquet(store.joinpath(table_name, f"{checkpoint_name}.parquet"))
 else:
 complib = config.setting("pipeline_complib", None)
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Another setting to not get lost in the Pydantic task.
 if complib is None or len(df.columns) == 0:
 # tables with no columns can't be compressed successfully, so to
 # avoid them getting just lost and dropped they are instead written
 # in fixed format with no compression, which should be just fine
 # since they have no data anyhow.
 store.put(
 pipeline_table_key(table_name, checkpoint_name),
 df,
 )
 else:
 store.put(
 pipeline_table_key(table_name, checkpoint_name),
 df,
 "table",
 complib=complib,
 )
 store.flush()


def rewrap(table_name, df=None):
Expand DownExpand Up@@ -615,7 +660,8 @@ def close_pipeline():

 close_open_files()

 _PIPELINE.pipeline_store.close()
 if not isinstance(_PIPELINE.pipeline_store, Path):
 _PIPELINE.pipeline_store.close()

 _PIPELINE.init_state()

Expand DownExpand Up@@ -789,12 +835,20 @@ def get_checkpoints():
 store = get_pipeline_store()

 if store is not None:
 df = store[CHECKPOINT_TABLE_NAME]
 if isinstance(store, Path):
 df = pd.read_parquet(store.joinpath(CHECKPOINT_TABLE_NAME, "None.parquet"))
 else:
 df = store[CHECKPOINT_TABLE_NAME]
 else:
 pipeline_file_path = config.pipeline_file_path(
 orca.get_injectable("pipeline_file_name")
 )
 df = pd.read_hdf(pipeline_file_path, CHECKPOINT_TABLE_NAME)
 if pipeline_file_path.endswith(".h5"):
 df = pd.read_hdf(pipeline_file_path, CHECKPOINT_TABLE_NAME)
 else:
 df = pd.read_parquet(
 Path(pipeline_file_path).joinpath(CHECKPOINT_TABLE_NAME, "None.parquet")
 )

 # non-table columns first (column order in df is random because created from a dict)
 table_names = [name for name in df.columns.values if name not in NON_TABLE_COLUMNS]
Expand Down

, '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
parquet pipeline#649

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

 Closed

jpn--
wants to merge
1
commit into

from

 Closed


parquet pipeline
#649
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


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


98 changes: 76 additions & 22 deletions
activitysim/core/pipeline.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,6 +4,7 @@
import logging
import os
from builtins import map, next, object
from pathlib import Path

import pandas as pd
from orca import orca
Expand DownExpand Up@@ -37,7 +38,7 @@ class Pipeline(object):
 def __init__(self):
 self.init_state()

 def init_state(self):
 def init_state(self, pipeline_file_format="parquet"):

 # most recent checkpoint
 self.last_checkpoint = {}
Expand DownExpand Up@@ -72,7 +73,7 @@ def is_open():
def is_readonly():
 if is_open():
 store = get_pipeline_store()
 if store and store._mode == "r":
 if store and not isinstance(store, Path) and store._mode == "r":
 return True
 return False

Expand All@@ -99,7 +100,11 @@ def close_open_files():

def open_pipeline_store(overwrite=False, mode="a"):
 """
 Open the pipeline checkpoint store
 Open the pipeline checkpoint store.

 If the pipeline_file_name setting ends in ".h5", then the pandas
 HDFStore file format is used, otherwise pipeline files are stored
 as parquet files organized in regular file system directories.
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

I assume documentation on this setting will to be addressed in the other Pydantic task?

 Parameters
 ----------
Expand All@@ -125,23 +130,36 @@ def open_pipeline_store(overwrite=False, mode="a"):
 inject.get_injectable("pipeline_file_name")
 )

 if overwrite:
 try:
 if os.path.isfile(pipeline_file_path):
 logger.debug("removing pipeline store: %s" % pipeline_file_path)
 os.unlink(pipeline_file_path)
 except Exception as e:
 print(e)
 logger.warning("Error removing %s: %s" % (pipeline_file_path, e))
 if pipeline_file_path.endswith(".h5"):

 if overwrite:
 try:
 if os.path.isfile(pipeline_file_path):
 logger.debug("removing pipeline store: %s" % pipeline_file_path)
 os.unlink(pipeline_file_path)
 except Exception as e:
 print(e)
 logger.warning("Error removing %s: %s" % (pipeline_file_path, e))

 _PIPELINE.pipeline_store = pd.HDFStore(pipeline_file_path, mode=mode)
 _PIPELINE.pipeline_store = pd.HDFStore(pipeline_file_path, mode=mode)

 else:
 _PIPELINE.pipeline_store = Path(pipeline_file_path)

 logger.debug(f"opened pipeline_store {pipeline_file_path}")


def get_pipeline_store():
 """
 Return the open pipeline hdf5 checkpoint store or return None if it not been opened
 Get the pipeline store.

 If the pipeline filename ends in ".h5" then the legacy HDF5 pipeline
 is used, otherwise the faster parquet format is used, and the value
 returned here is just the path to the pipeline directory.

 Returns
 -------
 pd.HDFStore or Path
 """
 return _PIPELINE.pipeline_store

Expand DownExpand Up@@ -181,7 +199,12 @@ def read_df(table_name, checkpoint_name=None):
 """

 store = get_pipeline_store()
 df = store[pipeline_table_key(table_name, checkpoint_name)]
 if isinstance(store, Path):
 df = pd.read_parquet(
 store.joinpath(table_name, f"{checkpoint_name}.parquet"),
 )
 else:
 df = store[pipeline_table_key(table_name, checkpoint_name)]

 return df

Expand All@@ -193,7 +216,11 @@ def write_df(df, table_name, checkpoint_name=None):
 We store multiple versions of all simulation tables, for every checkpoint in which they change,
 so we need to know both the table_name and the checkpoint_name to label the saved table

 The only exception is the checkpoints dataframe, which just has a table_name
 The only exception is the checkpoints dataframe, which just has a table_name,
 although when using the parquet storage format this file is stored as "None.parquet"
 to maintain a simple consistent file directory structure.

 If the
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Looks like unfinished thought here...

 Parameters
 ----------
Expand All@@ -209,10 +236,28 @@ def write_df(df, table_name, checkpoint_name=None):
 df.columns = df.columns.astype(str)

 store = get_pipeline_store()

 store[pipeline_table_key(table_name, checkpoint_name)] = df

 store.flush()
 if isinstance(store, Path):
 store.joinpath(table_name).mkdir(parents=True, exist_ok=True)
 df.to_parquet(store.joinpath(table_name, f"{checkpoint_name}.parquet"))
 else:
 complib = config.setting("pipeline_complib", None)
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Another setting to not get lost in the Pydantic task.
 if complib is None or len(df.columns) == 0:
 # tables with no columns can't be compressed successfully, so to
 # avoid them getting just lost and dropped they are instead written
 # in fixed format with no compression, which should be just fine
 # since they have no data anyhow.
 store.put(
 pipeline_table_key(table_name, checkpoint_name),
 df,
 )
 else:
 store.put(
 pipeline_table_key(table_name, checkpoint_name),
 df,
 "table",
 complib=complib,
 )
 store.flush()


def rewrap(table_name, df=None):
Expand DownExpand Up@@ -615,7 +660,8 @@ def close_pipeline():

 close_open_files()

 _PIPELINE.pipeline_store.close()
 if not isinstance(_PIPELINE.pipeline_store, Path):
 _PIPELINE.pipeline_store.close()

 _PIPELINE.init_state()

Expand DownExpand Up@@ -789,12 +835,20 @@ def get_checkpoints():
 store = get_pipeline_store()

 if store is not None:
 df = store[CHECKPOINT_TABLE_NAME]
 if isinstance(store, Path):
 df = pd.read_parquet(store.joinpath(CHECKPOINT_TABLE_NAME, "None.parquet"))
 else:
 df = store[CHECKPOINT_TABLE_NAME]
 else:
 pipeline_file_path = config.pipeline_file_path(
 orca.get_injectable("pipeline_file_name")
 )
 df = pd.read_hdf(pipeline_file_path, CHECKPOINT_TABLE_NAME)
 if pipeline_file_path.endswith(".h5"):
 df = pd.read_hdf(pipeline_file_path, CHECKPOINT_TABLE_NAME)
 else:
 df = pd.read_parquet(
 Path(pipeline_file_path).joinpath(CHECKPOINT_TABLE_NAME, "None.parquet")
 )

 # non-table columns first (column order in df is random because created from a dict)
 table_names = [name for name in df.columns.values if name not in NON_TABLE_COLUMNS]
Expand Down

, '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
parquet pipeline#649

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

 Closed

jpn--
wants to merge
1
commit into

from

 Closed


parquet pipeline
#649
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


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


98 changes: 76 additions & 22 deletions
activitysim/core/pipeline.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,6 +4,7 @@
import logging
import os
from builtins import map, next, object
from pathlib import Path

import pandas as pd
from orca import orca
Expand DownExpand Up@@ -37,7 +38,7 @@ class Pipeline(object):
 def __init__(self):
 self.init_state()

 def init_state(self):
 def init_state(self, pipeline_file_format="parquet"):

 # most recent checkpoint
 self.last_checkpoint = {}
Expand DownExpand Up@@ -72,7 +73,7 @@ def is_open():
def is_readonly():
 if is_open():
 store = get_pipeline_store()
 if store and store._mode == "r":
 if store and not isinstance(store, Path) and store._mode == "r":
 return True
 return False

Expand All@@ -99,7 +100,11 @@ def close_open_files():

def open_pipeline_store(overwrite=False, mode="a"):
 """
 Open the pipeline checkpoint store
 Open the pipeline checkpoint store.

 If the pipeline_file_name setting ends in ".h5", then the pandas
 HDFStore file format is used, otherwise pipeline files are stored
 as parquet files organized in regular file system directories.
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

I assume documentation on this setting will to be addressed in the other Pydantic task?

 Parameters
 ----------
Expand All@@ -125,23 +130,36 @@ def open_pipeline_store(overwrite=False, mode="a"):
 inject.get_injectable("pipeline_file_name")
 )

 if overwrite:
 try:
 if os.path.isfile(pipeline_file_path):
 logger.debug("removing pipeline store: %s" % pipeline_file_path)
 os.unlink(pipeline_file_path)
 except Exception as e:
 print(e)
 logger.warning("Error removing %s: %s" % (pipeline_file_path, e))
 if pipeline_file_path.endswith(".h5"):

 if overwrite:
 try:
 if os.path.isfile(pipeline_file_path):
 logger.debug("removing pipeline store: %s" % pipeline_file_path)
 os.unlink(pipeline_file_path)
 except Exception as e:
 print(e)
 logger.warning("Error removing %s: %s" % (pipeline_file_path, e))

 _PIPELINE.pipeline_store = pd.HDFStore(pipeline_file_path, mode=mode)
 _PIPELINE.pipeline_store = pd.HDFStore(pipeline_file_path, mode=mode)

 else:
 _PIPELINE.pipeline_store = Path(pipeline_file_path)

 logger.debug(f"opened pipeline_store {pipeline_file_path}")


def get_pipeline_store():
 """
 Return the open pipeline hdf5 checkpoint store or return None if it not been opened
 Get the pipeline store.

 If the pipeline filename ends in ".h5" then the legacy HDF5 pipeline
 is used, otherwise the faster parquet format is used, and the value
 returned here is just the path to the pipeline directory.

 Returns
 -------
 pd.HDFStore or Path
 """
 return _PIPELINE.pipeline_store

Expand DownExpand Up@@ -181,7 +199,12 @@ def read_df(table_name, checkpoint_name=None):
 """

 store = get_pipeline_store()
 df = store[pipeline_table_key(table_name, checkpoint_name)]
 if isinstance(store, Path):
 df = pd.read_parquet(
 store.joinpath(table_name, f"{checkpoint_name}.parquet"),
 )
 else:
 df = store[pipeline_table_key(table_name, checkpoint_name)]

 return df

Expand All@@ -193,7 +216,11 @@ def write_df(df, table_name, checkpoint_name=None):
 We store multiple versions of all simulation tables, for every checkpoint in which they change,
 so we need to know both the table_name and the checkpoint_name to label the saved table

 The only exception is the checkpoints dataframe, which just has a table_name
 The only exception is the checkpoints dataframe, which just has a table_name,
 although when using the parquet storage format this file is stored as "None.parquet"
 to maintain a simple consistent file directory structure.

 If the
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Looks like unfinished thought here...

 Parameters
 ----------
Expand All@@ -209,10 +236,28 @@ def write_df(df, table_name, checkpoint_name=None):
 df.columns = df.columns.astype(str)

 store = get_pipeline_store()

 store[pipeline_table_key(table_name, checkpoint_name)] = df

 store.flush()
 if isinstance(store, Path):
 store.joinpath(table_name).mkdir(parents=True, exist_ok=True)
 df.to_parquet(store.joinpath(table_name, f"{checkpoint_name}.parquet"))
 else:
 complib = config.setting("pipeline_complib", None)
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Another setting to not get lost in the Pydantic task.
 if complib is None or len(df.columns) == 0:
 # tables with no columns can't be compressed successfully, so to
 # avoid them getting just lost and dropped they are instead written
 # in fixed format with no compression, which should be just fine
 # since they have no data anyhow.
 store.put(
 pipeline_table_key(table_name, checkpoint_name),
 df,
 )
 else:
 store.put(
 pipeline_table_key(table_name, checkpoint_name),
 df,
 "table",
 complib=complib,
 )
 store.flush()


def rewrap(table_name, df=None):
Expand DownExpand Up@@ -615,7 +660,8 @@ def close_pipeline():

 close_open_files()

 _PIPELINE.pipeline_store.close()
 if not isinstance(_PIPELINE.pipeline_store, Path):
 _PIPELINE.pipeline_store.close()

 _PIPELINE.init_state()

Expand DownExpand Up@@ -789,12 +835,20 @@ def get_checkpoints():
 store = get_pipeline_store()

 if store is not None:
 df = store[CHECKPOINT_TABLE_NAME]
 if isinstance(store, Path):
 df = pd.read_parquet(store.joinpath(CHECKPOINT_TABLE_NAME, "None.parquet"))
 else:
 df = store[CHECKPOINT_TABLE_NAME]
 else:
 pipeline_file_path = config.pipeline_file_path(
 orca.get_injectable("pipeline_file_name")
 )
 df = pd.read_hdf(pipeline_file_path, CHECKPOINT_TABLE_NAME)
 if pipeline_file_path.endswith(".h5"):
 df = pd.read_hdf(pipeline_file_path, CHECKPOINT_TABLE_NAME)
 else:
 df = pd.read_parquet(
 Path(pipeline_file_path).joinpath(CHECKPOINT_TABLE_NAME, "None.parquet")
 )

 # non-table columns first (column order in df is random because created from a dict)
 table_names = [name for name in df.columns.values if name not in NON_TABLE_COLUMNS]
Expand Down

, '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
parquet pipeline#649

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

 Closed

jpn--
wants to merge
1
commit into

from

 Closed


parquet pipeline
#649
 Changes from all commits
Commits

Show all changes


1 commit


Select commit


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


98 changes: 76 additions & 22 deletions
activitysim/core/pipeline.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -4,6 +4,7 @@
import logging
import os
from builtins import map, next, object
from pathlib import Path

import pandas as pd
from orca import orca
Expand DownExpand Up@@ -37,7 +38,7 @@ class Pipeline(object):
 def __init__(self):
 self.init_state()

 def init_state(self):
 def init_state(self, pipeline_file_format="parquet"):

 # most recent checkpoint
 self.last_checkpoint = {}
Expand DownExpand Up@@ -72,7 +73,7 @@ def is_open():
def is_readonly():
 if is_open():
 store = get_pipeline_store()
 if store and store._mode == "r":
 if store and not isinstance(store, Path) and store._mode == "r":
 return True
 return False

Expand All@@ -99,7 +100,11 @@ def close_open_files():

def open_pipeline_store(overwrite=False, mode="a"):
 """
 Open the pipeline checkpoint store
 Open the pipeline checkpoint store.

 If the pipeline_file_name setting ends in ".h5", then the pandas
 HDFStore file format is used, otherwise pipeline files are stored
 as parquet files organized in regular file system directories.
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

I assume documentation on this setting will to be addressed in the other Pydantic task?

 Parameters
 ----------
Expand All@@ -125,23 +130,36 @@ def open_pipeline_store(overwrite=False, mode="a"):
 inject.get_injectable("pipeline_file_name")
 )

 if overwrite:
 try:
 if os.path.isfile(pipeline_file_path):
 logger.debug("removing pipeline store: %s" % pipeline_file_path)
 os.unlink(pipeline_file_path)
 except Exception as e:
 print(e)
 logger.warning("Error removing %s: %s" % (pipeline_file_path, e))
 if pipeline_file_path.endswith(".h5"):

 if overwrite:
 try:
 if os.path.isfile(pipeline_file_path):
 logger.debug("removing pipeline store: %s" % pipeline_file_path)
 os.unlink(pipeline_file_path)
 except Exception as e:
 print(e)
 logger.warning("Error removing %s: %s" % (pipeline_file_path, e))

 _PIPELINE.pipeline_store = pd.HDFStore(pipeline_file_path, mode=mode)
 _PIPELINE.pipeline_store = pd.HDFStore(pipeline_file_path, mode=mode)

 else:
 _PIPELINE.pipeline_store = Path(pipeline_file_path)

 logger.debug(f"opened pipeline_store {pipeline_file_path}")


def get_pipeline_store():
 """
 Return the open pipeline hdf5 checkpoint store or return None if it not been opened
 Get the pipeline store.

 If the pipeline filename ends in ".h5" then the legacy HDF5 pipeline
 is used, otherwise the faster parquet format is used, and the value
 returned here is just the path to the pipeline directory.

 Returns
 -------
 pd.HDFStore or Path
 """
 return _PIPELINE.pipeline_store

Expand DownExpand Up@@ -181,7 +199,12 @@ def read_df(table_name, checkpoint_name=None):
 """

 store = get_pipeline_store()
 df = store[pipeline_table_key(table_name, checkpoint_name)]
 if isinstance(store, Path):
 df = pd.read_parquet(
 store.joinpath(table_name, f"{checkpoint_name}.parquet"),
 )
 else:
 df = store[pipeline_table_key(table_name, checkpoint_name)]

 return df

Expand All@@ -193,7 +216,11 @@ def write_df(df, table_name, checkpoint_name=None):
 We store multiple versions of all simulation tables, for every checkpoint in which they change,
 so we need to know both the table_name and the checkpoint_name to label the saved table

 The only exception is the checkpoints dataframe, which just has a table_name
 The only exception is the checkpoints dataframe, which just has a table_name,
 although when using the parquet storage format this file is stored as "None.parquet"
 to maintain a simple consistent file directory structure.

 If the
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Looks like unfinished thought here...

 Parameters
 ----------
Expand All@@ -209,10 +236,28 @@ def write_df(df, table_name, checkpoint_name=None):
 df.columns = df.columns.astype(str)

 store = get_pipeline_store()

 store[pipeline_table_key(table_name, checkpoint_name)] = df

 store.flush()
 if isinstance(store, Path):
 store.joinpath(table_name).mkdir(parents=True, exist_ok=True)
 df.to_parquet(store.joinpath(table_name, f"{checkpoint_name}.parquet"))
 else:
 complib = config.setting("pipeline_complib", None)
@dhensledhensleFeb 25, 2023

Copy link


Copy Markdown

Contributor
Choose a reason for hiding this comment

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

Another setting to not get lost in the Pydantic task.
 if complib is None or len(df.columns) == 0:
 # tables with no columns can't be compressed successfully, so to
 # avoid them getting just lost and dropped they are instead written
 # in fixed format with no compression, which should be just fine
 # since they have no data anyhow.
 store.put(
 pipeline_table_key(table_name, checkpoint_name),
 df,
 )
 else:
 store.put(
 pipeline_table_key(table_name, checkpoint_name),
 df,
 "table",
 complib=complib,
 )
 store.flush()


def rewrap(table_name, df=None):
Expand DownExpand Up@@ -615,7 +660,8 @@ def close_pipeline():

 close_open_files()

 _PIPELINE.pipeline_store.close()
 if not isinstance(_PIPELINE.pipeline_store, Path):
 _PIPELINE.pipeline_store.close()

 _PIPELINE.init_state()

Expand DownExpand Up@@ -789,12 +835,20 @@ def get_checkpoints():
 store = get_pipeline_store()

 if store is not None:
 df = store[CHECKPOINT_TABLE_NAME]
 if isinstance(store, Path):
 df = pd.read_parquet(store.joinpath(CHECKPOINT_TABLE_NAME, "None.parquet"))
 else:
 df = store[CHECKPOINT_TABLE_NAME]
 else:
 pipeline_file_path = config.pipeline_file_path(
 orca.get_injectable("pipeline_file_name")
 )
 df = pd.read_hdf(pipeline_file_path, CHECKPOINT_TABLE_NAME)
 if pipeline_file_path.endswith(".h5"):
 df = pd.read_hdf(pipeline_file_path, CHECKPOINT_TABLE_NAME)
 else:
 df = pd.read_parquet(
 Path(pipeline_file_path).joinpath(CHECKPOINT_TABLE_NAME, "None.parquet")
 )

 # non-table columns first (column order in df is random because created from a dict)
 table_names = [name for name in df.columns.values if name not in NON_TABLE_COLUMNS]
Expand Down