CDAP Performance Improvements#51

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
fscottfoti merged 12 commits into from
May 8, 2015
Merged

CDAP Performance Improvements #51

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
92d96be
add easy-to-profile simulation script
jiffyclub Apr 27, 2015
fe3af75
remove one loop from cdap initial_household_utilities
jiffyclub Apr 27, 2015
3a48d8b
do one less loc in cdap initial_household_utilities
jiffyclub Apr 27, 2015
75872f6
do less indexing in cdap.apply_final_rules
jiffyclub Apr 27, 2015
d43ad7c
use numpy indexing instead of pandas lookup
jiffyclub Apr 28, 2015
2d98991
Skip loops in cdap.apply_final_rules
jiffyclub Apr 28, 2015
43a13bc
move apply_final_rules work into numpy funcs
jiffyclub May 4, 2015
528c2ce
use numpy indexing in cdap.make_interactions
jiffyclub May 5, 2015
579927c
cache a couple more things in cdap.initial_household_utilities
jiffyclub May 5, 2015
bbc6ee0
Cache arrays in cdap.apply_final_rules
jiffyclub May 6, 2015
0149190
allow numpy to broadcast alt in cdap.apply_final_rules
jiffyclub May 6, 2015
c3b7966
itertools.product is slightly faster than doing lookups in a list comp
jiffyclub May 6, 2015
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
92 changes: 70 additions & 22 deletions activitysim/cdap/cdap.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -48,24 +48,42 @@ def make_interactions(people, hh_id_col, p_type_col):
three_fmt = '{}{}{}'.format
two = []
three = []
two_perm_cache = {}
three_combo_cache = {}

for hh_id, df in people.groupby(hh_id_col, sort=False):
hh_size = len(df)

for hh, df in people.groupby(hh_id_col, sort=False):
# skip households with only one person
if len(df) == 1:
if hh_size == 1:
continue

ptypes = df[p_type_col]
ptypes = df[p_type_col].values
hh_idx = df.index.values

if hh_size in two_perm_cache:
two_perms = two_perm_cache[hh_size]
else:
two_perms = list(itertools.permutations(np.arange(hh_size), 2))
two_perm_cache[hh_size] = two_perms

for pA, pB in itertools.permutations(df.index, 2):
two.append((pA, two_fmt(*ptypes[[pA, pB]])))
two.extend(
(hh_idx[pA], two_fmt(*ptypes[[pA, pB]])) for pA, pB in two_perms)

# now skip households with two people
if len(df) == 2:
if hh_size == 2:
continue

for idx in itertools.combinations(df.index, 3):
combo = three_fmt(*ptypes[list(idx)])
three.extend((p, combo) for p in idx)
if hh_size in three_combo_cache:
three_combos = three_combo_cache[hh_size]
else:
three_combos = list(itertools.combinations(np.arange(hh_size), 3))
three_combo_cache[hh_size] = three_combos

three.extend(
(hh_idx[p], three_fmt(*ptypes.take(idx)))
for idx in three_combos
for p in idx)

if two:
two_idx, two_val = zip(*two)
Expand DownExpand Up@@ -162,17 +180,25 @@ def initial_household_utilities(utilities, people, hh_id_col):
hh_util = {}

alts = utilities.columns
combo_cache = {}

for hh_id, df in people.groupby(hh_id_col, sort=False):
utils = utilities.loc[df.index]
hh = []
hh_size = len(df)
utils = utilities.loc[df.index].as_matrix()

for combo in itertools.product(alts, repeat=len(df)):
hh.append(
(combo, utils.lookup(df.index, combo).sum()))
if hh_size in combo_cache:
ncombos, combos, flat_combos, tiled = combo_cache[hh_size]
else:
combos = list(itertools.product(alts, repeat=hh_size))
flat_combos = list(
tz.concat(itertools.product(range(len(alts)), repeat=hh_size)))
ncombos = len(combos)
tiled = np.tile(np.arange(hh_size), ncombos)
combo_cache[hh_size] = (ncombos, combos, flat_combos, tiled)

u = utils[tiled, flat_combos].reshape((ncombos, hh_size)).sum(axis=1)

idx, u = zip(*hh)
hh_util[hh_id] = pd.Series(u, index=idx)
hh_util[hh_id] = pd.Series(u, index=combos)

return hh_util

Expand DownExpand Up@@ -205,24 +231,46 @@ def apply_final_rules(hh_util, people, hh_id_col, final_rules):
"""
rule_mask = eval_variables(final_rules.index, people)

if not rule_mask.as_matrix().any():
# if the rules don't apply to anyone then return now
return

alt_match_cache = {}

for hh_id, df in people.groupby(hh_id_col, sort=False):
mask = rule_mask.loc[df.index]
if not mask.as_matrix().any():
# if the mask doesn't apply to anyone in this household
# carry on to the next household
continue

utils = hh_util[hh_id]
hh_size = len(df)

for exp, row in final_rules.iterrows():
m = mask[exp].as_matrix()
if not m.any():
# if this sub-mask doesn't apply to anyone here then
# carry on to the next rule
continue

# this crazy business combines three things to figure out
# which household alternatives need to be modified by this rule.
# the three things are:
# - the mask of people for whom the rule expression is true (m)
# - the individual alternative to which the rule applies
# (row.iloc[0])
# - the alternative combinations for the household (combo)
app = [
((np.array([row.iloc[0]] * len(utils.index[0])) == combo) & m
).any()
for combo in utils.index]
# (alt)
# - the alternative combinations for the household
# (utils.index)
alt = row.iloc[0]
key = (alt, hh_size)
if key in alt_match_cache:
alt_match = alt_match_cache[key]
else:
alt_match = np.array(utils.index.values.tolist()) == alt
alt_match_cache[key] = alt_match

app = np.any(np.bitwise_and(alt_match, m), axis=1)

utils[app] = row.iloc[1]

Expand Down
59 changes: 59 additions & 0 deletions example/simulation.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,59 @@
# coding: utf-8
import orca
from activitysim import defaults


import pandas as pd
import numpy as np
import os
orca.add_injectable("store", pd.HDFStore(
os.path.join("..", "activitysim", "defaults", "test", "test.h5"), "r"))
orca.add_injectable("nonmotskm_matrix", np.ones((1454, 1454)))


# In[4]:

orca.run(["school_location_simulate"])


# In[5]:

orca.run(["workplace_location_simulate"])


# In[7]:

orca.run(["auto_ownership_simulate"])


# In[8]:

orca.run(["cdap_simulate"])


# In[9]:

orca.run(['mandatory_tour_frequency'])

# In[11]:

orca.run(["mandatory_scheduling"])


# In[12]:

orca.run(['non_mandatory_tour_frequency'])

# In[14]:

orca.run(["destination_choice"])


# In[15]:

orca.run(["non_mandatory_scheduling"])


# In[16]:

orca.run(['mode_choice_simulate'])
, '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
CDAP Performance Improvements#51

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

fscottfoti
merged 12 commits into

from

May 8, 2015
 Merged


CDAP Performance Improvements
#51
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


12 commits


Select commit
Hold shift + click to select a range
92d96be

add easy-to-profile simulation script


jiffyclub Apr 27, 2015
fe3af75

remove one loop from cdap initial_household_utilities


jiffyclub Apr 27, 2015
3a48d8b

do one less loc in cdap initial_household_utilities


jiffyclub Apr 27, 2015
75872f6

do less indexing in cdap.apply_final_rules


jiffyclub Apr 27, 2015
d43ad7c

use numpy indexing instead of pandas lookup


jiffyclub Apr 28, 2015
2d98991

Skip loops in cdap.apply_final_rules


jiffyclub Apr 28, 2015
43a13bc

move apply_final_rules work into numpy funcs


jiffyclub May 4, 2015
528c2ce

use numpy indexing in cdap.make_interactions


jiffyclub May 5, 2015
579927c

cache a couple more things in cdap.initial_household_utilities


jiffyclub May 5, 2015
bbc6ee0

Cache arrays in cdap.apply_final_rules


jiffyclub May 6, 2015
0149190

allow numpy to broadcast alt in cdap.apply_final_rules


jiffyclub May 6, 2015
c3b7966

itertools.product is slightly faster than doing lookups in a list comp


jiffyclub May 6, 2015

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


92 changes: 70 additions & 22 deletions
activitysim/cdap/cdap.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -48,24 +48,42 @@ def make_interactions(people, hh_id_col, p_type_col):
 three_fmt = '{}{}{}'.format
 two = []
 three = []
 two_perm_cache = {}
 three_combo_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
 hh_size = len(df)

 for hh, df in people.groupby(hh_id_col, sort=False):
 # skip households with only one person
 if len(df) == 1:
 if hh_size == 1:
 continue

 ptypes = df[p_type_col]
 ptypes = df[p_type_col].values
 hh_idx = df.index.values

 if hh_size in two_perm_cache:
 two_perms = two_perm_cache[hh_size]
 else:
 two_perms = list(itertools.permutations(np.arange(hh_size), 2))
 two_perm_cache[hh_size] = two_perms

for pA, pB in itertools.permutations(df.index, 2):
two.append((pA, two_fmt(*ptypes[[pA, pB]])))
two.extend(
(hh_idx[pA], two_fmt(*ptypes[[pA, pB]])) for pA, pB in two_perms)

 # now skip households with two people
 if len(df) == 2:
 if hh_size == 2:
 continue

 for idx in itertools.combinations(df.index, 3):
 combo = three_fmt(*ptypes[list(idx)])
 three.extend((p, combo) for p in idx)
 if hh_size in three_combo_cache:
 three_combos = three_combo_cache[hh_size]
 else:
 three_combos = list(itertools.combinations(np.arange(hh_size), 3))
 three_combo_cache[hh_size] = three_combos

 three.extend(
 (hh_idx[p], three_fmt(*ptypes.take(idx)))
 for idx in three_combos
 for p in idx)

 if two:
 two_idx, two_val = zip(*two)
Expand DownExpand Up@@ -162,17 +180,25 @@ def initial_household_utilities(utilities, people, hh_id_col):
 hh_util = {}

 alts = utilities.columns
 combo_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
utils = utilities.loc[df.index]
hh = []
hh_size = len(df)
utils = utilities.loc[df.index].as_matrix()

 for combo in itertools.product(alts, repeat=len(df)):
 hh.append(
 (combo, utils.lookup(df.index, combo).sum()))
 if hh_size in combo_cache:
 ncombos, combos, flat_combos, tiled = combo_cache[hh_size]
 else:
 combos = list(itertools.product(alts, repeat=hh_size))
 flat_combos = list(
 tz.concat(itertools.product(range(len(alts)), repeat=hh_size)))
 ncombos = len(combos)
 tiled = np.tile(np.arange(hh_size), ncombos)
 combo_cache[hh_size] = (ncombos, combos, flat_combos, tiled)

 u = utils[tiled, flat_combos].reshape((ncombos, hh_size)).sum(axis=1)

 idx, u = zip(*hh)
 hh_util[hh_id] = pd.Series(u, index=idx)
 hh_util[hh_id] = pd.Series(u, index=combos)

 return hh_util

Expand DownExpand Up@@ -205,24 +231,46 @@ def apply_final_rules(hh_util, people, hh_id_col, final_rules):
 """
 rule_mask = eval_variables(final_rules.index, people)

 if not rule_mask.as_matrix().any():
 # if the rules don't apply to anyone then return now
 return

 alt_match_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
 mask = rule_mask.loc[df.index]
 if not mask.as_matrix().any():
 # if the mask doesn't apply to anyone in this household
 # carry on to the next household
 continue

 utils = hh_util[hh_id]
 hh_size = len(df)

 for exp, row in final_rules.iterrows():
 m = mask[exp].as_matrix()
 if not m.any():
 # if this sub-mask doesn't apply to anyone here then
 # carry on to the next rule
 continue

 # this crazy business combines three things to figure out
 # which household alternatives need to be modified by this rule.
 # the three things are:
 # - the mask of people for whom the rule expression is true (m)
 # - the individual alternative to which the rule applies
 # (row.iloc[0])
 # - the alternative combinations for the household (combo)
 app = [
 ((np.array([row.iloc[0]] * len(utils.index[0])) == combo) & m
 ).any()
 for combo in utils.index]
 # (alt)
 # - the alternative combinations for the household
 # (utils.index)
 alt = row.iloc[0]
 key = (alt, hh_size)
 if key in alt_match_cache:
 alt_match = alt_match_cache[key]
 else:
 alt_match = np.array(utils.index.values.tolist()) == alt
 alt_match_cache[key] = alt_match

 app = np.any(np.bitwise_and(alt_match, m), axis=1)

 utils[app] = row.iloc[1]

Expand Down

59 changes: 59 additions & 0 deletions
example/simulation.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,59 @@
# coding: utf-8
import orca
from activitysim import defaults


import pandas as pd
import numpy as np
import os
orca.add_injectable("store", pd.HDFStore(
 os.path.join("..", "activitysim", "defaults", "test", "test.h5"), "r"))
orca.add_injectable("nonmotskm_matrix", np.ones((1454, 1454)))


# In[4]:

orca.run(["school_location_simulate"])


# In[5]:

orca.run(["workplace_location_simulate"])


# In[7]:

orca.run(["auto_ownership_simulate"])


# In[8]:

orca.run(["cdap_simulate"])


# In[9]:

orca.run(['mandatory_tour_frequency'])

# In[11]:

orca.run(["mandatory_scheduling"])


# In[12]:

orca.run(['non_mandatory_tour_frequency'])

# In[14]:

orca.run(["destination_choice"])


# In[15]:

orca.run(["non_mandatory_scheduling"])


# In[16]:

orca.run(['mode_choice_simulate'])

, '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
CDAP Performance Improvements#51

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

fscottfoti
merged 12 commits into

from

May 8, 2015
 Merged


CDAP Performance Improvements
#51
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


12 commits


Select commit
Hold shift + click to select a range
92d96be

add easy-to-profile simulation script


jiffyclub Apr 27, 2015
fe3af75

remove one loop from cdap initial_household_utilities


jiffyclub Apr 27, 2015
3a48d8b

do one less loc in cdap initial_household_utilities


jiffyclub Apr 27, 2015
75872f6

do less indexing in cdap.apply_final_rules


jiffyclub Apr 27, 2015
d43ad7c

use numpy indexing instead of pandas lookup


jiffyclub Apr 28, 2015
2d98991

Skip loops in cdap.apply_final_rules


jiffyclub Apr 28, 2015
43a13bc

move apply_final_rules work into numpy funcs


jiffyclub May 4, 2015
528c2ce

use numpy indexing in cdap.make_interactions


jiffyclub May 5, 2015
579927c

cache a couple more things in cdap.initial_household_utilities


jiffyclub May 5, 2015
bbc6ee0

Cache arrays in cdap.apply_final_rules


jiffyclub May 6, 2015
0149190

allow numpy to broadcast alt in cdap.apply_final_rules


jiffyclub May 6, 2015
c3b7966

itertools.product is slightly faster than doing lookups in a list comp


jiffyclub May 6, 2015

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


92 changes: 70 additions & 22 deletions
activitysim/cdap/cdap.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -48,24 +48,42 @@ def make_interactions(people, hh_id_col, p_type_col):
 three_fmt = '{}{}{}'.format
 two = []
 three = []
 two_perm_cache = {}
 three_combo_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
 hh_size = len(df)

 for hh, df in people.groupby(hh_id_col, sort=False):
 # skip households with only one person
 if len(df) == 1:
 if hh_size == 1:
 continue

 ptypes = df[p_type_col]
 ptypes = df[p_type_col].values
 hh_idx = df.index.values

 if hh_size in two_perm_cache:
 two_perms = two_perm_cache[hh_size]
 else:
 two_perms = list(itertools.permutations(np.arange(hh_size), 2))
 two_perm_cache[hh_size] = two_perms

for pA, pB in itertools.permutations(df.index, 2):
two.append((pA, two_fmt(*ptypes[[pA, pB]])))
two.extend(
(hh_idx[pA], two_fmt(*ptypes[[pA, pB]])) for pA, pB in two_perms)

 # now skip households with two people
 if len(df) == 2:
 if hh_size == 2:
 continue

 for idx in itertools.combinations(df.index, 3):
 combo = three_fmt(*ptypes[list(idx)])
 three.extend((p, combo) for p in idx)
 if hh_size in three_combo_cache:
 three_combos = three_combo_cache[hh_size]
 else:
 three_combos = list(itertools.combinations(np.arange(hh_size), 3))
 three_combo_cache[hh_size] = three_combos

 three.extend(
 (hh_idx[p], three_fmt(*ptypes.take(idx)))
 for idx in three_combos
 for p in idx)

 if two:
 two_idx, two_val = zip(*two)
Expand DownExpand Up@@ -162,17 +180,25 @@ def initial_household_utilities(utilities, people, hh_id_col):
 hh_util = {}

 alts = utilities.columns
 combo_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
utils = utilities.loc[df.index]
hh = []
hh_size = len(df)
utils = utilities.loc[df.index].as_matrix()

 for combo in itertools.product(alts, repeat=len(df)):
 hh.append(
 (combo, utils.lookup(df.index, combo).sum()))
 if hh_size in combo_cache:
 ncombos, combos, flat_combos, tiled = combo_cache[hh_size]
 else:
 combos = list(itertools.product(alts, repeat=hh_size))
 flat_combos = list(
 tz.concat(itertools.product(range(len(alts)), repeat=hh_size)))
 ncombos = len(combos)
 tiled = np.tile(np.arange(hh_size), ncombos)
 combo_cache[hh_size] = (ncombos, combos, flat_combos, tiled)

 u = utils[tiled, flat_combos].reshape((ncombos, hh_size)).sum(axis=1)

 idx, u = zip(*hh)
 hh_util[hh_id] = pd.Series(u, index=idx)
 hh_util[hh_id] = pd.Series(u, index=combos)

 return hh_util

Expand DownExpand Up@@ -205,24 +231,46 @@ def apply_final_rules(hh_util, people, hh_id_col, final_rules):
 """
 rule_mask = eval_variables(final_rules.index, people)

 if not rule_mask.as_matrix().any():
 # if the rules don't apply to anyone then return now
 return

 alt_match_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
 mask = rule_mask.loc[df.index]
 if not mask.as_matrix().any():
 # if the mask doesn't apply to anyone in this household
 # carry on to the next household
 continue

 utils = hh_util[hh_id]
 hh_size = len(df)

 for exp, row in final_rules.iterrows():
 m = mask[exp].as_matrix()
 if not m.any():
 # if this sub-mask doesn't apply to anyone here then
 # carry on to the next rule
 continue

 # this crazy business combines three things to figure out
 # which household alternatives need to be modified by this rule.
 # the three things are:
 # - the mask of people for whom the rule expression is true (m)
 # - the individual alternative to which the rule applies
 # (row.iloc[0])
 # - the alternative combinations for the household (combo)
 app = [
 ((np.array([row.iloc[0]] * len(utils.index[0])) == combo) & m
 ).any()
 for combo in utils.index]
 # (alt)
 # - the alternative combinations for the household
 # (utils.index)
 alt = row.iloc[0]
 key = (alt, hh_size)
 if key in alt_match_cache:
 alt_match = alt_match_cache[key]
 else:
 alt_match = np.array(utils.index.values.tolist()) == alt
 alt_match_cache[key] = alt_match

 app = np.any(np.bitwise_and(alt_match, m), axis=1)

 utils[app] = row.iloc[1]

Expand Down

59 changes: 59 additions & 0 deletions
example/simulation.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,59 @@
# coding: utf-8
import orca
from activitysim import defaults


import pandas as pd
import numpy as np
import os
orca.add_injectable("store", pd.HDFStore(
 os.path.join("..", "activitysim", "defaults", "test", "test.h5"), "r"))
orca.add_injectable("nonmotskm_matrix", np.ones((1454, 1454)))


# In[4]:

orca.run(["school_location_simulate"])


# In[5]:

orca.run(["workplace_location_simulate"])


# In[7]:

orca.run(["auto_ownership_simulate"])


# In[8]:

orca.run(["cdap_simulate"])


# In[9]:

orca.run(['mandatory_tour_frequency'])

# In[11]:

orca.run(["mandatory_scheduling"])


# In[12]:

orca.run(['non_mandatory_tour_frequency'])

# In[14]:

orca.run(["destination_choice"])


# In[15]:

orca.run(["non_mandatory_scheduling"])


# In[16]:

orca.run(['mode_choice_simulate'])

, '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
CDAP Performance Improvements#51

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

fscottfoti
merged 12 commits into

from

May 8, 2015
 Merged


CDAP Performance Improvements
#51
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


12 commits


Select commit
Hold shift + click to select a range
92d96be

add easy-to-profile simulation script


jiffyclub Apr 27, 2015
fe3af75

remove one loop from cdap initial_household_utilities


jiffyclub Apr 27, 2015
3a48d8b

do one less loc in cdap initial_household_utilities


jiffyclub Apr 27, 2015
75872f6

do less indexing in cdap.apply_final_rules


jiffyclub Apr 27, 2015
d43ad7c

use numpy indexing instead of pandas lookup


jiffyclub Apr 28, 2015
2d98991

Skip loops in cdap.apply_final_rules


jiffyclub Apr 28, 2015
43a13bc

move apply_final_rules work into numpy funcs


jiffyclub May 4, 2015
528c2ce

use numpy indexing in cdap.make_interactions


jiffyclub May 5, 2015
579927c

cache a couple more things in cdap.initial_household_utilities


jiffyclub May 5, 2015
bbc6ee0

Cache arrays in cdap.apply_final_rules


jiffyclub May 6, 2015
0149190

allow numpy to broadcast alt in cdap.apply_final_rules


jiffyclub May 6, 2015
c3b7966

itertools.product is slightly faster than doing lookups in a list comp


jiffyclub May 6, 2015

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


92 changes: 70 additions & 22 deletions
activitysim/cdap/cdap.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -48,24 +48,42 @@ def make_interactions(people, hh_id_col, p_type_col):
 three_fmt = '{}{}{}'.format
 two = []
 three = []
 two_perm_cache = {}
 three_combo_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
 hh_size = len(df)

 for hh, df in people.groupby(hh_id_col, sort=False):
 # skip households with only one person
 if len(df) == 1:
 if hh_size == 1:
 continue

 ptypes = df[p_type_col]
 ptypes = df[p_type_col].values
 hh_idx = df.index.values

 if hh_size in two_perm_cache:
 two_perms = two_perm_cache[hh_size]
 else:
 two_perms = list(itertools.permutations(np.arange(hh_size), 2))
 two_perm_cache[hh_size] = two_perms

for pA, pB in itertools.permutations(df.index, 2):
two.append((pA, two_fmt(*ptypes[[pA, pB]])))
two.extend(
(hh_idx[pA], two_fmt(*ptypes[[pA, pB]])) for pA, pB in two_perms)

 # now skip households with two people
 if len(df) == 2:
 if hh_size == 2:
 continue

 for idx in itertools.combinations(df.index, 3):
 combo = three_fmt(*ptypes[list(idx)])
 three.extend((p, combo) for p in idx)
 if hh_size in three_combo_cache:
 three_combos = three_combo_cache[hh_size]
 else:
 three_combos = list(itertools.combinations(np.arange(hh_size), 3))
 three_combo_cache[hh_size] = three_combos

 three.extend(
 (hh_idx[p], three_fmt(*ptypes.take(idx)))
 for idx in three_combos
 for p in idx)

 if two:
 two_idx, two_val = zip(*two)
Expand DownExpand Up@@ -162,17 +180,25 @@ def initial_household_utilities(utilities, people, hh_id_col):
 hh_util = {}

 alts = utilities.columns
 combo_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
utils = utilities.loc[df.index]
hh = []
hh_size = len(df)
utils = utilities.loc[df.index].as_matrix()

 for combo in itertools.product(alts, repeat=len(df)):
 hh.append(
 (combo, utils.lookup(df.index, combo).sum()))
 if hh_size in combo_cache:
 ncombos, combos, flat_combos, tiled = combo_cache[hh_size]
 else:
 combos = list(itertools.product(alts, repeat=hh_size))
 flat_combos = list(
 tz.concat(itertools.product(range(len(alts)), repeat=hh_size)))
 ncombos = len(combos)
 tiled = np.tile(np.arange(hh_size), ncombos)
 combo_cache[hh_size] = (ncombos, combos, flat_combos, tiled)

 u = utils[tiled, flat_combos].reshape((ncombos, hh_size)).sum(axis=1)

 idx, u = zip(*hh)
 hh_util[hh_id] = pd.Series(u, index=idx)
 hh_util[hh_id] = pd.Series(u, index=combos)

 return hh_util

Expand DownExpand Up@@ -205,24 +231,46 @@ def apply_final_rules(hh_util, people, hh_id_col, final_rules):
 """
 rule_mask = eval_variables(final_rules.index, people)

 if not rule_mask.as_matrix().any():
 # if the rules don't apply to anyone then return now
 return

 alt_match_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
 mask = rule_mask.loc[df.index]
 if not mask.as_matrix().any():
 # if the mask doesn't apply to anyone in this household
 # carry on to the next household
 continue

 utils = hh_util[hh_id]
 hh_size = len(df)

 for exp, row in final_rules.iterrows():
 m = mask[exp].as_matrix()
 if not m.any():
 # if this sub-mask doesn't apply to anyone here then
 # carry on to the next rule
 continue

 # this crazy business combines three things to figure out
 # which household alternatives need to be modified by this rule.
 # the three things are:
 # - the mask of people for whom the rule expression is true (m)
 # - the individual alternative to which the rule applies
 # (row.iloc[0])
 # - the alternative combinations for the household (combo)
 app = [
 ((np.array([row.iloc[0]] * len(utils.index[0])) == combo) & m
 ).any()
 for combo in utils.index]
 # (alt)
 # - the alternative combinations for the household
 # (utils.index)
 alt = row.iloc[0]
 key = (alt, hh_size)
 if key in alt_match_cache:
 alt_match = alt_match_cache[key]
 else:
 alt_match = np.array(utils.index.values.tolist()) == alt
 alt_match_cache[key] = alt_match

 app = np.any(np.bitwise_and(alt_match, m), axis=1)

 utils[app] = row.iloc[1]

Expand Down

59 changes: 59 additions & 0 deletions
example/simulation.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,59 @@
# coding: utf-8
import orca
from activitysim import defaults


import pandas as pd
import numpy as np
import os
orca.add_injectable("store", pd.HDFStore(
 os.path.join("..", "activitysim", "defaults", "test", "test.h5"), "r"))
orca.add_injectable("nonmotskm_matrix", np.ones((1454, 1454)))


# In[4]:

orca.run(["school_location_simulate"])


# In[5]:

orca.run(["workplace_location_simulate"])


# In[7]:

orca.run(["auto_ownership_simulate"])


# In[8]:

orca.run(["cdap_simulate"])


# In[9]:

orca.run(['mandatory_tour_frequency'])

# In[11]:

orca.run(["mandatory_scheduling"])


# In[12]:

orca.run(['non_mandatory_tour_frequency'])

# In[14]:

orca.run(["destination_choice"])


# In[15]:

orca.run(["non_mandatory_scheduling"])


# In[16]:

orca.run(['mode_choice_simulate'])

, '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
CDAP Performance Improvements#51

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

fscottfoti
merged 12 commits into

from

May 8, 2015
 Merged


CDAP Performance Improvements
#51
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


12 commits


Select commit
Hold shift + click to select a range
92d96be

add easy-to-profile simulation script


jiffyclub Apr 27, 2015
fe3af75

remove one loop from cdap initial_household_utilities


jiffyclub Apr 27, 2015
3a48d8b

do one less loc in cdap initial_household_utilities


jiffyclub Apr 27, 2015
75872f6

do less indexing in cdap.apply_final_rules


jiffyclub Apr 27, 2015
d43ad7c

use numpy indexing instead of pandas lookup


jiffyclub Apr 28, 2015
2d98991

Skip loops in cdap.apply_final_rules


jiffyclub Apr 28, 2015
43a13bc

move apply_final_rules work into numpy funcs


jiffyclub May 4, 2015
528c2ce

use numpy indexing in cdap.make_interactions


jiffyclub May 5, 2015
579927c

cache a couple more things in cdap.initial_household_utilities


jiffyclub May 5, 2015
bbc6ee0

Cache arrays in cdap.apply_final_rules


jiffyclub May 6, 2015
0149190

allow numpy to broadcast alt in cdap.apply_final_rules


jiffyclub May 6, 2015
c3b7966

itertools.product is slightly faster than doing lookups in a list comp


jiffyclub May 6, 2015

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


92 changes: 70 additions & 22 deletions
activitysim/cdap/cdap.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -48,24 +48,42 @@ def make_interactions(people, hh_id_col, p_type_col):
 three_fmt = '{}{}{}'.format
 two = []
 three = []
 two_perm_cache = {}
 three_combo_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
 hh_size = len(df)

 for hh, df in people.groupby(hh_id_col, sort=False):
 # skip households with only one person
 if len(df) == 1:
 if hh_size == 1:
 continue

 ptypes = df[p_type_col]
 ptypes = df[p_type_col].values
 hh_idx = df.index.values

 if hh_size in two_perm_cache:
 two_perms = two_perm_cache[hh_size]
 else:
 two_perms = list(itertools.permutations(np.arange(hh_size), 2))
 two_perm_cache[hh_size] = two_perms

for pA, pB in itertools.permutations(df.index, 2):
two.append((pA, two_fmt(*ptypes[[pA, pB]])))
two.extend(
(hh_idx[pA], two_fmt(*ptypes[[pA, pB]])) for pA, pB in two_perms)

 # now skip households with two people
 if len(df) == 2:
 if hh_size == 2:
 continue

 for idx in itertools.combinations(df.index, 3):
 combo = three_fmt(*ptypes[list(idx)])
 three.extend((p, combo) for p in idx)
 if hh_size in three_combo_cache:
 three_combos = three_combo_cache[hh_size]
 else:
 three_combos = list(itertools.combinations(np.arange(hh_size), 3))
 three_combo_cache[hh_size] = three_combos

 three.extend(
 (hh_idx[p], three_fmt(*ptypes.take(idx)))
 for idx in three_combos
 for p in idx)

 if two:
 two_idx, two_val = zip(*two)
Expand DownExpand Up@@ -162,17 +180,25 @@ def initial_household_utilities(utilities, people, hh_id_col):
 hh_util = {}

 alts = utilities.columns
 combo_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
utils = utilities.loc[df.index]
hh = []
hh_size = len(df)
utils = utilities.loc[df.index].as_matrix()

 for combo in itertools.product(alts, repeat=len(df)):
 hh.append(
 (combo, utils.lookup(df.index, combo).sum()))
 if hh_size in combo_cache:
 ncombos, combos, flat_combos, tiled = combo_cache[hh_size]
 else:
 combos = list(itertools.product(alts, repeat=hh_size))
 flat_combos = list(
 tz.concat(itertools.product(range(len(alts)), repeat=hh_size)))
 ncombos = len(combos)
 tiled = np.tile(np.arange(hh_size), ncombos)
 combo_cache[hh_size] = (ncombos, combos, flat_combos, tiled)

 u = utils[tiled, flat_combos].reshape((ncombos, hh_size)).sum(axis=1)

 idx, u = zip(*hh)
 hh_util[hh_id] = pd.Series(u, index=idx)
 hh_util[hh_id] = pd.Series(u, index=combos)

 return hh_util

Expand DownExpand Up@@ -205,24 +231,46 @@ def apply_final_rules(hh_util, people, hh_id_col, final_rules):
 """
 rule_mask = eval_variables(final_rules.index, people)

 if not rule_mask.as_matrix().any():
 # if the rules don't apply to anyone then return now
 return

 alt_match_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
 mask = rule_mask.loc[df.index]
 if not mask.as_matrix().any():
 # if the mask doesn't apply to anyone in this household
 # carry on to the next household
 continue

 utils = hh_util[hh_id]
 hh_size = len(df)

 for exp, row in final_rules.iterrows():
 m = mask[exp].as_matrix()
 if not m.any():
 # if this sub-mask doesn't apply to anyone here then
 # carry on to the next rule
 continue

 # this crazy business combines three things to figure out
 # which household alternatives need to be modified by this rule.
 # the three things are:
 # - the mask of people for whom the rule expression is true (m)
 # - the individual alternative to which the rule applies
 # (row.iloc[0])
 # - the alternative combinations for the household (combo)
 app = [
 ((np.array([row.iloc[0]] * len(utils.index[0])) == combo) & m
 ).any()
 for combo in utils.index]
 # (alt)
 # - the alternative combinations for the household
 # (utils.index)
 alt = row.iloc[0]
 key = (alt, hh_size)
 if key in alt_match_cache:
 alt_match = alt_match_cache[key]
 else:
 alt_match = np.array(utils.index.values.tolist()) == alt
 alt_match_cache[key] = alt_match

 app = np.any(np.bitwise_and(alt_match, m), axis=1)

 utils[app] = row.iloc[1]

Expand Down

59 changes: 59 additions & 0 deletions
example/simulation.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,59 @@
# coding: utf-8
import orca
from activitysim import defaults


import pandas as pd
import numpy as np
import os
orca.add_injectable("store", pd.HDFStore(
 os.path.join("..", "activitysim", "defaults", "test", "test.h5"), "r"))
orca.add_injectable("nonmotskm_matrix", np.ones((1454, 1454)))


# In[4]:

orca.run(["school_location_simulate"])


# In[5]:

orca.run(["workplace_location_simulate"])


# In[7]:

orca.run(["auto_ownership_simulate"])


# In[8]:

orca.run(["cdap_simulate"])


# In[9]:

orca.run(['mandatory_tour_frequency'])

# In[11]:

orca.run(["mandatory_scheduling"])


# In[12]:

orca.run(['non_mandatory_tour_frequency'])

# In[14]:

orca.run(["destination_choice"])


# In[15]:

orca.run(["non_mandatory_scheduling"])


# In[16]:

orca.run(['mode_choice_simulate'])

, '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
CDAP Performance Improvements#51

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

fscottfoti
merged 12 commits into

from

May 8, 2015
 Merged


CDAP Performance Improvements
#51
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


12 commits


Select commit
Hold shift + click to select a range
92d96be

add easy-to-profile simulation script


jiffyclub Apr 27, 2015
fe3af75

remove one loop from cdap initial_household_utilities


jiffyclub Apr 27, 2015
3a48d8b

do one less loc in cdap initial_household_utilities


jiffyclub Apr 27, 2015
75872f6

do less indexing in cdap.apply_final_rules


jiffyclub Apr 27, 2015
d43ad7c

use numpy indexing instead of pandas lookup


jiffyclub Apr 28, 2015
2d98991

Skip loops in cdap.apply_final_rules


jiffyclub Apr 28, 2015
43a13bc

move apply_final_rules work into numpy funcs


jiffyclub May 4, 2015
528c2ce

use numpy indexing in cdap.make_interactions


jiffyclub May 5, 2015
579927c

cache a couple more things in cdap.initial_household_utilities


jiffyclub May 5, 2015
bbc6ee0

Cache arrays in cdap.apply_final_rules


jiffyclub May 6, 2015
0149190

allow numpy to broadcast alt in cdap.apply_final_rules


jiffyclub May 6, 2015
c3b7966

itertools.product is slightly faster than doing lookups in a list comp


jiffyclub May 6, 2015

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


92 changes: 70 additions & 22 deletions
activitysim/cdap/cdap.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -48,24 +48,42 @@ def make_interactions(people, hh_id_col, p_type_col):
 three_fmt = '{}{}{}'.format
 two = []
 three = []
 two_perm_cache = {}
 three_combo_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
 hh_size = len(df)

 for hh, df in people.groupby(hh_id_col, sort=False):
 # skip households with only one person
 if len(df) == 1:
 if hh_size == 1:
 continue

 ptypes = df[p_type_col]
 ptypes = df[p_type_col].values
 hh_idx = df.index.values

 if hh_size in two_perm_cache:
 two_perms = two_perm_cache[hh_size]
 else:
 two_perms = list(itertools.permutations(np.arange(hh_size), 2))
 two_perm_cache[hh_size] = two_perms

for pA, pB in itertools.permutations(df.index, 2):
two.append((pA, two_fmt(*ptypes[[pA, pB]])))
two.extend(
(hh_idx[pA], two_fmt(*ptypes[[pA, pB]])) for pA, pB in two_perms)

 # now skip households with two people
 if len(df) == 2:
 if hh_size == 2:
 continue

 for idx in itertools.combinations(df.index, 3):
 combo = three_fmt(*ptypes[list(idx)])
 three.extend((p, combo) for p in idx)
 if hh_size in three_combo_cache:
 three_combos = three_combo_cache[hh_size]
 else:
 three_combos = list(itertools.combinations(np.arange(hh_size), 3))
 three_combo_cache[hh_size] = three_combos

 three.extend(
 (hh_idx[p], three_fmt(*ptypes.take(idx)))
 for idx in three_combos
 for p in idx)

 if two:
 two_idx, two_val = zip(*two)
Expand DownExpand Up@@ -162,17 +180,25 @@ def initial_household_utilities(utilities, people, hh_id_col):
 hh_util = {}

 alts = utilities.columns
 combo_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
utils = utilities.loc[df.index]
hh = []
hh_size = len(df)
utils = utilities.loc[df.index].as_matrix()

 for combo in itertools.product(alts, repeat=len(df)):
 hh.append(
 (combo, utils.lookup(df.index, combo).sum()))
 if hh_size in combo_cache:
 ncombos, combos, flat_combos, tiled = combo_cache[hh_size]
 else:
 combos = list(itertools.product(alts, repeat=hh_size))
 flat_combos = list(
 tz.concat(itertools.product(range(len(alts)), repeat=hh_size)))
 ncombos = len(combos)
 tiled = np.tile(np.arange(hh_size), ncombos)
 combo_cache[hh_size] = (ncombos, combos, flat_combos, tiled)

 u = utils[tiled, flat_combos].reshape((ncombos, hh_size)).sum(axis=1)

 idx, u = zip(*hh)
 hh_util[hh_id] = pd.Series(u, index=idx)
 hh_util[hh_id] = pd.Series(u, index=combos)

 return hh_util

Expand DownExpand Up@@ -205,24 +231,46 @@ def apply_final_rules(hh_util, people, hh_id_col, final_rules):
 """
 rule_mask = eval_variables(final_rules.index, people)

 if not rule_mask.as_matrix().any():
 # if the rules don't apply to anyone then return now
 return

 alt_match_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
 mask = rule_mask.loc[df.index]
 if not mask.as_matrix().any():
 # if the mask doesn't apply to anyone in this household
 # carry on to the next household
 continue

 utils = hh_util[hh_id]
 hh_size = len(df)

 for exp, row in final_rules.iterrows():
 m = mask[exp].as_matrix()
 if not m.any():
 # if this sub-mask doesn't apply to anyone here then
 # carry on to the next rule
 continue

 # this crazy business combines three things to figure out
 # which household alternatives need to be modified by this rule.
 # the three things are:
 # - the mask of people for whom the rule expression is true (m)
 # - the individual alternative to which the rule applies
 # (row.iloc[0])
 # - the alternative combinations for the household (combo)
 app = [
 ((np.array([row.iloc[0]] * len(utils.index[0])) == combo) & m
 ).any()
 for combo in utils.index]
 # (alt)
 # - the alternative combinations for the household
 # (utils.index)
 alt = row.iloc[0]
 key = (alt, hh_size)
 if key in alt_match_cache:
 alt_match = alt_match_cache[key]
 else:
 alt_match = np.array(utils.index.values.tolist()) == alt
 alt_match_cache[key] = alt_match

 app = np.any(np.bitwise_and(alt_match, m), axis=1)

 utils[app] = row.iloc[1]

Expand Down

59 changes: 59 additions & 0 deletions
example/simulation.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,59 @@
# coding: utf-8
import orca
from activitysim import defaults


import pandas as pd
import numpy as np
import os
orca.add_injectable("store", pd.HDFStore(
 os.path.join("..", "activitysim", "defaults", "test", "test.h5"), "r"))
orca.add_injectable("nonmotskm_matrix", np.ones((1454, 1454)))


# In[4]:

orca.run(["school_location_simulate"])


# In[5]:

orca.run(["workplace_location_simulate"])


# In[7]:

orca.run(["auto_ownership_simulate"])


# In[8]:

orca.run(["cdap_simulate"])


# In[9]:

orca.run(['mandatory_tour_frequency'])

# In[11]:

orca.run(["mandatory_scheduling"])


# In[12]:

orca.run(['non_mandatory_tour_frequency'])

# In[14]:

orca.run(["destination_choice"])


# In[15]:

orca.run(["non_mandatory_scheduling"])


# In[16]:

orca.run(['mode_choice_simulate'])

, '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
CDAP Performance Improvements#51

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

fscottfoti
merged 12 commits into

from

May 8, 2015
 Merged


CDAP Performance Improvements
#51
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


12 commits


Select commit
Hold shift + click to select a range
92d96be

add easy-to-profile simulation script


jiffyclub Apr 27, 2015
fe3af75

remove one loop from cdap initial_household_utilities


jiffyclub Apr 27, 2015
3a48d8b

do one less loc in cdap initial_household_utilities


jiffyclub Apr 27, 2015
75872f6

do less indexing in cdap.apply_final_rules


jiffyclub Apr 27, 2015
d43ad7c

use numpy indexing instead of pandas lookup


jiffyclub Apr 28, 2015
2d98991

Skip loops in cdap.apply_final_rules


jiffyclub Apr 28, 2015
43a13bc

move apply_final_rules work into numpy funcs


jiffyclub May 4, 2015
528c2ce

use numpy indexing in cdap.make_interactions


jiffyclub May 5, 2015
579927c

cache a couple more things in cdap.initial_household_utilities


jiffyclub May 5, 2015
bbc6ee0

Cache arrays in cdap.apply_final_rules


jiffyclub May 6, 2015
0149190

allow numpy to broadcast alt in cdap.apply_final_rules


jiffyclub May 6, 2015
c3b7966

itertools.product is slightly faster than doing lookups in a list comp


jiffyclub May 6, 2015

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


92 changes: 70 additions & 22 deletions
activitysim/cdap/cdap.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -48,24 +48,42 @@ def make_interactions(people, hh_id_col, p_type_col):
 three_fmt = '{}{}{}'.format
 two = []
 three = []
 two_perm_cache = {}
 three_combo_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
 hh_size = len(df)

 for hh, df in people.groupby(hh_id_col, sort=False):
 # skip households with only one person
 if len(df) == 1:
 if hh_size == 1:
 continue

 ptypes = df[p_type_col]
 ptypes = df[p_type_col].values
 hh_idx = df.index.values

 if hh_size in two_perm_cache:
 two_perms = two_perm_cache[hh_size]
 else:
 two_perms = list(itertools.permutations(np.arange(hh_size), 2))
 two_perm_cache[hh_size] = two_perms

for pA, pB in itertools.permutations(df.index, 2):
two.append((pA, two_fmt(*ptypes[[pA, pB]])))
two.extend(
(hh_idx[pA], two_fmt(*ptypes[[pA, pB]])) for pA, pB in two_perms)

 # now skip households with two people
 if len(df) == 2:
 if hh_size == 2:
 continue

 for idx in itertools.combinations(df.index, 3):
 combo = three_fmt(*ptypes[list(idx)])
 three.extend((p, combo) for p in idx)
 if hh_size in three_combo_cache:
 three_combos = three_combo_cache[hh_size]
 else:
 three_combos = list(itertools.combinations(np.arange(hh_size), 3))
 three_combo_cache[hh_size] = three_combos

 three.extend(
 (hh_idx[p], three_fmt(*ptypes.take(idx)))
 for idx in three_combos
 for p in idx)

 if two:
 two_idx, two_val = zip(*two)
Expand DownExpand Up@@ -162,17 +180,25 @@ def initial_household_utilities(utilities, people, hh_id_col):
 hh_util = {}

 alts = utilities.columns
 combo_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
utils = utilities.loc[df.index]
hh = []
hh_size = len(df)
utils = utilities.loc[df.index].as_matrix()

 for combo in itertools.product(alts, repeat=len(df)):
 hh.append(
 (combo, utils.lookup(df.index, combo).sum()))
 if hh_size in combo_cache:
 ncombos, combos, flat_combos, tiled = combo_cache[hh_size]
 else:
 combos = list(itertools.product(alts, repeat=hh_size))
 flat_combos = list(
 tz.concat(itertools.product(range(len(alts)), repeat=hh_size)))
 ncombos = len(combos)
 tiled = np.tile(np.arange(hh_size), ncombos)
 combo_cache[hh_size] = (ncombos, combos, flat_combos, tiled)

 u = utils[tiled, flat_combos].reshape((ncombos, hh_size)).sum(axis=1)

 idx, u = zip(*hh)
 hh_util[hh_id] = pd.Series(u, index=idx)
 hh_util[hh_id] = pd.Series(u, index=combos)

 return hh_util

Expand DownExpand Up@@ -205,24 +231,46 @@ def apply_final_rules(hh_util, people, hh_id_col, final_rules):
 """
 rule_mask = eval_variables(final_rules.index, people)

 if not rule_mask.as_matrix().any():
 # if the rules don't apply to anyone then return now
 return

 alt_match_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
 mask = rule_mask.loc[df.index]
 if not mask.as_matrix().any():
 # if the mask doesn't apply to anyone in this household
 # carry on to the next household
 continue

 utils = hh_util[hh_id]
 hh_size = len(df)

 for exp, row in final_rules.iterrows():
 m = mask[exp].as_matrix()
 if not m.any():
 # if this sub-mask doesn't apply to anyone here then
 # carry on to the next rule
 continue

 # this crazy business combines three things to figure out
 # which household alternatives need to be modified by this rule.
 # the three things are:
 # - the mask of people for whom the rule expression is true (m)
 # - the individual alternative to which the rule applies
 # (row.iloc[0])
 # - the alternative combinations for the household (combo)
 app = [
 ((np.array([row.iloc[0]] * len(utils.index[0])) == combo) & m
 ).any()
 for combo in utils.index]
 # (alt)
 # - the alternative combinations for the household
 # (utils.index)
 alt = row.iloc[0]
 key = (alt, hh_size)
 if key in alt_match_cache:
 alt_match = alt_match_cache[key]
 else:
 alt_match = np.array(utils.index.values.tolist()) == alt
 alt_match_cache[key] = alt_match

 app = np.any(np.bitwise_and(alt_match, m), axis=1)

 utils[app] = row.iloc[1]

Expand Down

59 changes: 59 additions & 0 deletions
example/simulation.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,59 @@
# coding: utf-8
import orca
from activitysim import defaults


import pandas as pd
import numpy as np
import os
orca.add_injectable("store", pd.HDFStore(
 os.path.join("..", "activitysim", "defaults", "test", "test.h5"), "r"))
orca.add_injectable("nonmotskm_matrix", np.ones((1454, 1454)))


# In[4]:

orca.run(["school_location_simulate"])


# In[5]:

orca.run(["workplace_location_simulate"])


# In[7]:

orca.run(["auto_ownership_simulate"])


# In[8]:

orca.run(["cdap_simulate"])


# In[9]:

orca.run(['mandatory_tour_frequency'])

# In[11]:

orca.run(["mandatory_scheduling"])


# In[12]:

orca.run(['non_mandatory_tour_frequency'])

# In[14]:

orca.run(["destination_choice"])


# In[15]:

orca.run(["non_mandatory_scheduling"])


# In[16]:

orca.run(['mode_choice_simulate'])

, '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
CDAP Performance Improvements#51

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

fscottfoti
merged 12 commits into

from

May 8, 2015
 Merged


CDAP Performance Improvements
#51
Show file tree
Hide file tree
 Changes from all commits
Commits

Show all changes


12 commits


Select commit
Hold shift + click to select a range
92d96be

add easy-to-profile simulation script


jiffyclub Apr 27, 2015
fe3af75

remove one loop from cdap initial_household_utilities


jiffyclub Apr 27, 2015
3a48d8b

do one less loc in cdap initial_household_utilities


jiffyclub Apr 27, 2015
75872f6

do less indexing in cdap.apply_final_rules


jiffyclub Apr 27, 2015
d43ad7c

use numpy indexing instead of pandas lookup


jiffyclub Apr 28, 2015
2d98991

Skip loops in cdap.apply_final_rules


jiffyclub Apr 28, 2015
43a13bc

move apply_final_rules work into numpy funcs


jiffyclub May 4, 2015
528c2ce

use numpy indexing in cdap.make_interactions


jiffyclub May 5, 2015
579927c

cache a couple more things in cdap.initial_household_utilities


jiffyclub May 5, 2015
bbc6ee0

Cache arrays in cdap.apply_final_rules


jiffyclub May 6, 2015
0149190

allow numpy to broadcast alt in cdap.apply_final_rules


jiffyclub May 6, 2015
c3b7966

itertools.product is slightly faster than doing lookups in a list comp


jiffyclub May 6, 2015

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


92 changes: 70 additions & 22 deletions
activitysim/cdap/cdap.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -48,24 +48,42 @@ def make_interactions(people, hh_id_col, p_type_col):
 three_fmt = '{}{}{}'.format
 two = []
 three = []
 two_perm_cache = {}
 three_combo_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
 hh_size = len(df)

 for hh, df in people.groupby(hh_id_col, sort=False):
 # skip households with only one person
 if len(df) == 1:
 if hh_size == 1:
 continue

 ptypes = df[p_type_col]
 ptypes = df[p_type_col].values
 hh_idx = df.index.values

 if hh_size in two_perm_cache:
 two_perms = two_perm_cache[hh_size]
 else:
 two_perms = list(itertools.permutations(np.arange(hh_size), 2))
 two_perm_cache[hh_size] = two_perms

for pA, pB in itertools.permutations(df.index, 2):
two.append((pA, two_fmt(*ptypes[[pA, pB]])))
two.extend(
(hh_idx[pA], two_fmt(*ptypes[[pA, pB]])) for pA, pB in two_perms)

 # now skip households with two people
 if len(df) == 2:
 if hh_size == 2:
 continue

 for idx in itertools.combinations(df.index, 3):
 combo = three_fmt(*ptypes[list(idx)])
 three.extend((p, combo) for p in idx)
 if hh_size in three_combo_cache:
 three_combos = three_combo_cache[hh_size]
 else:
 three_combos = list(itertools.combinations(np.arange(hh_size), 3))
 three_combo_cache[hh_size] = three_combos

 three.extend(
 (hh_idx[p], three_fmt(*ptypes.take(idx)))
 for idx in three_combos
 for p in idx)

 if two:
 two_idx, two_val = zip(*two)
Expand DownExpand Up@@ -162,17 +180,25 @@ def initial_household_utilities(utilities, people, hh_id_col):
 hh_util = {}

 alts = utilities.columns
 combo_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
utils = utilities.loc[df.index]
hh = []
hh_size = len(df)
utils = utilities.loc[df.index].as_matrix()

 for combo in itertools.product(alts, repeat=len(df)):
 hh.append(
 (combo, utils.lookup(df.index, combo).sum()))
 if hh_size in combo_cache:
 ncombos, combos, flat_combos, tiled = combo_cache[hh_size]
 else:
 combos = list(itertools.product(alts, repeat=hh_size))
 flat_combos = list(
 tz.concat(itertools.product(range(len(alts)), repeat=hh_size)))
 ncombos = len(combos)
 tiled = np.tile(np.arange(hh_size), ncombos)
 combo_cache[hh_size] = (ncombos, combos, flat_combos, tiled)

 u = utils[tiled, flat_combos].reshape((ncombos, hh_size)).sum(axis=1)

 idx, u = zip(*hh)
 hh_util[hh_id] = pd.Series(u, index=idx)
 hh_util[hh_id] = pd.Series(u, index=combos)

 return hh_util

Expand DownExpand Up@@ -205,24 +231,46 @@ def apply_final_rules(hh_util, people, hh_id_col, final_rules):
 """
 rule_mask = eval_variables(final_rules.index, people)

 if not rule_mask.as_matrix().any():
 # if the rules don't apply to anyone then return now
 return

 alt_match_cache = {}

 for hh_id, df in people.groupby(hh_id_col, sort=False):
 mask = rule_mask.loc[df.index]
 if not mask.as_matrix().any():
 # if the mask doesn't apply to anyone in this household
 # carry on to the next household
 continue

 utils = hh_util[hh_id]
 hh_size = len(df)

 for exp, row in final_rules.iterrows():
 m = mask[exp].as_matrix()
 if not m.any():
 # if this sub-mask doesn't apply to anyone here then
 # carry on to the next rule
 continue

 # this crazy business combines three things to figure out
 # which household alternatives need to be modified by this rule.
 # the three things are:
 # - the mask of people for whom the rule expression is true (m)
 # - the individual alternative to which the rule applies
 # (row.iloc[0])
 # - the alternative combinations for the household (combo)
 app = [
 ((np.array([row.iloc[0]] * len(utils.index[0])) == combo) & m
 ).any()
 for combo in utils.index]
 # (alt)
 # - the alternative combinations for the household
 # (utils.index)
 alt = row.iloc[0]
 key = (alt, hh_size)
 if key in alt_match_cache:
 alt_match = alt_match_cache[key]
 else:
 alt_match = np.array(utils.index.values.tolist()) == alt
 alt_match_cache[key] = alt_match

 app = np.any(np.bitwise_and(alt_match, m), axis=1)

 utils[app] = row.iloc[1]

Expand Down

59 changes: 59 additions & 0 deletions
example/simulation.py

View file


Open in desktop

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,59 @@
# coding: utf-8
import orca
from activitysim import defaults


import pandas as pd
import numpy as np
import os
orca.add_injectable("store", pd.HDFStore(
 os.path.join("..", "activitysim", "defaults", "test", "test.h5"), "r"))
orca.add_injectable("nonmotskm_matrix", np.ones((1454, 1454)))


# In[4]:

orca.run(["school_location_simulate"])


# In[5]:

orca.run(["workplace_location_simulate"])


# In[7]:

orca.run(["auto_ownership_simulate"])


# In[8]:

orca.run(["cdap_simulate"])


# In[9]:

orca.run(['mandatory_tour_frequency'])

# In[11]:

orca.run(["mandatory_scheduling"])


# In[12]:

orca.run(['non_mandatory_tour_frequency'])

# In[14]:

orca.run(["destination_choice"])


# In[15]:

orca.run(["non_mandatory_scheduling"])


# In[16]:

orca.run(['mode_choice_simulate'])