import pandas as pd

FILEPATH = "../countries-of-the-world.csv"

df = pd.read_csv(FILEPATH)

df.head(2)

for col in df.columns:
    print(col)

Country
Region
Population
Area (sq. mi.)
Pop. Density (per sq. mi.)
Coastline (coast/area ratio)
Net migration
Infant mortality (per 1000 births)
GDP ($ per capita)
Literacy (%)
Phones (per 1000)
Arable (%)
Crops (%)
Other (%)
Climate
Birthrate
Deathrate
Agriculture
Industry
Service

# print all cols

new_cols = {}
for old_col in list(df.columns):
    # print(col)

    col = old_col
    col = col.lower()

    col = col.replace(".", "")
    col = col.replace(" ", "_")
    col = col.replace("(", "")
    col = col.replace(")", "")
    col = col.replace("%", "")
    col = col.replace("/", "")
    col = col.replace("$", "")

    # if " " in col or "(" in col:
    # print(col)

    new_cols[old_col] = col

new_cols

{'Country': 'country',
 'Region': 'region',
 'Population': 'population',
 'Area (sq. mi.)': 'area_sq_mi',
 'Pop. Density (per sq. mi.)': 'pop_density_per_sq_mi',
 'Coastline (coast/area ratio)': 'coastline_coastarea_ratio',
 'Net migration': 'net_migration',
 'Infant mortality (per 1000 births)': 'infant_mortality_per_1000_births',
 'GDP ($ per capita)': 'gdp__per_capita',
 'Literacy (%)': 'literacy_',
 'Phones (per 1000)': 'phones_per_1000',
 'Arable (%)': 'arable_',
 'Crops (%)': 'crops_',
 'Other (%)': 'other_',
 'Climate': 'climate',
 'Birthrate': 'birthrate',
 'Deathrate': 'deathrate',
 'Agriculture': 'agriculture',
 'Industry': 'industry',
 'Service': 'service'}

df.rename(
    columns = new_cols, 
    inplace = True
)

df.head(2)

df.to_csv('../countries-of-the-world-cleaned.csv')