Skip to content
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

chore: testing Black #275

Open
wants to merge 1 commit into
base: develop
Choose a base branch
from
Open

chore: testing Black #275

Show file tree
Hide file tree
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
13 changes: 11 additions & 2 deletions analysis/bootstrapping.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,10 +2,12 @@
import copy
import analysis.statistics


def get_seeds(number_of_seeds):
return np.arange(1, number_of_seeds + 1) * 1000

def configure(context, stage, sample_size, parameters = {}, alias = None, ephemeral = True):

def configure(context, stage, sample_size, parameters={}, alias=None, ephemeral=True):
if alias is None:
alias = stage

Expand All @@ -15,11 +17,18 @@ def configure(context, stage, sample_size, parameters = {}, alias = None, epheme
sample_parameters = copy.copy(parameters)
sample_parameters["random_seed"] = int(random_seed)

context.stage(stage, sample_parameters, alias = "bootstrap_%s_%d" % (alias, index), ephemeral = ephemeral)
context.stage(
stage,
sample_parameters,
alias="bootstrap_%s_%d" % (alias, index),
ephemeral=ephemeral,
)


def get_stage(context, alias, index):
return context.stage("bootstrap_%s_%d" % (alias, index))


def get_stages(context, alias, sample_size):
for index in range(sample_size):
yield get_stage(context, alias, index)
26 changes: 17 additions & 9 deletions analysis/chains.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,22 +9,30 @@
("chain", "sex"),
("chain_length_class", "age_class"),
("chain_length_class", "sex"),
("chain",), ("chain_length_class",),
("chain",),
("chain_length_class",),
("age_range", "sex", "chain"),
("age_range", "sex", "chain_length_class")
("age_range", "sex", "chain_length_class"),
]

PURPOSE_MAPPING = {
"home": "h", "work": "w", "education": "e",
"shop": "s", "leisure": "l", "other": "o"
"home": "h",
"work": "w",
"education": "e",
"shop": "s",
"leisure": "l",
"other": "o",
}


def aggregate_chains(df_chains):
current_person_id = None
current_chain = None
records = []

for person_id, purpose in zip(df_chains["person_id"].values, df_chains["purpose"].values):
for person_id, purpose in zip(
df_chains["person_id"].values, df_chains["purpose"].values
):
if not person_id == current_person_id:
if not current_person_id is None:
records.append((current_person_id, current_chain))
Expand All @@ -36,11 +44,11 @@ def aggregate_chains(df_chains):

records.append((current_person_id, current_chain))

df_chains = pd.DataFrame.from_records(records, columns = ["person_id", "chain"])
df_chains = pd.DataFrame.from_records(records, columns=["person_id", "chain"])

#df_chains["chain"] = df_chains["chain"].apply(lambda x: re.sub(r"w+", "w", x))
#df_chains["chain"] = df_chains["chain"].apply(lambda x: re.sub(r"e+", "e", x))
#df_chains["chain"] = df_chains["chain"].apply(lambda x: re.sub(r"h+", "h", x))
# df_chains["chain"] = df_chains["chain"].apply(lambda x: re.sub(r"w+", "w", x))
# df_chains["chain"] = df_chains["chain"].apply(lambda x: re.sub(r"e+", "e", x))
# df_chains["chain"] = df_chains["chain"].apply(lambda x: re.sub(r"h+", "h", x))

df_chains["chain_length"] = df_chains["chain"].str.len()

Expand Down
26 changes: 15 additions & 11 deletions analysis/debug/sc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,11 +1,13 @@
import numpy as np
import pandas as pd


def configure(context):
context.stage("data.census.filtered", alias = "census")
context.stage("data.hts.selected", alias = "hts")
context.stage("data.census.filtered", alias="census")
context.stage("data.hts.selected", alias="hts")
context.config("output_path")


def execute(context):
df_census = context.stage("census")
df_hts = context.stage("hts")[1]
Expand All @@ -19,14 +21,16 @@ def execute(context):
f_census = df_census["socioprofessional_class"] == value
f_hts = df_hts["socioprofessional_class"] == value

df_output.append({
"value": value,
"census_count": np.count_nonzero(f_census),
"hts_count": np.count_nonzero(f_hts),
"census_weight": df_census[f_census]["weight"].sum(),
"hts_weight": df_hts[f_hts]["person_weight"].sum()
})
df_output.append(
{
"value": value,
"census_count": np.count_nonzero(f_census),
"hts_count": np.count_nonzero(f_hts),
"census_weight": df_census[f_census]["weight"].sum(),
"hts_weight": df_hts[f_hts]["person_weight"].sum(),
}
)

pd.DataFrame.from_records(df_output).to_csv(
"{}/debug_sc.csv".format(context.config("output_path")),
sep = ";", index = False)
"{}/debug_sc.csv".format(context.config("output_path")), sep=";", index=False
)
Loading
Loading