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

Jump to bottom

Mutation analysis #348

Open
wants to merge 12 commits into
base: master
Choose a base branch
from
Open

Mutation analysis #348

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
b8e62e9
add groundwork
Sep 27, 2022
a4b4e28
add to_json
Sep 30, 2022
77a9ec6
update URL for cov spectrum
emmahodcroft Oct 8, 2022
54a9760
add plotting, filter for S, query by nextstrainClade
Oct 26, 2022
9442e37
add nextstrain_clade as simplified nextstrain id
emmahodcroft Jan 4, 2023
759d174
add country to URL, use new nextstrain clade, store only NTD/RBD
emmahodcroft Jan 4, 2023
b14407b
new comment
emmahodcroft Jan 4, 2023
276540c
include bi-weekly querying
Jan 20, 2023
06fb999
update perCountryData & CaseCounts jsons
Jan 20, 2023
1a50a49
add catch if no pango-lineage in clusters[clus]
emmahodcroft Jan 23, 2023
5f79e67
include case estimates
Feb 16, 2023
b473c0b
fix bug wrong population, add stable legend
Mar 23, 2023
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
20 changes: 20 additions & 0 deletions scripts/clusters.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@
"old_build_names": ["S.501Y.V1"],
"who_name": ["Alpha"],
"nextstrain_name": "20I (Alpha, V1)",
"nextstrain_clade": "20I",
"pango_lineages": [
{"name": "B.1.1.7", "url": None}
],
Expand Down Expand Up @@ -75,6 +76,7 @@
"old_build_names": ["S.501Y.V2"],
"who_name": ["Beta"],
"nextstrain_name": "20H (Beta, V2)",
"nextstrain_clade": "20H",
"pango_lineages": [
{"name": "B.1.351", "url": None}
],
Expand Down Expand Up @@ -127,6 +129,7 @@
"old_build_names": ["S.501Y.V3"],
"who_name": ["Gamma"],
"nextstrain_name": "20J (Gamma, V3)",
"nextstrain_clade": "20J",
"pango_lineages": [
{"name": "P.1", "url": None}
],
Expand Down Expand Up @@ -191,6 +194,7 @@
"old_build_names": ["21A.S.478K"],
"who_name": ["Delta"],
"nextstrain_name": "21A (Delta)",
"nextstrain_clade": "21A",
"pango_lineages": [
{"name": "B.1.617.2", "url": "https://cov-lineages.org/lineages/lineage_B.1.617.2.html"}
],
Expand Down Expand Up @@ -246,6 +250,7 @@
"old_build_names": [],
"who_name": ["Delta"],
"nextstrain_name": "21I (Delta)",
"nextstrain_clade": "21I",
"pango_lineages": [
{"name": "B.1.617.1", "url": "https://cov-lineages.org/lineages/lineage_B.1.617.1.html"}
],
Expand Down Expand Up @@ -308,6 +313,7 @@
"old_build_names": [],
"who_name": ["Delta"],
"nextstrain_name": "21J (Delta)",
"nextstrain_clade": "21J",
"pango_lineages": [
{"name": "B.1.617.1", "url": "https://cov-lineages.org/lineages/lineage_B.1.617.1.html"}
],
Expand Down Expand Up @@ -373,6 +379,7 @@
"old_build_names": ["21K"],
"alt_display_name": ["BA.1"],
"nextstrain_name": "21K",
"nextstrain_clade": "21K",
"pango_lineages": [
{"name": "BA.1", "url": "https://cov-lineages.org/lineages/lineage_BA.1.html"},
],
Expand Down Expand Up @@ -475,6 +482,7 @@
"old_build_names": ["21L"],
"alt_display_name": ["BA.2"],
"nextstrain_name": "21L (Omicron)",
"nextstrain_clade": "21L",
"pango_lineages": [
{"name": "BA.2", "url": "https://cov-lineages.org/lineages/lineage_BA.2.html"},
],
Expand Down Expand Up @@ -576,6 +584,7 @@
"col": "#000000",
"display_name": "21M (Omicron)",
"build_name": "21M.Omicron",
"nextstrain_clade": "21M",
"pango_lineages": [
{"name": "B.1.1.529", "url": None}
],
Expand Down Expand Up @@ -659,6 +668,7 @@
"who_name": ["Omicron"],
"old_build_names": ["22A"],
"nextstrain_name": "22A",
"nextstrain_clade": "22A",
"pango_lineages": [
{"name": "BA.4", "url": "https://cov-lineages.org/lineage.html?lineage=BA.4"}
],
Expand Down Expand Up @@ -798,6 +808,7 @@
"who_name": ["Omicron"],
"old_build_names": ["22B"],
"nextstrain_name": "22B",
"nextstrain_clade": "22B",
"pango_lineages": [
{"name": "BA.5", "url": "https://cov-lineages.org/lineage.html?lineage=BA.5"}
],
Expand Down Expand Up @@ -931,6 +942,7 @@
"who_name": ["Omicron"],
"old_build_names": ["22C"],
"nextstrain_name": "22C",
"nextstrain_clade": "22C",
"pango_lineages": [
{"name": "BA.2.12.1", "url": "https://cov-lineages.org/lineage.html?lineage=BA.2.12.1"}
],
Expand Down Expand Up @@ -1068,6 +1080,7 @@
"who_name": ["Omicron"],
"old_build_names": ["22D"],
"nextstrain_name": "22D",
"nextstrain_clade": "22D",
"pango_lineages": [
{"name": "BA.2.75", "url": "https://cov-lineages.org/lineage.html?lineage=BA.2.75"}
],
Expand Down Expand Up @@ -1216,6 +1229,7 @@
"old_build_names": ["21A.S.154K"],
"who_name": ["Kappa"],
"nextstrain_name": "21B (Kappa)",
"nextstrain_clade": "21B",
"pango_lineages": [
{"name": "B.1.617.1", "url": "https://cov-lineages.org/lineages/lineage_B.1.617.1.html"}
],
Expand Down Expand Up @@ -1287,6 +1301,7 @@
"old_build_names": ["20A.S.484K"],
"who_name": ["Eta"],
"nextstrain_name": "21D (Eta)",
"nextstrain_clade": "21D",
"pango_lineages": [
{"name": "B.1.525", "url": None}
],
Expand Down Expand Up @@ -1350,6 +1365,7 @@
"old_build_names": ["20C.S.484K"],
"who_name": ["Iota"],
"nextstrain_name": "21F (Iota)",
"nextstrain_clade": "21F",
"pango_lineages": [
{"name": "B.1.526", "url": None}
],
Expand Down Expand Up @@ -1401,6 +1417,7 @@
"old_build_names": [],
"who_name": ["Lambda"],
"nextstrain_name": "21G (Lambda)",
"nextstrain_clade": "21G",
"pango_lineages": [
{"name": "C.37", "url": None}
],
Expand Down Expand Up @@ -1464,6 +1481,7 @@
"old_build_names": ["21H"],
"who_name": ["Mu"],
"nextstrain_name": "21H (Mu)",
"nextstrain_clade": "21H",
"pango_lineages": [
{"name": "B.1.621", "url": None}
],
Expand Down Expand Up @@ -1628,6 +1646,7 @@
"alt_display_name": ["20A.EU1"],
"build_name": "20A.EU1",
"nextstrain_name": "20E (EU1)",
"nextstrain_clade": "20E",
"pango_lineages": [
{"name": "B.1.177", "url": None},
],
Expand Down Expand Up @@ -1664,6 +1683,7 @@
"old_build_names": ["S.L452R"],
"who_name": ["Epsilon"],
"nextstrain_name": "21C (Epsilon)",
"nextstrain_clade": "21C",
"pango_lineages": [
{"name": "B.1.427", "url": None},
{"name": "B.1.429", "url": None}
Expand Down
147 changes: 147 additions & 0 deletions scripts/include_case_counts_estimates.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,147 @@
import os
import pandas as pd
import json
import datetime
import sys
from helpers import to2week_ordinal, to2week_ordinal_string

# key: country names in covariants
# value: country name in owid
alernative_country_names = {
"USA" : "United States",
"Czech Republic" : "Czechia",
"Côte d'Ivoire": "Cote d'Ivoire",
"Democratic Republic of the Congo": "Democratic Republic of Congo",
"Sint Maarten": "Sint Maarten (Dutch part)",

# Are these correct?
"Bonaire" : "Bonaire Sint Eustatius and Saba",
"Republic of the Congo" : "Congo"
}

def divide_by_population(owid_estimates, owid):
owid_estimates = pd.merge(owid_estimates, owid, how='inner', left_on=['Entity','Day'], right_on = ['location','date'])
owid_estimates["estimated_infections_per_population"] = owid_estimates["Daily new estimated infections of COVID-19 (IHME, mean)"] / owid_estimates["population"]*1000000
return owid_estimates


THIS_DIR = os.path.dirname(os.path.realpath(__file__))

OWID_CSV_FILENAME = "owid-covid-data.csv"
OWID_CSV_INPUT_PATH = os.path.join(THIS_DIR, "..", "data", "owid", OWID_CSV_FILENAME)

OWID_CSV_FILENAME_ESTIMATES = "daily-new-estimated-covid-19-infections-ihme-model.csv"
OWID_CSV_INPUT_PATH_ESTIMATES = os.path.join(THIS_DIR, "..", "data", "owid", OWID_CSV_FILENAME_ESTIMATES)

COUNTRY_CSV_FILENAME = "perCountryData.json"
COUNTRY_CSV_INPUT_PATH = os.path.join(THIS_DIR, "..", "web", "data", COUNTRY_CSV_FILENAME)

OUTPUT_CSV_FILENAME_ESTIMATES = "perCountryDataCaseCountsEstimates.json"
OUTPUT_CSV_PATH_ESTIMATES = os.path.join(THIS_DIR, "..", "web", "data", OUTPUT_CSV_FILENAME_ESTIMATES)

# TODO: Adjust thresholds?
THRESHOLD = 0.0 #0.03 is 3%
PERIOD_PASS = 0.0 #0.5 is 50%

columns = ["location", "date", "population"]
owid = pd.read_csv(OWID_CSV_INPUT_PATH, usecols=columns)

columns_estimates = ["Entity", "Day", "Daily new estimated infections of COVID-19 (IHME, mean)"]
owid_estimates = pd.read_csv(OWID_CSV_INPUT_PATH_ESTIMATES, usecols=columns_estimates)

owid_estimates = divide_by_population(owid_estimates, owid)

owid_estimates["date_formatted"] = owid_estimates["Day"].apply(lambda x: datetime.datetime.strptime(x, "%Y-%m-%d"))

# get ordinal dates, but as a string, so can compare to dates in perCOuntryData.json
owid_estimates["date_2weeks"] = owid_estimates["date_formatted"].apply(to2week_ordinal_string)

owid_grouped = owid_estimates.groupby(["date_2weeks", "Entity"])[["estimated_infections_per_population", "Daily new estimated infections of COVID-19 (IHME, mean)"]].sum().reset_index()

with open(COUNTRY_CSV_INPUT_PATH) as f:
perCountryData = json.load(f)

world_data = perCountryData["regions"][0]["distributions"]
per_country_intro_content = perCountryData["regions"][0]["per_country_intro_content"]
max_date = perCountryData["regions"][0]["max_date"]
min_date = perCountryData["regions"][0]["min_date"]
cluster_names = perCountryData["regions"][0]["cluster_names"]

world_data_counts = []

for i in range(len(world_data)):
country = world_data[i]["country"]
if country not in owid_grouped["Entity"].values and country not in alernative_country_names:
print("Attention! Country not found in owid data: " + country)
continue

country_owid = country
if country in alernative_country_names:
country_owid = alernative_country_names[country]

world_data_counts.append({"country": country, "distribution": []})
for j in world_data[i]["distribution"]:
cluster_counts = j["cluster_counts"]
total_sequences = j["total_sequences"]
week = j["week"]

percent_counts = {c : float(n) / total_sequences for c, n in cluster_counts.items()}

stand_total_cases = owid_grouped.loc[(owid_grouped.date_2weeks == week) & (owid_grouped.Entity == country_owid)]["estimated_infections_per_population"]
total_cases = owid_grouped.loc[(owid_grouped.date_2weeks == week) & (owid_grouped.Entity == country_owid)]["Daily new estimated infections of COVID-19 (IHME, mean)"]

if len(stand_total_cases) > 0:
stand_total_cases = int(stand_total_cases.iloc[0])
else: # No count data
continue # Skip if no count data

if len(total_cases) > 0:
total_cases = int(total_cases.iloc[0])
else: # No count data
continue # Skip if no count data

stand_estimated_cases = {c: round(float(n) * stand_total_cases) for c, n in percent_counts.items()}
stand_estimated_cases["others"] = stand_total_cases - sum(stand_estimated_cases.values())
percent_total_cases = total_sequences / total_cases if total_cases != 0 else None

world_data_counts[-1]["distribution"].append({"week": week, "total_sequences": total_sequences, "stand_total_cases" : stand_total_cases, "stand_estimated_cases" : stand_estimated_cases, "percent_total_cases" : percent_total_cases})


### Check which countries pass the threshold
weeks = []
countries = []
# First collect all weeks and countries
for i in range(len(world_data_counts)):
country = world_data_counts[i]["country"]
countries.append(country)
for j in world_data_counts[i]["distribution"]:
week = j["week"]
if week not in weeks and "2020" not in week:
weeks.append(week)

df = pd.DataFrame(columns=sorted(weeks), index=sorted(countries))

for i in range(len(world_data_counts)):
country = world_data_counts[i]["country"]
for j in world_data_counts[i]["distribution"]:
week = j["week"]
if week in weeks:
percent_total_cases = j["percent_total_cases"]
df[week][country]= percent_total_cases

total_weeks = len(weeks)
df_threshold = (df>=THRESHOLD).sum(axis=1)
countries_pass = df_threshold[(df_threshold/float(total_weeks)) >= PERIOD_PASS].index

world_data_counts_cutoff = [x for x in world_data_counts if x["country"] in countries_pass]

print(f"{len(world_data_counts_cutoff)}/{len(world_data_counts)} countries have passed threshold {THRESHOLD} and period_pass {PERIOD_PASS}")

if len(world_data_counts_cutoff) == 0:
with open(OUTPUT_CSV_PATH_ESTIMATES, "w") as out:
out.write("")
sys.exit("**FAILED TO FIND ANY COUNTRIES THAT PASS THRESHOLD - CHECK FOR ERRORS!**")


with open(OUTPUT_CSV_PATH_ESTIMATES, "w") as out:
json.dump({"regions": [{"region": "World", "distributions" : world_data_counts_cutoff, "per_country_intro_content": per_country_intro_content, "max_date": max_date, "min_date": min_date, "cluster_names": cluster_names}]}, out, indent=2, sort_keys=True)
Loading