summary statistics in Python

import pandas as pd
import numpy as np

da = pd.read_csv("nhanes_2015_2016.csv")
x = da.BMXWT.dropna()  # Extract all non-missing values of BMXWT into a variable called 'x'
print(x.mean()) # Pandas method
print(np.mean(x)) # Numpy function

print(x.median())
print(np.percentile(x, 50))  # 50th percentile, same as the median
print(np.percentile(x, 75))  # 75th percentile
print(x.quantile(0.75)) # Pandas method for quantiles, equivalent to 75th percentile

# Considering only the systolic condition, we can calculate the proprotion of the NHANES sample who would be considered to have pre-hypertension.
np.mean((da.BPXSY1 >= 120) & (da.BPXSY2 <= 139))  # "&" means "and"
np.mean((da.BPXDI1 >= 80) & (da.BPXDI2 <= 89))

# or
a = (da.BPXSY1 >= 120) & (da.BPXSY2 <= 139)
b = (da.BPXDI1 >= 80) & (da.BPXDI2 <= 89)
print(np.mean(a | b))  # "|" means "or"