def run_pipeline(indicator):
# The Excel sheet to use
sheet = INDICATOR_MAP[indicator.replace("yougov_", "")]
# Read dataframe
dataset = pandas.read_excel(request.content, sheet_name=sheet, header=2)
dataset = dataset.rename(columns={"Country/region": "country"})
dataset = dataset.drop(columns=["region"])
# Stack dates
dataset = dataset.set_index("country")
dataset = dataset.stack()
dataset = dataset.reset_index()
dataset = dataset.rename(columns={"level_1": "date", 0: "value"})
# Normalize countries
dataset["iso_code"] = dataset["country"].apply(
lambda country: normalize_country(country))
# Normalize date
# Drop any unnamed columns
dataset["invalid_date"] = dataset["date"].apply(
lambda date: type(date) == str and date.startswith("Unnamed"))
dataset = dataset[dataset["invalid_date"] == False]
dataset["date"] = dataset["date"].apply(lambda date: normalize_date(
date if type(date) == str else date.strftime("%Y-%m-%d"), "%Y-%m-%d"))
# Rename the value column
dataset = dataset.rename(columns={"value": indicator})
# Create slice of data with country ID, date, and indicator
dataset = dataset[["iso_code", "date", indicator]]
save_indicator(indicator, dataset=dataset)
def run_pipeline(indicator):
# Parse into dataframe
url = repository_url + file_map[indicator]
data = pd.read_csv(url)
# Relabel country and state column
data = data.rename(columns={
"Country/Region": "country",
"Province/State": "state"
})
# Keep country, state, and dates only
data = data[["country", "state"] +
[column for column in data if is_date(column, "%m/%d/%y")]]
# Normalize country names:
# * Drop non-countries
data = data[~data.country.isin(
["Diamond Princess", "MS Zaandam", "Kosovo", "Summer Olympics 2020"])]
# * Fix Taiwan: It is not clear why there is a star next to the name
data["country"] = data["country"].replace({"Taiwan*": "Taiwan"})
# * Fix Micronesia: Micronesia refers to the Federated States
data["country"] = data["country"].replace(
{"Micronesia": "Micronesia, Federated States of"})
# * Perform conversion
data["iso_code"] = data["country"].apply(
lambda country: normalize_country(country))
# * Drop country name
data = data.drop(columns=["country"])
# Reshape into list
data = data.melt(id_vars=["iso_code", "state"])
data = data.rename(columns={"variable": "date", "value": indicator})
# Normalize date format
data["date"] = data["date"].apply(
lambda date: normalize_date(date, "%m/%d/%y"))
# Verify uniqueness
if data.duplicated(["iso_code", "state", "date"]).any(axis=None):
raise Exception("Duplicates in data detected")
# Collapse states into country
data = data.groupby(["iso_code", "date"], as_index=False).agg("sum")
# Save as CSV file
save_indicator(indicator, dataset=data)
def run_pipeline(indicator):
# Find the chart series for this indicator
chart_series = None
# The YouGov label to look for
needle = INDICATOR_MAP[indicator.replace("yougov_", "")]
for id, object in data_dict.items():
label = id.replace("chart_", "#") + " " + object["title"]
if needle.lower() == label.lower():
chart_series = object["chartSeries"]
break
# Convert the data in the dict into a pandas dataframe:
# The series contains the country name and a data object
# The data object is a list of data points in the format [timestamp, value]
data = []
for series in chart_series:
for observation in series["data"]:
data.append({
"country":
series["name"],
"date":
strftime("%Y-%m-%d", gmtime(observation[0] / 1000)),
"value":
observation[1],
})
# Convert dict to dataframe
dataset = pandas.DataFrame.from_dict(data)
# Normalize countries
dataset["iso_code"] = dataset["country"].apply(
lambda country: normalize_country(country))
# Normalize date
dataset["date"] = dataset["date"].apply(
lambda date: normalize_date(date, "%Y-%m-%d"))
# Rename the value column
dataset = dataset.rename(columns={"value": indicator})
# Create slice of data with country ID, date, and indicator
dataset = dataset[["iso_code", "date", indicator]]
save_indicator(indicator, dataset=dataset)
dataset_url = (
"https://covid.ourworldindata.org/data/excess_mortality/excess_mortality.csv"
)
req = Request(dataset_url)
req.add_header(
"User-Agent",
"Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:77.0) Gecko/20100101 Firefox/77.0",
)
content = urlopen(req)
# Parse into dataframe
dataset = pd.read_csv(content)
# Normalize date format
dataset["date"] = dataset["date"].apply(lambda date: normalize_date(date, "%Y-%m-%d"))
# Rename p-score columns
new_column_names = {}
for column in dataset.columns:
new_column_names[column] = (
column.replace("p_scores_", "weekly_excess_mortality_p_score_")
.replace("_all_ages", "")
.replace("average_", "avg_")
.replace("deaths_", "weekly_deaths_")
)
dataset.rename(columns=new_column_names, inplace=True)
# Normalize country names:
# * Drop non countries
# Drop any rows with subnational observations
dataset = dataset[dataset[[
"sub_region_1",
"sub_region_2",
"metro_area",
"iso_3166_2_code",
"census_fips_code",
]].isnull().all(axis="columns")]
# Normalize countries
dataset["iso_code"] = dataset["country_region"].apply(
lambda country: normalize_country(country))
# Normalize date format
dataset["date"] = dataset["date"].apply(
lambda date: normalize_date(date, "%Y-%m-%d"))
def run_pipeline(indicator):
# Get the column name for this indicator
column = (indicator.replace("google_mobility_change_", "", 1) +
"_percent_change_from_baseline")
# Create slice of data with country ID, date, and indicator
frame = dataset[["iso_code", "date", column]]
# Rename column to indicator
frame = frame.rename(columns={column: indicator})
# Drop rows without observation
frame = frame.dropna(subset=[indicator], axis="index")
from helpers.camel_case_to_snake_case import camel_case_to_snake_case
dataset_url = "https://raw.githubusercontent.com/OxCGRT/covid-policy-tracker/master/data/OxCGRT_latest.csv"
# Parse into dataframe
dataset = pd.read_csv(dataset_url, low_memory=False)
# Drop subnational data
dataset = dataset[dataset["RegionCode"].isnull()]
# Rename columns
dataset = dataset.rename(columns={"CountryCode": "iso_code", "Date": "date"})
# Normalize date format
dataset["date"] = dataset["date"].apply(
lambda date: normalize_date(str(date), "%Y%m%d"))
def normalize_column(column_name):
normalized = column_name.replace(" ", "_").replace("/", "_or_")
normalized = camel_case_to_snake_case(normalized)
return "ox_" + normalized
def run_pipeline(indicator):
# Get the column name for this indicator
column = next(c for c in list(dataset.columns)
if normalize_column(c) == indicator)
# Create slice of data with country ID, date, and indicator
frame = dataset[["iso_code", "date", column]]
from helpers.save_indicator import save_indicator
from helpers.camel_case_to_snake_case import camel_case_to_snake_case
dataset_url = (
"https://raw.githubusercontent.com/RobertoFerC/SDSN_data_request/main/SDSN_Data.csv"
)
# Parse into dataframe
dataset = pd.read_csv(dataset_url, low_memory=False)
# Rename columns
dataset = dataset.rename(columns={"Country": "iso_code", "Date": "date"})
# Normalize date format
dataset["date"] = dataset["date"].apply(
lambda date: normalize_date(str(date), "%Y-%m-%d"))
def run_pipeline(indicator):
# Rename value column to indicator
frame = dataset.rename(columns={indicator.replace("icl_", ""): indicator})
# Keep only relevant columns
frame = frame[["iso_code", "date", indicator]]
# Drop observations without indicator value
frame = frame.dropna(subset=[indicator], axis="index")
# Save as CSV file
save_indicator(indicator, dataset=frame)
