import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from scipy import stats
import statsmodels.api as sm
from statsmodels.stats.outliers_influence import variance_inflation_factor
from statsmodels.tools.tools import add_constant
sns.set_style("whitegrid")
# Import dataset:
data = pd.read_csv("luc_van_der_gun-beau_nienhuis-data.csv")
# Print amount of entries and list of keys:
print("{:>22}: {}\n".format("amount of entries", data['video_id'].count()))
for key in data.keys():
print("{:>22}: {} missing values".format(key, data[key].isna().sum()))