INNER CODE UNIT · Python
prep_air_quality_data
aeturrell/coding-for-economists · data_set_prep.py:145
def prep_air_quality_data():
# first download data from Air Quality Historical Data Platform
df = pd.read_csv(Path("/Users/aet/Downloads/beijing-air-quality.csv"))
df["date"] = pd.to_datetime(df["date"], format="%d/%m/%Y")
df = df.set_index("date")
df = df.sort_index()
# make 7 day rolling
df = df.rolling(7).mean()
df.to_csv(Path("data/beijing_pm.csv"))
def create_smaller_cut_flights_data():
url = "https://raw.githubusercontent.com/byuidatascience/data4python4ds/master/data-raw/flights/flights.csv"
flights = pd.read_csv(url)
flights["time_hour"] = pd.to_datetime(flights["time_hour"])
in_cols = ["year", "month", "day", "flight", "minute", "distance", "hour"]
for col in in_cols:
flights[col] = flights[col].astype("int")