import pandas as pd
import xgboost as xgb

df = pd.read_csv("2018_all_indicators.csv")
df = df[['dimension','indicator_name','iso3','country_name','2017']]
df.shape # (25636, 5)
df = df.dropna() # getting rid of NaNs

df.shape #(12728, 5)
df.iso3.unique().shape # 195 countries